2381 files changed, 46228 insertions, 20443 deletions

diff --git a/.get_maintainer.ignore b/.get_maintainer.ignore
index a64d21913745..c298bab3d320 100644
--- a/.get_maintainer.ignore
+++ b/.get_maintainer.ignore
@@ -1,2 +1,4 @@
+Alan Cox <alan@lxorguk.ukuu.org.uk>
+Alan Cox <root@hraefn.swansea.linux.org.uk>
 Christoph Hellwig <hch@lst.de>
 Marc Gonzalez <marc.w.gonzalez@free.fr>
diff --git a/.gitignore b/.gitignore
index 265959544978..5da004814678 100644
--- a/.gitignore
+++ b/.gitignore
@@ -37,6 +37,8 @@
 *.o
 *.o.*
 *.patch
+*.rmeta
+*.rsi
 *.s
 *.so
 *.so.dbg
@@ -97,6 +99,7 @@ modules.order
 !.gitattributes
 !.gitignore
 !.mailmap
+!.rustfmt.toml
 
 #
 # Generated include files
@@ -162,3 +165,6 @@ x509.genkey
 
 # Documentation toolchain
 sphinx_*/
+
+# Rust analyzer configuration
+/rust-project.json
diff --git a/.mailmap b/.mailmap
index 38255d412f0b..191778125ef1 100644
--- a/.mailmap
+++ b/.mailmap
@@ -71,6 +71,9 @@ Ben M Cahill <ben.m.cahill@intel.com>
 Ben Widawsky <bwidawsk@kernel.org> <ben@bwidawsk.net>
 Ben Widawsky <bwidawsk@kernel.org> <ben.widawsky@intel.com>
 Ben Widawsky <bwidawsk@kernel.org> <benjamin.widawsky@intel.com>
+Bjorn Andersson <andersson@kernel.org> <bjorn@kryo.se>
+Bjorn Andersson <andersson@kernel.org> <bjorn.andersson@linaro.org>
+Bjorn Andersson <andersson@kernel.org> <bjorn.andersson@sonymobile.com>
 Björn Steinbrink <B.Steinbrink@gmx.de>
 Björn Töpel <bjorn@kernel.org> <bjorn.topel@gmail.com>
 Björn Töpel <bjorn@kernel.org> <bjorn.topel@intel.com>
@@ -98,8 +101,7 @@ Christian Brauner <brauner@kernel.org> <christian.brauner@ubuntu.com>
 Christian Marangi <ansuelsmth@gmail.com>
 Christophe Ricard <christophe.ricard@gmail.com>
 Christoph Hellwig <hch@lst.de>
-Colin Ian King <colin.king@intel.com> <colin.king@canonical.com>
-Colin Ian King <colin.king@intel.com> <colin.i.king@gmail.com>
+Colin Ian King <colin.i.king@gmail.com> <colin.king@canonical.com>
 Corey Minyard <minyard@acm.org>
 Damian Hobson-Garcia <dhobsong@igel.co.jp>
 Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com>
@@ -150,6 +152,8 @@ Greg Kroah-Hartman <gregkh@suse.de>
 Greg Kroah-Hartman <greg@kroah.com>
 Greg Kurz <groug@kaod.org> <gkurz@linux.vnet.ibm.com>
 Gregory CLEMENT <gregory.clement@bootlin.com> <gregory.clement@free-electrons.com>
+Guilherme G. Piccoli <kernel@gpiccoli.net> <gpiccoli@linux.vnet.ibm.com>
+Guilherme G. Piccoli <kernel@gpiccoli.net> <gpiccoli@canonical.com>
 Guo Ren <guoren@kernel.org> <guoren@linux.alibaba.com>
 Guo Ren <guoren@kernel.org> <ren_guo@c-sky.com>
 Gustavo Padovan <gustavo@las.ic.unicamp.br>
@@ -253,6 +257,7 @@ Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de>
 Li Yang <leoyang.li@nxp.com> <leoli@freescale.com>
 Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org>
 Lorenzo Pieralisi <lpieralisi@kernel.org> <lorenzo.pieralisi@arm.com>
+Luca Ceresoli <luca.ceresoli@bootlin.com> <luca@lucaceresoli.net>
 Lukasz Luba <lukasz.luba@arm.com> <l.luba@partner.samsung.com>
 Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com>
 Maciej W. Rozycki <macro@orcam.me.uk> <macro@linux-mips.org>
@@ -313,6 +318,7 @@ Morten Welinder <welinder@troll.com>
 Mythri P K <mythripk@ti.com>
 Nadia Yvette Chambers <nyc@holomorphy.com> William Lee Irwin III <wli@holomorphy.com>
 Nathan Chancellor <nathan@kernel.org> <natechancellor@gmail.com>
+Neil Armstrong <neil.armstrong@linaro.org> <narmstrong@baylibre.com>
 Nguyen Anh Quynh <aquynh@gmail.com>
 Nicholas Piggin <npiggin@gmail.com> <npiggen@suse.de>
 Nicholas Piggin <npiggin@gmail.com> <npiggin@kernel.dk>
diff --git a/.rustfmt.toml b/.rustfmt.toml
new file mode 100644
index 000000000000..3de5cc497465
--- /dev/null
+++ b/.rustfmt.toml
@@ -0,0 +1,12 @@
+edition = "2021"
+newline_style = "Unix"
+
+# Unstable options that help catching some mistakes in formatting and that we may want to enable
+# when they become stable.
+#
+# They are kept here since they are useful to run from time to time.
+#format_code_in_doc_comments = true
+#reorder_impl_items = true
+#comment_width = 100
+#wrap_comments = true
+#normalize_comments = true
diff --git a/Documentation/ABI/testing/sysfs-bus-bcma b/Documentation/ABI/testing/sysfs-bus-bcma
index 721b4aea3020..e93d3ddca844 100644
--- a/Documentation/ABI/testing/sysfs-bus-bcma
+++ b/Documentation/ABI/testing/sysfs-bus-bcma
@@ -3,7 +3,7 @@ Date:		May 2011
 KernelVersion:	3.0
 Contact:	Rafał Miłecki <zajec5@gmail.com>
 Description:
-		Each BCMA core has it's manufacturer id. See
+		Each BCMA core has its manufacturer id. See
 		include/linux/bcma/bcma.h for possible values.
 
 What:		/sys/bus/bcma/devices/.../id
diff --git a/Documentation/ABI/testing/sysfs-bus-fcoe b/Documentation/ABI/testing/sysfs-bus-fcoe
index 8fe787cc4ab7..5a4f2091ac37 100644
--- a/Documentation/ABI/testing/sysfs-bus-fcoe
+++ b/Documentation/ABI/testing/sysfs-bus-fcoe
@@ -31,7 +31,7 @@ Description:	'FCoE Controller' instances on the fcoe bus.
 		1) Write interface name to ctlr_create 2) Configure the FCoE
 		Controller (ctlr_X) 3) Enable the FCoE Controller to begin
 		discovery and login. The FCoE Controller is destroyed by
-		writing it's name, i.e. ctlr_X to the ctlr_delete file.
+		writing its name, i.e. ctlr_X to the ctlr_delete file.
 
 Attributes:
 
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-proximity b/Documentation/ABI/testing/sysfs-bus-iio-proximity
index 3aac6dab8775..9b9d1cc9b703 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-proximity
+++ b/Documentation/ABI/testing/sysfs-bus-iio-proximity
@@ -18,7 +18,7 @@ Description:
 		on the signal from which time of flight measurements are
 		taken.
 		The appropriate values to take is dependent on both the
-		sensor and it's operating environment:
+		sensor and its operating environment:
 		* as3935 (0-31 range)
 		18 = indoors (default)
 		14 = outdoors
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 5bf61881f012..f54867cadb0f 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -296,7 +296,7 @@ Description:	Processor frequency boosting control
 
 		This switch controls the boost setting for the whole system.
 		Boosting allows the CPU and the firmware to run at a frequency
-		beyond it's nominal limit.
+		beyond its nominal limit.
 
 		More details can be found in
 		Documentation/admin-guide/pm/cpufreq.rst
@@ -523,6 +523,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
 		/sys/devices/system/cpu/vulnerabilities/itlb_multihit
 		/sys/devices/system/cpu/vulnerabilities/mmio_stale_data
+		/sys/devices/system/cpu/vulnerabilities/retbleed
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Information about CPU vulnerabilities
diff --git a/Documentation/ABI/testing/sysfs-platform-chipidea-usb2 b/Documentation/ABI/testing/sysfs-platform-chipidea-usb2
index b0f4684a83fe..b9f7d924f28a 100644
--- a/Documentation/ABI/testing/sysfs-platform-chipidea-usb2
+++ b/Documentation/ABI/testing/sysfs-platform-chipidea-usb2
@@ -2,8 +2,8 @@ What:		/sys/bus/platform/devices/ci_hdrc.0/role
 Date:		Mar 2017
 Contact:	Peter Chen <peter.chen@nxp.com>
 Description:
-		It returns string "gadget" or "host" when read it, it indicates
-		current controller role.
+		When read, it returns string "gadget" or "host", indicating
+		the current controller role.
 
-		It will do role switch when write "gadget" or "host" to it.
+		It will do role switch when "gadget" or "host" is written to it.
 		Only controller at dual-role configuration supports writing.
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power
index 90ec4987074b..f99d433ff311 100644
--- a/Documentation/ABI/testing/sysfs-power
+++ b/Documentation/ABI/testing/sysfs-power
@@ -152,7 +152,7 @@ Description:
 		case further investigation is required to determine which
 		device is causing the problem.  Note that genuine RTC clock
 		values (such as when pm_trace has not been used), can still
-		match a device and output it's name here.
+		match a device and output its name here.
 
 What:		/sys/power/pm_async
 Date:		January 2009
diff --git a/Documentation/RCU/checklist.rst b/Documentation/RCU/checklist.rst
index 42cc5d891bd2..048c5bc1f813 100644
--- a/Documentation/RCU/checklist.rst
+++ b/Documentation/RCU/checklist.rst
@@ -66,8 +66,13 @@ over a rather long period of time, but improvements are always welcome!
 	As a rough rule of thumb, any dereference of an RCU-protected
 	pointer must be covered by rcu_read_lock(), rcu_read_lock_bh(),
 	rcu_read_lock_sched(), or by the appropriate update-side lock.
-	Disabling of preemption can serve as rcu_read_lock_sched(), but
-	is less readable and prevents lockdep from detecting locking issues.
+	Explicit disabling of preemption (preempt_disable(), for example)
+	can serve as rcu_read_lock_sched(), but is less readable and
+	prevents lockdep from detecting locking issues.
+
+	Please not that you *cannot* rely on code known to be built
+	only in non-preemptible kernels.  Such code can and will break,
+	especially in kernels built with CONFIG_PREEMPT_COUNT=y.
 
 	Letting RCU-protected pointers "leak" out of an RCU read-side
 	critical section is every bit as bad as letting them leak out
@@ -185,6 +190,9 @@ over a rather long period of time, but improvements are always welcome!
 
 5.	If call_rcu() or call_srcu() is used, the callback function will
 	be called from softirq context.  In particular, it cannot block.
+	If you need the callback to block, run that code in a workqueue
+	handler scheduled from the callback.  The queue_rcu_work()
+	function does this for you in the case of call_rcu().
 
 6.	Since synchronize_rcu() can block, it cannot be called
 	from any sort of irq context.  The same rule applies
@@ -297,7 +305,8 @@ over a rather long period of time, but improvements are always welcome!
 		the machine.
 
 	d.	Periodically invoke synchronize_rcu(), permitting a limited
-		number of updates per grace period.
+		number of updates per grace period.  Better yet, periodically
+		invoke rcu_barrier() to wait for all outstanding callbacks.
 
 	The same cautions apply to call_srcu() and kfree_rcu().
 
@@ -477,6 +486,6 @@ over a rather long period of time, but improvements are always welcome!
 	So if you need to wait for both an RCU grace period and for
 	all pre-existing call_rcu() callbacks, you will need to execute
 	both rcu_barrier() and synchronize_rcu(), if necessary, using
-	something like workqueues to to execute them concurrently.
+	something like workqueues to execute them concurrently.
 
 	See rcubarrier.rst for more information.
diff --git a/Documentation/RCU/lockdep.rst b/Documentation/RCU/lockdep.rst
index cc860a0c296b..a94f55991a71 100644
--- a/Documentation/RCU/lockdep.rst
+++ b/Documentation/RCU/lockdep.rst
@@ -61,7 +61,7 @@ checking of rcu_dereference() primitives:
 	rcu_access_pointer(p):
 		Return the value of the pointer and omit all barriers,
 		but retain the compiler constraints that prevent duplicating
-		or coalescsing.  This is useful when when testing the
+		or coalescsing.  This is useful when testing the
 		value of the pointer itself, for example, against NULL.
 
 The rcu_dereference_check() check expression can be any boolean
diff --git a/Documentation/RCU/rcu_dereference.rst b/Documentation/RCU/rcu_dereference.rst
index 0b418a5b243c..81e828c8313b 100644
--- a/Documentation/RCU/rcu_dereference.rst
+++ b/Documentation/RCU/rcu_dereference.rst
@@ -128,10 +128,16 @@ Follow these rules to keep your RCU code working properly:
 		This sort of comparison occurs frequently when scanning
 		RCU-protected circular linked lists.
 
-		Note that if checks for being within an RCU read-side
-		critical section are not required and the pointer is never
-		dereferenced, rcu_access_pointer() should be used in place
-		of rcu_dereference().
+		Note that if the pointer comparison is done outside
+		of an RCU read-side critical section, and the pointer
+		is never dereferenced, rcu_access_pointer() should be
+		used in place of rcu_dereference().  In most cases,
+		it is best to avoid accidental dereferences by testing
+		the rcu_access_pointer() return value directly, without
+		assigning it to a variable.
+
+		Within an RCU read-side critical section, there is little
+		reason to use rcu_access_pointer().
 
 	-	The comparison is against a pointer that references memory
 		that was initialized "a long time ago."  The reason
diff --git a/Documentation/RCU/whatisRCU.rst b/Documentation/RCU/whatisRCU.rst
index 77ea260efd12..1c747ac3f2c8 100644
--- a/Documentation/RCU/whatisRCU.rst
+++ b/Documentation/RCU/whatisRCU.rst
@@ -6,13 +6,15 @@ What is RCU?  --  "Read, Copy, Update"
 Please note that the "What is RCU?" LWN series is an excellent place
 to start learning about RCU:
 
-| 1.	What is RCU, Fundamentally?  http://lwn.net/Articles/262464/
-| 2.	What is RCU? Part 2: Usage   http://lwn.net/Articles/263130/
-| 3.	RCU part 3: the RCU API      http://lwn.net/Articles/264090/
-| 4.	The RCU API, 2010 Edition    http://lwn.net/Articles/418853/
-| 	2010 Big API Table           http://lwn.net/Articles/419086/
-| 5.	The RCU API, 2014 Edition    http://lwn.net/Articles/609904/
-|	2014 Big API Table           http://lwn.net/Articles/609973/
+| 1.	What is RCU, Fundamentally?  https://lwn.net/Articles/262464/
+| 2.	What is RCU? Part 2: Usage   https://lwn.net/Articles/263130/
+| 3.	RCU part 3: the RCU API      https://lwn.net/Articles/264090/
+| 4.	The RCU API, 2010 Edition    https://lwn.net/Articles/418853/
+| 	2010 Big API Table           https://lwn.net/Articles/419086/
+| 5.	The RCU API, 2014 Edition    https://lwn.net/Articles/609904/
+|	2014 Big API Table           https://lwn.net/Articles/609973/
+| 6.	The RCU API, 2019 Edition    https://lwn.net/Articles/777036/
+|	2019 Big API Table           https://lwn.net/Articles/777165/
 
 
 What is RCU?
@@ -915,13 +917,18 @@ which an RCU reference is held include:
 The understanding that RCU provides a reference that only prevents a
 change of type is particularly visible with objects allocated from a
 slab cache marked ``SLAB_TYPESAFE_BY_RCU``.  RCU operations may yield a
-reference to an object from such a cache that has been concurrently
-freed and the memory reallocated to a completely different object,
-though of the same type.  In this case RCU doesn't even protect the
-identity of the object from changing, only its type.  So the object
-found may not be the one expected, but it will be one where it is safe
-to take a reference or spinlock and then confirm that the identity
-matches the expectations.
+reference to an object from such a cache that has been concurrently freed
+and the memory reallocated to a completely different object, though of
+the same type.  In this case RCU doesn't even protect the identity of the
+object from changing, only its type.  So the object found may not be the
+one expected, but it will be one where it is safe to take a reference
+(and then potentially acquiring a spinlock), allowing subsequent code
+to check whether the identity matches expectations.  It is tempting
+to simply acquire the spinlock without first taking the reference, but
+unfortunately any spinlock in a ``SLAB_TYPESAFE_BY_RCU`` object must be
+initialized after each and every call to kmem_cache_alloc(), which renders
+reference-free spinlock acquisition completely unsafe.  Therefore, when
+using ``SLAB_TYPESAFE_BY_RCU``, make proper use of a reference counter.
 
 With traditional reference counting -- such as that implemented by the
 kref library in Linux -- there is typically code that runs when the last
@@ -1057,14 +1064,20 @@ SRCU: Initialization/cleanup::
 	init_srcu_struct
 	cleanup_srcu_struct
 
-All: lockdep-checked RCU-protected pointer access::
+All: lockdep-checked RCU utility APIs::
 
-	rcu_access_pointer
-	rcu_dereference_raw
 	RCU_LOCKDEP_WARN
 	rcu_sleep_check
 	RCU_NONIDLE
 
+All: Unchecked RCU-protected pointer access::
+
+	rcu_dereference_raw
+
+All: Unchecked RCU-protected pointer access with dereferencing prohibited::
+
+	rcu_access_pointer
+
 See the comment headers in the source code (or the docbook generated
 from them) for more information.
 
diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst
index caa3c09a5c3f..9a969c0157f1 100644
--- a/Documentation/admin-guide/README.rst
+++ b/Documentation/admin-guide/README.rst
@@ -1,9 +1,9 @@
 .. _readme:
 
-Linux kernel release 5.x <http://kernel.org/>
+Linux kernel release 6.x <http://kernel.org/>
 =============================================
 
-These are the release notes for Linux version 5.  Read them carefully,
+These are the release notes for Linux version 6.  Read them carefully,
 as they tell you what this is all about, explain how to install the
 kernel, and what to do if something goes wrong.
 
@@ -63,7 +63,7 @@ Installing the kernel source
    directory where you have permissions (e.g. your home directory) and
    unpack it::
 
-     xz -cd linux-5.x.tar.xz | tar xvf -
+     xz -cd linux-6.x.tar.xz | tar xvf -
 
    Replace "X" with the version number of the latest kernel.
 
@@ -72,12 +72,12 @@ Installing the kernel source
    files.  They should match the library, and not get messed up by
    whatever the kernel-du-jour happens to be.
 
- - You can also upgrade between 5.x releases by patching.  Patches are
+ - You can also upgrade between 6.x releases by patching.  Patches are
    distributed in the xz format.  To install by patching, get all the
    newer patch files, enter the top level directory of the kernel source
-   (linux-5.x) and execute::
+   (linux-6.x) and execute::
 
-     xz -cd ../patch-5.x.xz | patch -p1
+     xz -cd ../patch-6.x.xz | patch -p1
 
    Replace "x" for all versions bigger than the version "x" of your current
    source tree, **in_order**, and you should be ok.  You may want to remove
@@ -85,13 +85,13 @@ Installing the kernel source
    that there are no failed patches (some-file-name# or some-file-name.rej).
    If there are, either you or I have made a mistake.
 
-   Unlike patches for the 5.x kernels, patches for the 5.x.y kernels
+   Unlike patches for the 6.x kernels, patches for the 6.x.y kernels
    (also known as the -stable kernels) are not incremental but instead apply
-   directly to the base 5.x kernel.  For example, if your base kernel is 5.0
-   and you want to apply the 5.0.3 patch, you must not first apply the 5.0.1
-   and 5.0.2 patches. Similarly, if you are running kernel version 5.0.2 and
-   want to jump to 5.0.3, you must first reverse the 5.0.2 patch (that is,
-   patch -R) **before** applying the 5.0.3 patch. You can read more on this in
+   directly to the base 6.x kernel.  For example, if your base kernel is 6.0
+   and you want to apply the 6.0.3 patch, you must not first apply the 6.0.1
+   and 6.0.2 patches. Similarly, if you are running kernel version 6.0.2 and
+   want to jump to 6.0.3, you must first reverse the 6.0.2 patch (that is,
+   patch -R) **before** applying the 6.0.3 patch. You can read more on this in
    :ref:`Documentation/process/applying-patches.rst <applying_patches>`.
 
    Alternatively, the script patch-kernel can be used to automate this
@@ -114,7 +114,7 @@ Installing the kernel source
 Software requirements
 ---------------------
 
-   Compiling and running the 5.x kernels requires up-to-date
+   Compiling and running the 6.x kernels requires up-to-date
    versions of various software packages.  Consult
    :ref:`Documentation/process/changes.rst <changes>` for the minimum version numbers
    required and how to get updates for these packages.  Beware that using
@@ -132,12 +132,12 @@ Build directory for the kernel
    place for the output files (including .config).
    Example::
 
-     kernel source code: /usr/src/linux-5.x
+     kernel source code: /usr/src/linux-6.x
      build directory:    /home/name/build/kernel
 
    To configure and build the kernel, use::
 
-     cd /usr/src/linux-5.x
+     cd /usr/src/linux-6.x
      make O=/home/name/build/kernel menuconfig
      make O=/home/name/build/kernel
      sudo make O=/home/name/build/kernel modules_install install
@@ -262,8 +262,6 @@ Compiling the kernel
  - Make sure you have at least gcc 5.1 available.
    For more information, refer to :ref:`Documentation/process/changes.rst <changes>`.
 
-   Please note that you can still run a.out user programs with this kernel.
-
  - Do a ``make`` to create a compressed kernel image. It is also
    possible to do ``make install`` if you have lilo installed to suit the
    kernel makefiles, but you may want to check your particular lilo setup first.
@@ -332,85 +330,10 @@ Compiling the kernel
 If something goes wrong
 -----------------------
 
- - If you have problems that seem to be due to kernel bugs, please check
-   the file MAINTAINERS to see if there is a particular person associated
-   with the part of the kernel that you are having trouble with. If there
-   isn't anyone listed there, then the second best thing is to mail
-   them to me (torvalds@linux-foundation.org), and possibly to any other
-   relevant mailing-list or to the newsgroup.
-
- - In all bug-reports, *please* tell what kernel you are talking about,
-   how to duplicate the problem, and what your setup is (use your common
-   sense).  If the problem is new, tell me so, and if the problem is
-   old, please try to tell me when you first noticed it.
-
- - If the bug results in a message like::
-
-     unable to handle kernel paging request at address C0000010
-     Oops: 0002
-     EIP:   0010:XXXXXXXX
-     eax: xxxxxxxx   ebx: xxxxxxxx   ecx: xxxxxxxx   edx: xxxxxxxx
-     esi: xxxxxxxx   edi: xxxxxxxx   ebp: xxxxxxxx
-     ds: xxxx  es: xxxx  fs: xxxx  gs: xxxx
-     Pid: xx, process nr: xx
-     xx xx xx xx xx xx xx xx xx xx
-
-   or similar kernel debugging information on your screen or in your
-   system log, please duplicate it *exactly*.  The dump may look
-   incomprehensible to you, but it does contain information that may
-   help debugging the problem.  The text above the dump is also
-   important: it tells something about why the kernel dumped code (in
-   the above example, it's due to a bad kernel pointer). More information
-   on making sense of the dump is in Documentation/admin-guide/bug-hunting.rst
-
- - If you compiled the kernel with CONFIG_KALLSYMS you can send the dump
-   as is, otherwise you will have to use the ``ksymoops`` program to make
-   sense of the dump (but compiling with CONFIG_KALLSYMS is usually preferred).
-   This utility can be downloaded from
-   https://www.kernel.org/pub/linux/utils/kernel/ksymoops/ .
-   Alternatively, you can do the dump lookup by hand:
-
- - In debugging dumps like the above, it helps enormously if you can
-   look up what the EIP value means.  The hex value as such doesn't help
-   me or anybody else very much: it will depend on your particular
-   kernel setup.  What you should do is take the hex value from the EIP
-   line (ignore the ``0010:``), and look it up in the kernel namelist to
-   see which kernel function contains the offending address.
-
-   To find out the kernel function name, you'll need to find the system
-   binary associated with the kernel that exhibited the symptom.  This is
-   the file 'linux/vmlinux'.  To extract the namelist and match it against
-   the EIP from the kernel crash, do::
-
-     nm vmlinux | sort | less
-
-   This will give you a list of kernel addresses sorted in ascending
-   order, from which it is simple to find the function that contains the
-   offending address.  Note that the address given by the kernel
-   debugging messages will not necessarily match exactly with the
-   function addresses (in fact, that is very unlikely), so you can't
-   just 'grep' the list: the list will, however, give you the starting
-   point of each kernel function, so by looking for the function that
-   has a starting address lower than the one you are searching for but
-   is followed by a function with a higher address you will find the one
-   you want.  In fact, it may be a good idea to include a bit of
-   "context" in your problem report, giving a few lines around the
-   interesting one.
-
-   If you for some reason cannot do the above (you have a pre-compiled
-   kernel image or similar), telling me as much about your setup as
-   possible will help.  Please read
-   'Documentation/admin-guide/reporting-issues.rst' for details.
-
- - Alternatively, you can use gdb on a running kernel. (read-only; i.e. you
-   cannot change values or set break points.) To do this, first compile the
-   kernel with -g; edit arch/x86/Makefile appropriately, then do a ``make
-   clean``. You'll also need to enable CONFIG_PROC_FS (via ``make config``).
-
-   After you've rebooted with the new kernel, do ``gdb vmlinux /proc/kcore``.
-   You can now use all the usual gdb commands. The command to look up the
-   point where your system crashed is ``l *0xXXXXXXXX``. (Replace the XXXes
-   with the EIP value.)
-
-   gdb'ing a non-running kernel currently fails because ``gdb`` (wrongly)
-   disregards the starting offset for which the kernel is compiled.
+If you have problems that seem to be due to kernel bugs, please follow the
+instructions at 'Documentation/admin-guide/reporting-issues.rst'.
+
+Hints on understanding kernel bug reports are in
+'Documentation/admin-guide/bug-hunting.rst'. More on debugging the kernel
+with gdb is in 'Documentation/dev-tools/gdb-kernel-debugging.rst' and
+'Documentation/dev-tools/kgdb.rst'.
diff --git a/Documentation/admin-guide/acpi/dsdt-override.rst b/Documentation/admin-guide/acpi/dsdt-override.rst
deleted file mode 100644
index 50bd7f194bf4..000000000000
--- a/Documentation/admin-guide/acpi/dsdt-override.rst
+++ /dev/null
@@ -1,13 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-
-===============
-Overriding DSDT
-===============
-
-Linux supports a method of overriding the BIOS DSDT:
-
-CONFIG_ACPI_CUSTOM_DSDT - builds the image into the kernel.
-
-When to use this method is described in detail on the
-Linux/ACPI home page:
-https://01.org/linux-acpi/documentation/overriding-dsdt
diff --git a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
index 9393c50b5afc..c98fd11907cc 100644
--- a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
+++ b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
@@ -230,6 +230,20 @@ The possible values in this file are:
      * - 'Mitigation: Clear CPU buffers'
        - The processor is vulnerable and the CPU buffer clearing mitigation is
          enabled.
+     * - 'Unknown: No mitigations'
+       - The processor vulnerability status is unknown because it is
+	 out of Servicing period. Mitigation is not attempted.
+
+Definitions:
+------------
+
+Servicing period: The process of providing functional and security updates to
+Intel processors or platforms, utilizing the Intel Platform Update (IPU)
+process or other similar mechanisms.
+
+End of Servicing Updates (ESU): ESU is the date at which Intel will no
+longer provide Servicing, such as through IPU or other similar update
+processes. ESU dates will typically be aligned to end of quarter.
 
 If the processor is vulnerable then the following information is appended to
 the above information:
diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst
index 2ce2a38cdd55..c4dcdb3d0d45 100644
--- a/Documentation/admin-guide/hw-vuln/spectre.rst
+++ b/Documentation/admin-guide/hw-vuln/spectre.rst
@@ -613,6 +613,7 @@ kernel command line.
                 eibrs                   enhanced IBRS
                 eibrs,retpoline         enhanced IBRS + Retpolines
                 eibrs,lfence            enhanced IBRS + LFENCE
+                ibrs                    use IBRS to protect kernel
 
 		Not specifying this option is equivalent to
 		spectre_v2=auto.
diff --git a/Documentation/admin-guide/kdump/vmcoreinfo.rst b/Documentation/admin-guide/kdump/vmcoreinfo.rst
index 8419019b6a88..6726f439958c 100644
--- a/Documentation/admin-guide/kdump/vmcoreinfo.rst
+++ b/Documentation/admin-guide/kdump/vmcoreinfo.rst
@@ -200,7 +200,7 @@ prb
 
 A pointer to the printk ringbuffer (struct printk_ringbuffer). This
 may be pointing to the static boot ringbuffer or the dynamically
-allocated ringbuffer, depending on when the the core dump occurred.
+allocated ringbuffer, depending on when the core dump occurred.
 Used by user-space tools to read the active kernel log buffer.
 
 printk_rb_static
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index d7f30902fda0..2bc11a61c4d0 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3805,6 +3805,10 @@
 
 	nox2apic	[X86-64,APIC] Do not enable x2APIC mode.
 
+			NOTE: this parameter will be ignored on systems with the
+			LEGACY_XAPIC_DISABLED bit set in the
+			IA32_XAPIC_DISABLE_STATUS MSR.
+
 	nps_mtm_hs_ctr=	[KNL,ARC]
 			This parameter sets the maximum duration, in
 			cycles, each HW thread of the CTOP can run
@@ -5331,6 +5335,8 @@
 	rodata=		[KNL]
 		on	Mark read-only kernel memory as read-only (default).
 		off	Leave read-only kernel memory writable for debugging.
+		full	Mark read-only kernel memory and aliases as read-only
+		        [arm64]
 
 	rockchip.usb_uart
 			Enable the uart passthrough on the designated usb port
diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst
index d52f572a9029..ca91ecc29078 100644
--- a/Documentation/admin-guide/mm/damon/usage.rst
+++ b/Documentation/admin-guide/mm/damon/usage.rst
@@ -50,10 +50,10 @@ For a short example, users can monitor the virtual address space of a given
 workload as below. ::
 
     # cd /sys/kernel/mm/damon/admin/
-    # echo 1 > kdamonds/nr && echo 1 > kdamonds/0/contexts/nr
+    # echo 1 > kdamonds/nr_kdamonds && echo 1 > kdamonds/0/contexts/nr_contexts
     # echo vaddr > kdamonds/0/contexts/0/operations
-    # echo 1 > kdamonds/0/contexts/0/targets/nr
-    # echo $(pidof <workload>) > kdamonds/0/contexts/0/targets/0/pid
+    # echo 1 > kdamonds/0/contexts/0/targets/nr_targets
+    # echo $(pidof <workload>) > kdamonds/0/contexts/0/targets/0/pid_target
     # echo on > kdamonds/0/state
 
 Files Hierarchy
@@ -366,12 +366,12 @@ memory rate becomes larger than 60%, or lower than 30%". ::
     # echo 1 > kdamonds/0/contexts/0/schemes/nr_schemes
     # cd kdamonds/0/contexts/0/schemes/0
     # # set the basic access pattern and the action
-    # echo 4096 > access_patterns/sz/min
-    # echo 8192 > access_patterns/sz/max
-    # echo 0 > access_patterns/nr_accesses/min
-    # echo 5 > access_patterns/nr_accesses/max
-    # echo 10 > access_patterns/age/min
-    # echo 20 > access_patterns/age/max
+    # echo 4096 > access_pattern/sz/min
+    # echo 8192 > access_pattern/sz/max
+    # echo 0 > access_pattern/nr_accesses/min
+    # echo 5 > access_pattern/nr_accesses/max
+    # echo 10 > access_pattern/age/min
+    # echo 20 > access_pattern/age/max
     # echo pageout > action
     # # set quotas
     # echo 10 > quotas/ms
diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst
index 8e2727dc18d4..19f27c0d92e0 100644
--- a/Documentation/admin-guide/mm/hugetlbpage.rst
+++ b/Documentation/admin-guide/mm/hugetlbpage.rst
@@ -65,7 +65,7 @@ HugePages_Surp
 	may be temporarily larger than the maximum number of surplus huge
 	pages when the system is under memory pressure.
 Hugepagesize
-	is the default hugepage size (in Kb).
+	is the default hugepage size (in kB).
 Hugetlb
         is the total amount of memory (in kB), consumed by huge
         pages of all sizes.
diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst
index 805f2281e000..60d44165fba7 100644
--- a/Documentation/admin-guide/sysctl/net.rst
+++ b/Documentation/admin-guide/sysctl/net.rst
@@ -271,7 +271,7 @@ poll cycle or the number of packets processed reaches netdev_budget.
 netdev_max_backlog
 ------------------
 
-Maximum number  of  packets,  queued  on  the  INPUT  side, when the interface
+Maximum number of packets, queued on the INPUT side, when the interface
 receives packets faster than kernel can process them.
 
 netdev_rss_key
diff --git a/Documentation/admin-guide/tainted-kernels.rst b/Documentation/admin-guide/tainted-kernels.rst
index 7d80e8c307d1..92a8a07f5c43 100644
--- a/Documentation/admin-guide/tainted-kernels.rst
+++ b/Documentation/admin-guide/tainted-kernels.rst
@@ -134,6 +134,12 @@ More detailed explanation for tainting
        scsi/snic on something else than x86_64, scsi/ips on non
        x86/x86_64/itanium, have broken firmware settings for the
        irqchip/irq-gic on arm64 ...).
+     - x86/x86_64: Microcode late loading is dangerous and will result in
+       tainting the kernel. It requires that all CPUs rendezvous to make sure
+       the update happens when the system is as quiescent as possible. However,
+       a higher priority MCE/SMI/NMI can move control flow away from that
+       rendezvous and interrupt the update, which can be detrimental to the
+       machine.
 
  3)  ``R`` if a module was force unloaded by ``rmmod -f``, ``' '`` if all
      modules were unloaded normally.
diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst
index 52b75a25c205..311021f2e560 100644
--- a/Documentation/arm64/elf_hwcaps.rst
+++ b/Documentation/arm64/elf_hwcaps.rst
@@ -242,44 +242,34 @@ HWCAP2_MTE3
     by Documentation/arm64/memory-tagging-extension.rst.
 
 HWCAP2_SME
-
     Functionality implied by ID_AA64PFR1_EL1.SME == 0b0001, as described
     by Documentation/arm64/sme.rst.
 
 HWCAP2_SME_I16I64
-
     Functionality implied by ID_AA64SMFR0_EL1.I16I64 == 0b1111.
 
 HWCAP2_SME_F64F64
-
     Functionality implied by ID_AA64SMFR0_EL1.F64F64 == 0b1.
 
 HWCAP2_SME_I8I32
-
     Functionality implied by ID_AA64SMFR0_EL1.I8I32 == 0b1111.
 
 HWCAP2_SME_F16F32
-
     Functionality implied by ID_AA64SMFR0_EL1.F16F32 == 0b1.
 
 HWCAP2_SME_B16F32
-
     Functionality implied by ID_AA64SMFR0_EL1.B16F32 == 0b1.
 
 HWCAP2_SME_F32F32
-
     Functionality implied by ID_AA64SMFR0_EL1.F32F32 == 0b1.
 
 HWCAP2_SME_FA64
-
     Functionality implied by ID_AA64SMFR0_EL1.FA64 == 0b1.
 
 HWCAP2_WFXT
-
     Functionality implied by ID_AA64ISAR2_EL1.WFXT == 0b0010.
 
 HWCAP2_EBF16
-
     Functionality implied by ID_AA64ISAR1_EL1.BF16 == 0b0010.
 
 4. Unused AT_HWCAP bits
diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst
index 33b04db8408f..fda97b3fcf01 100644
--- a/Documentation/arm64/silicon-errata.rst
+++ b/Documentation/arm64/silicon-errata.rst
@@ -52,6 +52,8 @@ stable kernels.
 | Allwinner      | A64/R18         | UNKNOWN1        | SUN50I_ERRATUM_UNKNOWN1     |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A510     | #2457168        | ARM64_ERRATUM_2457168       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A510     | #2064142        | ARM64_ERRATUM_2064142       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A510     | #2038923        | ARM64_ERRATUM_2038923       |
diff --git a/Documentation/atomic_bitops.txt b/Documentation/atomic_bitops.txt
index 093cdaefdb37..edea4656c5c0 100644
--- a/Documentation/atomic_bitops.txt
+++ b/Documentation/atomic_bitops.txt
@@ -58,13 +58,11 @@ Like with atomic_t, the rule of thumb is:
 
  - RMW operations that have a return value are fully ordered.
 
- - RMW operations that are conditional are unordered on FAILURE,
-   otherwise the above rules apply. In the case of test_and_{}_bit() operations,
-   if the bit in memory is unchanged by the operation then it is deemed to have
-   failed.
+ - RMW operations that are conditional are fully ordered.
 
-Except for a successful test_and_set_bit_lock() which has ACQUIRE semantics and
-clear_bit_unlock() which has RELEASE semantics.
+Except for a successful test_and_set_bit_lock() which has ACQUIRE semantics,
+clear_bit_unlock() which has RELEASE semantics and test_bit_acquire which has
+ACQUIRE semantics.
 
 Since a platform only has a single means of achieving atomic operations
 the same barriers as for atomic_t are used, see atomic_t.txt.
diff --git a/Documentation/block/index.rst b/Documentation/block/index.rst
index 68f115f2b1c6..c4c73db748a8 100644
--- a/Documentation/block/index.rst
+++ b/Documentation/block/index.rst
@@ -23,3 +23,4 @@ Block
    stat
    switching-sched
    writeback_cache_control
+   ublk
diff --git a/Documentation/block/ublk.rst b/Documentation/block/ublk.rst
new file mode 100644
index 000000000000..2122d1a4a541
--- /dev/null
+++ b/Documentation/block/ublk.rst
@@ -0,0 +1,253 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========================================
+Userspace block device driver (ublk driver)
+===========================================
+
+Overview
+========
+
+ublk is a generic framework for implementing block device logic from userspace.
+The motivation behind it is that moving virtual block drivers into userspace,
+such as loop, nbd and similar can be very helpful. It can help to implement
+new virtual block device such as ublk-qcow2 (there are several attempts of
+implementing qcow2 driver in kernel).
+
+Userspace block devices are attractive because:
+
+- They can be written many programming languages.
+- They can use libraries that are not available in the kernel.
+- They can be debugged with tools familiar to application developers.
+- Crashes do not kernel panic the machine.
+- Bugs are likely to have a lower security impact than bugs in kernel
+  code.
+- They can be installed and updated independently of the kernel.
+- They can be used to simulate block device easily with user specified
+  parameters/setting for test/debug purpose
+
+ublk block device (``/dev/ublkb*``) is added by ublk driver. Any IO request
+on the device will be forwarded to ublk userspace program. For convenience,
+in this document, ``ublk server`` refers to generic ublk userspace
+program. ``ublksrv`` [#userspace]_ is one of such implementation. It
+provides ``libublksrv`` [#userspace_lib]_ library for developing specific
+user block device conveniently, while also generic type block device is
+included, such as loop and null. Richard W.M. Jones wrote userspace nbd device
+``nbdublk`` [#userspace_nbdublk]_  based on ``libublksrv`` [#userspace_lib]_.
+
+After the IO is handled by userspace, the result is committed back to the
+driver, thus completing the request cycle. This way, any specific IO handling
+logic is totally done by userspace, such as loop's IO handling, NBD's IO
+communication, or qcow2's IO mapping.
+
+``/dev/ublkb*`` is driven by blk-mq request-based driver. Each request is
+assigned by one queue wide unique tag. ublk server assigns unique tag to each
+IO too, which is 1:1 mapped with IO of ``/dev/ublkb*``.
+
+Both the IO request forward and IO handling result committing are done via
+``io_uring`` passthrough command; that is why ublk is also one io_uring based
+block driver. It has been observed that using io_uring passthrough command can
+give better IOPS than block IO; which is why ublk is one of high performance
+implementation of userspace block device: not only IO request communication is
+done by io_uring, but also the preferred IO handling in ublk server is io_uring
+based approach too.
+
+ublk provides control interface to set/get ublk block device parameters.
+The interface is extendable and kabi compatible: basically any ublk request
+queue's parameter or ublk generic feature parameters can be set/get via the
+interface. Thus, ublk is generic userspace block device framework.
+For example, it is easy to setup a ublk device with specified block
+parameters from userspace.
+
+Using ublk
+==========
+
+ublk requires userspace ublk server to handle real block device logic.
+
+Below is example of using ``ublksrv`` to provide ublk-based loop device.
+
+- add a device::
+
+     ublk add -t loop -f ublk-loop.img
+
+- format with xfs, then use it::
+
+     mkfs.xfs /dev/ublkb0
+     mount /dev/ublkb0 /mnt
+     # do anything. all IOs are handled by io_uring
+     ...
+     umount /mnt
+
+- list the devices with their info::
+
+     ublk list
+
+- delete the device::
+
+     ublk del -a
+     ublk del -n $ublk_dev_id
+
+See usage details in README of ``ublksrv`` [#userspace_readme]_.
+
+Design
+======
+
+Control plane
+-------------
+
+ublk driver provides global misc device node (``/dev/ublk-control``) for
+managing and controlling ublk devices with help of several control commands:
+
+- ``UBLK_CMD_ADD_DEV``
+
+  Add a ublk char device (``/dev/ublkc*``) which is talked with ublk server
+  WRT IO command communication. Basic device info is sent together with this
+  command. It sets UAPI structure of ``ublksrv_ctrl_dev_info``,
+  such as ``nr_hw_queues``, ``queue_depth``, and max IO request buffer size,
+  for which the info is negotiated with the driver and sent back to the server.
+  When this command is completed, the basic device info is immutable.
+
+- ``UBLK_CMD_SET_PARAMS`` / ``UBLK_CMD_GET_PARAMS``
+
+  Set or get parameters of the device, which can be either generic feature
+  related, or request queue limit related, but can't be IO logic specific,
+  because the driver does not handle any IO logic. This command has to be
+  sent before sending ``UBLK_CMD_START_DEV``.
+
+- ``UBLK_CMD_START_DEV``
+
+  After the server prepares userspace resources (such as creating per-queue
+  pthread & io_uring for handling ublk IO), this command is sent to the
+  driver for allocating & exposing ``/dev/ublkb*``. Parameters set via
+  ``UBLK_CMD_SET_PARAMS`` are applied for creating the device.
+
+- ``UBLK_CMD_STOP_DEV``
+
+  Halt IO on ``/dev/ublkb*`` and remove the device. When this command returns,
+  ublk server will release resources (such as destroying per-queue pthread &
+  io_uring).
+
+- ``UBLK_CMD_DEL_DEV``
+
+  Remove ``/dev/ublkc*``. When this command returns, the allocated ublk device
+  number can be reused.
+
+- ``UBLK_CMD_GET_QUEUE_AFFINITY``
+
+  When ``/dev/ublkc`` is added, the driver creates block layer tagset, so
+  that each queue's affinity info is available. The server sends
+  ``UBLK_CMD_GET_QUEUE_AFFINITY`` to retrieve queue affinity info. It can
+  set up the per-queue context efficiently, such as bind affine CPUs with IO
+  pthread and try to allocate buffers in IO thread context.
+
+- ``UBLK_CMD_GET_DEV_INFO``
+
+  For retrieving device info via ``ublksrv_ctrl_dev_info``. It is the server's
+  responsibility to save IO target specific info in userspace.
+
+Data plane
+----------
+
+ublk server needs to create per-queue IO pthread & io_uring for handling IO
+commands via io_uring passthrough. The per-queue IO pthread
+focuses on IO handling and shouldn't handle any control & management
+tasks.
+
+The's IO is assigned by a unique tag, which is 1:1 mapping with IO
+request of ``/dev/ublkb*``.
+
+UAPI structure of ``ublksrv_io_desc`` is defined for describing each IO from
+the driver. A fixed mmaped area (array) on ``/dev/ublkc*`` is provided for
+exporting IO info to the server; such as IO offset, length, OP/flags and
+buffer address. Each ``ublksrv_io_desc`` instance can be indexed via queue id
+and IO tag directly.
+
+The following IO commands are communicated via io_uring passthrough command,
+and each command is only for forwarding the IO and committing the result
+with specified IO tag in the command data:
+
+- ``UBLK_IO_FETCH_REQ``
+
+  Sent from the server IO pthread for fetching future incoming IO requests
+  destined to ``/dev/ublkb*``. This command is sent only once from the server
+  IO pthread for ublk driver to setup IO forward environment.
+
+- ``UBLK_IO_COMMIT_AND_FETCH_REQ``
+
+  When an IO request is destined to ``/dev/ublkb*``, the driver stores
+  the IO's ``ublksrv_io_desc`` to the specified mapped area; then the
+  previous received IO command of this IO tag (either ``UBLK_IO_FETCH_REQ``
+  or ``UBLK_IO_COMMIT_AND_FETCH_REQ)`` is completed, so the server gets
+  the IO notification via io_uring.
+
+  After the server handles the IO, its result is committed back to the
+  driver by sending ``UBLK_IO_COMMIT_AND_FETCH_REQ`` back. Once ublkdrv
+  received this command, it parses the result and complete the request to
+  ``/dev/ublkb*``. In the meantime setup environment for fetching future
+  requests with the same IO tag. That is, ``UBLK_IO_COMMIT_AND_FETCH_REQ``
+  is reused for both fetching request and committing back IO result.
+
+- ``UBLK_IO_NEED_GET_DATA``
+
+  With ``UBLK_F_NEED_GET_DATA`` enabled, the WRITE request will be firstly
+  issued to ublk server without data copy. Then, IO backend of ublk server
+  receives the request and it can allocate data buffer and embed its addr
+  inside this new io command. After the kernel driver gets the command,
+  data copy is done from request pages to this backend's buffer. Finally,
+  backend receives the request again with data to be written and it can
+  truly handle the request.
+
+  ``UBLK_IO_NEED_GET_DATA`` adds one additional round-trip and one
+  io_uring_enter() syscall. Any user thinks that it may lower performance
+  should not enable UBLK_F_NEED_GET_DATA. ublk server pre-allocates IO
+  buffer for each IO by default. Any new project should try to use this
+  buffer to communicate with ublk driver. However, existing project may
+  break or not able to consume the new buffer interface; that's why this
+  command is added for backwards compatibility so that existing projects
+  can still consume existing buffers.
+
+- data copy between ublk server IO buffer and ublk block IO request
+
+  The driver needs to copy the block IO request pages into the server buffer
+  (pages) first for WRITE before notifying the server of the coming IO, so
+  that the server can handle WRITE request.
+
+  When the server handles READ request and sends
+  ``UBLK_IO_COMMIT_AND_FETCH_REQ`` to the server, ublkdrv needs to copy
+  the server buffer (pages) read to the IO request pages.
+
+Future development
+==================
+
+Container-aware ublk deivice
+----------------------------
+
+ublk driver doesn't handle any IO logic. Its function is well defined
+for now and very limited userspace interfaces are needed, which is also
+well defined too. It is possible to make ublk devices container-aware block
+devices in future as Stefan Hajnoczi suggested [#stefan]_, by removing
+ADMIN privilege.
+
+Zero copy
+---------
+
+Zero copy is a generic requirement for nbd, fuse or similar drivers. A
+problem [#xiaoguang]_ Xiaoguang mentioned is that pages mapped to userspace
+can't be remapped any more in kernel with existing mm interfaces. This can
+occurs when destining direct IO to ``/dev/ublkb*``. Also, he reported that
+big requests (IO size >= 256 KB) may benefit a lot from zero copy.
+
+
+References
+==========
+
+.. [#userspace] https://github.com/ming1/ubdsrv
+
+.. [#userspace_lib] https://github.com/ming1/ubdsrv/tree/master/lib
+
+.. [#userspace_nbdublk] https://gitlab.com/rwmjones/libnbd/-/tree/nbdublk
+
+.. [#userspace_readme] https://github.com/ming1/ubdsrv/blob/master/README
+
+.. [#stefan] https://lore.kernel.org/linux-block/YoOr6jBfgVm8GvWg@stefanha-x1.localdomain/
+
+.. [#xiaoguang] https://lore.kernel.org/linux-block/YoOr6jBfgVm8GvWg@stefanha-x1.localdomain/
diff --git a/Documentation/bpf/instruction-set.rst b/Documentation/bpf/instruction-set.rst
index 1b0e6711dec9..0ac7ae40be37 100644
--- a/Documentation/bpf/instruction-set.rst
+++ b/Documentation/bpf/instruction-set.rst
@@ -133,7 +133,7 @@ code field of ``BPF_END``.
 The byte swap instructions operate on the destination register
 only and do not use a separate source register or immediate value.
 
-The 1-bit source operand field in the opcode is used to to select what byte
+The 1-bit source operand field in the opcode is used to select what byte
 order the operation convert from or to:
 
   =========  =====  =================================================
diff --git a/Documentation/bpf/map_cgroup_storage.rst b/Documentation/bpf/map_cgroup_storage.rst
index cab9543017bf..8e5fe532c07e 100644
--- a/Documentation/bpf/map_cgroup_storage.rst
+++ b/Documentation/bpf/map_cgroup_storage.rst
@@ -31,7 +31,7 @@ The map uses key of type of either ``__u64 cgroup_inode_id`` or
     };
 
 ``cgroup_inode_id`` is the inode id of the cgroup directory.
-``attach_type`` is the the program's attach type.
+``attach_type`` is the program's attach type.
 
 Linux 5.9 added support for type ``__u64 cgroup_inode_id`` as the key type.
 When this key type is used, then all attach types of the particular cgroup and
@@ -155,7 +155,7 @@ However, the BPF program can still only associate with one map of each type
 ``BPF_MAP_TYPE_CGROUP_STORAGE`` or more than one
 ``BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE``.
 
-In all versions, userspace may use the the attach parameters of cgroup and
+In all versions, userspace may use the attach parameters of cgroup and
 attach type pair in ``struct bpf_cgroup_storage_key`` as the key to the BPF map
 APIs to read or update the storage for a given attachment. For Linux 5.9
 attach type shared storages, only the first value in the struct, cgroup inode
diff --git a/Documentation/conf.py b/Documentation/conf.py
index 934727e23e0e..b50c85083149 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -15,6 +15,18 @@
 import sys
 import os
 import sphinx
+import shutil
+
+# helper
+# ------
+
+def have_command(cmd):
+    """Search ``cmd`` in the ``PATH`` environment.
+
+    If found, return True.
+    If not found, return False.
+    """
+    return shutil.which(cmd) is not None
 
 # Get Sphinx version
 major, minor, patch = sphinx.version_info[:3]
@@ -86,6 +98,7 @@ if major >= 3:
             "__used",
             "__weak",
             "noinline",
+            "__fix_address",
 
             # include/linux/memblock.h:
             "__init_memblock",
@@ -106,7 +119,32 @@ else:
 autosectionlabel_prefix_document = True
 autosectionlabel_maxdepth = 2
 
-extensions.append("sphinx.ext.imgmath")
+# Load math renderer:
+# For html builder, load imgmath only when its dependencies are met.
+# mathjax is the default math renderer since Sphinx 1.8.
+have_latex =  have_command('latex')
+have_dvipng = have_command('dvipng')
+load_imgmath = have_latex and have_dvipng
+
+# Respect SPHINX_IMGMATH (for html docs only)
+if 'SPHINX_IMGMATH' in os.environ:
+    env_sphinx_imgmath = os.environ['SPHINX_IMGMATH']
+    if 'yes' in env_sphinx_imgmath:
+        load_imgmath = True
+    elif 'no' in env_sphinx_imgmath:
+        load_imgmath = False
+    else:
+        sys.stderr.write("Unknown env SPHINX_IMGMATH=%s ignored.\n" % env_sphinx_imgmath)
+
+# Always load imgmath for Sphinx <1.8 or for epub docs
+load_imgmath = (load_imgmath or (major == 1 and minor < 8)
+                or 'epub' in sys.argv)
+
+if load_imgmath:
+    extensions.append("sphinx.ext.imgmath")
+    math_renderer = 'imgmath'
+else:
+    math_renderer = 'mathjax'
 
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']
@@ -332,7 +370,8 @@ html_static_path = ['sphinx-static']
 html_use_smartypants = False
 
 # Custom sidebar templates, maps document names to template names.
-#html_sidebars = {}
+# Note that the RTD theme ignores this.
+html_sidebars = { '**': ['searchbox.html', 'localtoc.html', 'sourcelink.html']}
 
 # Additional templates that should be rendered to pages, maps page names to
 # template names.
diff --git a/Documentation/asm-annotations.rst b/Documentation/core-api/asm-annotations.rst
index a64f2ca469d4..bc514ed59887 100644
--- a/Documentation/asm-annotations.rst
+++ b/Documentation/core-api/asm-annotations.rst
@@ -43,10 +43,11 @@ annotated objects like this, tools can be run on them to generate more useful
 information. In particular, on properly annotated objects, ``objtool`` can be
 run to check and fix the object if needed. Currently, ``objtool`` can report
 missing frame pointer setup/destruction in functions. It can also
-automatically generate annotations for :doc:`ORC unwinder <x86/orc-unwinder>`
+automatically generate annotations for the ORC unwinder
+(Documentation/x86/orc-unwinder.rst)
 for most code. Both of these are especially important to support reliable
-stack traces which are in turn necessary for :doc:`Kernel live patching
-<livepatch/livepatch>`.
+stack traces which are in turn necessary for kernel live patching
+(Documentation/livepatch/livepatch.rst).
 
 Caveat and Discussion
 ---------------------
diff --git a/Documentation/core-api/cpu_hotplug.rst b/Documentation/core-api/cpu_hotplug.rst
index c6f4ba2fb32d..f75778d37488 100644
--- a/Documentation/core-api/cpu_hotplug.rst
+++ b/Documentation/core-api/cpu_hotplug.rst
@@ -560,7 +560,7 @@ available:
   * cpuhp_state_remove_instance(state, node)
   * cpuhp_state_remove_instance_nocalls(state, node)
 
-The arguments are the same as for the the cpuhp_state_add_instance*()
+The arguments are the same as for the cpuhp_state_add_instance*()
 variants above.
 
 The functions differ in the way how the installed callbacks are treated:
diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index dc95df462eea..b0e7b4771fff 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -23,6 +23,7 @@ it.
    printk-formats
    printk-index
    symbol-namespaces
+   asm-annotations
 
 Data structures and low-level utilities
 =======================================
@@ -44,6 +45,8 @@ Library functionality that is used throughout the kernel.
    this_cpu_ops
    timekeeping
    errseq
+   wrappers/atomic_t
+   wrappers/atomic_bitops
 
 Low level entry and exit
 ========================
@@ -67,6 +70,7 @@ Documentation/locking/index.rst for more related documentation.
    local_ops
    padata
    ../RCU/index
+   wrappers/memory-barriers.rst
 
 Low-level hardware management
 =============================
diff --git a/Documentation/core-api/irq/irq-domain.rst b/Documentation/core-api/irq/irq-domain.rst
index d30b4d0a9769..f88a6ee67a35 100644
--- a/Documentation/core-api/irq/irq-domain.rst
+++ b/Documentation/core-api/irq/irq-domain.rst
@@ -71,7 +71,7 @@ variety of methods:
 Note that irq domain lookups must happen in contexts that are
 compatible with a RCU read-side critical section.
 
-The irq_create_mapping() function must be called *atleast once*
+The irq_create_mapping() function must be called *at least once*
 before any call to irq_find_mapping(), lest the descriptor will not
 be allocated.
 
diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst
index 5e89497ba314..dbe1aacc79d0 100644
--- a/Documentation/core-api/printk-formats.rst
+++ b/Documentation/core-api/printk-formats.rst
@@ -625,6 +625,16 @@ Examples::
 	%p4cc	Y10  little-endian (0x20303159)
 	%p4cc	NV12 big-endian (0xb231564e)
 
+Rust
+----
+
+::
+
+	%pA
+
+Only intended to be used from Rust code to format ``core::fmt::Arguments``.
+Do *not* use it from C.
+
 Thanks
 ======
 
diff --git a/Documentation/core-api/wrappers/atomic_bitops.rst b/Documentation/core-api/wrappers/atomic_bitops.rst
new file mode 100644
index 000000000000..bf24e4081a8f
--- /dev/null
+++ b/Documentation/core-api/wrappers/atomic_bitops.rst
@@ -0,0 +1,18 @@
+.. SPDX-License-Identifier: GPL-2.0
+   This is a simple wrapper to bring atomic_bitops.txt into the RST world
+   until such a time as that file can be converted directly.
+
+=============
+Atomic bitops
+=============
+
+.. raw:: latex
+
+    \footnotesize
+
+.. include:: ../../atomic_bitops.txt
+   :literal:
+
+.. raw:: latex
+
+    \normalsize
diff --git a/Documentation/core-api/wrappers/atomic_t.rst b/Documentation/core-api/wrappers/atomic_t.rst
new file mode 100644
index 000000000000..ed109a964c77
--- /dev/null
+++ b/Documentation/core-api/wrappers/atomic_t.rst
@@ -0,0 +1,19 @@
+.. SPDX-License-Identifier: GPL-2.0
+   This is a simple wrapper to bring atomic_t.txt into the RST world
+   until such a time as that file can be converted directly.
+
+============
+Atomic types
+============
+
+.. raw:: latex
+
+    \footnotesize
+
+.. include:: ../../atomic_t.txt
+   :literal:
+
+.. raw:: latex
+
+    \normalsize
+
diff --git a/Documentation/core-api/wrappers/memory-barriers.rst b/Documentation/core-api/wrappers/memory-barriers.rst
new file mode 100644
index 000000000000..532460b5e3eb
--- /dev/null
+++ b/Documentation/core-api/wrappers/memory-barriers.rst
@@ -0,0 +1,18 @@
+.. SPDX-License-Identifier: GPL-2.0
+   This is a simple wrapper to bring memory-barriers.txt into the RST world
+   until such a time as that file can be converted directly.
+
+============================
+Linux kernel memory barriers
+============================
+
+.. raw:: latex
+
+    \footnotesize
+
+.. include:: ../../memory-barriers.txt
+   :literal:
+
+.. raw:: latex
+
+    \normalsize
diff --git a/Documentation/devicetree/bindings/arm/amlogic/amlogic,meson-gx-ao-secure.yaml b/Documentation/devicetree/bindings/arm/amlogic/amlogic,meson-gx-ao-secure.yaml
index 6cc74523ebfd..1748f1605cc7 100644
--- a/Documentation/devicetree/bindings/arm/amlogic/amlogic,meson-gx-ao-secure.yaml
+++ b/Documentation/devicetree/bindings/arm/amlogic/amlogic,meson-gx-ao-secure.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic Meson Firmware registers Interface
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 description: |
   The Meson SoCs have a register bank with status and data shared with the
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml
index 4a92a4c7dcd7..f8168986a0a9 100644
--- a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml
+++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml
@@ -233,6 +233,7 @@ allOf:
               - allwinner,sun8i-a83t-tcon-lcd
               - allwinner,sun8i-v3s-tcon
               - allwinner,sun9i-a80-tcon-lcd
+              - allwinner,sun20i-d1-tcon-lcd
 
     then:
       properties:
@@ -252,6 +253,7 @@ allOf:
               - allwinner,sun8i-a83t-tcon-tv
               - allwinner,sun8i-r40-tcon-tv
               - allwinner,sun9i-a80-tcon-tv
+              - allwinner,sun20i-d1-tcon-tv
 
     then:
       properties:
@@ -278,6 +280,7 @@ allOf:
               - allwinner,sun9i-a80-tcon-lcd
               - allwinner,sun4i-a10-tcon
               - allwinner,sun8i-a83t-tcon-lcd
+              - allwinner,sun20i-d1-tcon-lcd
 
     then:
       required:
@@ -294,6 +297,7 @@ allOf:
               - allwinner,sun8i-a23-tcon
               - allwinner,sun8i-a33-tcon
               - allwinner,sun8i-a83t-tcon-lcd
+              - allwinner,sun20i-d1-tcon-lcd
 
     then:
       properties:
diff --git a/Documentation/devicetree/bindings/display/amlogic,meson-dw-hdmi.yaml b/Documentation/devicetree/bindings/display/amlogic,meson-dw-hdmi.yaml
index 2e208d2fc98f..7cdffdb131ac 100644
--- a/Documentation/devicetree/bindings/display/amlogic,meson-dw-hdmi.yaml
+++ b/Documentation/devicetree/bindings/display/amlogic,meson-dw-hdmi.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic specific extensions to the Synopsys Designware HDMI Controller
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 allOf:
   - $ref: /schemas/sound/name-prefix.yaml#
diff --git a/Documentation/devicetree/bindings/display/amlogic,meson-vpu.yaml b/Documentation/devicetree/bindings/display/amlogic,meson-vpu.yaml
index 047fd69e0377..6655a93b1874 100644
--- a/Documentation/devicetree/bindings/display/amlogic,meson-vpu.yaml
+++ b/Documentation/devicetree/bindings/display/amlogic,meson-vpu.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic Meson Display Controller
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 description: |
   The Amlogic Meson Display controller is composed of several components
diff --git a/Documentation/devicetree/bindings/display/bridge/analogix,anx7814.yaml b/Documentation/devicetree/bindings/display/bridge/analogix,anx7814.yaml
index bce96b5b0db0..4a5e5d9d6f90 100644
--- a/Documentation/devicetree/bindings/display/bridge/analogix,anx7814.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/analogix,anx7814.yaml
@@ -8,7 +8,7 @@ title: Analogix ANX7814 SlimPort (Full-HD Transmitter)
 
 maintainers:
   - Andrzej Hajda <andrzej.hajda@intel.com>
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
   - Robert Foss <robert.foss@linaro.org>
 
 properties:
diff --git a/Documentation/devicetree/bindings/display/bridge/ite,it66121.yaml b/Documentation/devicetree/bindings/display/bridge/ite,it66121.yaml
index c6e81f532215..1b2185be92cd 100644
--- a/Documentation/devicetree/bindings/display/bridge/ite,it66121.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/ite,it66121.yaml
@@ -8,7 +8,7 @@ title: ITE it66121 HDMI bridge Device Tree Bindings
 
 maintainers:
   - Phong LE <ple@baylibre.com>
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 description: |
   The IT66121 is a high-performance and low-power single channel HDMI
diff --git a/Documentation/devicetree/bindings/display/panel/sgd,gktw70sdae4se.yaml b/Documentation/devicetree/bindings/display/panel/sgd,gktw70sdae4se.yaml
index 44e02decdf3a..2e75e3738ff0 100644
--- a/Documentation/devicetree/bindings/display/panel/sgd,gktw70sdae4se.yaml
+++ b/Documentation/devicetree/bindings/display/panel/sgd,gktw70sdae4se.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Solomon Goldentek Display GKTW70SDAE4SE 7" WVGA LVDS Display Panel
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
   - Thierry Reding <thierry.reding@gmail.com>
 
 allOf:
diff --git a/Documentation/devicetree/bindings/dma/moxa,moxart-dma.txt b/Documentation/devicetree/bindings/dma/moxa,moxart-dma.txt
index 8a9f3559335b..7e14e26676ec 100644
--- a/Documentation/devicetree/bindings/dma/moxa,moxart-dma.txt
+++ b/Documentation/devicetree/bindings/dma/moxa,moxart-dma.txt
@@ -34,8 +34,8 @@ Example:
 Use specific request line passing from dma
 For example, MMC request line is 5
 
-	sdhci: sdhci@98e00000 {
-		compatible = "moxa,moxart-sdhci";
+	mmc: mmc@98e00000 {
+		compatible = "moxa,moxart-mmc";
 		reg = <0x98e00000 0x5C>;
 		interrupts = <5 0>;
 		clocks = <&clk_apb>;
diff --git a/Documentation/devicetree/bindings/hwmon/moortec,mr75203.yaml b/Documentation/devicetree/bindings/hwmon/moortec,mr75203.yaml
index b79f069a04c2..8ea97e774364 100644
--- a/Documentation/devicetree/bindings/hwmon/moortec,mr75203.yaml
+++ b/Documentation/devicetree/bindings/hwmon/moortec,mr75203.yaml
@@ -48,7 +48,6 @@ required:
   - compatible
   - reg
   - reg-names
-  - intel,vm-map
   - clocks
   - resets
   - "#thermal-sensor-cells"
diff --git a/Documentation/devicetree/bindings/i2c/amlogic,meson6-i2c.yaml b/Documentation/devicetree/bindings/i2c/amlogic,meson6-i2c.yaml
index 6ecb0270d88d..199a354ccb97 100644
--- a/Documentation/devicetree/bindings/i2c/amlogic,meson6-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/amlogic,meson6-i2c.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic Meson I2C Controller
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
   - Beniamino Galvani <b.galvani@gmail.com>
 
 allOf:
diff --git a/Documentation/devicetree/bindings/i2c/renesas,riic.yaml b/Documentation/devicetree/bindings/i2c/renesas,riic.yaml
index 2f315489aaae..d3c0d5c427ac 100644
--- a/Documentation/devicetree/bindings/i2c/renesas,riic.yaml
+++ b/Documentation/devicetree/bindings/i2c/renesas,riic.yaml
@@ -60,6 +60,9 @@ properties:
   power-domains:
     maxItems: 1
 
+  resets:
+    maxItems: 1
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml b/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml
index a41588763786..bf396e9466aa 100644
--- a/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml
@@ -57,6 +57,11 @@ properties:
       - description: interrupt ID for I2C event
       - description: interrupt ID for I2C error
 
+  interrupt-names:
+    items:
+      - const: event
+      - const: error
+
   resets:
     maxItems: 1
 
@@ -92,6 +97,8 @@ properties:
           - description: register offset within syscfg
           - description: register bitmask for FMP bit
 
+  wakeup-source: true
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/iio/gyroscope/bosch,bmg160.yaml b/Documentation/devicetree/bindings/iio/gyroscope/bosch,bmg160.yaml
index b6bbc312a7cf..1414ba9977c1 100644
--- a/Documentation/devicetree/bindings/iio/gyroscope/bosch,bmg160.yaml
+++ b/Documentation/devicetree/bindings/iio/gyroscope/bosch,bmg160.yaml
@@ -24,8 +24,10 @@ properties:
 
   interrupts:
     minItems: 1
+    maxItems: 2
     description:
       Should be configured with type IRQ_TYPE_EDGE_RISING.
+      If two interrupts are provided, expected order is INT1 and INT2.
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/input/touchscreen/goodix.yaml b/Documentation/devicetree/bindings/input/touchscreen/goodix.yaml
index 93f2ce3130ae..19ac9da421df 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/goodix.yaml
+++ b/Documentation/devicetree/bindings/input/touchscreen/goodix.yaml
@@ -16,6 +16,7 @@ properties:
   compatible:
     enum:
       - goodix,gt1151
+      - goodix,gt1158
       - goodix,gt5663
       - goodix,gt5688
       - goodix,gt911
diff --git a/Documentation/devicetree/bindings/interconnect/fsl,imx8m-noc.yaml b/Documentation/devicetree/bindings/interconnect/fsl,imx8m-noc.yaml
index 09c8948b5e25..fa4f7685ab2b 100644
--- a/Documentation/devicetree/bindings/interconnect/fsl,imx8m-noc.yaml
+++ b/Documentation/devicetree/bindings/interconnect/fsl,imx8m-noc.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Generic i.MX bus frequency device
 
 maintainers:
-  - Leonard Crestez <leonard.crestez@nxp.com>
+  - Peng Fan <peng.fan@nxp.com>
 
 description: |
   The i.MX SoC family has multiple buses for which clock frequency (and
diff --git a/Documentation/devicetree/bindings/interrupt-controller/apple,aic.yaml b/Documentation/devicetree/bindings/interrupt-controller/apple,aic.yaml
index 85c85b694217..e18107eafe7c 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/apple,aic.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/apple,aic.yaml
@@ -96,7 +96,7 @@ properties:
               Documentation/devicetree/bindings/arm/cpus.yaml).
 
         required:
-          - fiq-index
+          - apple,fiq-index
           - cpus
 
 required:
diff --git a/Documentation/devicetree/bindings/mailbox/amlogic,meson-gxbb-mhu.yaml b/Documentation/devicetree/bindings/mailbox/amlogic,meson-gxbb-mhu.yaml
index ea06976fbbc7..dfd26b998189 100644
--- a/Documentation/devicetree/bindings/mailbox/amlogic,meson-gxbb-mhu.yaml
+++ b/Documentation/devicetree/bindings/mailbox/amlogic,meson-gxbb-mhu.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic Meson Message-Handling-Unit Controller
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 description: |
   The Amlogic's Meson SoCs Message-Handling-Unit (MHU) is a mailbox controller
diff --git a/Documentation/devicetree/bindings/media/amlogic,axg-ge2d.yaml b/Documentation/devicetree/bindings/media/amlogic,axg-ge2d.yaml
index bee93bd84771..e551be5e680e 100644
--- a/Documentation/devicetree/bindings/media/amlogic,axg-ge2d.yaml
+++ b/Documentation/devicetree/bindings/media/amlogic,axg-ge2d.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic GE2D Acceleration Unit
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/media/amlogic,gx-vdec.yaml b/Documentation/devicetree/bindings/media/amlogic,gx-vdec.yaml
index 5044c4bb94e0..b827edabcafa 100644
--- a/Documentation/devicetree/bindings/media/amlogic,gx-vdec.yaml
+++ b/Documentation/devicetree/bindings/media/amlogic,gx-vdec.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic Video Decoder
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
   - Maxime Jourdan <mjourdan@baylibre.com>
 
 description: |
diff --git a/Documentation/devicetree/bindings/media/amlogic,meson-gx-ao-cec.yaml b/Documentation/devicetree/bindings/media/amlogic,meson-gx-ao-cec.yaml
index d93aea6a0258..8d844f4312d1 100644
--- a/Documentation/devicetree/bindings/media/amlogic,meson-gx-ao-cec.yaml
+++ b/Documentation/devicetree/bindings/media/amlogic,meson-gx-ao-cec.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic Meson AO-CEC Controller
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 description: |
   The Amlogic Meson AO-CEC module is present is Amlogic SoCs and its purpose is
diff --git a/Documentation/devicetree/bindings/memory-controllers/fsl/imx8m-ddrc.yaml b/Documentation/devicetree/bindings/memory-controllers/fsl/imx8m-ddrc.yaml
index 445e46feda69..2b39fce5f650 100644
--- a/Documentation/devicetree/bindings/memory-controllers/fsl/imx8m-ddrc.yaml
+++ b/Documentation/devicetree/bindings/memory-controllers/fsl/imx8m-ddrc.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: i.MX8M DDR Controller
 
 maintainers:
-  - Leonard Crestez <leonard.crestez@nxp.com>
+  - Peng Fan <peng.fan@nxp.com>
 
 description:
   The DDRC block is integrated in i.MX8M for interfacing with DDR based
diff --git a/Documentation/devicetree/bindings/mfd/khadas,mcu.yaml b/Documentation/devicetree/bindings/mfd/khadas,mcu.yaml
index a3b976f101e8..5750cc06e923 100644
--- a/Documentation/devicetree/bindings/mfd/khadas,mcu.yaml
+++ b/Documentation/devicetree/bindings/mfd/khadas,mcu.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Khadas on-board Microcontroller Device Tree Bindings
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 description: |
   Khadas embeds a microcontroller on their VIM and Edge boards adding some
diff --git a/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml b/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml
index 608e1d62bed5..ddd5a073c3a8 100644
--- a/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic Meson DWMAC Ethernet controller
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
   - Martin Blumenstingl <martin.blumenstingl@googlemail.com>
 
 # We need a select here so we don't match all nodes with 'snps,dwmac'
diff --git a/Documentation/devicetree/bindings/net/qcom-emac.txt b/Documentation/devicetree/bindings/net/qcom-emac.txt
index e6cb2291471c..7ae8aa148634 100644
--- a/Documentation/devicetree/bindings/net/qcom-emac.txt
+++ b/Documentation/devicetree/bindings/net/qcom-emac.txt
@@ -14,7 +14,7 @@ MAC node:
 - mac-address : The 6-byte MAC address. If present, it is the default
 	MAC address.
 - internal-phy : phandle to the internal PHY node
-- phy-handle : phandle the external PHY node
+- phy-handle : phandle to the external PHY node
 
 Internal PHY node:
 - compatible : Should be "qcom,fsm9900-emac-sgmii" or "qcom,qdf2432-emac-sgmii".
diff --git a/Documentation/devicetree/bindings/opp/opp-v2-kryo-cpu.yaml b/Documentation/devicetree/bindings/opp/opp-v2-kryo-cpu.yaml
index 59663e897dae..a202b6c6561d 100644
--- a/Documentation/devicetree/bindings/opp/opp-v2-kryo-cpu.yaml
+++ b/Documentation/devicetree/bindings/opp/opp-v2-kryo-cpu.yaml
@@ -40,6 +40,7 @@ properties:
 patternProperties:
   '^opp-?[0-9]+$':
     type: object
+    additionalProperties: false
 
     properties:
       opp-hz: true
diff --git a/Documentation/devicetree/bindings/opp/opp-v2-qcom-level.yaml b/Documentation/devicetree/bindings/opp/opp-v2-qcom-level.yaml
index 14a7a689ad6d..df8442fb11f0 100644
--- a/Documentation/devicetree/bindings/opp/opp-v2-qcom-level.yaml
+++ b/Documentation/devicetree/bindings/opp/opp-v2-qcom-level.yaml
@@ -19,6 +19,7 @@ properties:
 patternProperties:
   '^opp-?[0-9]+$':
     type: object
+    additionalProperties: false
 
     properties:
       opp-level: true
diff --git a/Documentation/devicetree/bindings/phy/amlogic,axg-mipi-dphy.yaml b/Documentation/devicetree/bindings/phy/amlogic,axg-mipi-dphy.yaml
index be485f500887..5eddaed3d853 100644
--- a/Documentation/devicetree/bindings/phy/amlogic,axg-mipi-dphy.yaml
+++ b/Documentation/devicetree/bindings/phy/amlogic,axg-mipi-dphy.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic AXG MIPI D-PHY
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb2-phy.yaml b/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb2-phy.yaml
index 399ebde45409..f3a5fbabbbb5 100644
--- a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb2-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb2-phy.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic G12A USB2 PHY
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml
index 453c083cf44c..868b4e6fde71 100644
--- a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic G12A USB3 + PCIE Combo PHY
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml
index 33d1d37fdf6d..624e14f00790 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml
@@ -8,7 +8,6 @@ title: Qualcomm Technologies, Inc. Low Power Audio SubSystem (LPASS)
   Low Power Island (LPI) TLMM block
 
 maintainers:
-  - Srinivasa Rao Mandadapu <srivasam@codeaurora.org>
   - Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
 
 description: |
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml
index 2d228164357c..2bd60c49a442 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Qualcomm Technologies, Inc. SC7280 TLMM block
 
 maintainers:
-  - Rajendra Nayak <rnayak@codeaurora.org>
+  - Bjorn Andersson <andersson@kernel.org>
 
 description: |
   This binding describes the Top Level Mode Multiplexer block found in the
diff --git a/Documentation/devicetree/bindings/power/amlogic,meson-ee-pwrc.yaml b/Documentation/devicetree/bindings/power/amlogic,meson-ee-pwrc.yaml
index 5390e988a934..43a932237a92 100644
--- a/Documentation/devicetree/bindings/power/amlogic,meson-ee-pwrc.yaml
+++ b/Documentation/devicetree/bindings/power/amlogic,meson-ee-pwrc.yaml
@@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Amlogic Meson Everything-Else Power Domains
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 description: |+
   The Everything-Else Power Domains node should be the child of a syscon
diff --git a/Documentation/devicetree/bindings/power/qcom,rpmpd.yaml b/Documentation/devicetree/bindings/power/qcom,rpmpd.yaml
index 0ccca493251a..3934a2b44894 100644
--- a/Documentation/devicetree/bindings/power/qcom,rpmpd.yaml
+++ b/Documentation/devicetree/bindings/power/qcom,rpmpd.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Qualcomm RPM/RPMh Power domains
 
 maintainers:
-  - Rajendra Nayak <rnayak@codeaurora.org>
+  - Bjorn Andersson <andersson@kernel.org>
 
 description:
   For RPM/RPMh Power domains, we communicate a performance state to RPM/RPMh
diff --git a/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml b/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml
index b539781e39aa..835b53302db8 100644
--- a/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/nxp,pca9450-regulator.yaml
@@ -47,12 +47,6 @@ properties:
         description:
           Properties for single LDO regulator.
 
-        properties:
-          regulator-name:
-            pattern: "^LDO[1-5]$"
-            description:
-              should be "LDO1", ..., "LDO5"
-
         unevaluatedProperties: false
 
       "^BUCK[1-6]$":
@@ -62,11 +56,6 @@ properties:
           Properties for single BUCK regulator.
 
         properties:
-          regulator-name:
-            pattern: "^BUCK[1-6]$"
-            description:
-              should be "BUCK1", ..., "BUCK6"
-
           nxp,dvs-run-voltage:
             $ref: "/schemas/types.yaml#/definitions/uint32"
             minimum: 600000
diff --git a/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.yaml b/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.yaml
index 8b7c4af4b551..faa4af9fd035 100644
--- a/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.yaml
@@ -35,6 +35,7 @@ patternProperties:
     description: List of regulators and its properties
     type: object
     $ref: regulator.yaml#
+    unevaluatedProperties: false
 
     properties:
       qcom,ocp-max-retries:
@@ -100,8 +101,6 @@ patternProperties:
           SAW controlled gang leader. Will be configured as SAW regulator.
         type: boolean
 
-      unevaluatedProperties: false
-
 required:
   - compatible
 
diff --git a/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml b/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml
index 494a454928ce..98db2aa74dc8 100644
--- a/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml
+++ b/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic Meson SoC Reset Controller
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml b/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml
index 69cdab18d629..ca3b9be58058 100644
--- a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml
+++ b/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml
@@ -17,9 +17,6 @@ description:
   acts as directory-based coherency manager.
   All the properties in ePAPR/DeviceTree specification applies for this platform.
 
-allOf:
-  - $ref: /schemas/cache-controller.yaml#
-
 select:
   properties:
     compatible:
@@ -33,11 +30,16 @@ select:
 
 properties:
   compatible:
-    items:
-      - enum:
-          - sifive,fu540-c000-ccache
-          - sifive,fu740-c000-ccache
-      - const: cache
+    oneOf:
+      - items:
+          - enum:
+              - sifive,fu540-c000-ccache
+              - sifive,fu740-c000-ccache
+          - const: cache
+      - items:
+          - const: microchip,mpfs-ccache
+          - const: sifive,fu540-c000-ccache
+          - const: cache
 
   cache-block-size:
     const: 64
@@ -72,29 +74,46 @@ properties:
       The reference to the reserved-memory for the L2 Loosely Integrated Memory region.
       The reserved memory node should be defined as per the bindings in reserved-memory.txt.
 
-if:
-  properties:
-    compatible:
-      contains:
-        const: sifive,fu540-c000-ccache
+allOf:
+  - $ref: /schemas/cache-controller.yaml#
 
-then:
-  properties:
-    interrupts:
-      description: |
-        Must contain entries for DirError, DataError and DataFail signals.
-      maxItems: 3
-    cache-sets:
-      const: 1024
-
-else:
-  properties:
-    interrupts:
-      description: |
-        Must contain entries for DirError, DataError, DataFail, DirFail signals.
-      minItems: 4
-    cache-sets:
-      const: 2048
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - sifive,fu740-c000-ccache
+              - microchip,mpfs-ccache
+
+    then:
+      properties:
+        interrupts:
+          description: |
+            Must contain entries for DirError, DataError, DataFail, DirFail signals.
+          minItems: 4
+
+    else:
+      properties:
+        interrupts:
+          description: |
+            Must contain entries for DirError, DataError and DataFail signals.
+          maxItems: 3
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: sifive,fu740-c000-ccache
+
+    then:
+      properties:
+        cache-sets:
+          const: 2048
+
+    else:
+      properties:
+        cache-sets:
+          const: 1024
 
 additionalProperties: false
 
diff --git a/Documentation/devicetree/bindings/rng/amlogic,meson-rng.yaml b/Documentation/devicetree/bindings/rng/amlogic,meson-rng.yaml
index 444be32a8a29..09c6c906b1f9 100644
--- a/Documentation/devicetree/bindings/rng/amlogic,meson-rng.yaml
+++ b/Documentation/devicetree/bindings/rng/amlogic,meson-rng.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic Meson Random number generator
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/serial/amlogic,meson-uart.yaml b/Documentation/devicetree/bindings/serial/amlogic,meson-uart.yaml
index 72e8868db3e0..7822705ad16c 100644
--- a/Documentation/devicetree/bindings/serial/amlogic,meson-uart.yaml
+++ b/Documentation/devicetree/bindings/serial/amlogic,meson-uart.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic Meson SoC UART Serial Interface
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 description: |
   The Amlogic Meson SoC UART Serial Interface is present on a large range
diff --git a/Documentation/devicetree/bindings/soc/amlogic/amlogic,canvas.yaml b/Documentation/devicetree/bindings/soc/amlogic/amlogic,canvas.yaml
index 17db87cb9dab..c3c599096353 100644
--- a/Documentation/devicetree/bindings/soc/amlogic/amlogic,canvas.yaml
+++ b/Documentation/devicetree/bindings/soc/amlogic/amlogic,canvas.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic Canvas Video Lookup Table
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
   - Maxime Jourdan <mjourdan@baylibre.com>
 
 description: |
diff --git a/Documentation/devicetree/bindings/spi/amlogic,meson-gx-spicc.yaml b/Documentation/devicetree/bindings/spi/amlogic,meson-gx-spicc.yaml
index 50de0da42c13..0c10f7678178 100644
--- a/Documentation/devicetree/bindings/spi/amlogic,meson-gx-spicc.yaml
+++ b/Documentation/devicetree/bindings/spi/amlogic,meson-gx-spicc.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic Meson SPI Communication Controller
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 allOf:
   - $ref: "spi-controller.yaml#"
diff --git a/Documentation/devicetree/bindings/spi/amlogic,meson6-spifc.yaml b/Documentation/devicetree/bindings/spi/amlogic,meson6-spifc.yaml
index 8a9d526d06eb..ac3b2ec300ac 100644
--- a/Documentation/devicetree/bindings/spi/amlogic,meson6-spifc.yaml
+++ b/Documentation/devicetree/bindings/spi/amlogic,meson6-spifc.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic Meson SPI Flash Controller
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 allOf:
   - $ref: "spi-controller.yaml#"
diff --git a/Documentation/devicetree/bindings/spi/cdns,qspi-nor-peripheral-props.yaml b/Documentation/devicetree/bindings/spi/cdns,qspi-nor-peripheral-props.yaml
index 553601a441a7..510b82c177c0 100644
--- a/Documentation/devicetree/bindings/spi/cdns,qspi-nor-peripheral-props.yaml
+++ b/Documentation/devicetree/bindings/spi/cdns,qspi-nor-peripheral-props.yaml
@@ -10,7 +10,7 @@ description:
   See spi-peripheral-props.yaml for more info.
 
 maintainers:
-  - Pratyush Yadav <p.yadav@ti.com>
+  - Vaishnav Achath <vaishnav.a@ti.com>
 
 properties:
   # cdns,qspi-nor.yaml
diff --git a/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml b/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml
index 0a537fa3a641..4707294d8f59 100644
--- a/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml
+++ b/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Cadence Quad SPI controller
 
 maintainers:
-  - Pratyush Yadav <p.yadav@ti.com>
+  - Vaishnav Achath <vaishnav.a@ti.com>
 
 allOf:
   - $ref: spi-controller.yaml#
diff --git a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml
index ce048e782e80..a4abe1588005 100644
--- a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml
@@ -16,7 +16,7 @@ description:
   their own separate schema that should be referenced from here.
 
 maintainers:
-  - Pratyush Yadav <p.yadav@ti.com>
+  - Mark Brown <broonie@kernel.org>
 
 properties:
   reg:
diff --git a/Documentation/devicetree/bindings/thermal/rcar-thermal.yaml b/Documentation/devicetree/bindings/thermal/rcar-thermal.yaml
index 00dcbdd36144..119998d10ff4 100644
--- a/Documentation/devicetree/bindings/thermal/rcar-thermal.yaml
+++ b/Documentation/devicetree/bindings/thermal/rcar-thermal.yaml
@@ -42,7 +42,7 @@ properties:
     description:
       Address ranges of the thermal registers. If more then one range is given
       the first one must be the common registers followed by each sensor
-      according the datasheet.
+      according to the datasheet.
     minItems: 1
     maxItems: 4
 
diff --git a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml
index 2d34f3ccb257..8d2c6d74b605 100644
--- a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml
+++ b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml
@@ -214,6 +214,7 @@ patternProperties:
       - polling-delay
       - polling-delay-passive
       - thermal-sensors
+      - trips
 
     additionalProperties: false
 
diff --git a/Documentation/devicetree/bindings/usb/amlogic,meson-g12a-usb-ctrl.yaml b/Documentation/devicetree/bindings/usb/amlogic,meson-g12a-usb-ctrl.yaml
index e349fa5de606..daf2a859418d 100644
--- a/Documentation/devicetree/bindings/usb/amlogic,meson-g12a-usb-ctrl.yaml
+++ b/Documentation/devicetree/bindings/usb/amlogic,meson-g12a-usb-ctrl.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Amlogic Meson G12A DWC3 USB SoC Controller Glue
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 description: |
   The Amlogic G12A embeds a DWC3 USB IP Core configured for USB2 and USB3
diff --git a/Documentation/devicetree/bindings/usb/mediatek,mtu3.yaml b/Documentation/devicetree/bindings/usb/mediatek,mtu3.yaml
index e63b66545317..b019d490170d 100644
--- a/Documentation/devicetree/bindings/usb/mediatek,mtu3.yaml
+++ b/Documentation/devicetree/bindings/usb/mediatek,mtu3.yaml
@@ -24,6 +24,7 @@ properties:
           - mediatek,mt2712-mtu3
           - mediatek,mt8173-mtu3
           - mediatek,mt8183-mtu3
+          - mediatek,mt8188-mtu3
           - mediatek,mt8192-mtu3
           - mediatek,mt8195-mtu3
       - const: mediatek,mtu3
diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
index fea3e7092ace..cd2f7cb6745a 100644
--- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
@@ -33,6 +33,7 @@ properties:
           - qcom,sm6115-dwc3
           - qcom,sm6125-dwc3
           - qcom,sm6350-dwc3
+          - qcom,sm6375-dwc3
           - qcom,sm8150-dwc3
           - qcom,sm8250-dwc3
           - qcom,sm8350-dwc3
@@ -108,12 +109,17 @@ properties:
       HS/FS/LS modes are supported.
     type: boolean
 
+  wakeup-source: true
+
 # Required child node:
 
 patternProperties:
   "^usb@[0-9a-f]+$":
     $ref: snps,dwc3.yaml#
 
+    properties:
+      wakeup-source: false
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml b/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml
index c7459cf70e30..497d60408ea0 100644
--- a/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml
+++ b/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml
@@ -8,7 +8,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: Meson GXBB SoCs Watchdog timer
 
 maintainers:
-  - Neil Armstrong <narmstrong@baylibre.com>
+  - Neil Armstrong <neil.armstrong@linaro.org>
 
 allOf:
   - $ref: watchdog.yaml#
diff --git a/Documentation/doc-guide/kernel-doc.rst b/Documentation/doc-guide/kernel-doc.rst
index 9c779bd7a751..1dcbd7332476 100644
--- a/Documentation/doc-guide/kernel-doc.rst
+++ b/Documentation/doc-guide/kernel-doc.rst
@@ -14,6 +14,9 @@ when it is embedded in source files.
    reasons. The kernel source contains tens of thousands of kernel-doc
    comments. Please stick to the style described here.
 
+.. note:: kernel-doc does not cover Rust code: please see
+   Documentation/rust/general-information.rst instead.
+
 The kernel-doc structure is extracted from the comments, and proper
 `Sphinx C Domain`_ function and type descriptions with anchors are
 generated from them. The descriptions are filtered for special kernel-doc
diff --git a/Documentation/doc-guide/sphinx.rst b/Documentation/doc-guide/sphinx.rst
index 1228b85f6f77..c708cec889af 100644
--- a/Documentation/doc-guide/sphinx.rst
+++ b/Documentation/doc-guide/sphinx.rst
@@ -48,10 +48,6 @@ or ``virtualenv``, depending on how your distribution packaged Python 3.
       on the Sphinx version, it should be installed separately,
       with ``pip install sphinx_rtd_theme``.
 
-   #) Some ReST pages contain math expressions. Due to the way Sphinx works,
-      those expressions are written using LaTeX notation. It needs texlive
-      installed with amsfonts and amsmath in order to evaluate them.
-
 In summary, if you want to install Sphinx version 2.4.4, you should do::
 
        $ virtualenv sphinx_2.4.4
@@ -86,6 +82,27 @@ Depending on the distribution, you may also need to install a series of
 ``texlive`` packages that provide the minimal set of functionalities
 required for ``XeLaTeX`` to work.
 
+Math Expressions in HTML
+------------------------
+
+Some ReST pages contain math expressions. Due to the way Sphinx works,
+those expressions are written using LaTeX notation.
+There are two options for Sphinx to render math expressions in html output.
+One is an extension called `imgmath`_ which converts math expressions into
+images and embeds them in html pages.
+The other is an extension called `mathjax`_ which delegates math rendering
+to JavaScript capable web browsers.
+The former was the only option for pre-6.1 kernel documentation and it
+requires quite a few texlive packages including amsfonts and amsmath among
+others.
+
+Since kernel release 6.1, html pages with math expressions can be built
+without installing any texlive packages. See `Choice of Math Renderer`_ for
+further info.
+
+.. _imgmath: https://www.sphinx-doc.org/en/master/usage/extensions/math.html#module-sphinx.ext.imgmath
+.. _mathjax: https://www.sphinx-doc.org/en/master/usage/extensions/math.html#module-sphinx.ext.mathjax
+
 .. _sphinx-pre-install:
 
 Checking for Sphinx dependencies
@@ -164,6 +181,38 @@ To remove the generated documentation, run ``make cleandocs``.
 	  as well would improve the quality of images embedded in PDF
 	  documents, especially for kernel releases 5.18 and later.
 
+Choice of Math Renderer
+-----------------------
+
+Since kernel release 6.1, mathjax works as a fallback math renderer for
+html output.\ [#sph1_8]_
+
+Math renderer is chosen depending on available commands as shown below:
+
+.. table:: Math Renderer Choices for HTML
+
+    ============= ================= ============
+    Math renderer Required commands Image format
+    ============= ================= ============
+    imgmath       latex, dvipng     PNG (raster)
+    mathjax
+    ============= ================= ============
+
+The choice can be overridden by setting an environment variable
+``SPHINX_IMGMATH`` as shown below:
+
+.. table:: Effect of Setting ``SPHINX_IMGMATH``
+
+    ====================== ========
+    Setting                Renderer
+    ====================== ========
+    ``SPHINX_IMGMATH=yes`` imgmath
+    ``SPHINX_IMGMATH=no``  mathjax
+    ====================== ========
+
+.. [#sph1_8] Fallback of math renderer requires Sphinx >=1.8.
+
+
 Writing Documentation
 =====================
 
diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst
index 55272942e721..dc1b2353cea3 100644
--- a/Documentation/driver-api/driver-model/devres.rst
+++ b/Documentation/driver-api/driver-model/devres.rst
@@ -301,6 +301,7 @@ IO region
   devm_release_region()
   devm_release_resource()
   devm_request_mem_region()
+  devm_request_free_mem_region()
   devm_request_region()
   devm_request_resource()
 
@@ -334,7 +335,7 @@ IRQ
   devm_irq_alloc_descs_from()
   devm_irq_alloc_generic_chip()
   devm_irq_setup_generic_chip()
-  devm_irq_sim_init()
+  devm_irq_domain_create_sim()
 
 LED
   devm_led_classdev_register()
@@ -392,7 +393,9 @@ PHY
 PINCTRL
   devm_pinctrl_get()
   devm_pinctrl_put()
+  devm_pinctrl_get_select()
   devm_pinctrl_register()
+  devm_pinctrl_register_and_init()
   devm_pinctrl_unregister()
 
 POWER
@@ -427,6 +430,8 @@ SLAVE DMA ENGINE
   devm_acpi_dma_controller_register()
 
 SPI
+  devm_spi_alloc_master()
+  devm_spi_alloc_slave()
   devm_spi_register_master()
 
 WATCHDOG
diff --git a/Documentation/driver-api/isa.rst b/Documentation/driver-api/isa.rst
index def4a7b690b5..3df1b1696524 100644
--- a/Documentation/driver-api/isa.rst
+++ b/Documentation/driver-api/isa.rst
@@ -100,7 +100,7 @@ I believe platform_data is available for this, but if rather not, moving
 the isa_driver pointer to the private struct isa_dev is ofcourse fine as
 well.
 
-Then, if the the driver did not provide a .match, it matches. If it did,
+Then, if the driver did not provide a .match, it matches. If it did,
 the driver match() method is called to determine a match.
 
 If it did **not** match, dev->platform_data is reset to indicate this to
diff --git a/Documentation/fb/udlfb.rst b/Documentation/fb/udlfb.rst
index 732b37db3504..99cfbb7a1922 100644
--- a/Documentation/fb/udlfb.rst
+++ b/Documentation/fb/udlfb.rst
@@ -86,17 +86,24 @@ Module Options
 Special configuration for udlfb is usually unnecessary. There are a few
 options, however.
 
-From the command line, pass options to modprobe
-modprobe udlfb fb_defio=0 console=1 shadow=1
+From the command line, pass options to modprobe::
 
-Or modify options on the fly at /sys/module/udlfb/parameters directory via
-sudo nano fb_defio
-change the parameter in place, and save the file.
+  modprobe udlfb fb_defio=0 console=1 shadow=1
 
-Unplug/replug USB device to apply with new settings
+Or change options on the fly by editing
+/sys/module/udlfb/parameters/PARAMETER_NAME ::
 
-Or for permanent option, create file like /etc/modprobe.d/udlfb.conf with text
-options udlfb fb_defio=0 console=1 shadow=1
+  cd /sys/module/udlfb/parameters
+  ls # to see a list of parameter names
+  sudo nano PARAMETER_NAME
+  # change the parameter in place, and save the file.
+
+Unplug/replug USB device to apply with new settings.
+
+Or to apply options permanently, create a modprobe configuration file
+like /etc/modprobe.d/udlfb.conf with text::
+
+  options udlfb fb_defio=0 console=1 shadow=1
 
 Accepted boolean options:
 
diff --git a/Documentation/filesystems/caching/backend-api.rst b/Documentation/filesystems/caching/backend-api.rst
index d7507becf674..3a199fc50828 100644
--- a/Documentation/filesystems/caching/backend-api.rst
+++ b/Documentation/filesystems/caching/backend-api.rst
@@ -122,7 +122,7 @@ volumes, calling::
 to tell fscache that a volume has been withdrawn.  This waits for all
 outstanding accesses on the volume to complete before returning.
 
-When the the cache is completely withdrawn, fscache should be notified by
+When the cache is completely withdrawn, fscache should be notified by
 calling::
 
 	void fscache_relinquish_cache(struct fscache_cache *cache);
diff --git a/Documentation/filesystems/ext4/super.rst b/Documentation/filesystems/ext4/super.rst
index 268888522e35..0152888cac29 100644
--- a/Documentation/filesystems/ext4/super.rst
+++ b/Documentation/filesystems/ext4/super.rst
@@ -456,15 +456,15 @@ The ext4 superblock is laid out as follows in
    * - 0x277
      - __u8
      - s_lastcheck_hi
-     - Upper 8 bits of the s_lastcheck_hi field.
+     - Upper 8 bits of the s_lastcheck field.
    * - 0x278
      - __u8
      - s_first_error_time_hi
-     - Upper 8 bits of the s_first_error_time_hi field.
+     - Upper 8 bits of the s_first_error_time field.
    * - 0x279
      - __u8
      - s_last_error_time_hi
-     - Upper 8 bits of the s_last_error_time_hi field.
+     - Upper 8 bits of the s_last_error_time field.
    * - 0x27A
      - __u8
      - s_pad[2]
diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst
index d0c09663dae8..17df9a02ccff 100644
--- a/Documentation/filesystems/f2fs.rst
+++ b/Documentation/filesystems/f2fs.rst
@@ -286,9 +286,8 @@ compress_algorithm=%s:%d Control compress algorithm and its compress level, now,
 			 algorithm	level range
 			 lz4		3 - 16
 			 zstd		1 - 22
-compress_log_size=%u	 Support configuring compress cluster size, the size will
-			 be 4KB * (1 << %u), 16KB is minimum size, also it's
-			 default size.
+compress_log_size=%u	 Support configuring compress cluster size. The size will
+			 be 4KB * (1 << %u). The default and minimum sizes are 16KB.
 compress_extension=%s	 Support adding specified extension, so that f2fs can enable
 			 compression on those corresponding files, e.g. if all files
 			 with '.ext' has high compression rate, we can set the '.ext'
diff --git a/Documentation/filesystems/idmappings.rst b/Documentation/filesystems/idmappings.rst
index c1db8748389c..b9b31066aef2 100644
--- a/Documentation/filesystems/idmappings.rst
+++ b/Documentation/filesystems/idmappings.rst
@@ -661,7 +661,7 @@ idmappings::
  mount idmapping:      u0:k10000:r10000
 
 Assume a file owned by ``u1000`` is read from disk. The filesystem maps this id
-to ``k21000`` according to it's idmapping. This is what is stored in the
+to ``k21000`` according to its idmapping. This is what is stored in the
 inode's ``i_uid`` and ``i_gid`` fields.
 
 When the caller queries the ownership of this file via ``stat()`` the kernel
diff --git a/Documentation/filesystems/qnx6.rst b/Documentation/filesystems/qnx6.rst
index fd13433d362c..523b798f04e7 100644
--- a/Documentation/filesystems/qnx6.rst
+++ b/Documentation/filesystems/qnx6.rst
@@ -176,7 +176,7 @@ Then userspace.
 The requirement for a static, fixed preallocated system area comes from how
 qnx6fs deals with writes.
 
-Each superblock got it's own half of the system area. So superblock #1
+Each superblock got its own half of the system area. So superblock #1
 always uses blocks from the lower half while superblock #2 just writes to
 blocks represented by the upper half bitmap system area bits.
 
diff --git a/Documentation/filesystems/spufs/spufs.rst b/Documentation/filesystems/spufs/spufs.rst
index 8a42859bb100..ca0441cbe37e 100644
--- a/Documentation/filesystems/spufs/spufs.rst
+++ b/Documentation/filesystems/spufs/spufs.rst
@@ -227,7 +227,7 @@ Files
               from the data buffer, updating the value of the specified signal
               notification register.  The signal  notification  register  will
               either be replaced with the input data or will be updated to the
-              bitwise OR or the old value and the input data, depending on the
+              bitwise OR of the old value and the input data, depending on the
               contents  of  the  signal1_type,  or  signal2_type respectively,
               file.
 
diff --git a/Documentation/filesystems/xfs-delayed-logging-design.rst b/Documentation/filesystems/xfs-delayed-logging-design.rst
index 4ef419f54663..6402ab8e370c 100644
--- a/Documentation/filesystems/xfs-delayed-logging-design.rst
+++ b/Documentation/filesystems/xfs-delayed-logging-design.rst
@@ -100,7 +100,7 @@ transactions together::
 
 	ntp = xfs_trans_dup(tp);
 	xfs_trans_commit(tp);
-	xfs_log_reserve(ntp);
+	xfs_trans_reserve(ntp);
 
 This results in a series of "rolling transactions" where the inode is locked
 across the entire chain of transactions.  Hence while this series of rolling
@@ -191,7 +191,7 @@ transaction rolling mechanism to re-reserve space on every transaction roll. We
 know from the implementation of the permanent transactions how many transaction
 rolls are likely for the common modifications that need to be made.
 
-For example, and inode allocation is typically two transactions - one to
+For example, an inode allocation is typically two transactions - one to
 physically allocate a free inode chunk on disk, and another to allocate an inode
 from an inode chunk that has free inodes in it.  Hence for an inode allocation
 transaction, we might set the reservation log count to a value of 2 to indicate
@@ -200,7 +200,7 @@ chain. Each time a permanent transaction rolls, it consumes an entire unit
 reservation.
 
 Hence when the permanent transaction is first allocated, the log space
-reservation is increases from a single unit reservation to multiple unit
+reservation is increased from a single unit reservation to multiple unit
 reservations. That multiple is defined by the reservation log count, and this
 means we can roll the transaction multiple times before we have to re-reserve
 log space when we roll the transaction. This ensures that the common
@@ -259,7 +259,7 @@ the next transaction in the sequeunce, but we have none remaining. We cannot
 sleep during the transaction commit process waiting for new log space to become
 available, as we may end up on the end of the FIFO queue and the items we have
 locked while we sleep could end up pinning the tail of the log before there is
-enough free space in the log to fulfil all of the pending reservations and
+enough free space in the log to fulfill all of the pending reservations and
 then wake up transaction commit in progress.
 
 To take a new reservation without sleeping requires us to be able to take a
@@ -551,14 +551,14 @@ Essentially, this shows that an item that is in the AIL can still be modified
 and relogged, so any tracking must be separate to the AIL infrastructure. As
 such, we cannot reuse the AIL list pointers for tracking committed items, nor
 can we store state in any field that is protected by the AIL lock. Hence the
-committed item tracking needs it's own locks, lists and state fields in the log
+committed item tracking needs its own locks, lists and state fields in the log
 item.
 
 Similar to the AIL, tracking of committed items is done through a new list
 called the Committed Item List (CIL).  The list tracks log items that have been
 committed and have formatted memory buffers attached to them. It tracks objects
 in transaction commit order, so when an object is relogged it is removed from
-it's place in the list and re-inserted at the tail. This is entirely arbitrary
+its place in the list and re-inserted at the tail. This is entirely arbitrary
 and done to make it easy for debugging - the last items in the list are the
 ones that are most recently modified. Ordering of the CIL is not necessary for
 transactional integrity (as discussed in the next section) so the ordering is
@@ -615,7 +615,7 @@ those changes into the current checkpoint context. We then initialise a new
 context and attach that to the CIL for aggregation of new transactions.
 
 This allows us to unlock the CIL immediately after transfer of all the
-committed items and effectively allow new transactions to be issued while we
+committed items and effectively allows new transactions to be issued while we
 are formatting the checkpoint into the log. It also allows concurrent
 checkpoints to be written into the log buffers in the case of log force heavy
 workloads, just like the existing transaction commit code does. This, however,
@@ -884,9 +884,9 @@ pin the object the first time it is inserted into the CIL - if it is already in
 the CIL during a transaction commit, then we do not pin it again. Because there
 can be multiple outstanding checkpoint contexts, we can still see elevated pin
 counts, but as each checkpoint completes the pin count will retain the correct
-value according to it's context.
+value according to its context.
 
-Just to make matters more slightly more complex, this checkpoint level context
+Just to make matters slightly more complex, this checkpoint level context
 for the pin count means that the pinning of an item must take place under the
 CIL commit/flush lock. If we pin the object outside this lock, we cannot
 guarantee which context the pin count is associated with. This is because of
diff --git a/Documentation/firmware-guide/acpi/enumeration.rst b/Documentation/firmware-guide/acpi/enumeration.rst
index dbb03022b127..b9dc0c603f36 100644
--- a/Documentation/firmware-guide/acpi/enumeration.rst
+++ b/Documentation/firmware-guide/acpi/enumeration.rst
@@ -21,7 +21,7 @@ possible we decided to do following:
   - Devices behind real busses where there is a connector resource
     are represented as struct spi_device or struct i2c_device. Note
     that standard UARTs are not busses so there is no struct uart_device,
-    although some of them may be represented by sturct serdev_device.
+    although some of them may be represented by struct serdev_device.
 
 As both ACPI and Device Tree represent a tree of devices (and their
 resources) this implementation follows the Device Tree way as much as
@@ -205,7 +205,7 @@ Here is what the ACPI namespace for a SPI slave might look like::
 		}
 		...
 
-The SPI device drivers only need to add ACPI IDs in a similar way than with
+The SPI device drivers only need to add ACPI IDs in a similar way to
 the platform device drivers. Below is an example where we add ACPI support
 to at25 SPI eeprom driver (this is meant for the above ACPI snippet)::
 
@@ -362,7 +362,7 @@ These GPIO numbers are controller relative and path "\\_SB.PCI0.GPI0"
 specifies the path to the controller. In order to use these GPIOs in Linux
 we need to translate them to the corresponding Linux GPIO descriptors.
 
-There is a standard GPIO API for that and is documented in
+There is a standard GPIO API for that and it is documented in
 Documentation/admin-guide/gpio/.
 
 In the above example we can get the corresponding two GPIO descriptors with
@@ -538,8 +538,8 @@ information.
 PCI hierarchy representation
 ============================
 
-Sometimes could be useful to enumerate a PCI device, knowing its position on the
-PCI bus.
+Sometimes it could be useful to enumerate a PCI device, knowing its position on
+the PCI bus.
 
 For example, some systems use PCI devices soldered directly on the mother board,
 in a fixed position (ethernet, Wi-Fi, serial ports, etc.). In this conditions it
@@ -550,7 +550,7 @@ To identify a PCI device, a complete hierarchical description is required, from
 the chipset root port to the final device, through all the intermediate
 bridges/switches of the board.
 
-For example, let us assume to have a system with a PCIe serial port, an
+For example, let's assume we have a system with a PCIe serial port, an
 Exar XR17V3521, soldered on the main board. This UART chip also includes
 16 GPIOs and we want to add the property ``gpio-line-names`` [1] to these pins.
 In this case, the ``lspci`` output for this component is::
@@ -593,8 +593,8 @@ of the chipset bridge (also called "root port") with address::
 
 	Bus: 0 - Device: 14 - Function: 1
 
-To find this information is necessary disassemble the BIOS ACPI tables, in
-particular the DSDT (see also [2])::
+To find this information, it is necessary to disassemble the BIOS ACPI tables,
+in particular the DSDT (see also [2])::
 
 	mkdir ~/tables/
 	cd ~/tables/
diff --git a/Documentation/firmware-guide/acpi/osi.rst b/Documentation/firmware-guide/acpi/osi.rst
index 05869c0045d7..784850adfcb6 100644
--- a/Documentation/firmware-guide/acpi/osi.rst
+++ b/Documentation/firmware-guide/acpi/osi.rst
@@ -41,26 +41,23 @@ But it is likely that they will all eventually be added.
 What should an OEM do if they want to support Linux and Windows
 using the same BIOS image?  Often they need to do something different
 for Linux to deal with how Linux is different from Windows.
-Here the BIOS should ask exactly what it wants to know:
 
+In this case, the OEM should create custom ASL to be executed by the
+Linux kernel and changes to Linux kernel drivers to execute this custom
+ASL.  The easiest way to accomplish this is to introduce a device specific
+method (_DSM) that is called from the Linux kernel.
+
+In the past the kernel used to support something like:
 _OSI("Linux-OEM-my_interface_name")
 where 'OEM' is needed if this is an OEM-specific hook,
 and 'my_interface_name' describes the hook, which could be a
 quirk, a bug, or a bug-fix.
 
-In addition, the OEM should send a patch to upstream Linux
-via the linux-acpi@vger.kernel.org mailing list.  When that patch
-is checked into Linux, the OS will answer "YES" when the BIOS
-on the OEM's system uses _OSI to ask if the interface is supported
-by the OS.  Linux distributors can back-port that patch for Linux
-pre-installs, and it will be included by all distributions that
-re-base to upstream.  If the distribution can not update the kernel binary,
-they can also add an acpi_osi=Linux-OEM-my_interface_name
-cmdline parameter to the boot loader, as needed.
-
-If the string refers to a feature where the upstream kernel
-eventually grows support, a patch should be sent to remove
-the string when that support is added to the kernel.
+However this was discovered to be abused by other BIOS vendors to change
+completely unrelated code on completely unrelated systems.  This prompted
+an evaluation of all of it's uses. This uncovered that they aren't needed
+for any of the original reasons. As such, the kernel will not respond to
+any custom Linux-* strings by default.
 
 That was easy.  Read on, to find out how to do it wrong.
 
diff --git a/Documentation/i2c/busses/i2c-piix4.rst b/Documentation/i2c/busses/i2c-piix4.rst
index cc9000259223..07fe6f6f4b18 100644
--- a/Documentation/i2c/busses/i2c-piix4.rst
+++ b/Documentation/i2c/busses/i2c-piix4.rst
@@ -64,7 +64,7 @@ correct address for this module, you could get in big trouble (read:
 crashes, data corruption, etc.). Try this only as a last resort (try BIOS
 updates first, for example), and backup first! An even more dangerous
 option is 'force_addr=<IOPORT>'. This will not only enable the PIIX4 like
-'force' foes, but it will also set a new base I/O port address. The SMBus
+'force' does, but it will also set a new base I/O port address. The SMBus
 parts of the PIIX4 needs a range of 8 of these addresses to function
 correctly. If these addresses are already reserved by some other device,
 you will get into big trouble! DON'T USE THIS IF YOU ARE NOT VERY SURE
@@ -86,15 +86,15 @@ If you own Force CPCI735 motherboard or other OSB4 based systems you may need
 to change the SMBus Interrupt Select register so the SMBus controller uses
 the SMI mode.
 
-1) Use lspci command and locate the PCI device with the SMBus controller:
+1) Use ``lspci`` command and locate the PCI device with the SMBus controller:
    00:0f.0 ISA bridge: ServerWorks OSB4 South Bridge (rev 4f)
    The line may vary for different chipsets. Please consult the driver source
-   for all possible PCI ids (and lspci -n to match them). Lets assume the
+   for all possible PCI ids (and ``lspci -n`` to match them). Let's assume the
    device is located at 00:0f.0.
 2) Now you just need to change the value in 0xD2 register. Get it first with
-   command: lspci -xxx -s 00:0f.0
+   command: ``lspci -xxx -s 00:0f.0``
    If the value is 0x3 then you need to change it to 0x1:
-   setpci  -s 00:0f.0 d2.b=1
+   ``setpci  -s 00:0f.0 d2.b=1``
 
 Please note that you don't need to do that in all cases, just when the SMBus is
 not working properly.
@@ -109,6 +109,3 @@ which can easily get corrupted due to a state machine bug. These are mostly
 Thinkpad laptops, but desktop systems may also be affected. We have no list
 of all affected systems, so the only safe solution was to prevent access to
 the SMBus on all IBM systems (detected using DMI data.)
-
-For additional information, read:
-http://www.lm-sensors.org/browser/lm-sensors/trunk/README
diff --git a/Documentation/i2c/dev-interface.rst b/Documentation/i2c/dev-interface.rst
index 73ad34849f99..c277a8e1202b 100644
--- a/Documentation/i2c/dev-interface.rst
+++ b/Documentation/i2c/dev-interface.rst
@@ -148,7 +148,7 @@ You can do plain I2C transactions by using read(2) and write(2) calls.
 You do not need to pass the address byte; instead, set it through
 ioctl I2C_SLAVE before you try to access the device.
 
-You can do SMBus level transactions (see documentation file smbus-protocol
+You can do SMBus level transactions (see documentation file smbus-protocol.rst
 for details) through the following functions::
 
   __s32 i2c_smbus_write_quick(int file, __u8 value);
diff --git a/Documentation/i2c/i2c-topology.rst b/Documentation/i2c/i2c-topology.rst
index 7cb53819778e..48fce0f7491b 100644
--- a/Documentation/i2c/i2c-topology.rst
+++ b/Documentation/i2c/i2c-topology.rst
@@ -5,6 +5,8 @@ I2C muxes and complex topologies
 There are a couple of reasons for building more complex I2C topologies
 than a straight-forward I2C bus with one adapter and one or more devices.
 
+Some example use cases are:
+
 1. A mux may be needed on the bus to prevent address collisions.
 
 2. The bus may be accessible from some external bus master, and arbitration
@@ -14,10 +16,10 @@ than a straight-forward I2C bus with one adapter and one or more devices.
    from the I2C bus, at least most of the time, and sits behind a gate
    that has to be operated before the device can be accessed.
 
-Etc
-===
+Several types of hardware components such as I2C muxes, I2C gates and I2C
+arbitrators allow to handle such needs.
 
-These constructs are represented as I2C adapter trees by Linux, where
+These components are represented as I2C adapter trees by Linux, where
 each adapter has a parent adapter (except the root adapter) and zero or
 more child adapters. The root adapter is the actual adapter that issues
 I2C transfers, and all adapters with a parent are part of an "i2c-mux"
@@ -35,46 +37,7 @@ Locking
 =======
 
 There are two variants of locking available to I2C muxes, they can be
-mux-locked or parent-locked muxes. As is evident from below, it can be
-useful to know if a mux is mux-locked or if it is parent-locked. The
-following list was correct at the time of writing:
-
-In drivers/i2c/muxes/:
-
-======================    =============================================
-i2c-arb-gpio-challenge    Parent-locked
-i2c-mux-gpio              Normally parent-locked, mux-locked iff
-                          all involved gpio pins are controlled by the
-                          same I2C root adapter that they mux.
-i2c-mux-gpmux             Normally parent-locked, mux-locked iff
-                          specified in device-tree.
-i2c-mux-ltc4306           Mux-locked
-i2c-mux-mlxcpld           Parent-locked
-i2c-mux-pca9541           Parent-locked
-i2c-mux-pca954x           Parent-locked
-i2c-mux-pinctrl           Normally parent-locked, mux-locked iff
-                          all involved pinctrl devices are controlled
-                          by the same I2C root adapter that they mux.
-i2c-mux-reg               Parent-locked
-======================    =============================================
-
-In drivers/iio/:
-
-======================    =============================================
-gyro/mpu3050              Mux-locked
-imu/inv_mpu6050/          Mux-locked
-======================    =============================================
-
-In drivers/media/:
-
-=======================   =============================================
-dvb-frontends/lgdt3306a   Mux-locked
-dvb-frontends/m88ds3103   Parent-locked
-dvb-frontends/rtl2830     Parent-locked
-dvb-frontends/rtl2832     Mux-locked
-dvb-frontends/si2168      Mux-locked
-usb/cx231xx/              Parent-locked
-=======================   =============================================
+mux-locked or parent-locked muxes.
 
 
 Mux-locked muxes
@@ -89,40 +52,8 @@ full transaction, unrelated I2C transfers may interleave the different
 stages of the transaction. This has the benefit that the mux driver
 may be easier and cleaner to implement, but it has some caveats.
 
-==== =====================================================================
-ML1. If you build a topology with a mux-locked mux being the parent
-     of a parent-locked mux, this might break the expectation from the
-     parent-locked mux that the root adapter is locked during the
-     transaction.
-
-ML2. It is not safe to build arbitrary topologies with two (or more)
-     mux-locked muxes that are not siblings, when there are address
-     collisions between the devices on the child adapters of these
-     non-sibling muxes.
-
-     I.e. the select-transfer-deselect transaction targeting e.g. device
-     address 0x42 behind mux-one may be interleaved with a similar
-     operation targeting device address 0x42 behind mux-two. The
-     intension with such a topology would in this hypothetical example
-     be that mux-one and mux-two should not be selected simultaneously,
-     but mux-locked muxes do not guarantee that in all topologies.
-
-ML3. A mux-locked mux cannot be used by a driver for auto-closing
-     gates/muxes, i.e. something that closes automatically after a given
-     number (one, in most cases) of I2C transfers. Unrelated I2C transfers
-     may creep in and close prematurely.
-
-ML4. If any non-I2C operation in the mux driver changes the I2C mux state,
-     the driver has to lock the root adapter during that operation.
-     Otherwise garbage may appear on the bus as seen from devices
-     behind the mux, when an unrelated I2C transfer is in flight during
-     the non-I2C mux-changing operation.
-==== =====================================================================
-
-
 Mux-locked Example
-------------------
-
+~~~~~~~~~~~~~~~~~~
 
 ::
 
@@ -153,6 +84,43 @@ This means that accesses to D2 are lockout out for the full duration
 of the entire operation. But accesses to D3 are possibly interleaved
 at any point.
 
+Mux-locked caveats
+~~~~~~~~~~~~~~~~~~
+
+When using a mux-locked mux, be aware of the following restrictions:
+
+[ML1]
+  If you build a topology with a mux-locked mux being the parent
+  of a parent-locked mux, this might break the expectation from the
+  parent-locked mux that the root adapter is locked during the
+  transaction.
+
+[ML2]
+  It is not safe to build arbitrary topologies with two (or more)
+  mux-locked muxes that are not siblings, when there are address
+  collisions between the devices on the child adapters of these
+  non-sibling muxes.
+
+  I.e. the select-transfer-deselect transaction targeting e.g. device
+  address 0x42 behind mux-one may be interleaved with a similar
+  operation targeting device address 0x42 behind mux-two. The
+  intent with such a topology would in this hypothetical example
+  be that mux-one and mux-two should not be selected simultaneously,
+  but mux-locked muxes do not guarantee that in all topologies.
+
+[ML3]
+  A mux-locked mux cannot be used by a driver for auto-closing
+  gates/muxes, i.e. something that closes automatically after a given
+  number (one, in most cases) of I2C transfers. Unrelated I2C transfers
+  may creep in and close prematurely.
+
+[ML4]
+  If any non-I2C operation in the mux driver changes the I2C mux state,
+  the driver has to lock the root adapter during that operation.
+  Otherwise garbage may appear on the bus as seen from devices
+  behind the mux, when an unrelated I2C transfer is in flight during
+  the non-I2C mux-changing operation.
+
 
 Parent-locked muxes
 -------------------
@@ -161,28 +129,10 @@ Parent-locked muxes lock the parent adapter during the full select-
 transfer-deselect transaction. The implication is that the mux driver
 has to ensure that any and all I2C transfers through that parent
 adapter during the transaction are unlocked I2C transfers (using e.g.
-__i2c_transfer), or a deadlock will follow. There are a couple of
-caveats.
-
-==== ====================================================================
-PL1. If you build a topology with a parent-locked mux being the child
-     of another mux, this might break a possible assumption from the
-     child mux that the root adapter is unused between its select op
-     and the actual transfer (e.g. if the child mux is auto-closing
-     and the parent mux issues I2C transfers as part of its select).
-     This is especially the case if the parent mux is mux-locked, but
-     it may also happen if the parent mux is parent-locked.
-
-PL2. If select/deselect calls out to other subsystems such as gpio,
-     pinctrl, regmap or iio, it is essential that any I2C transfers
-     caused by these subsystems are unlocked. This can be convoluted to
-     accomplish, maybe even impossible if an acceptably clean solution
-     is sought.
-==== ====================================================================
-
+__i2c_transfer), or a deadlock will follow.
 
 Parent-locked Example
----------------------
+~~~~~~~~~~~~~~~~~~~~~
 
 ::
 
@@ -212,10 +162,30 @@ When there is an access to D1, this happens:
  9.  M1 unlocks its parent adapter.
  10. M1 unlocks muxes on its parent.
 
-
 This means that accesses to both D2 and D3 are locked out for the full
 duration of the entire operation.
 
+Parent-locked Caveats
+~~~~~~~~~~~~~~~~~~~~~
+
+When using a parent-locked mux, be aware of the following restrictions:
+
+[PL1]
+  If you build a topology with a parent-locked mux being the child
+  of another mux, this might break a possible assumption from the
+  child mux that the root adapter is unused between its select op
+  and the actual transfer (e.g. if the child mux is auto-closing
+  and the parent mux issues I2C transfers as part of its select).
+  This is especially the case if the parent mux is mux-locked, but
+  it may also happen if the parent mux is parent-locked.
+
+[PL2]
+  If select/deselect calls out to other subsystems such as gpio,
+  pinctrl, regmap or iio, it is essential that any I2C transfers
+  caused by these subsystems are unlocked. This can be convoluted to
+  accomplish, maybe even impossible if an acceptably clean solution
+  is sought.
+
 
 Complex Examples
 ================
@@ -261,8 +231,10 @@ This is a good topology::
 When device D1 is accessed, accesses to D2 are locked out for the
 full duration of the operation (muxes on the top child adapter of M1
 are locked). But accesses to D3 and D4 are possibly interleaved at
-any point. Accesses to D3 locks out D1 and D2, but accesses to D4
-are still possibly interleaved.
+any point.
+
+Accesses to D3 locks out D1 and D2, but accesses to D4 are still possibly
+interleaved.
 
 
 Mux-locked mux as parent of parent-locked mux
@@ -394,3 +366,47 @@ This is a good topology::
 When D1 or D2 are accessed, accesses to D3 and D4 are locked out while
 accesses to D5 may interleave. When D3 or D4 are accessed, accesses to
 all other devices are locked out.
+
+
+Mux type of existing device drivers
+===================================
+
+Whether a device is mux-locked or parent-locked depends on its
+implementation. The following list was correct at the time of writing:
+
+In drivers/i2c/muxes/:
+
+======================    =============================================
+i2c-arb-gpio-challenge    Parent-locked
+i2c-mux-gpio              Normally parent-locked, mux-locked iff
+                          all involved gpio pins are controlled by the
+                          same I2C root adapter that they mux.
+i2c-mux-gpmux             Normally parent-locked, mux-locked iff
+                          specified in device-tree.
+i2c-mux-ltc4306           Mux-locked
+i2c-mux-mlxcpld           Parent-locked
+i2c-mux-pca9541           Parent-locked
+i2c-mux-pca954x           Parent-locked
+i2c-mux-pinctrl           Normally parent-locked, mux-locked iff
+                          all involved pinctrl devices are controlled
+                          by the same I2C root adapter that they mux.
+i2c-mux-reg               Parent-locked
+======================    =============================================
+
+In drivers/iio/:
+
+======================    =============================================
+gyro/mpu3050              Mux-locked
+imu/inv_mpu6050/          Mux-locked
+======================    =============================================
+
+In drivers/media/:
+
+=======================   =============================================
+dvb-frontends/lgdt3306a   Mux-locked
+dvb-frontends/m88ds3103   Parent-locked
+dvb-frontends/rtl2830     Parent-locked
+dvb-frontends/rtl2832     Mux-locked
+dvb-frontends/si2168      Mux-locked
+usb/cx231xx/              Parent-locked
+=======================   =============================================
diff --git a/Documentation/i2c/slave-interface.rst b/Documentation/i2c/slave-interface.rst
index 82ea3e1d6fe4..58fb143baee4 100644
--- a/Documentation/i2c/slave-interface.rst
+++ b/Documentation/i2c/slave-interface.rst
@@ -32,9 +32,9 @@ User manual
 ===========
 
 I2C slave backends behave like standard I2C clients. So, you can instantiate
-them as described in the document 'instantiating-devices'. The only difference
-is that i2c slave backends have their own address space. So, you have to add
-0x1000 to the address you would originally request. An example for
+them as described in the document instantiating-devices.rst. The only
+difference is that i2c slave backends have their own address space. So, you
+have to add 0x1000 to the address you would originally request. An example for
 instantiating the slave-eeprom driver from userspace at the 7 bit address 0x64
 on bus 1::
 
diff --git a/Documentation/i2c/writing-clients.rst b/Documentation/i2c/writing-clients.rst
index e3b126cf4a3b..47f7cbf4ed1a 100644
--- a/Documentation/i2c/writing-clients.rst
+++ b/Documentation/i2c/writing-clients.rst
@@ -364,7 +364,7 @@ stop condition is issued between transaction. The i2c_msg structure
 contains for each message the client address, the number of bytes of the
 message and the message data itself.
 
-You can read the file ``i2c-protocol`` for more information about the
+You can read the file i2c-protocol.rst for more information about the
 actual I2C protocol.
 
 
@@ -414,7 +414,7 @@ transactions return 0 on success; the 'read' transactions return the read
 value, except for block transactions, which return the number of values
 read. The block buffers need not be longer than 32 bytes.
 
-You can read the file ``smbus-protocol`` for more information about the
+You can read the file smbus-protocol.rst for more information about the
 actual SMBus protocol.
 
 
diff --git a/Documentation/index.rst b/Documentation/index.rst
index 4737c18c97ff..bf6aa681c960 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -1,11 +1,5 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-
-.. The Linux Kernel documentation master file, created by
-   sphinx-quickstart on Fri Feb 12 13:51:46 2016.
-   You can adapt this file completely to your liking, but it should at least
-   contain the root `toctree` directive.
-
 .. _linux_doc:
 
 The Linux Kernel documentation
@@ -18,133 +12,85 @@ documents into a coherent whole.  Please note that improvements to the
 documentation are welcome; join the linux-doc list at vger.kernel.org if
 you want to help out.
 
-Licensing documentation
------------------------
+Working with the development community
+--------------------------------------
 
-The following describes the license of the Linux kernel source code
-(GPLv2), how to properly mark the license of individual files in the source
-tree, as well as links to the full license text.
-
-* :ref:`kernel_licensing`
-
-User-oriented documentation
----------------------------
-
-The following manuals are written for *users* of the kernel — those who are
-trying to get it to work optimally on a given system.
+The essential guides for interacting with the kernel's development
+community and getting your work upstream.
 
 .. toctree::
-   :maxdepth: 2
-
-   admin-guide/index
-   kbuild/index
-
-Firmware-related documentation
-------------------------------
-The following holds information on the kernel's expectations regarding the
-platform firmwares.
+   :maxdepth: 1
 
-.. toctree::
-   :maxdepth: 2
+   process/development-process
+   process/submitting-patches
+   Code of conduct <process/code-of-conduct>
+   maintainer/index
+   All development-process docs <process/index>
 
-   firmware-guide/index
-   devicetree/index
 
-Application-developer documentation
------------------------------------
+Internal API manuals
+--------------------
 
-The user-space API manual gathers together documents describing aspects of
-the kernel interface as seen by application developers.
+Manuals for use by developers working to interface with the rest of the
+kernel.
 
 .. toctree::
-   :maxdepth: 2
-
-   userspace-api/index
+   :maxdepth: 1
 
+   core-api/index
+   driver-api/index
+   subsystem-apis
+   Locking in the kernel <locking/index>
 
-Introduction to kernel development
-----------------------------------
+Development tools and processes
+-------------------------------
 
-These manuals contain overall information about how to develop the kernel.
-The kernel community is quite large, with thousands of developers
-contributing over the course of a year.  As with any large community,
-knowing how things are done will make the process of getting your changes
-merged much easier.
+Various other manuals with useful information for all kernel developers.
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
 
-   process/index
-   dev-tools/index
+   process/license-rules
    doc-guide/index
+   dev-tools/index
+   dev-tools/testing-overview
    kernel-hacking/index
    trace/index
-   maintainer/index
    fault-injection/index
    livepatch/index
+   rust/index
 
 
-Kernel API documentation
-------------------------
+User-oriented documentation
+---------------------------
 
-These books get into the details of how specific kernel subsystems work
-from the point of view of a kernel developer.  Much of the information here
-is taken directly from the kernel source, with supplemental material added
-as needed (or at least as we managed to add it — probably *not* all that is
-needed).
+The following manuals are written for *users* of the kernel — those who are
+trying to get it to work optimally on a given system and application
+developers seeking information on the kernel's user-space APIs.
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
 
-   driver-api/index
-   core-api/index
-   locking/index
-   accounting/index
-   block/index
-   cdrom/index
-   cpu-freq/index
-   fb/index
-   fpga/index
-   hid/index
-   i2c/index
-   iio/index
-   isdn/index
-   infiniband/index
-   leds/index
-   netlabel/index
-   networking/index
-   pcmcia/index
-   power/index
-   target/index
-   timers/index
-   spi/index
-   w1/index
-   watchdog/index
-   virt/index
-   input/index
-   hwmon/index
-   gpu/index
-   security/index
-   sound/index
-   crypto/index
-   filesystems/index
-   mm/index
-   bpf/index
-   usb/index
-   PCI/index
-   scsi/index
-   misc-devices/index
-   scheduler/index
-   mhi/index
-   peci/index
-
-Architecture-agnostic documentation
------------------------------------
+   admin-guide/index
+   The kernel build system <kbuild/index>
+   admin-guide/reporting-issues.rst
+   User-space tools <tools/index>
+   userspace-api/index
+
+See also: the `Linux man pages <https://www.kernel.org/doc/man-pages/>`_,
+which are kept separately from the kernel's own documentation.
+
+Firmware-related documentation
+------------------------------
+The following holds information on the kernel's expectations regarding the
+platform firmwares.
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
+
+   firmware-guide/index
+   devicetree/index
 
-   asm-annotations
 
 Architecture-specific documentation
 -----------------------------------
@@ -163,9 +109,8 @@ of the documentation body, or may require some adjustments and/or conversion
 to ReStructured Text format, or are simply too old.
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
 
-   tools/index
    staging/index
 
 
diff --git a/Documentation/input/joydev/joystick.rst b/Documentation/input/joydev/joystick.rst
index f615906a0821..6d721396717a 100644
--- a/Documentation/input/joydev/joystick.rst
+++ b/Documentation/input/joydev/joystick.rst
@@ -517,6 +517,7 @@ All I-Force devices are supported by the iforce module. This includes:
 * AVB Mag Turbo Force
 * AVB Top Shot Pegasus
 * AVB Top Shot Force Feedback Racing Wheel
+* Boeder Force Feedback Wheel
 * Logitech WingMan Force
 * Logitech WingMan Force Wheel
 * Guillemot Race Leader Force Feedback
diff --git a/Documentation/kbuild/gcc-plugins.rst b/Documentation/kbuild/gcc-plugins.rst
index 0ba76719f1b9..c578c6ba3eb6 100644
--- a/Documentation/kbuild/gcc-plugins.rst
+++ b/Documentation/kbuild/gcc-plugins.rst
@@ -90,7 +90,11 @@ e.g., on Ubuntu for gcc-10::
 
 Or on Fedora::
 
-	dnf install gcc-plugin-devel
+	dnf install gcc-plugin-devel libmpc-devel
+
+Or on Fedora when using cross-compilers that include plugins::
+
+	dnf install libmpc-devel
 
 Enable the GCC plugin infrastructure and some plugin(s) you want to use
 in the kernel config::
@@ -99,6 +103,19 @@ in the kernel config::
 	CONFIG_GCC_PLUGIN_LATENT_ENTROPY=y
 	...
 
+Run gcc (native or cross-compiler) to ensure plugin headers are detected::
+
+	gcc -print-file-name=plugin
+	CROSS_COMPILE=arm-linux-gnu- ${CROSS_COMPILE}gcc -print-file-name=plugin
+
+The word "plugin" means they are not detected::
+
+	plugin
+
+A full path means they are detected::
+
+       /usr/lib/gcc/x86_64-redhat-linux/12/plugin
+
 To compile the minimum tool set including the plugin(s)::
 
 	make scripts
diff --git a/Documentation/kbuild/kbuild.rst b/Documentation/kbuild/kbuild.rst
index ef19b9c13523..08f575e6236c 100644
--- a/Documentation/kbuild/kbuild.rst
+++ b/Documentation/kbuild/kbuild.rst
@@ -48,6 +48,10 @@ KCFLAGS
 -------
 Additional options to the C compiler (for built-in and modules).
 
+KRUSTFLAGS
+----------
+Additional options to the Rust compiler (for built-in and modules).
+
 CFLAGS_KERNEL
 -------------
 Additional options for $(CC) when used to compile
@@ -57,6 +61,15 @@ CFLAGS_MODULE
 -------------
 Additional module specific options to use for $(CC).
 
+RUSTFLAGS_KERNEL
+----------------
+Additional options for $(RUSTC) when used to compile
+code that is compiled as built-in.
+
+RUSTFLAGS_MODULE
+----------------
+Additional module specific options to use for $(RUSTC).
+
 LDFLAGS_MODULE
 --------------
 Additional options used for $(LD) when linking modules.
@@ -69,6 +82,10 @@ HOSTCXXFLAGS
 ------------
 Additional flags to be passed to $(HOSTCXX) when building host programs.
 
+HOSTRUSTFLAGS
+-------------
+Additional flags to be passed to $(HOSTRUSTC) when building host programs.
+
 HOSTLDFLAGS
 -----------
 Additional flags to be passed when linking host programs.
diff --git a/Documentation/kbuild/kconfig-language.rst b/Documentation/kbuild/kconfig-language.rst
index 7fb398649f51..858ed5d80def 100644
--- a/Documentation/kbuild/kconfig-language.rst
+++ b/Documentation/kbuild/kconfig-language.rst
@@ -525,8 +525,8 @@ followed by a test macro::
 If you need to expose a compiler capability to makefiles and/or C source files,
 `CC_HAS_` is the recommended prefix for the config option::
 
-  config CC_HAS_ASM_GOTO
-	def_bool $(success,$(srctree)/scripts/gcc-goto.sh $(CC))
+  config CC_HAS_FOO
+	def_bool $(success,$(srctree)/scripts/cc-check-foo.sh $(CC))
 
 Build as module only
 ~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst
index 11a296e52d68..5ea1e72d89c8 100644
--- a/Documentation/kbuild/makefiles.rst
+++ b/Documentation/kbuild/makefiles.rst
@@ -29,8 +29,9 @@ This document describes the Linux kernel Makefiles.
 	   --- 4.1 Simple Host Program
 	   --- 4.2 Composite Host Programs
 	   --- 4.3 Using C++ for host programs
-	   --- 4.4 Controlling compiler options for host programs
-	   --- 4.5 When host programs are actually built
+	   --- 4.4 Using Rust for host programs
+	   --- 4.5 Controlling compiler options for host programs
+	   --- 4.6 When host programs are actually built
 
 	=== 5 Userspace Program support
 	   --- 5.1 Simple Userspace Program
@@ -835,7 +836,24 @@ Both possibilities are described in the following.
 		qconf-cxxobjs := qconf.o
 		qconf-objs    := check.o
 
-4.4 Controlling compiler options for host programs
+4.4 Using Rust for host programs
+--------------------------------
+
+	Kbuild offers support for host programs written in Rust. However,
+	since a Rust toolchain is not mandatory for kernel compilation,
+	it may only be used in scenarios where Rust is required to be
+	available (e.g. when  ``CONFIG_RUST`` is enabled).
+
+	Example::
+
+		hostprogs     := target
+		target-rust   := y
+
+	Kbuild will compile ``target`` using ``target.rs`` as the crate root,
+	located in the same directory as the ``Makefile``. The crate may
+	consist of several source files (see ``samples/rust/hostprogs``).
+
+4.5 Controlling compiler options for host programs
 --------------------------------------------------
 
 	When compiling host programs, it is possible to set specific flags.
@@ -867,7 +885,7 @@ Both possibilities are described in the following.
 	When linking qconf, it will be passed the extra option
 	"-L$(QTDIR)/lib".
 
-4.5 When host programs are actually built
+4.6 When host programs are actually built
 -----------------------------------------
 
 	Kbuild will only build host-programs when they are referenced
@@ -1181,6 +1199,17 @@ When kbuild executes, the following steps are followed (roughly):
 	The first example utilises the trick that a config option expands
 	to 'y' when selected.
 
+    KBUILD_RUSTFLAGS
+	$(RUSTC) compiler flags
+
+	Default value - see top level Makefile
+	Append or modify as required per architecture.
+
+	Often, the KBUILD_RUSTFLAGS variable depends on the configuration.
+
+	Note that target specification file generation (for ``--target``)
+	is handled in ``scripts/generate_rust_target.rs``.
+
     KBUILD_AFLAGS_KERNEL
 	Assembler options specific for built-in
 
@@ -1208,6 +1237,19 @@ When kbuild executes, the following steps are followed (roughly):
 	are used for $(CC).
 	From commandline CFLAGS_MODULE shall be used (see kbuild.rst).
 
+    KBUILD_RUSTFLAGS_KERNEL
+	$(RUSTC) options specific for built-in
+
+	$(KBUILD_RUSTFLAGS_KERNEL) contains extra Rust compiler flags used to
+	compile resident kernel code.
+
+    KBUILD_RUSTFLAGS_MODULE
+	Options for $(RUSTC) when building modules
+
+	$(KBUILD_RUSTFLAGS_MODULE) is used to add arch-specific options that
+	are used for $(RUSTC).
+	From commandline RUSTFLAGS_MODULE shall be used (see kbuild.rst).
+
     KBUILD_LDFLAGS_MODULE
 	Options for $(LD) when linking modules
 
diff --git a/Documentation/locking/seqlock.rst b/Documentation/locking/seqlock.rst
index 64405e5da63e..bfda1a5fecad 100644
--- a/Documentation/locking/seqlock.rst
+++ b/Documentation/locking/seqlock.rst
@@ -39,7 +39,7 @@ as the writer can invalidate a pointer that the reader is following.
 Sequence counters (``seqcount_t``)
 ==================================
 
-This is the the raw counting mechanism, which does not protect against
+This is the raw counting mechanism, which does not protect against
 multiple writers.  Write side critical sections must thus be serialized
 by an external lock.
 
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 832b5d36e279..06f80e3785c5 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -52,7 +52,7 @@ CONTENTS
 
      - Varieties of memory barrier.
      - What may not be assumed about memory barriers?
-     - Data dependency barriers (historical).
+     - Address-dependency barriers (historical).
      - Control dependencies.
      - SMP barrier pairing.
      - Examples of memory barrier sequences.
@@ -187,9 +187,9 @@ As a further example, consider this sequence of events:
 	B = 4;		Q = P;
 	P = &B;		D = *Q;
 
-There is an obvious data dependency here, as the value loaded into D depends on
-the address retrieved from P by CPU 2.  At the end of the sequence, any of the
-following results are possible:
+There is an obvious address dependency here, as the value loaded into D depends
+on the address retrieved from P by CPU 2.  At the end of the sequence, any of
+the following results are possible:
 
 	(Q == &A) and (D == 1)
 	(Q == &B) and (D == 2)
@@ -391,58 +391,62 @@ Memory barriers come in four basic varieties:
      memory system as time progresses.  All stores _before_ a write barrier
      will occur _before_ all the stores after the write barrier.
 
-     [!] Note that write barriers should normally be paired with read or data
-     dependency barriers; see the "SMP barrier pairing" subsection.
+     [!] Note that write barriers should normally be paired with read or
+     address-dependency barriers; see the "SMP barrier pairing" subsection.
 
 
- (2) Data dependency barriers.
+ (2) Address-dependency barriers (historical).
 
-     A data dependency barrier is a weaker form of read barrier.  In the case
-     where two loads are performed such that the second depends on the result
-     of the first (eg: the first load retrieves the address to which the second
-     load will be directed), a data dependency barrier would be required to
-     make sure that the target of the second load is updated after the address
-     obtained by the first load is accessed.
+     An address-dependency barrier is a weaker form of read barrier.  In the
+     case where two loads are performed such that the second depends on the
+     result of the first (eg: the first load retrieves the address to which
+     the second load will be directed), an address-dependency barrier would
+     be required to make sure that the target of the second load is updated
+     after the address obtained by the first load is accessed.
 
-     A data dependency barrier is a partial ordering on interdependent loads
-     only; it is not required to have any effect on stores, independent loads
-     or overlapping loads.
+     An address-dependency barrier is a partial ordering on interdependent
+     loads only; it is not required to have any effect on stores, independent
+     loads or overlapping loads.
 
      As mentioned in (1), the other CPUs in the system can be viewed as
      committing sequences of stores to the memory system that the CPU being
-     considered can then perceive.  A data dependency barrier issued by the CPU
-     under consideration guarantees that for any load preceding it, if that
-     load touches one of a sequence of stores from another CPU, then by the
-     time the barrier completes, the effects of all the stores prior to that
-     touched by the load will be perceptible to any loads issued after the data
-     dependency barrier.
+     considered can then perceive.  An address-dependency barrier issued by
+     the CPU under consideration guarantees that for any load preceding it,
+     if that load touches one of a sequence of stores from another CPU, then
+     by the time the barrier completes, the effects of all the stores prior to
+     that touched by the load will be perceptible to any loads issued after
+     the address-dependency barrier.
 
      See the "Examples of memory barrier sequences" subsection for diagrams
      showing the ordering constraints.
 
-     [!] Note that the first load really has to have a _data_ dependency and
+     [!] Note that the first load really has to have an _address_ dependency and
      not a control dependency.  If the address for the second load is dependent
      on the first load, but the dependency is through a conditional rather than
      actually loading the address itself, then it's a _control_ dependency and
      a full read barrier or better is required.  See the "Control dependencies"
      subsection for more information.
 
-     [!] Note that data dependency barriers should normally be paired with
+     [!] Note that address-dependency barriers should normally be paired with
      write barriers; see the "SMP barrier pairing" subsection.
 
+     [!] Kernel release v5.9 removed kernel APIs for explicit address-
+     dependency barriers.  Nowadays, APIs for marking loads from shared
+     variables such as READ_ONCE() and rcu_dereference() provide implicit
+     address-dependency barriers.
 
  (3) Read (or load) memory barriers.
 
-     A read barrier is a data dependency barrier plus a guarantee that all the
-     LOAD operations specified before the barrier will appear to happen before
-     all the LOAD operations specified after the barrier with respect to the
-     other components of the system.
+     A read barrier is an address-dependency barrier plus a guarantee that all
+     the LOAD operations specified before the barrier will appear to happen
+     before all the LOAD operations specified after the barrier with respect to
+     the other components of the system.
 
      A read barrier is a partial ordering on loads only; it is not required to
      have any effect on stores.
 
-     Read memory barriers imply data dependency barriers, and so can substitute
-     for them.
+     Read memory barriers imply address-dependency barriers, and so can
+     substitute for them.
 
      [!] Note that read barriers should normally be paired with write barriers;
      see the "SMP barrier pairing" subsection.
@@ -550,17 +554,21 @@ There are certain things that the Linux kernel memory barriers do not guarantee:
 	    Documentation/core-api/dma-api.rst
 
 
-DATA DEPENDENCY BARRIERS (HISTORICAL)
--------------------------------------
+ADDRESS-DEPENDENCY BARRIERS (HISTORICAL)
+----------------------------------------
 
 As of v4.15 of the Linux kernel, an smp_mb() was added to READ_ONCE() for
 DEC Alpha, which means that about the only people who need to pay attention
 to this section are those working on DEC Alpha architecture-specific code
 and those working on READ_ONCE() itself.  For those who need it, and for
 those who are interested in the history, here is the story of
-data-dependency barriers.
+address-dependency barriers.
+
+[!] While address dependencies are observed in both load-to-load and
+load-to-store relations, address-dependency barriers are not necessary
+for load-to-store situations.
 
-The usage requirements of data dependency barriers are a little subtle, and
+The requirement of address-dependency barriers is a little subtle, and
 it's not always obvious that they're needed.  To illustrate, consider the
 following sequence of events:
 
@@ -570,11 +578,14 @@ following sequence of events:
 	B = 4;
 	<write barrier>
 	WRITE_ONCE(P, &B);
-			      Q = READ_ONCE(P);
+			      Q = READ_ONCE_OLD(P);
 			      D = *Q;
 
-There's a clear data dependency here, and it would seem that by the end of the
-sequence, Q must be either &A or &B, and that:
+[!] READ_ONCE_OLD() corresponds to READ_ONCE() of pre-4.15 kernel, which
+doesn't imply an address-dependency barrier.
+
+There's a clear address dependency here, and it would seem that by the end of
+the sequence, Q must be either &A or &B, and that:
 
 	(Q == &A) implies (D == 1)
 	(Q == &B) implies (D == 4)
@@ -588,8 +599,8 @@ While this may seem like a failure of coherency or causality maintenance, it
 isn't, and this behaviour can be observed on certain real CPUs (such as the DEC
 Alpha).
 
-To deal with this, a data dependency barrier or better must be inserted
-between the address load and the data load:
+To deal with this, READ_ONCE() provides an implicit address-dependency barrier
+since kernel release v4.15:
 
 	CPU 1		      CPU 2
 	===============	      ===============
@@ -598,7 +609,7 @@ between the address load and the data load:
 	<write barrier>
 	WRITE_ONCE(P, &B);
 			      Q = READ_ONCE(P);
-			      <data dependency barrier>
+			      <implicit address-dependency barrier>
 			      D = *Q;
 
 This enforces the occurrence of one of the two implications, and prevents the
@@ -615,13 +626,13 @@ odd-numbered bank is idle, one can see the new value of the pointer P (&B),
 but the old value of the variable B (2).
 
 
-A data-dependency barrier is not required to order dependent writes
-because the CPUs that the Linux kernel supports don't do writes
-until they are certain (1) that the write will actually happen, (2)
-of the location of the write, and (3) of the value to be written.
+An address-dependency barrier is not required to order dependent writes
+because the CPUs that the Linux kernel supports don't do writes until they
+are certain (1) that the write will actually happen, (2) of the location of
+the write, and (3) of the value to be written.
 But please carefully read the "CONTROL DEPENDENCIES" section and the
-Documentation/RCU/rcu_dereference.rst file:  The compiler can and does
-break dependencies in a great many highly creative ways.
+Documentation/RCU/rcu_dereference.rst file:  The compiler can and does break
+dependencies in a great many highly creative ways.
 
 	CPU 1		      CPU 2
 	===============	      ===============
@@ -629,12 +640,12 @@ break dependencies in a great many highly creative ways.
 	B = 4;
 	<write barrier>
 	WRITE_ONCE(P, &B);
-			      Q = READ_ONCE(P);
+			      Q = READ_ONCE_OLD(P);
 			      WRITE_ONCE(*Q, 5);
 
-Therefore, no data-dependency barrier is required to order the read into
+Therefore, no address-dependency barrier is required to order the read into
 Q with the store into *Q.  In other words, this outcome is prohibited,
-even without a data-dependency barrier:
+even without an implicit address-dependency barrier of modern READ_ONCE():
 
 	(Q == &B) && (B == 4)
 
@@ -645,12 +656,12 @@ can be used to record rare error conditions and the like, and the CPUs'
 naturally occurring ordering prevents such records from being lost.
 
 
-Note well that the ordering provided by a data dependency is local to
+Note well that the ordering provided by an address dependency is local to
 the CPU containing it.  See the section on "Multicopy atomicity" for
 more information.
 
 
-The data dependency barrier is very important to the RCU system,
+The address-dependency barrier is very important to the RCU system,
 for example.  See rcu_assign_pointer() and rcu_dereference() in
 include/linux/rcupdate.h.  This permits the current target of an RCU'd
 pointer to be replaced with a new modified target, without the replacement
@@ -667,20 +678,21 @@ not understand them.  The purpose of this section is to help you prevent
 the compiler's ignorance from breaking your code.
 
 A load-load control dependency requires a full read memory barrier, not
-simply a data dependency barrier to make it work correctly.  Consider the
-following bit of code:
+simply an (implicit) address-dependency barrier to make it work correctly.
+Consider the following bit of code:
 
 	q = READ_ONCE(a);
+	<implicit address-dependency barrier>
 	if (q) {
-		<data dependency barrier>  /* BUG: No data dependency!!! */
+		/* BUG: No address dependency!!! */
 		p = READ_ONCE(b);
 	}
 
-This will not have the desired effect because there is no actual data
+This will not have the desired effect because there is no actual address
 dependency, but rather a control dependency that the CPU may short-circuit
 by attempting to predict the outcome in advance, so that other CPUs see
-the load from b as having happened before the load from a.  In such a
-case what's actually required is:
+the load from b as having happened before the load from a.  In such a case
+what's actually required is:
 
 	q = READ_ONCE(a);
 	if (q) {
@@ -927,9 +939,9 @@ General barriers pair with each other, though they also pair with most
 other types of barriers, albeit without multicopy atomicity.  An acquire
 barrier pairs with a release barrier, but both may also pair with other
 barriers, including of course general barriers.  A write barrier pairs
-with a data dependency barrier, a control dependency, an acquire barrier,
+with an address-dependency barrier, a control dependency, an acquire barrier,
 a release barrier, a read barrier, or a general barrier.  Similarly a
-read barrier, control dependency, or a data dependency barrier pairs
+read barrier, control dependency, or an address-dependency barrier pairs
 with a write barrier, an acquire barrier, a release barrier, or a
 general barrier:
 
@@ -948,7 +960,7 @@ Or:
 	a = 1;
 	<write barrier>
 	WRITE_ONCE(b, &a);    x = READ_ONCE(b);
-			      <data dependency barrier>
+			      <implicit address-dependency barrier>
 			      y = *x;
 
 Or even:
@@ -968,8 +980,8 @@ Basically, the read barrier always has to be there, even though it can be of
 the "weaker" type.
 
 [!] Note that the stores before the write barrier would normally be expected to
-match the loads after the read barrier or the data dependency barrier, and vice
-versa:
+match the loads after the read barrier or the address-dependency barrier, and
+vice versa:
 
 	CPU 1                               CPU 2
 	===================                 ===================
@@ -1021,8 +1033,8 @@ STORE B, STORE C } all occurring before the unordered set of { STORE D, STORE E
 	                   V
 
 
-Secondly, data dependency barriers act as partial orderings on data-dependent
-loads.  Consider the following sequence of events:
+Secondly, address-dependency barriers act as partial orderings on address-
+dependent loads.  Consider the following sequence of events:
 
 	CPU 1			CPU 2
 	=======================	=======================
@@ -1067,8 +1079,8 @@ effectively random order, despite the write barrier issued by CPU 1:
 In the above example, CPU 2 perceives that B is 7, despite the load of *C
 (which would be B) coming after the LOAD of C.
 
-If, however, a data dependency barrier were to be placed between the load of C
-and the load of *C (ie: B) on CPU 2:
+If, however, an address-dependency barrier were to be placed between the load
+of C and the load of *C (ie: B) on CPU 2:
 
 	CPU 1			CPU 2
 	=======================	=======================
@@ -1078,7 +1090,7 @@ and the load of *C (ie: B) on CPU 2:
 	<write barrier>
 	STORE C = &B		LOAD X
 	STORE D = 4		LOAD C (gets &B)
-				<data dependency barrier>
+				<address-dependency barrier>
 				LOAD *C (reads B)
 
 then the following will occur:
@@ -1101,7 +1113,7 @@ then the following will occur:
 	                               |        +-------+       |       |
 	                               |        | X->9  |------>|       |
 	                               |        +-------+       |       |
-	  Makes sure all effects --->   \   ddddddddddddddddd   |       |
+	  Makes sure all effects --->   \   aaaaaaaaaaaaaaaaa   |       |
 	  prior to the store of C        \      +-------+       |       |
 	  are perceptible to              ----->| B->2  |------>|       |
 	  subsequent loads                      +-------+       |       |
@@ -1292,7 +1304,7 @@ Which might appear as this:
 	LOAD with immediate effect              :       :       +-------+
 
 
-Placing a read barrier or a data dependency barrier just before the second
+Placing a read barrier or an address-dependency barrier just before the second
 load:
 
 	CPU 1			CPU 2
@@ -1816,20 +1828,20 @@ which may then reorder things however it wishes.
 CPU MEMORY BARRIERS
 -------------------
 
-The Linux kernel has eight basic CPU memory barriers:
+The Linux kernel has seven basic CPU memory barriers:
 
-	TYPE		MANDATORY		SMP CONDITIONAL
-	===============	=======================	===========================
-	GENERAL		mb()			smp_mb()
-	WRITE		wmb()			smp_wmb()
-	READ		rmb()			smp_rmb()
-	DATA DEPENDENCY				READ_ONCE()
+	TYPE			MANDATORY	SMP CONDITIONAL
+	=======================	===============	===============
+	GENERAL			mb()		smp_mb()
+	WRITE			wmb()		smp_wmb()
+	READ			rmb()		smp_rmb()
+	ADDRESS DEPENDENCY			READ_ONCE()
 
 
-All memory barriers except the data dependency barriers imply a compiler
-barrier.  Data dependencies do not impose any additional compiler ordering.
+All memory barriers except the address-dependency barriers imply a compiler
+barrier.  Address dependencies do not impose any additional compiler ordering.
 
-Aside: In the case of data dependencies, the compiler would be expected
+Aside: In the case of address dependencies, the compiler would be expected
 to issue the loads in the correct order (eg. `a[b]` would have to load
 the value of b before loading a[b]), however there is no guarantee in
 the C specification that the compiler may not speculate the value of b
@@ -2749,7 +2761,8 @@ is discarded from the CPU's cache and reloaded.  To deal with this, the
 appropriate part of the kernel must invalidate the overlapping bits of the
 cache on each CPU.
 
-See Documentation/core-api/cachetlb.rst for more information on cache management.
+See Documentation/core-api/cachetlb.rst for more information on cache
+management.
 
 
 CACHE COHERENCY VS MMIO
@@ -2889,8 +2902,8 @@ AND THEN THERE'S THE ALPHA
 The DEC Alpha CPU is one of the most relaxed CPUs there is.  Not only that,
 some versions of the Alpha CPU have a split data cache, permitting them to have
 two semantically-related cache lines updated at separate times.  This is where
-the data dependency barrier really becomes necessary as this synchronises both
-caches with the memory coherence system, thus making it seem like pointer
+the address-dependency barrier really becomes necessary as this synchronises
+both caches with the memory coherence system, thus making it seem like pointer
 changes vs new data occur in the right order.
 
 The Alpha defines the Linux kernel's memory model, although as of v4.15
diff --git a/Documentation/mm/unevictable-lru.rst b/Documentation/mm/unevictable-lru.rst
index b280367d6a44..4a0e158aa9ce 100644
--- a/Documentation/mm/unevictable-lru.rst
+++ b/Documentation/mm/unevictable-lru.rst
@@ -197,7 +197,7 @@ unevictable list for the memory cgroup and node being scanned.
 There may be situations where a page is mapped into a VM_LOCKED VMA, but the
 page is not marked as PG_mlocked.  Such pages will make it all the way to
 shrink_active_list() or shrink_page_list() where they will be detected when
-vmscan walks the reverse map in page_referenced() or try_to_unmap().  The page
+vmscan walks the reverse map in folio_referenced() or try_to_unmap().  The page
 is culled to the unevictable list when it is released by the shrinker.
 
 To "cull" an unevictable page, vmscan simply puts the page back on the LRU list
@@ -267,7 +267,7 @@ the LRU.  Such pages can be "noticed" by memory management in several places:
  (4) in the fault path and when a VM_LOCKED stack segment is expanded; or
 
  (5) as mentioned above, in vmscan:shrink_page_list() when attempting to
-     reclaim a page in a VM_LOCKED VMA by page_referenced() or try_to_unmap().
+     reclaim a page in a VM_LOCKED VMA by folio_referenced() or try_to_unmap().
 
 mlocked pages become unlocked and rescued from the unevictable list when:
 
@@ -547,7 +547,7 @@ vmscan's shrink_inactive_list() and shrink_page_list() also divert obviously
 unevictable pages found on the inactive lists to the appropriate memory cgroup
 and node unevictable list.
 
-rmap's page_referenced_one(), called via vmscan's shrink_active_list() or
+rmap's folio_referenced_one(), called via vmscan's shrink_active_list() or
 shrink_page_list(), and rmap's try_to_unmap_one() called via shrink_page_list(),
 check for (3) pages still mapped into VM_LOCKED VMAs, and call mlock_vma_page()
 to correct them.  Such pages are culled to the unevictable list when released
diff --git a/Documentation/networking/devlink/netdevsim.rst b/Documentation/networking/devlink/netdevsim.rst
index 8a292fb5aaea..ec5e6d79b2e2 100644
--- a/Documentation/networking/devlink/netdevsim.rst
+++ b/Documentation/networking/devlink/netdevsim.rst
@@ -67,7 +67,7 @@ The ``netdevsim`` driver supports rate objects management, which includes:
 - setting tx_share and tx_max rate values for any rate object type;
 - setting parent node for any rate object type.
 
-Rate nodes and it's parameters are exposed in ``netdevsim`` debugfs in RO mode.
+Rate nodes and their parameters are exposed in ``netdevsim`` debugfs in RO mode.
 For example created rate node with name ``some_group``:
 
 .. code:: shell
diff --git a/Documentation/networking/driver.rst b/Documentation/networking/driver.rst
index c8f59dbda46f..64f7236ff10b 100644
--- a/Documentation/networking/driver.rst
+++ b/Documentation/networking/driver.rst
@@ -8,7 +8,7 @@ Transmit path guidelines:
 
 1) The ndo_start_xmit method must not return NETDEV_TX_BUSY under
    any normal circumstances.  It is considered a hard error unless
-   there is no way your device can tell ahead of time when it's
+   there is no way your device can tell ahead of time when its
    transmit function will become busy.
 
    Instead it must maintain the queue properly.  For example,
diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 56cd4ea059b2..a759872a2883 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -1035,7 +1035,10 @@ tcp_limit_output_bytes - INTEGER
 tcp_challenge_ack_limit - INTEGER
 	Limits number of Challenge ACK sent per second, as recommended
 	in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks)
-	Default: 1000
+	Note that this per netns rate limit can allow some side channel
+	attacks and probably should not be enabled.
+	TCP stack implements per TCP socket limits anyway.
+	Default: INT_MAX (unlimited)
 
 UDP variables
 =============
diff --git a/Documentation/networking/ipvlan.rst b/Documentation/networking/ipvlan.rst
index 694adcba36b0..0000c1d383bc 100644
--- a/Documentation/networking/ipvlan.rst
+++ b/Documentation/networking/ipvlan.rst
@@ -11,7 +11,7 @@ Initial Release:
 ================
 This is conceptually very similar to the macvlan driver with one major
 exception of using L3 for mux-ing /demux-ing among slaves. This property makes
-the master device share the L2 with it's slave devices. I have developed this
+the master device share the L2 with its slave devices. I have developed this
 driver in conjunction with network namespaces and not sure if there is use case
 outside of it.
 
diff --git a/Documentation/networking/l2tp.rst b/Documentation/networking/l2tp.rst
index 498b382d25a0..7f383e99dbad 100644
--- a/Documentation/networking/l2tp.rst
+++ b/Documentation/networking/l2tp.rst
@@ -530,7 +530,7 @@ its tunnel close actions. For L2TPIP sockets, the socket's close
 handler initiates the same tunnel close actions. All sessions are
 first closed. Each session drops its tunnel ref. When the tunnel ref
 reaches zero, the tunnel puts its socket ref. When the socket is
-eventually destroyed, it's sk_destruct finally frees the L2TP tunnel
+eventually destroyed, its sk_destruct finally frees the L2TP tunnel
 context.
 
 Sessions
diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index e263dfcc4b40..213510698014 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -47,7 +47,6 @@ allow_join_initial_addr_port - BOOLEAN
 	Default: 1
 
 pm_type - INTEGER
-
 	Set the default path manager type to use for each new MPTCP
 	socket. In-kernel path management will control subflow
 	connections and address advertisements according to
diff --git a/Documentation/networking/nf_conntrack-sysctl.rst b/Documentation/networking/nf_conntrack-sysctl.rst
index 834945ebc4cd..1120d71f28d7 100644
--- a/Documentation/networking/nf_conntrack-sysctl.rst
+++ b/Documentation/networking/nf_conntrack-sysctl.rst
@@ -70,15 +70,6 @@ nf_conntrack_generic_timeout - INTEGER (seconds)
 	Default for generic timeout.  This refers to layer 4 unknown/unsupported
 	protocols.
 
-nf_conntrack_helper - BOOLEAN
-	- 0 - disabled (default)
-	- not 0 - enabled
-
-	Enable automatic conntrack helper assignment.
-	If disabled it is required to set up iptables rules to assign
-	helpers to connections.  See the CT target description in the
-	iptables-extensions(8) man page for further information.
-
 nf_conntrack_icmp_timeout - INTEGER (seconds)
 	default 30
 
diff --git a/Documentation/networking/rxrpc.rst b/Documentation/networking/rxrpc.rst
index 39c2249c7aa7..39494a6ea739 100644
--- a/Documentation/networking/rxrpc.rst
+++ b/Documentation/networking/rxrpc.rst
@@ -1055,17 +1055,6 @@ The kernel interface functions are as follows:
      first function to change.  Note that this must be called in TASK_RUNNING
      state.
 
- (#) Get reply timestamp::
-
-	bool rxrpc_kernel_get_reply_time(struct socket *sock,
-					 struct rxrpc_call *call,
-					 ktime_t *_ts)
-
-     This allows the timestamp on the first DATA packet of the reply of a
-     client call to be queried, provided that it is still in the Rx ring.  If
-     successful, the timestamp will be stored into ``*_ts`` and true will be
-     returned; false will be returned otherwise.
-
  (#) Get remote client epoch::
 
 	u32 rxrpc_kernel_get_epoch(struct socket *sock,
diff --git a/Documentation/networking/switchdev.rst b/Documentation/networking/switchdev.rst
index f1f4e6a85a29..bbf272e9d607 100644
--- a/Documentation/networking/switchdev.rst
+++ b/Documentation/networking/switchdev.rst
@@ -159,7 +159,7 @@ tools such as iproute2.
 
 The switchdev driver can know a particular port's position in the topology by
 monitoring NETDEV_CHANGEUPPER notifications.  For example, a port moved into a
-bond will see it's upper master change.  If that bond is moved into a bridge,
+bond will see its upper master change.  If that bond is moved into a bridge,
 the bond's upper master will change.  And so on.  The driver will track such
 movements to know what position a port is in in the overall topology by
 registering for netdevice events and acting on NETDEV_CHANGEUPPER.
diff --git a/Documentation/process/5.Posting.rst b/Documentation/process/5.Posting.rst
index 906235c11c24..d87f1fee4cbc 100644
--- a/Documentation/process/5.Posting.rst
+++ b/Documentation/process/5.Posting.rst
@@ -256,8 +256,10 @@ The tags in common use are:
  - Cc: the named person received a copy of the patch and had the
    opportunity to comment on it.
 
-Be careful in the addition of tags to your patches: only Cc: is appropriate
-for addition without the explicit permission of the person named.
+Be careful in the addition of tags to your patches, as only Cc: is appropriate
+for addition without the explicit permission of the person named; using
+Reported-by: is fine most of the time as well, but ask for permission if
+the bug was reported in private.
 
 
 Sending the patch
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index 19c286c23786..9a90197989dd 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -31,6 +31,8 @@ you probably needn't concern yourself with pcmciautils.
 ====================== ===============  ========================================
 GNU C                  5.1              gcc --version
 Clang/LLVM (optional)  11.0.0           clang --version
+Rust (optional)        1.62.0           rustc --version
+bindgen (optional)     0.56.0           bindgen --version
 GNU make               3.81             make --version
 bash                   4.2              bash --version
 binutils               2.23             ld -v
@@ -80,6 +82,29 @@ kernels. Older releases aren't guaranteed to work, and we may drop workarounds
 from the kernel that were used to support older versions. Please see additional
 docs on :ref:`Building Linux with Clang/LLVM <kbuild_llvm>`.
 
+Rust (optional)
+---------------
+
+A particular version of the Rust toolchain is required. Newer versions may or
+may not work because the kernel depends on some unstable Rust features, for
+the moment.
+
+Each Rust toolchain comes with several "components", some of which are required
+(like ``rustc``) and some that are optional. The ``rust-src`` component (which
+is optional) needs to be installed to build the kernel. Other components are
+useful for developing.
+
+Please see Documentation/rust/quick-start.rst for instructions on how to
+satisfy the build requirements of Rust support. In particular, the ``Makefile``
+target ``rustavailable`` is useful to check why the Rust toolchain may not
+be detected.
+
+bindgen (optional)
+------------------
+
+``bindgen`` is used to generate the Rust bindings to the C side of the kernel.
+It depends on ``libclang``.
+
 Make
 ----
 
@@ -348,6 +373,12 @@ Sphinx
 Please see :ref:`sphinx_install` in :ref:`Documentation/doc-guide/sphinx.rst <sphinxdoc>`
 for details about Sphinx requirements.
 
+rustdoc
+-------
+
+``rustdoc`` is used to generate the documentation for Rust code. Please see
+Documentation/rust/general-information.rst for more information.
+
 Getting updated software
 ========================
 
@@ -364,6 +395,16 @@ Clang/LLVM
 
 - :ref:`Getting LLVM <getting_llvm>`.
 
+Rust
+----
+
+- Documentation/rust/quick-start.rst.
+
+bindgen
+-------
+
+- Documentation/rust/quick-start.rst.
+
 Make
 ----
 
diff --git a/Documentation/process/code-of-conduct-interpretation.rst b/Documentation/process/code-of-conduct-interpretation.rst
index e899f14a4ba2..922e0b547bc3 100644
--- a/Documentation/process/code-of-conduct-interpretation.rst
+++ b/Documentation/process/code-of-conduct-interpretation.rst
@@ -51,7 +51,7 @@ the Technical Advisory Board (TAB) or other maintainers if you're
 uncertain how to handle situations that come up.  It will not be
 considered a violation report unless you want it to be.  If you are
 uncertain about approaching the TAB or any other maintainers, please
-reach out to our conflict mediator, Mishi Choudhary <mishi@linux.com>.
+reach out to our conflict mediator, Joanna Lee <joanna.lee@gesmer.com>.
 
 In the end, "be kind to each other" is really what the end goal is for
 everybody.  We know everyone is human and we all fail at times, but the
@@ -127,10 +127,12 @@ are listed at https://kernel.org/code-of-conduct.html.  Members can not
 access reports made before they joined or after they have left the
 committee.
 
-The initial Code of Conduct Committee consists of volunteer members of
-the TAB, as well as a professional mediator acting as a neutral third
-party.  The first task of the committee is to establish documented
-processes, which will be made public.
+The Code of Conduct Committee consists of volunteer community members
+appointed by the TAB, as well as a professional mediator acting as a
+neutral third party.  The processes the Code of Conduct committee will
+use to address reports is varied and will depend on the individual
+circumstance, however, this file serves as documentation for the
+general process used.
 
 Any member of the committee, including the mediator, can be contacted
 directly if a reporter does not wish to include the full committee in a
@@ -141,16 +143,16 @@ processes (see above) and consults with the TAB as needed and
 appropriate, for instance to request and receive information about the
 kernel community.
 
-Any decisions by the committee will be brought to the TAB, for
-implementation of enforcement with the relevant maintainers if needed.
-A decision by the Code of Conduct Committee can be overturned by the TAB
-by a two-thirds vote.
+Any decisions regarding enforcement recommendations will be brought to
+the TAB for implementation of enforcement with the relevant maintainers
+if needed.  A decision by the Code of Conduct Committee can be overturned
+by the TAB by a two-thirds vote.
 
 At quarterly intervals, the Code of Conduct Committee and TAB will
 provide a report summarizing the anonymised reports that the Code of
 Conduct committee has received and their status, as well details of any
 overridden decisions including complete and identifiable voting details.
 
-We expect to establish a different process for Code of Conduct Committee
-staffing beyond the bootstrap period.  This document will be updated
-with that information when this occurs.
+Because how we interpret and enforce the Code of Conduct will evolve over
+time, this document will be updated when necessary to reflect any
+changes.
diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst
index 03eb53fd029a..007e49ef6cec 100644
--- a/Documentation/process/coding-style.rst
+++ b/Documentation/process/coding-style.rst
@@ -1186,6 +1186,68 @@ expression used.  For instance:
 	#endif /* CONFIG_SOMETHING */
 
 
+22) Do not crash the kernel
+---------------------------
+
+In general, the decision to crash the kernel belongs to the user, rather
+than to the kernel developer.
+
+Avoid panic()
+*************
+
+panic() should be used with care and primarily only during system boot.
+panic() is, for example, acceptable when running out of memory during boot and
+not being able to continue.
+
+Use WARN() rather than BUG()
+****************************
+
+Do not add new code that uses any of the BUG() variants, such as BUG(),
+BUG_ON(), or VM_BUG_ON(). Instead, use a WARN*() variant, preferably
+WARN_ON_ONCE(), and possibly with recovery code. Recovery code is not
+required if there is no reasonable way to at least partially recover.
+
+"I'm too lazy to do error handling" is not an excuse for using BUG(). Major
+internal corruptions with no way of continuing may still use BUG(), but need
+good justification.
+
+Use WARN_ON_ONCE() rather than WARN() or WARN_ON()
+**************************************************
+
+WARN_ON_ONCE() is generally preferred over WARN() or WARN_ON(), because it
+is common for a given warning condition, if it occurs at all, to occur
+multiple times. This can fill up and wrap the kernel log, and can even slow
+the system enough that the excessive logging turns into its own, additional
+problem.
+
+Do not WARN lightly
+*******************
+
+WARN*() is intended for unexpected, this-should-never-happen situations.
+WARN*() macros are not to be used for anything that is expected to happen
+during normal operation. These are not pre- or post-condition asserts, for
+example. Again: WARN*() must not be used for a condition that is expected
+to trigger easily, for example, by user space actions. pr_warn_once() is a
+possible alternative, if you need to notify the user of a problem.
+
+Do not worry about panic_on_warn users
+**************************************
+
+A few more words about panic_on_warn: Remember that ``panic_on_warn`` is an
+available kernel option, and that many users set this option. This is why
+there is a "Do not WARN lightly" writeup, above. However, the existence of
+panic_on_warn users is not a valid reason to avoid the judicious use
+WARN*(). That is because, whoever enables panic_on_warn has explicitly
+asked the kernel to crash if a WARN*() fires, and such users must be
+prepared to deal with the consequences of a system that is somewhat more
+likely to crash.
+
+Use BUILD_BUG_ON() for compile-time assertions
+**********************************************
+
+The use of BUILD_BUG_ON() is acceptable and encouraged, because it is a
+compile-time assertion that has no effect at runtime.
+
 Appendix I) References
 ----------------------
 
diff --git a/Documentation/process/deprecated.rst b/Documentation/process/deprecated.rst
index a6e36d9c3d14..c8fd53a11a20 100644
--- a/Documentation/process/deprecated.rst
+++ b/Documentation/process/deprecated.rst
@@ -138,17 +138,20 @@ be NUL terminated. This can lead to various linear read overflows and
 other misbehavior due to the missing termination. It also NUL-pads
 the destination buffer if the source contents are shorter than the
 destination buffer size, which may be a needless performance penalty
-for callers using only NUL-terminated strings. The safe replacement is
+for callers using only NUL-terminated strings.
+
+When the destination is required to be NUL-terminated, the replacement is
 strscpy(), though care must be given to any cases where the return value
 of strncpy() was used, since strscpy() does not return a pointer to the
 destination, but rather a count of non-NUL bytes copied (or negative
 errno when it truncates). Any cases still needing NUL-padding should
 instead use strscpy_pad().
 
-If a caller is using non-NUL-terminated strings, strncpy() can
-still be used, but destinations should be marked with the `__nonstring
+If a caller is using non-NUL-terminated strings, strtomem() should be
+used, and the destinations should be marked with the `__nonstring
 <https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html>`_
-attribute to avoid future compiler warnings.
+attribute to avoid future compiler warnings. For cases still needing
+NUL-padding, strtomem_pad() can be used.
 
 strlcpy()
 ---------
diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst
index 2ba2a1582bbe..d4b6217472b0 100644
--- a/Documentation/process/index.rst
+++ b/Documentation/process/index.rst
@@ -5,6 +5,7 @@
 
 .. _process_index:
 
+=============================================
 Working with the kernel development community
 =============================================
 
diff --git a/Documentation/process/maintainer-pgp-guide.rst b/Documentation/process/maintainer-pgp-guide.rst
index 29e7d7b1cd44..40bfbd3b7648 100644
--- a/Documentation/process/maintainer-pgp-guide.rst
+++ b/Documentation/process/maintainer-pgp-guide.rst
@@ -121,57 +121,56 @@ edit your ``~/.gnupg/gpg-agent.conf`` file to set your own values::
     to remove anything you had in place for older versions of GnuPG, as
     it may not be doing the right thing any more.
 
-Set up a refresh cronjob
-~~~~~~~~~~~~~~~~~~~~~~~~
-
-You will need to regularly refresh your keyring in order to get the
-latest changes on other people's public keys, which is best done with a
-daily cronjob::
-
-    @daily /usr/bin/gpg2 --refresh >/dev/null 2>&1
-
-Check the full path to your ``gpg`` or ``gpg2`` command and use the
-``gpg2`` command if regular ``gpg`` for you is the legacy GnuPG v.1.
-
-.. _master_key:
+.. _protect_your_key:
 
-Protect your master PGP key
-===========================
+Protect your PGP key
+====================
 
 This guide assumes that you already have a PGP key that you use for Linux
 kernel development purposes. If you do not yet have one, please see the
 "`Protecting Code Integrity`_" document mentioned earlier for guidance
 on how to create a new one.
 
-You should also make a new key if your current one is weaker than 2048 bits
-(RSA).
-
-Master key vs. Subkeys
-----------------------
-
-Subkeys are fully independent PGP keypairs that are tied to the "master"
-key using certifying key signatures (certificates). It is important to
-understand the following:
-
-1. There are no technical differences between the "master key" and "subkeys."
-2. At creation time, we assign functional limitations to each key by
-   giving it specific capabilities.
-3. A PGP key can have 4 capabilities:
-
-   - **[S]** key can be used for signing
-   - **[E]** key can be used for encryption
-   - **[A]** key can be used for authentication
-   - **[C]** key can be used for certifying other keys
-
-4. A single key may have multiple capabilities.
-5. A subkey is fully independent from the master key. A message
-   encrypted to a subkey cannot be decrypted with the master key. If you
-   lose your private subkey, it cannot be recreated from the master key
-   in any way.
-
-The key carrying the **[C]** (certify) capability is considered the
-"master" key because it is the only key that can be used to indicate
-relationship with other keys. Only the **[C]** key can be used to:
+You should also make a new key if your current one is weaker than 2048
+bits (RSA).
+
+Understanding PGP Subkeys
+-------------------------
+
+A PGP key rarely consists of a single keypair -- usually it is a
+collection of independent subkeys that can be used for different
+purposes based on their capabilities, assigned at their creation time.
+PGP defines four capabilities that a key can have:
+
+- **[S]** keys can be used for signing
+- **[E]** keys can be used for encryption
+- **[A]** keys can be used for authentication
+- **[C]** keys can be used for certifying other keys
+
+The key with the **[C]** capability is often called the "master" key,
+but this terminology is misleading because it implies that the Certify
+key can be used in place of any of other subkey on the same chain (like
+a physical "master key" can be used to open the locks made for other
+keys). Since this is not the case, this guide will refer to it as "the
+Certify key" to avoid any ambiguity.
+
+It is critical to fully understand the following:
+
+1. All subkeys are fully independent from each other. If you lose a
+   private subkey, it cannot be restored or recreated from any other
+   private key on your chain.
+2. With the exception of the Certify key, there can be multiple subkeys
+   with identical capabilities (e.g. you can have 2 valid encryption
+   subkeys, 3 valid signing subkeys, but only one valid certification
+   subkey). All subkeys are fully independent -- a message encrypted to
+   one **[E]** subkey cannot be decrypted with any other **[E]** subkey
+   you may also have.
+3. A single subkey may have multiple capabilities (e.g. your **[C]** key
+   can also be your **[S]** key).
+
+The key carrying the **[C]** (certify) capability is the only key that
+can be used to indicate relationship with other keys. Only the **[C]**
+key can be used to:
 
 - add or revoke other keys (subkeys) with S/E/A capabilities
 - add, change or revoke identities (uids) associated with the key
@@ -180,7 +179,7 @@ relationship with other keys. Only the **[C]** key can be used to:
 
 By default, GnuPG creates the following when generating new keys:
 
-- A master key carrying both Certify and Sign capabilities (**[SC]**)
+- One subkey carrying both Certify and Sign capabilities (**[SC]**)
 - A separate subkey with the Encryption capability (**[E]**)
 
 If you used the default parameters when generating your key, then that
@@ -192,9 +191,6 @@ for example::
     uid           [ultimate] Alice Dev <adev@kernel.org>
     ssb   rsa2048 2018-01-23 [E] [expires: 2020-01-23]
 
-Any key carrying the **[C]** capability is your master key, regardless
-of any other capabilities it may have assigned to it.
-
 The long line under the ``sec`` entry is your key fingerprint --
 whenever you see ``[fpr]`` in the examples below, that 40-character
 string is what it refers to.
@@ -215,37 +211,30 @@ strong passphrase. To set it or change it, use::
 Create a separate Signing subkey
 --------------------------------
 
-Our goal is to protect your master key by moving it to offline media, so
-if you only have a combined **[SC]** key, then you should create a separate
-signing subkey::
+Our goal is to protect your Certify key by moving it to offline media,
+so if you only have a combined **[SC]** key, then you should create a
+separate signing subkey::
 
     $ gpg --quick-addkey [fpr] ed25519 sign
 
-Remember to tell the keyservers about this change, so others can pull down
-your new subkey::
-
-    $ gpg --send-key [fpr]
-
 .. note:: ECC support in GnuPG
 
     GnuPG 2.1 and later has full support for Elliptic Curve
     Cryptography, with ability to combine ECC subkeys with traditional
-    RSA master keys. The main upside of ECC cryptography is that it is
-    much faster computationally and creates much smaller signatures when
+    RSA keys. The main upside of ECC cryptography is that it is much
+    faster computationally and creates much smaller signatures when
     compared byte for byte with 2048+ bit RSA keys. Unless you plan on
     using a smartcard device that does not support ECC operations, we
     recommend that you create an ECC signing subkey for your kernel
     work.
 
-    If for some reason you prefer to stay with RSA subkeys, just replace
-    "ed25519" with "rsa2048" in the above command. Additionally, if you
-    plan to use a hardware device that does not support ED25519 ECC
-    keys, like Nitrokey Pro or a Yubikey, then you should use
-    "nistp256" instead or "ed25519."
+    Note, that if you plan to use a hardware device that does not
+    support ED25519 ECC keys, you should choose "nistp256" instead or
+    "ed25519."
 
 
-Back up your master key for disaster recovery
----------------------------------------------
+Back up your Certify key for disaster recovery
+----------------------------------------------
 
 The more signatures you have on your PGP key from other developers, the
 more reasons you have to create a backup version that lives on something
@@ -277,9 +266,7 @@ home, such as your bank vault.
     Your printer is probably no longer a simple dumb device connected to
     your parallel port, but since the output is still encrypted with
     your passphrase, printing out even to "cloud-integrated" modern
-    printers should remain a relatively safe operation. One option is to
-    change the passphrase on your master key immediately after you are
-    done with paperkey.
+    printers should remain a relatively safe operation.
 
 Back up your whole GnuPG directory
 ----------------------------------
@@ -300,7 +287,7 @@ will use for backup purposes. You will need to encrypt them using LUKS
 -- refer to your distro's documentation on how to accomplish this.
 
 For the encryption passphrase, you can use the same one as on your
-master key.
+PGP key.
 
 Once the encryption process is over, re-insert the USB drive and make
 sure it gets properly mounted. Copy your entire ``.gnupg`` directory
@@ -319,7 +306,7 @@ far away, because you'll need to use it every now and again for things
 like editing identities, adding or revoking subkeys, or signing other
 people's keys.
 
-Remove the master key from  your homedir
+Remove the Certify key from your homedir
 ----------------------------------------
 
 The files in our home directory are not as well protected as we like to
@@ -334,7 +321,7 @@ think.  They can be leaked or stolen via many different means:
 Protecting your key with a good passphrase greatly helps reduce the risk
 of any of the above, but passphrases can be discovered via keyloggers,
 shoulder-surfing, or any number of other means. For this reason, the
-recommended setup is to remove your master key from your home directory
+recommended setup is to remove your Certify key from your home directory
 and store it on offline storage.
 
 .. warning::
@@ -343,7 +330,7 @@ and store it on offline storage.
     your GnuPG directory in its entirety. What we are about to do will
     render your key useless if you do not have a usable backup!
 
-First, identify the keygrip of your master key::
+First, identify the keygrip of your Certify key::
 
     $ gpg --with-keygrip --list-key [fpr]
 
@@ -359,7 +346,7 @@ The output will be something like this::
           Keygrip = 3333000000000000000000000000000000000000
 
 Find the keygrip entry that is beneath the ``pub`` line (right under the
-master key fingerprint). This will correspond directly to a file in your
+Certify key fingerprint). This will correspond directly to a file in your
 ``~/.gnupg`` directory::
 
     $ cd ~/.gnupg/private-keys-v1.d
@@ -369,13 +356,13 @@ master key fingerprint). This will correspond directly to a file in your
     3333000000000000000000000000000000000000.key
 
 All you have to do is simply remove the .key file that corresponds to
-the master keygrip::
+the Certify key keygrip::
 
     $ cd ~/.gnupg/private-keys-v1.d
     $ rm 1111000000000000000000000000000000000000.key
 
 Now, if you issue the ``--list-secret-keys`` command, it will show that
-the master key is missing (the ``#`` indicates it is not available)::
+the Certify key is missing (the ``#`` indicates it is not available)::
 
     $ gpg --list-secret-keys
     sec#  rsa2048 2018-01-24 [SC] [expires: 2020-01-24]
@@ -404,7 +391,7 @@ file, which still contains your private keys.
 Move the subkeys to a dedicated crypto device
 =============================================
 
-Even though the master key is now safe from being leaked or stolen, the
+Even though the Certify key is now safe from being leaked or stolen, the
 subkeys are still in your home directory. Anyone who manages to get
 their hands on those will be able to decrypt your communication or fake
 your signatures (if they know the passphrase). Furthermore, each time a
@@ -447,7 +434,8 @@ functionality. There are several options available:
 - `Yubikey 5`_: proprietary hardware and software, but cheaper than
   Nitrokey Pro and comes available in the USB-C form that is more useful
   with newer laptops. Offers additional security features such as FIDO
-  U2F, among others, and now finally supports ECC keys (NISTP).
+  U2F, among others, and now finally supports NISTP and ED25519 ECC
+  keys.
 
 `LWN has a good review`_ of some of the above models, as well as several
 others. Your choice will depend on cost, shipping availability in your
@@ -460,7 +448,7 @@ geographical region, and open/proprietary hardware considerations.
     Foundation.
 
 .. _`Nitrokey Start`: https://shop.nitrokey.com/shop/product/nitrokey-start-6
-.. _`Nitrokey Pro 2`: https://shop.nitrokey.com/shop/product/nitrokey-pro-2-3
+.. _`Nitrokey Pro 2`: https://shop.nitrokey.com/shop/product/nkpr2-nitrokey-pro-2-3
 .. _`Yubikey 5`: https://www.yubico.com/products/yubikey-5-overview/
 .. _Gnuk: https://www.fsij.org/doc-gnuk/
 .. _`LWN has a good review`: https://lwn.net/Articles/736231/
@@ -627,10 +615,10 @@ Other common GnuPG operations
 Here is a quick reference for some common operations you'll need to do
 with your PGP key.
 
-Mounting your master key offline storage
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Mounting your safe offline storage
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-You will need your master key for any of the operations below, so you
+You will need your Certify key for any of the operations below, so you
 will first need to mount your backup offline storage and tell GnuPG to
 use it::
 
@@ -644,7 +632,7 @@ your regular home directory location).
 Extending key expiration date
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-The master key has the default expiration date of 2 years from the date
+The Certify key has the default expiration date of 2 years from the date
 of creation. This is done both for security reasons and to make obsolete
 keys eventually disappear from keyservers.
 
@@ -685,6 +673,7 @@ remote end.
 
 .. _`Agent Forwarding over SSH`: https://wiki.gnupg.org/AgentForwarding
 
+.. _pgp_with_git:
 
 Using PGP with Git
 ==================
@@ -828,6 +817,63 @@ You can tell git to always sign commits::
 
 .. _verify_identities:
 
+
+How to work with signed patches
+-------------------------------
+
+It is possible to use your PGP key to sign patches sent to kernel
+developer mailing lists. Since existing email signature mechanisms
+(PGP-Mime or PGP-inline) tend to cause problems with regular code
+review tasks, you should use the tool kernel.org created for this
+purpose that puts cryptographic attestation signatures into message
+headers (a-la DKIM):
+
+- `Patatt Patch Attestation`_
+
+.. _`Patatt Patch Attestation`: https://pypi.org/project/patatt/
+
+Installing and configuring patatt
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Patatt is packaged for many distributions already, so please check there
+first. You can also install it from pypi using "``pip install patatt``".
+
+If you already have your PGP key configured with git (via the
+``user.signingKey`` configuration parameter), then patatt requires no
+further configuration. You can start signing your patches by installing
+the git-send-email hook in the repository you want::
+
+    patatt install-hook
+
+Now any patches you send with ``git send-email`` will be automatically
+signed with your cryptographic signature.
+
+Checking patatt signatures
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+If you are using ``b4`` to retrieve and apply patches, then it will
+automatically attempt to verify all DKIM and patatt signatures it
+encounters, for example::
+
+    $ b4 am 20220720205013.890942-1-broonie@kernel.org
+    [...]
+    Checking attestation on all messages, may take a moment...
+    ---
+      ✓ [PATCH v1 1/3] kselftest/arm64: Correct buffer allocation for SVE Z registers
+      ✓ [PATCH v1 2/3] arm64/sve: Document our actual ABI for clearing registers on syscall
+      ✓ [PATCH v1 3/3] kselftest/arm64: Enforce actual ABI for SVE syscalls
+      ---
+      ✓ Signed: openpgp/broonie@kernel.org
+      ✓ Signed: DKIM/kernel.org
+
+.. note::
+
+    Patatt and b4 are still in active development and you should check
+    the latest documentation for these projects for any new or updated
+    features.
+
+.. _kernel_identities:
+
 How to verify kernel developer identities
 =========================================
 
@@ -899,65 +945,17 @@ the new default in GnuPG v2). To set it, add (or modify) the
 
     trust-model tofu+pgp
 
-How to use keyservers (more) safely
------------------------------------
-
-If you get a "No public key" error when trying to validate someone's
-tag, then you should attempt to lookup that key using a keyserver. It is
-important to keep in mind that there is absolutely no guarantee that the
-key you retrieve from PGP keyservers belongs to the actual person --
-that much is by design. You are supposed to use the Web of Trust to
-establish key validity.
-
-How to properly maintain the Web of Trust is beyond the scope of this
-document, simply because doing it properly requires both effort and
-dedication that tends to be beyond the caring threshold of most human
-beings. Here are some shortcuts that will help you reduce the risk of
-importing a malicious key.
-
-First, let's say you've tried to run ``git verify-tag`` but it returned
-an error saying the key is not found::
-
-    $ git verify-tag sunxi-fixes-for-4.15-2
-    gpg: Signature made Sun 07 Jan 2018 10:51:55 PM EST
-    gpg:                using RSA key DA73759BF8619E484E5A3B47389A54219C0F2430
-    gpg:                issuer "wens@...org"
-    gpg: Can't check signature: No public key
-
-Let's query the keyserver for more info about that key fingerprint (the
-fingerprint probably belongs to a subkey, so we can't use it directly
-without finding out the ID of the master key it is associated with)::
-
-    $ gpg --search DA73759BF8619E484E5A3B47389A54219C0F2430
-    gpg: data source: hkp://keys.gnupg.net
-    (1) Chen-Yu Tsai <wens@...org>
-          4096 bit RSA key C94035C21B4F2AEB, created: 2017-03-14, expires: 2019-03-15
-    Keys 1-1 of 1 for "DA73759BF8619E484E5A3B47389A54219C0F2430".  Enter number(s), N)ext, or Q)uit > q
-
-Locate the ID of the master key in the output, in our example
-``C94035C21B4F2AEB``. Now display the key of Linus Torvalds that you
-have on your keyring::
-
-    $ gpg --list-key torvalds@kernel.org
-    pub   rsa2048 2011-09-20 [SC]
-          ABAF11C65A2970B130ABE3C479BE3E4300411886
-    uid           [ unknown] Linus Torvalds <torvalds@kernel.org>
-    sub   rsa2048 2011-09-20 [E]
-
-Next, find a trust path from Linus Torvalds to the key-id you found via ``gpg
---search`` of the unknown key.  For this, you can use several tools including
-https://github.com/mricon/wotmate,
-https://git.kernel.org/pub/scm/docs/kernel/pgpkeys.git/tree/graphs, and
-https://the.earth.li/~noodles/pathfind.html.
-
-If you get a few decent trust paths, then it's a pretty good indication
-that it is a valid key. You can add it to your keyring from the
-keyserver now::
-
-    $ gpg --recv-key C94035C21B4F2AEB
-
-This process is not perfect, and you are obviously trusting the
-administrators of the PGP Pathfinder service to not be malicious (in
-fact, this goes against :ref:`devs_not_infra`). However, if you
-do not carefully maintain your own web of trust, then it is a marked
-improvement over blindly trusting keyservers.
+Using the kernel.org web of trust repository
+--------------------------------------------
+
+Kernel.org maintains a git repository with developers' public keys as a
+replacement for replicating keyserver networks that have gone mostly
+dark in the past few years. The full documentation for how to set up
+that repository as your source of public keys can be found here:
+
+- `Kernel developer PGP Keyring`_
+
+If you are a kernel developer, please consider submitting your key for
+inclusion into that keyring.
+
+.. _`Kernel developer PGP Keyring`: https://korg.docs.kernel.org/pgpkeys.html
diff --git a/Documentation/process/stable-kernel-rules.rst b/Documentation/process/stable-kernel-rules.rst
index c61865e91f52..2fd8aa593a28 100644
--- a/Documentation/process/stable-kernel-rules.rst
+++ b/Documentation/process/stable-kernel-rules.rst
@@ -97,6 +97,12 @@ text, like this:
 
     commit <sha1> upstream.
 
+or alternatively:
+
+.. code-block:: none
+
+    [ Upstream commit <sha1> ]
+
 Additionally, some patches submitted via :ref:`option_1` may have additional
 patch prerequisites which can be cherry-picked. This can be specified in the
 following format in the sign-off area:
diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst
index be49d8f2601b..7dc94555417d 100644
--- a/Documentation/process/submitting-patches.rst
+++ b/Documentation/process/submitting-patches.rst
@@ -715,8 +715,8 @@ references.
 
 .. _backtraces:
 
-Backtraces in commit mesages
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+Backtraces in commit messages
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 Backtraces help document the call chain leading to a problem. However,
 not all backtraces are helpful. For example, early boot call chains are
diff --git a/Documentation/rust/arch-support.rst b/Documentation/rust/arch-support.rst
new file mode 100644
index 000000000000..6982b63775da
--- /dev/null
+++ b/Documentation/rust/arch-support.rst
@@ -0,0 +1,19 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Arch Support
+============
+
+Currently, the Rust compiler (``rustc``) uses LLVM for code generation,
+which limits the supported architectures that can be targeted. In addition,
+support for building the kernel with LLVM/Clang varies (please see
+Documentation/kbuild/llvm.rst). This support is needed for ``bindgen``
+which uses ``libclang``.
+
+Below is a general summary of architectures that currently work. Level of
+support corresponds to ``S`` values in the ``MAINTAINERS`` file.
+
+============  ================  ==============================================
+Architecture  Level of support  Constraints
+============  ================  ==============================================
+``x86``       Maintained        ``x86_64`` only.
+============  ================  ==============================================
diff --git a/Documentation/rust/coding-guidelines.rst b/Documentation/rust/coding-guidelines.rst
new file mode 100644
index 000000000000..aa8ed082613e
--- /dev/null
+++ b/Documentation/rust/coding-guidelines.rst
@@ -0,0 +1,216 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Coding Guidelines
+=================
+
+This document describes how to write Rust code in the kernel.
+
+
+Style & formatting
+------------------
+
+The code should be formatted using ``rustfmt``. In this way, a person
+contributing from time to time to the kernel does not need to learn and
+remember one more style guide. More importantly, reviewers and maintainers
+do not need to spend time pointing out style issues anymore, and thus
+less patch roundtrips may be needed to land a change.
+
+.. note:: Conventions on comments and documentation are not checked by
+  ``rustfmt``. Thus those are still needed to be taken care of.
+
+The default settings of ``rustfmt`` are used. This means the idiomatic Rust
+style is followed. For instance, 4 spaces are used for indentation rather
+than tabs.
+
+It is convenient to instruct editors/IDEs to format while typing,
+when saving or at commit time. However, if for some reason reformatting
+the entire kernel Rust sources is needed at some point, the following can be
+run::
+
+	make LLVM=1 rustfmt
+
+It is also possible to check if everything is formatted (printing a diff
+otherwise), for instance for a CI, with::
+
+	make LLVM=1 rustfmtcheck
+
+Like ``clang-format`` for the rest of the kernel, ``rustfmt`` works on
+individual files, and does not require a kernel configuration. Sometimes it may
+even work with broken code.
+
+
+Comments
+--------
+
+"Normal" comments (i.e. ``//``, rather than code documentation which starts
+with ``///`` or ``//!``) are written in Markdown the same way as documentation
+comments are, even though they will not be rendered. This improves consistency,
+simplifies the rules and allows to move content between the two kinds of
+comments more easily. For instance:
+
+.. code-block:: rust
+
+	// `object` is ready to be handled now.
+	f(object);
+
+Furthermore, just like documentation, comments are capitalized at the beginning
+of a sentence and ended with a period (even if it is a single sentence). This
+includes ``// SAFETY:``, ``// TODO:`` and other "tagged" comments, e.g.:
+
+.. code-block:: rust
+
+	// FIXME: The error should be handled properly.
+
+Comments should not be used for documentation purposes: comments are intended
+for implementation details, not users. This distinction is useful even if the
+reader of the source file is both an implementor and a user of an API. In fact,
+sometimes it is useful to use both comments and documentation at the same time.
+For instance, for a ``TODO`` list or to comment on the documentation itself.
+For the latter case, comments can be inserted in the middle; that is, closer to
+the line of documentation to be commented. For any other case, comments are
+written after the documentation, e.g.:
+
+.. code-block:: rust
+
+	/// Returns a new [`Foo`].
+	///
+	/// # Examples
+	///
+	// TODO: Find a better example.
+	/// ```
+	/// let foo = f(42);
+	/// ```
+	// FIXME: Use fallible approach.
+	pub fn f(x: i32) -> Foo {
+	    // ...
+	}
+
+One special kind of comments are the ``// SAFETY:`` comments. These must appear
+before every ``unsafe`` block, and they explain why the code inside the block is
+correct/sound, i.e. why it cannot trigger undefined behavior in any case, e.g.:
+
+.. code-block:: rust
+
+	// SAFETY: `p` is valid by the safety requirements.
+	unsafe { *p = 0; }
+
+``// SAFETY:`` comments are not to be confused with the ``# Safety`` sections
+in code documentation. ``# Safety`` sections specify the contract that callers
+(for functions) or implementors (for traits) need to abide by. ``// SAFETY:``
+comments show why a call (for functions) or implementation (for traits) actually
+respects the preconditions stated in a ``# Safety`` section or the language
+reference.
+
+
+Code documentation
+------------------
+
+Rust kernel code is not documented like C kernel code (i.e. via kernel-doc).
+Instead, the usual system for documenting Rust code is used: the ``rustdoc``
+tool, which uses Markdown (a lightweight markup language).
+
+To learn Markdown, there are many guides available out there. For instance,
+the one at:
+
+	https://commonmark.org/help/
+
+This is how a well-documented Rust function may look like:
+
+.. code-block:: rust
+
+	/// Returns the contained [`Some`] value, consuming the `self` value,
+	/// without checking that the value is not [`None`].
+	///
+	/// # Safety
+	///
+	/// Calling this method on [`None`] is *[undefined behavior]*.
+	///
+	/// [undefined behavior]: https://doc.rust-lang.org/reference/behavior-considered-undefined.html
+	///
+	/// # Examples
+	///
+	/// ```
+	/// let x = Some("air");
+	/// assert_eq!(unsafe { x.unwrap_unchecked() }, "air");
+	/// ```
+	pub unsafe fn unwrap_unchecked(self) -> T {
+	    match self {
+	        Some(val) => val,
+
+	        // SAFETY: The safety contract must be upheld by the caller.
+	        None => unsafe { hint::unreachable_unchecked() },
+	    }
+	}
+
+This example showcases a few ``rustdoc`` features and some conventions followed
+in the kernel:
+
+  - The first paragraph must be a single sentence briefly describing what
+    the documented item does. Further explanations must go in extra paragraphs.
+
+  - Unsafe functions must document their safety preconditions under
+    a ``# Safety`` section.
+
+  - While not shown here, if a function may panic, the conditions under which
+    that happens must be described under a ``# Panics`` section.
+
+    Please note that panicking should be very rare and used only with a good
+    reason. In almost all cases, a fallible approach should be used, typically
+    returning a ``Result``.
+
+  - If providing examples of usage would help readers, they must be written in
+    a section called ``# Examples``.
+
+  - Rust items (functions, types, constants...) must be linked appropriately
+    (``rustdoc`` will create a link automatically).
+
+  - Any ``unsafe`` block must be preceded by a ``// SAFETY:`` comment
+    describing why the code inside is sound.
+
+    While sometimes the reason might look trivial and therefore unneeded,
+    writing these comments is not just a good way of documenting what has been
+    taken into account, but most importantly, it provides a way to know that
+    there are no *extra* implicit constraints.
+
+To learn more about how to write documentation for Rust and extra features,
+please take a look at the ``rustdoc`` book at:
+
+	https://doc.rust-lang.org/rustdoc/how-to-write-documentation.html
+
+
+Naming
+------
+
+Rust kernel code follows the usual Rust naming conventions:
+
+	https://rust-lang.github.io/api-guidelines/naming.html
+
+When existing C concepts (e.g. macros, functions, objects...) are wrapped into
+a Rust abstraction, a name as close as reasonably possible to the C side should
+be used in order to avoid confusion and to improve readability when switching
+back and forth between the C and Rust sides. For instance, macros such as
+``pr_info`` from C are named the same in the Rust side.
+
+Having said that, casing should be adjusted to follow the Rust naming
+conventions, and namespacing introduced by modules and types should not be
+repeated in the item names. For instance, when wrapping constants like:
+
+.. code-block:: c
+
+	#define GPIO_LINE_DIRECTION_IN	0
+	#define GPIO_LINE_DIRECTION_OUT	1
+
+The equivalent in Rust may look like (ignoring documentation):
+
+.. code-block:: rust
+
+	pub mod gpio {
+	    pub enum LineDirection {
+	        In = bindings::GPIO_LINE_DIRECTION_IN as _,
+	        Out = bindings::GPIO_LINE_DIRECTION_OUT as _,
+	    }
+	}
+
+That is, the equivalent of ``GPIO_LINE_DIRECTION_IN`` would be referred to as
+``gpio::LineDirection::In``. In particular, it should not be named
+``gpio::gpio_line_direction::GPIO_LINE_DIRECTION_IN``.
diff --git a/Documentation/rust/general-information.rst b/Documentation/rust/general-information.rst
new file mode 100644
index 000000000000..49029ee82e55
--- /dev/null
+++ b/Documentation/rust/general-information.rst
@@ -0,0 +1,79 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+General Information
+===================
+
+This document contains useful information to know when working with
+the Rust support in the kernel.
+
+
+Code documentation
+------------------
+
+Rust kernel code is documented using ``rustdoc``, its built-in documentation
+generator.
+
+The generated HTML docs include integrated search, linked items (e.g. types,
+functions, constants), source code, etc. They may be read at (TODO: link when
+in mainline and generated alongside the rest of the documentation):
+
+	http://kernel.org/
+
+The docs can also be easily generated and read locally. This is quite fast
+(same order as compiling the code itself) and no special tools or environment
+are needed. This has the added advantage that they will be tailored to
+the particular kernel configuration used. To generate them, use the ``rustdoc``
+target with the same invocation used for compilation, e.g.::
+
+	make LLVM=1 rustdoc
+
+To read the docs locally in your web browser, run e.g.::
+
+	xdg-open rust/doc/kernel/index.html
+
+To learn about how to write the documentation, please see coding-guidelines.rst.
+
+
+Extra lints
+-----------
+
+While ``rustc`` is a very helpful compiler, some extra lints and analyses are
+available via ``clippy``, a Rust linter. To enable it, pass ``CLIPPY=1`` to
+the same invocation used for compilation, e.g.::
+
+	make LLVM=1 CLIPPY=1
+
+Please note that Clippy may change code generation, thus it should not be
+enabled while building a production kernel.
+
+
+Abstractions vs. bindings
+-------------------------
+
+Abstractions are Rust code wrapping kernel functionality from the C side.
+
+In order to use functions and types from the C side, bindings are created.
+Bindings are the declarations for Rust of those functions and types from
+the C side.
+
+For instance, one may write a ``Mutex`` abstraction in Rust which wraps
+a ``struct mutex`` from the C side and calls its functions through the bindings.
+
+Abstractions are not available for all the kernel internal APIs and concepts,
+but it is intended that coverage is expanded as time goes on. "Leaf" modules
+(e.g. drivers) should not use the C bindings directly. Instead, subsystems
+should provide as-safe-as-possible abstractions as needed.
+
+
+Conditional compilation
+-----------------------
+
+Rust code has access to conditional compilation based on the kernel
+configuration:
+
+.. code-block:: rust
+
+	#[cfg(CONFIG_X)]       // Enabled               (`y` or `m`)
+	#[cfg(CONFIG_X="y")]   // Enabled as a built-in (`y`)
+	#[cfg(CONFIG_X="m")]   // Enabled as a module   (`m`)
+	#[cfg(not(CONFIG_X))]  // Disabled
diff --git a/Documentation/rust/index.rst b/Documentation/rust/index.rst
new file mode 100644
index 000000000000..4ae8c66b94fa
--- /dev/null
+++ b/Documentation/rust/index.rst
@@ -0,0 +1,22 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Rust
+====
+
+Documentation related to Rust within the kernel. To start using Rust
+in the kernel, please read the quick-start.rst guide.
+
+.. toctree::
+    :maxdepth: 1
+
+    quick-start
+    general-information
+    coding-guidelines
+    arch-support
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`
diff --git a/Documentation/rust/quick-start.rst b/Documentation/rust/quick-start.rst
new file mode 100644
index 000000000000..13b7744b1e27
--- /dev/null
+++ b/Documentation/rust/quick-start.rst
@@ -0,0 +1,232 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Quick Start
+===========
+
+This document describes how to get started with kernel development in Rust.
+
+
+Requirements: Building
+----------------------
+
+This section explains how to fetch the tools needed for building.
+
+Some of these requirements might be available from Linux distributions
+under names like ``rustc``, ``rust-src``, ``rust-bindgen``, etc. However,
+at the time of writing, they are likely not to be recent enough unless
+the distribution tracks the latest releases.
+
+To easily check whether the requirements are met, the following target
+can be used::
+
+	make LLVM=1 rustavailable
+
+This triggers the same logic used by Kconfig to determine whether
+``RUST_IS_AVAILABLE`` should be enabled; but it also explains why not
+if that is the case.
+
+
+rustc
+*****
+
+A particular version of the Rust compiler is required. Newer versions may or
+may not work because, for the moment, the kernel depends on some unstable
+Rust features.
+
+If ``rustup`` is being used, enter the checked out source code directory
+and run::
+
+	rustup override set $(scripts/min-tool-version.sh rustc)
+
+Otherwise, fetch a standalone installer or install ``rustup`` from:
+
+	https://www.rust-lang.org
+
+
+Rust standard library source
+****************************
+
+The Rust standard library source is required because the build system will
+cross-compile ``core`` and ``alloc``.
+
+If ``rustup`` is being used, run::
+
+	rustup component add rust-src
+
+The components are installed per toolchain, thus upgrading the Rust compiler
+version later on requires re-adding the component.
+
+Otherwise, if a standalone installer is used, the Rust repository may be cloned
+into the installation folder of the toolchain::
+
+	git clone --recurse-submodules \
+		--branch $(scripts/min-tool-version.sh rustc) \
+		https://github.com/rust-lang/rust \
+		$(rustc --print sysroot)/lib/rustlib/src/rust
+
+In this case, upgrading the Rust compiler version later on requires manually
+updating this clone.
+
+
+libclang
+********
+
+``libclang`` (part of LLVM) is used by ``bindgen`` to understand the C code
+in the kernel, which means LLVM needs to be installed; like when the kernel
+is compiled with ``CC=clang`` or ``LLVM=1``.
+
+Linux distributions are likely to have a suitable one available, so it is
+best to check that first.
+
+There are also some binaries for several systems and architectures uploaded at:
+
+	https://releases.llvm.org/download.html
+
+Otherwise, building LLVM takes quite a while, but it is not a complex process:
+
+	https://llvm.org/docs/GettingStarted.html#getting-the-source-code-and-building-llvm
+
+Please see Documentation/kbuild/llvm.rst for more information and further ways
+to fetch pre-built releases and distribution packages.
+
+
+bindgen
+*******
+
+The bindings to the C side of the kernel are generated at build time using
+the ``bindgen`` tool. A particular version is required.
+
+Install it via (note that this will download and build the tool from source)::
+
+	cargo install --locked --version $(scripts/min-tool-version.sh bindgen) bindgen
+
+
+Requirements: Developing
+------------------------
+
+This section explains how to fetch the tools needed for developing. That is,
+they are not needed when just building the kernel.
+
+
+rustfmt
+*******
+
+The ``rustfmt`` tool is used to automatically format all the Rust kernel code,
+including the generated C bindings (for details, please see
+coding-guidelines.rst).
+
+If ``rustup`` is being used, its ``default`` profile already installs the tool,
+thus nothing needs to be done. If another profile is being used, the component
+can be installed manually::
+
+	rustup component add rustfmt
+
+The standalone installers also come with ``rustfmt``.
+
+
+clippy
+******
+
+``clippy`` is a Rust linter. Running it provides extra warnings for Rust code.
+It can be run by passing ``CLIPPY=1`` to ``make`` (for details, please see
+general-information.rst).
+
+If ``rustup`` is being used, its ``default`` profile already installs the tool,
+thus nothing needs to be done. If another profile is being used, the component
+can be installed manually::
+
+	rustup component add clippy
+
+The standalone installers also come with ``clippy``.
+
+
+cargo
+*****
+
+``cargo`` is the Rust native build system. It is currently required to run
+the tests since it is used to build a custom standard library that contains
+the facilities provided by the custom ``alloc`` in the kernel. The tests can
+be run using the ``rusttest`` Make target.
+
+If ``rustup`` is being used, all the profiles already install the tool,
+thus nothing needs to be done.
+
+The standalone installers also come with ``cargo``.
+
+
+rustdoc
+*******
+
+``rustdoc`` is the documentation tool for Rust. It generates pretty HTML
+documentation for Rust code (for details, please see
+general-information.rst).
+
+``rustdoc`` is also used to test the examples provided in documented Rust code
+(called doctests or documentation tests). The ``rusttest`` Make target uses
+this feature.
+
+If ``rustup`` is being used, all the profiles already install the tool,
+thus nothing needs to be done.
+
+The standalone installers also come with ``rustdoc``.
+
+
+rust-analyzer
+*************
+
+The `rust-analyzer <https://rust-analyzer.github.io/>`_ language server can
+be used with many editors to enable syntax highlighting, completion, go to
+definition, and other features.
+
+``rust-analyzer`` needs a configuration file, ``rust-project.json``, which
+can be generated by the ``rust-analyzer`` Make target.
+
+
+Configuration
+-------------
+
+``Rust support`` (``CONFIG_RUST``) needs to be enabled in the ``General setup``
+menu. The option is only shown if a suitable Rust toolchain is found (see
+above), as long as the other requirements are met. In turn, this will make
+visible the rest of options that depend on Rust.
+
+Afterwards, go to::
+
+	Kernel hacking
+	    -> Sample kernel code
+	        -> Rust samples
+
+And enable some sample modules either as built-in or as loadable.
+
+
+Building
+--------
+
+Building a kernel with a complete LLVM toolchain is the best supported setup
+at the moment. That is::
+
+	make LLVM=1
+
+For architectures that do not support a full LLVM toolchain, use::
+
+	make CC=clang
+
+Using GCC also works for some configurations, but it is very experimental at
+the moment.
+
+
+Hacking
+-------
+
+To dive deeper, take a look at the source code of the samples
+at ``samples/rust/``, the Rust support code under ``rust/`` and
+the ``Rust hacking`` menu under ``Kernel hacking``.
+
+If GDB/Binutils is used and Rust symbols are not getting demangled, the reason
+is the toolchain does not support Rust's new v0 mangling scheme yet.
+There are a few ways out:
+
+  - Install a newer release (GDB >= 10.2, Binutils >= 2.36).
+
+  - Some versions of GDB (e.g. vanilla GDB 10.1) are able to use
+    the pre-demangled names embedded in the debug info (``CONFIG_DEBUG_INFO``).
diff --git a/Documentation/scheduler/sched-design-CFS.rst b/Documentation/scheduler/sched-design-CFS.rst
index 59b2d1fb4dc4..03db55504515 100644
--- a/Documentation/scheduler/sched-design-CFS.rst
+++ b/Documentation/scheduler/sched-design-CFS.rst
@@ -94,7 +94,7 @@ other HZ detail.  Thus the CFS scheduler has no notion of "timeslices" in the
 way the previous scheduler had, and has no heuristics whatsoever.  There is
 only one central tunable (you have to switch on CONFIG_SCHED_DEBUG):
 
-   /proc/sys/kernel/sched_min_granularity_ns
+   /sys/kernel/debug/sched/min_granularity_ns
 
 which can be used to tune the scheduler from "desktop" (i.e., low latencies) to
 "server" (i.e., good batching) workloads.  It defaults to a setting suitable
diff --git a/Documentation/sphinx/kerneldoc-preamble.sty b/Documentation/sphinx/kerneldoc-preamble.sty
index 2a29cbe51396..9707e033c8c4 100644
--- a/Documentation/sphinx/kerneldoc-preamble.sty
+++ b/Documentation/sphinx/kerneldoc-preamble.sty
@@ -70,8 +70,16 @@
 
 % Translations have Asian (CJK) characters which are only displayed if
 % xeCJK is used
+\usepackage{ifthen}
+\newboolean{enablecjk}
+\setboolean{enablecjk}{false}
 \IfFontExistsTF{Noto Sans CJK SC}{
-    % Load xeCJK when CJK font is available
+    \IfFileExists{xeCJK.sty}{
+	\setboolean{enablecjk}{true}
+    }{}
+}{}
+\ifthenelse{\boolean{enablecjk}}{
+    % Load xeCJK when both the Noto Sans CJK font and xeCJK.sty are available.
     \usepackage{xeCJK}
     % Noto CJK fonts don't provide slant shape. [AutoFakeSlant] permits
     % its emulation.
@@ -196,7 +204,7 @@
     % Inactivate CJK after tableofcontents
     \apptocmd{\sphinxtableofcontents}{\kerneldocCJKoff}{}{}
     \xeCJKsetup{CJKspace = true}% For inter-phrase space of Korean TOC
-}{ % No CJK font found
+}{ % Don't enable CJK
     % Custom macros to on/off CJK and switch CJK fonts (Dummy)
     \newcommand{\kerneldocCJKon}{}
     \newcommand{\kerneldocCJKoff}{}
@@ -204,14 +212,16 @@
     %% and ignore the argument (#1) in their definitions, whole contents of
     %% CJK chapters can be ignored.
     \newcommand{\kerneldocBeginSC}[1]{%
-	%% Put a note on missing CJK fonts in place of zh_CN translation.
-	\begin{sphinxadmonition}{note}{Note on missing fonts:}
+	%% Put a note on missing CJK fonts or the xecjk package in place of
+	%% zh_CN translation.
+	\begin{sphinxadmonition}{note}{Note on missing fonts and a package:}
 	    Translations of Simplified Chinese (zh\_CN), Traditional Chinese
 	    (zh\_TW), Korean (ko\_KR), and Japanese (ja\_JP) were skipped
-	    due to the lack of suitable font families.
+	    due to the lack of suitable font families and/or the texlive-xecjk
+	    package.
 
 	    If you want them, please install ``Noto Sans CJK'' font families
-	    by following instructions from
+	    along with the texlive-xecjk package by following instructions from
 	    \sphinxcode{./scripts/sphinx-pre-install}.
 	    Having optional ``Noto Serif CJK'' font families will improve
 	    the looks of those translations.
diff --git a/Documentation/staging/index.rst b/Documentation/staging/index.rst
index abd0d18254d2..ded8254bc0d7 100644
--- a/Documentation/staging/index.rst
+++ b/Documentation/staging/index.rst
@@ -14,45 +14,3 @@ Unsorted Documentation
    static-keys
    tee
    xz
-
-Atomic Types
-============
-
-.. raw:: latex
-
-    \footnotesize
-
-.. include:: ../atomic_t.txt
-   :literal:
-
-.. raw:: latex
-
-    \normalsize
-
-Atomic bitops
-=============
-
-.. raw:: latex
-
-    \footnotesize
-
-.. include:: ../atomic_bitops.txt
-   :literal:
-
-.. raw:: latex
-
-    \normalsize
-
-Memory Barriers
-===============
-
-.. raw:: latex
-
-    \footnotesize
-
-.. include:: ../memory-barriers.txt
-   :literal:
-
-.. raw:: latex
-
-    \normalsize
diff --git a/Documentation/subsystem-apis.rst b/Documentation/subsystem-apis.rst
new file mode 100644
index 000000000000..af65004a80aa
--- /dev/null
+++ b/Documentation/subsystem-apis.rst
@@ -0,0 +1,58 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============================
+Kernel subsystem documentation
+==============================
+
+These books get into the details of how specific kernel subsystems work
+from the point of view of a kernel developer.  Much of the information here
+is taken directly from the kernel source, with supplemental material added
+as needed (or at least as we managed to add it — probably *not* all that is
+needed).
+
+**Fixme**: much more organizational work is needed here.
+
+.. toctree::
+   :maxdepth: 1
+
+   driver-api/index
+   core-api/index
+   locking/index
+   accounting/index
+   block/index
+   cdrom/index
+   cpu-freq/index
+   fb/index
+   fpga/index
+   hid/index
+   i2c/index
+   iio/index
+   isdn/index
+   infiniband/index
+   leds/index
+   netlabel/index
+   networking/index
+   pcmcia/index
+   power/index
+   target/index
+   timers/index
+   spi/index
+   w1/index
+   watchdog/index
+   virt/index
+   input/index
+   hwmon/index
+   gpu/index
+   security/index
+   sound/index
+   crypto/index
+   filesystems/index
+   mm/index
+   bpf/index
+   usb/index
+   PCI/index
+   scsi/index
+   misc-devices/index
+   scheduler/index
+   mhi/index
+   peci/index
diff --git a/Documentation/tools/rtla/rtla-timerlat-hist.rst b/Documentation/tools/rtla/rtla-timerlat-hist.rst
index e12eae1f3301..6bf7f0ca4556 100644
--- a/Documentation/tools/rtla/rtla-timerlat-hist.rst
+++ b/Documentation/tools/rtla/rtla-timerlat-hist.rst
@@ -33,7 +33,7 @@ EXAMPLE
 =======
 In the example below, **rtla timerlat hist** is set to run for *10* minutes,
 in the cpus *0-4*, *skipping zero* only lines. Moreover, **rtla timerlat
-hist** will change the priority of the *timelat* threads to run under
+hist** will change the priority of the *timerlat* threads to run under
 *SCHED_DEADLINE* priority, with a *10us* runtime every *1ms* period. The
 *1ms* period is also passed to the *timerlat* tracer::
 
diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst
index 859fd1b76c63..c1b685a38f6b 100644
--- a/Documentation/trace/histogram.rst
+++ b/Documentation/trace/histogram.rst
@@ -412,7 +412,7 @@ Extended error information
   Because the default sort key above is 'hitcount', the above shows a
   the list of call_sites by increasing hitcount, so that at the bottom
   we see the functions that made the most kmalloc calls during the
-  run.  If instead we we wanted to see the top kmalloc callers in
+  run.  If instead we wanted to see the top kmalloc callers in
   terms of the number of bytes requested rather than the number of
   calls, and we wanted the top caller to appear at the top, we can use
   the 'sort' parameter, along with the 'descending' modifier::
diff --git a/Documentation/trace/kprobes.rst b/Documentation/trace/kprobes.rst
index f318bceda1e6..48cf778a2468 100644
--- a/Documentation/trace/kprobes.rst
+++ b/Documentation/trace/kprobes.rst
@@ -328,8 +328,8 @@ Configuring Kprobes
 ===================
 
 When configuring the kernel using make menuconfig/xconfig/oldconfig,
-ensure that CONFIG_KPROBES is set to "y". Under "General setup", look
-for "Kprobes".
+ensure that CONFIG_KPROBES is set to "y", look for "Kprobes" under
+"General architecture-dependent options".
 
 So that you can load and unload Kprobes-based instrumentation modules,
 make sure "Loadable module support" (CONFIG_MODULES) and "Module
diff --git a/Documentation/trace/timerlat-tracer.rst b/Documentation/trace/timerlat-tracer.rst
index d643c95c01eb..db17df312bc8 100644
--- a/Documentation/trace/timerlat-tracer.rst
+++ b/Documentation/trace/timerlat-tracer.rst
@@ -20,7 +20,7 @@ For example::
         [root@f32 ~]# cd /sys/kernel/tracing/
         [root@f32 tracing]# echo timerlat > current_tracer
 
-It is possible to follow the trace by reading the trace trace file::
+It is possible to follow the trace by reading the trace file::
 
   [root@f32 tracing]# cat trace
   # tracer: timerlat
diff --git a/Documentation/translations/ja_JP/SubmittingPatches b/Documentation/translations/ja_JP/SubmittingPatches
index 66ce0d8b0526..04deb77b20c6 100644
--- a/Documentation/translations/ja_JP/SubmittingPatches
+++ b/Documentation/translations/ja_JP/SubmittingPatches
@@ -35,8 +35,7 @@ Linux カーãƒ�ルã�«å¤‰æ›´ã‚’加ã�ˆã�Ÿã�„ã�¨æ€�ã�£ã�¦ã�„る個人å�ˆã�¯ä¼šç¤¾ã�
 �もら�や���る�案を集��も���。
 
 コードを投稿�る���Documentation/process/submit-checklist.rst �項目リスト�目
-を通���ェック������。も�����ドライ�ーを投稿�よ���
-��る�ら�Documentation/process/submitting-drivers.rst �も目を通������。
+を通���ェック������。
 
 --------------------------------------------
 セクション1 パッ��作り方��り方
diff --git a/Documentation/translations/zh_CN/IRQ.txt b/Documentation/translations/zh_CN/IRQ.txt
deleted file mode 100644
index 9aec8dca4fcf..000000000000
--- a/Documentation/translations/zh_CN/IRQ.txt
+++ /dev/null
@@ -1,39 +0,0 @@
-Chinese translated version of Documentation/core-api/irq/index.rst
-
-If you have any comment or update to the content, please contact the
-original document maintainer directly.  However, if you have a problem
-communicating in English you can also ask the Chinese maintainer for
-help.  Contact the Chinese maintainer if this translation is outdated
-or if there is a problem with the translation.
-
-Maintainer: Eric W. Biederman <ebiederman@xmission.com>
-Chinese maintainer: Fu Wei <tekkamanninja@gmail.com>
----------------------------------------------------------------------
-Documentation/core-api/irq/index.rst 的中文翻译
-
-如果想评论或更新本文的内容，请直接�系原文档的维护者。如果你使用英文
-交�有困难的�，也�以�中文版维护者求助。如果本翻译更新��时或者翻
-译存在问题，请�系中文版维护者。
-英文版维护者： Eric W. Biederman <ebiederman@xmission.com>
-中文版维护者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
-中文版翻译者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
-中文版校译者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
-
-
-以下为正文
----------------------------------------------------------------------
-何为 IRQ?
-
-一个 IRQ 是�自�个设备的一个中断请求。目�，它们�以�自一个硬件引脚，
-或�自一个数�包。多个设备�能连接到�个硬件引脚，从而共享一个 IRQ。
-
-一个 IRQ 编�是用于告知硬件中断�的内核标识。通常情况下，这是一个
-全局 irq_desc 数组的索引，但是除了在 linux/interrupt.h 中的实现，
-具体的细节是体系结构特定的。
-
-一个 IRQ 编�是设备上�个�能的中断�的枚举。通常情况下，枚举的编�是
-该引脚在系统内中断控制器的所有输入引脚中的编�。对于 ISA 总线中的情况，
-枚举的是在两个 i8259 中断控制器中 16 个输入引脚。
-
-架构�以对 IRQ 编�指定�外的�义，在硬件涉�任何手工�置的情况下，
-是被�倡的。ISA 的 IRQ 是一个分�这类�外�义的典型例�。
diff --git a/Documentation/translations/zh_CN/PCI/acpi-info.rst b/Documentation/translations/zh_CN/PCI/acpi-info.rst
new file mode 100644
index 000000000000..a35f39dcd858
--- /dev/null
+++ b/Documentation/translations/zh_CN/PCI/acpi-info.rst
@@ -0,0 +1,139 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: Documentation/PCI/acpi-info.rst
+
+:翻译:
+
+ �延腾 Yanteng Si <siyanteng@loongson.cn>
+
+:校译:
+
+
+=====================
+PCI主桥的ACPI注�事项
+=====================
+
+一般的规则是，ACPI命�空间应该�述�作系统�能使用的所有东西，除�有其他方法让�作系
+统找到它[1, 2]。
+
+例如，没有标准的硬件机制�枚举PCI主桥，所以ACPI命�空间必须�述�个主桥�访问它
+下�的PCI�置空间的方法�主桥转�到PCI的地�空间窗�（使用_CRS）以�传统的INTx
+中断的路由（使用_PRT）。
+
+在主桥下�的PCI设备，通常�需�通过ACPI�述。�作系统�以通过标准的PCI枚举机制�
+�现它们，使用�置访问��现和识别设备，并读�和测�它们的BAR。然而，如果ACPI为它们
+�供电�管�或热�拔功能，或者如果设备有由平�中断控制器连接的INTx中断，需�一个_PRT
+��述这些连接，这�情况下ACPI�以�述PCI设备。
+
+ACPI资��述是通过ACPI命�空间中设备的_CRS对象完�的[2]。_CRS就�一个通用的PCI BAR：
+�作系统�以读�_CRS并找出正在消耗的资�，�使它没有该设备的驱动程�[3]。这一点很��，
+因为它�味�一个旧的�作系统�以正确地工作，�使是在�作系统�知�的新设备的系统上。新设
+备�能什么都��，但�作系统至少�以确�没有资�与它们冲�。
+
+�MCFG�HPET�ECDT等��表，�是�留地�空间的机制。��表是在�作系统在�动�期且在它
+能够解�ACPI命�空间之�需�知�的东西。如果定义了一个新的表，�使旧的�作系统忽略了这
+个表，它也需�正常�行。_CRS�许这样�，因为它是通用的，�以被旧的�作系统解�；而��表
+则��许。
+
+如果�作系统�管�一个通过ACPI�述的���现的设备，该设备将有一个特定的_HID/_CID，以
+告诉�作系统与之绑定的驱动程�，并且_CRS告诉�作系统和驱动程�该设备的寄存器在哪里。
+
+PCI主桥是PNP0A03或PNP0A08设备。它们的_CRS应该�述它们所消耗的所有地�空间。这包括它
+们转�到PCI总线上的所有窗�，以��转�到PCI的主桥本身的寄存器。主桥的寄存器包括次�/下
+级总线寄存器，决定了桥下�的总线范围，窗�寄存器�述了桥洞，等等。这些都是设备相关的，�
+架构相关的东西，所以PNP0A03/PNP0A08驱动�以管�它们的唯一方法是通过_PRS/_CRS/_SRS，
+它包�了特定于设备的细节。主桥寄存器也包括ECAM空间，因为它是由主桥消耗的。
+
+ACPI定义了一个Consumer/Producer��区分桥寄存器（“Consumer�下文译作消费者）和
+桥洞（“Producer�下文译作生产者）[4, 5]，但是早期的BIOS没有正确使用这个�。其结果
+是，目�的ACPI规范�为扩展地�空间�述符定义了消费者/生产者；在旧的QWord/Word/Word地
+�空间�述符中，该�应该被忽略。因此，�作系统必须�定所有的QWord/Word/Word�述符都是
+窗�。
+
+在增加扩展地�空间�述符之�，消费者/生产者的失败�味�没有办法�述PNP0A03/PNP0A08设
+备本身的桥寄存器。解决办法是在PNP0C02��器中�述桥寄存器（包括ECAM空间）[6]。
+除了ECAM之外，桥寄存器空间�正是特定于设备的，所以通用的PNP0A03/PNP0A08驱动程
+�(pci_root.c)没有必�了解它。
+
+新的架构应该能够在PNP0A03设备中使用“消费者�扩展地�空间�述符，用于桥寄存器，包括
+ECAM，尽管对[6]的严格解释�能�止这样�。旧的x86和ia64内核�定所有的地�空间�述
+符，包括“消费者�扩展地�空间的�述符，都是窗�，所以在这些架构上以这�方��述桥寄
+存器是�安全的。
+
+PNP0C02“主��设备基本上是万能的。除了“��将这些资�用于其他用途�之外，没有其他的编
+程模型。因此，PNP0C02 _CRS应该声明ACPI命�空间中(1)没有被_CRS声明的任何其他设备对
+象的地�空间，(2)�应该被OS分�给其他东西。
+
+除�有一个标准的固件接�用于�置访问，例如ia64 SAL接�[7]，�则PCIe规范�求使用增强
+型�置访问方法（ECAM）。主桥消耗ECAM内存地�空间并将内存访问转�为PCI�置访问。该规范
+定义了ECAM地�空间的布局和功能；�有地�空间的基础是特定于设备的。ACPI�作系统从��
+MCFG表或PNP0A03设备中的_CBA方法中了解基础地�。
+
+MCFG表必须�述�热�拔主桥的ECAM空间[8]。由于MCFG是一个��表，�能通过热�拔更新，
+PNP0A03设备中的_CBA方法�述了�热�拔主桥的ECAM空间[9]。请注�，对于MCFG和_CBA，
+基�总是对应于总线0，�使桥器下�的总线范围（通过_CRS报告）�从0开始。
+
+
+[1] ACPI 6.2, sec 6.1:
+    对于任何在�枚举类型的总线上的设备（例如，ISA总线），OSPM会枚举设备的标识符，ACPI
+    系统固件必须为�个设备�供一个_HID对象...以使OSPM能够�到这一点。
+
+[2] ACPI 6.2, sec 3.7:
+    �作系统枚举主�设备时，�需通过读�ACPI命�空间�寻找具有硬件ID的设备。
+
+    ACPI枚举的�个设备都包括ACPI命�空间中ACPI定义的对象，该对象报告设备�能�用的硬
+    件资�[_PRS]，报告设备当�使用的资�[_CRS]的对象，以��置这些资�的对象[_SRS]。
+    这些信�被���用�作系统（OSPM）用��置设备。
+
+[3] ACPI 6.2, sec 6.2:
+    OSPM使用设备�置对象��置通过ACPI列举的设备的硬件资�。设备�置对象�供了关于当�
+    和�能的资�需求的信�，共享资�之间的关系，以��置硬件资�的方法。
+
+    当OSPM枚举一个设备时，它调用_PRS�确定该设备的资�需求。它也�以调用_CRS�找到该设
+    备的当�资�设置。利用这些信�，���用系统决定设备应该消耗什么资�，并通过调用设备
+    的_SRS控制方法�设置这些资�。
+
+    在ACPI中，设备�以消耗资�（例如，传统的键盘），�供资�（例如，一个专有的PCI桥），
+    或者两者都�。除��有规定，设备的资�被�定为�自设备层次结构中设备上方最近的匹�资
+    �。
+
+[4] ACPI 6.2, sec 6.4.3.5.1, 2, 3, 4:
+    QWord/DWord/Word 地�空间�述符 (.1, .2, .3)
+      常规标志: Bit [0] 被忽略。
+
+    扩展地�空间�述符 (.4)
+      常规标志: Bit [0] 消费者/生产者:
+
+        * 1 – 这个设备消费这个资�
+        * 0 – 该设备生产和消费该资�
+
+[5] ACPI 6.2, sec 19.6.43:
+    ResourceUsage指定内存范围是由这个设备（ResourceConsumer）消费还是传递给�设备
+    （ResourceProducer）。如果没有指定，那么就�定是ResourceConsumer。
+
+[6] PCI Firmware 3.2, sec 4.1.2:
+    如果�作系统�能原生的懂得�留MMCFG区域，MMCFG区域必须由固件�留。在MCFG表中或通
+    过_CBA方法（�第4.1.3节）报告的地�范围必须通过声明主�资���留。对于大多数系统，
+    主�资�将出现在ACPI命�空间的根部（在_SB下），在一个节点的_HID为EISAID（PNP0C0
+    2），在这�情况下的资��应该�求在根PCI总线的_CRS。这些资��以选择在Int15 E820
+    或EFIGetMemoryMap中作为�留内存返回，但必须始终通过ACPI作为主�资�报告。
+
+[7] PCI Express 4.0, sec 7.2.2:
+    对于PC兼容的系统，或者没有实现�许访问�置空间的处�器架构特定固件接�标准的系统，需
+    �使用本节中定义的ECAM。
+
+[8] PCI Firmware 3.2, sec 4.1.2:
+    MCFG表是一个ACPI表，用于沟通的基础地�对应的�热的�移动的PCI段组范围内的PCI段组在
+    �动时�供给�作系统。这对PC兼容系统�说是必需的。
+
+    MCFG表仅用于沟通在�动时系统�用的PCI段组对应的基�。
+
+[9] PCI Firmware 3.2, sec 4.1.3:
+    _CBA (Memory mapped Configuration Base Address) 控制方法是一个�选的ACPI对
+    象，用于返回热�拔主桥的64�内存映射的�置基�。_CBA 返回的基�是与处�器相关的地�。
+    _CBA 控制方法被评估为一个整数。
+
+    这个控制方法出现在主桥对象下。当_CBA方法出现在一个活动的主桥对象下时，�作系统会评
+    估这个结构，以确定内存映射的�置基�，对应于_CRS方法中指定的总线编�范围的PCI段组。
+    一个包�_CBA方法的ACPI命�空间对象也必须包�一个相应的_SEG方法。
diff --git a/Documentation/translations/zh_CN/PCI/index.rst b/Documentation/translations/zh_CN/PCI/index.rst
index 16acb2bd9b58..cbeb33c34a98 100644
--- a/Documentation/translations/zh_CN/PCI/index.rst
+++ b/Documentation/translations/zh_CN/PCI/index.rst
@@ -10,9 +10,6 @@
 :校译:
 
 
-
-.. _cn_PCI_index.rst:
-
 ===================
 Linux PCI总线�系统
 ===================
@@ -26,12 +23,12 @@ Linux PCI总线�系统
    pci-iov-howto
    msi-howto
    sysfs-pci
+   acpi-info
 
 
 Todolist:
 
-   acpi-info
-   pci-error-recovery
-   pcieaer-howto
-   endpoint/index
-   boot-interrupts
+* pci-error-recovery
+* pcieaer-howto
+* endpoint/index
+* boot-interrupts
diff --git a/Documentation/translations/zh_CN/admin-guide/README.rst b/Documentation/translations/zh_CN/admin-guide/README.rst
index d20949e8bf6f..e679cbc3c89d 100644
--- a/Documentation/translations/zh_CN/admin-guide/README.rst
+++ b/Documentation/translations/zh_CN/admin-guide/README.rst
@@ -6,10 +6,10 @@
 
  �想� Wu XiangCheng <bobwxc@email.cn>
 
-Linux内核5.x版本 <http://kernel.org/>
+Linux内核6.x版本 <http://kernel.org/>
 =========================================
 
-以下是Linux版本5的�行注记。仔细阅读它们，
+以下是Linux版本6的�行注记。仔细阅读它们，
 它们会告诉你这些都是什么，解释如何安装内核，以��到问题时该如何�。
 
 什么是Linux？
@@ -61,27 +61,27 @@ Linux内核5.x版本 <http://kernel.org/>
  - 如果您�安装完整的�代�，请把内核tar档案包放在您有��的目录中（例如您
    的主目录）并将其解包::
 
-     xz -cd linux-5.x.tar.xz | tar xvf -
+     xz -cd linux-6.x.tar.xz | tar xvf -
 
    将“X�替��最新内核的版本�。
 
    ���】使用 /usr/src/linux 目录�这里有一组库头文件使用的内核头文件
    （通常是�完整的）。它们应该与库匹�，而�是被内核的�化�得一团糟。
 
- - 您还�以通过打补�在5.x版本之间�级。补�以xz格�分�。�通过打补�进行
-   安装，请获�所有较新的补�文件，进入内核�代�（linux-5.x）的目录并
+ - 您还�以通过打补�在6.x版本之间�级。补�以xz格�分�。�通过打补�进行
+   安装，请获�所有较新的补�文件，进入内核�代�（linux-6.x）的目录并
    执行::
 
-     xz -cd ../patch-5.x.xz | patch -p1
+     xz -cd ../patch-6.x.xz | patch -p1
 
    请�按顺�】替�所有大于当��代�树版本的“x�，这样就�以了。您�能想�
    删除备份文件（文件�类似xxx~ 或 xxx.orig)，并确�没有失败的补�（文件�
    类似xxx# 或 xxx.rej）。如果有，�是你就是我犯了错误。
 
-   与5.x内核的补���，5.x.y内核（也称为稳定版内核）的补��是增�的，而是
-   直接应用于基本的5.x内核。例如，如果您的基本内核是5.0，并且希望应用5.0.3
-   补�，则�应先应用5.0.1和5.0.2的补�。类似地，如果您�行的是5.0.2内核，
-   并且希望跳转到5.0.3，那么在应用5.0.3补�之�，必须首先撤销5.0.2补�
+   与6.x内核的补���，6.x.y内核（也称为稳定版内核）的补��是增�的，而是
+   直接应用于基本的6.x内核。例如，如果您的基本内核是6.0，并且希望应用6.0.3
+   补�，则�应先应用6.0.1和6.0.2的补�。类似地，如果您�行的是6.0.2内核，
+   并且希望跳转到6.0.3，那么在应用6.0.3补�之�，必须首先撤销6.0.2补�
    （�patch -R）。更多关于这方�的内容，请阅读
    :ref:`Documentation/process/applying-patches.rst <applying_patches>` 。
 
@@ -103,7 +103,7 @@ Linux内核5.x版本 <http://kernel.org/>
 软件�求
 ---------
 
-   编译和�行5.x内核需���软件包的最新版本。请�考
+   编译和�行6.x内核需���软件包的最新版本。请�考
    :ref:`Documentation/process/changes.rst <changes>`
    �了解最低版本�求以�如何�级软件包。请注�，使用过旧版本的这些包�能会
    导致很难追踪的间接错误，因此��以为在生�或�作过程中出现明显问题时�以
@@ -116,12 +116,12 @@ Linux内核5.x版本 <http://kernel.org/>
    ``make O=output/dir`` 选项�以为输出文件（包括 .config）指定备用�置。
    例如::
 
-     kernel source code: /usr/src/linux-5.x
+     kernel source code: /usr/src/linux-6.x
      build directory:    /home/name/build/kernel
 
    ��置和构建内核，请使用::
 
-     cd /usr/src/linux-5.x
+     cd /usr/src/linux-6.x
      make O=/home/name/build/kernel menuconfig
      make O=/home/name/build/kernel
      sudo make O=/home/name/build/kernel modules_install install
@@ -227,8 +227,6 @@ Linux内核5.x版本 <http://kernel.org/>
  - 确�您至少有gcc 5.1�用。
    有关更多信�，请�阅 :ref:`Documentation/process/changes.rst <changes>` 。
 
-   请注�，您�然�以使用此内核�行a.out用户程�。
-
  - 执行 ``make`` �创建压缩内核映�。如果您安装了lilo以适�内核makefile，
    那么也�以进行 ``make install`` ，但是您�能需�先检查特定的lilo设置。
 
@@ -282,67 +280,12 @@ Linux内核5.x版本 <http://kernel.org/>
 若�到问题
 -----------
 
- - 如果您�现了一些�能由于内核缺陷所导致的问题，请检查MAINTAINERS（维护者）
-   文件看看是�有人与令您�到麻烦的内核部分相关。如果无人在此列出，那么第二
-   个最好的方案就是把它们�给我（torvalds@linux-foundation.org），也�能��
-   到任何其他相关的邮件列表或新闻组。
-
- - 在所有的缺陷报告中，�请】告诉我们您在说什么内核，如何�现问题，以�您的
-   设置是什么的（使用您的常识）。如果问题是新的，请告诉我；如果问题是旧的，
-   请�试告诉我您什么时候首次注�到它。
-
- - 如果缺陷导致如下消�::
-
-     unable to handle kernel paging request at address C0000010
-     Oops: 0002
-     EIP:   0010:XXXXXXXX
-     eax: xxxxxxxx   ebx: xxxxxxxx   ecx: xxxxxxxx   edx: xxxxxxxx
-     esi: xxxxxxxx   edi: xxxxxxxx   ebp: xxxxxxxx
-     ds: xxxx  es: xxxx  fs: xxxx  gs: xxxx
-     Pid: xx, process nr: xx
-     xx xx xx xx xx xx xx xx xx xx
-
-   或者类似的内核调试信�显示在�幕上或在系统日志里，请�如实】�制它。
-   �能对你�说转储（dump）看起����解，但它确实包��能有助于调试问题的
-   信�。转储上方的文本也很��：它说明了内核转储代�的原因（在上�的示例中，
-   是由于内核指针错误）。更多关于如何�解转储的信�，请��
-   Documentation/admin-guide/bug-hunting.rst。
-
- - 如果使用 CONFIG_KALLSYMS 编译内核，则�以按原样��转储，�则必须使用
-   ``ksymoops`` 程���解转储（但通常首选使用CONFIG_KALLSYMS编译）。
-   此实用程��从
-   https://www.kernel.org/pub/linux/utils/kernel/ksymoops/ 下载。
-   或者，您�以手动执行转储查找：
-
- - 在调试�上�这样的转储时，如果您�以查找EIP值的�义，这将�常有帮助。
-   �六进制值本身对我或其他任何人都没有太大帮助：它会�决于特定的内核设置。
-   您应该�的是从EIP行获��六进制值（忽略 ``0010:`` ），然�在内核�字列表
-   中查找它，以查看哪个内核函数包�有问题的地�。
-
-   �找到内核函数�，您需�找到与显示症状的内核相关�的系统二进制文件。就是
-   文件“linux/vmlinux�。����字列表并将其与内核崩溃中的EIP进行匹�，
-   请执行::
-
-     nm vmlinux | sort | less
-
-   这将为您�供一个按��排�的内核地�列表，从中很容易找到包�有问题的地�
-   的函数。请注�，内核调试消��供的地��一定与函数地�完全匹�（事实上，
-   这是��能的），因此您�能�“grep�列表：�过列表将为您�供�个内核函数
-   的起点，因此通过查找起始地�低于你正在�索的地�，但�一个函数的高于的
-   函数，你会找到您想�的。实际上，在您的问题报告中加入一些“上下文��能是
-   一个好主�，给出相关的上下几行。
-
-   如果您由于�些原因无法完�上述�作（如您使用预编译的内核映�或类似的映�），
-   请尽�能多地告诉我您的相关设置信�，这会有所帮助。有关详细信�请阅读
-   ‘Documentation/admin-guide/reporting-issues.rst’。
-
- - 或者，您�以在正在�行的内核上使用gdb（�读的；��能更改值或设置断点）。
-   为此，请首先使用-g编译内核；适当地编辑arch/x86/Makefile，然�执行 ``make
-   clean`` 。您还需��用CONFIG_PROC_FS（通过 ``make config`` ）。
-
-   使用新内核�新�动�，执行 ``gdb vmlinux /proc/kcore`` 。现在�以使用所有
-   普通的gdb命令。查找系统崩溃点的命令是 ``l *0xXXXXXXXX`` （将xxx替�为EIP
-   值）。
-
-   用gdb无法调试一个当�未�行的内核是由于gdb（错误地）忽略了编译内核的起始
-   �移�。
+如果您�现了一些�能由于内核缺陷所导致的问题，请�阅：
+Documentation/translations/zh_CN/admin-guide/reporting-issues.rst 。
+
+想��解内核错误报告，请�阅：
+Documentation/translations/zh_CN/admin-guide/bug-hunting.rst 。
+
+更多用GDB调试内核的信�，请�阅：
+Documentation/translations/zh_CN/dev-tools/gdb-kernel-debugging.rst
+和 Documentation/dev-tools/kgdb.rst 。
diff --git a/Documentation/translations/zh_CN/admin-guide/bootconfig.rst b/Documentation/translations/zh_CN/admin-guide/bootconfig.rst
new file mode 100644
index 000000000000..072d17f5f199
--- /dev/null
+++ b/Documentation/translations/zh_CN/admin-guide/bootconfig.rst
@@ -0,0 +1,293 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: Documentation/admin-guide/bootconfig.rst
+
+:译者: �想� Wu XiangCheng <bobwxc@email.cn>
+
+========
+引导�置
+========
+
+:作者: Masami Hiramatsu <mhiramat@kernel.org>
+
+概述
+====
+
+引导�置扩展了现有的内核命令行，以一�更有效率的方�在引导内核时进一步支�
+键值数�。这�许管�员传递一份结构化关键字的�置文件。
+
+�置文件语法
+============
+
+引导�置文件的语法采用�常简�的键值结构。�个关键字由点连接的��组�，键
+和值由 ``=`` 连接。值以分�（ ``;`` ）或�行符（ ``\n`` ）结尾。数组值中�
+个元素由逗�（ ``,`` ）分隔。::
+
+  KEY[.WORD[...]] = VALUE[, VALUE2[...]][;]
+
+与内核命令行语法��，逗�和 ``=`` 周围�许有空格。
+
+关键字��许包�字��数字�连字符（ ``-`` ）和下划线（ ``_`` ）。值�包�
+�打�字符和空格，但分�（ ``;`` ）��行符（ ``\n`` ）�逗�（ ``,`` ）�
+井�（ ``#`` ）和�大括�（ ``}`` ）等分隔符除外。
+
+如果你需�在值中使用这些分隔符，�以用�引�（ ``"VALUE"`` ）或�引�
+（ ``'VALUE'`` ）括起�。注�，引�无法转义。
+
+键的值�以为空或�存在。这些键用于检查该键是�存在（类似布尔值）。
+
+键值语法
+--------
+
+引导�置文件语法�许用户通过大括��并键�部分相�的关键字。例如::
+
+ foo.bar.baz = value1
+ foo.bar.qux.quux = value2
+
+也�以写�::
+
+ foo.bar {
+    baz = value1
+    qux.quux = value2
+ }
+
+或者更紧凑一些，写�::
+
+ foo.bar { baz = value1; qux.quux = value2 }
+
+在这两�样�中，引导解�时相�的关键字都会自动�并。因此�以追加类似的树或
+键值。
+
+相�关键字的值
+--------------
+
+�止两个或多个值或数组共享�一个关键字。例如::
+
+ foo = bar, baz
+ foo = qux  # !错误! 我们��以�定义相�的关键字
+
+如果你想�更新值，必须显�使用覆盖�作符 ``:=`` 。例如::
+
+ foo = bar, baz
+ foo := qux
+
+这样 ``foo`` 关键字的值就��了 ``qux`` 。这对于通过添加（部分）自定义引导
+�置�覆盖默认值�常有用，�于解�默认引导�置。
+
+如果你想对现有关键字追加值作为数组�员，�以使用 ``+=`` �作符。例如::
+
+ foo = bar, baz
+ foo += qux
+
+这样， ``foo`` 关键字就�时拥有了 ``bar`` ， ``baz`` 和 ``qux`` 。
+
+此外，父关键字下��时存在值和�关键字。
+例如，下列�置是�行的。::
+
+ foo = value1
+ foo.bar = value2
+ foo := value3 # 这会更新foo的值。
+
+注�，裸值�能直接放进结构化关键字中，必须在大括�外定义它。例如::
+
+ foo {
+     bar = value1
+     bar {
+         baz = value2
+         qux = value3
+     }
+ }
+
+�时，关键字下值节点的顺�是固定的。如果值和�关键字�时存在，值永远是该关
+键字的第一个�节点。因此如果用户先指定�关键字，如::
+
+ foo.bar = value1
+ foo = value2
+
+则在程�（和/proc/bootconfig）中，它会按如下显示::
+
+ foo = value2
+ foo.bar = value1
+
+注释
+----
+
+�置语法接�shell脚本风格的注释。注释以井�（ ``#`` ）开始，到�行符
+（ ``\n`` ）结�。
+
+::
+
+ # comment line
+ foo = value # value is set to foo.
+ bar = 1, # 1st element
+       2, # 2nd element
+       3  # 3rd element
+
+会被解�为::
+
+ foo = value
+ bar = 1, 2, 3
+
+注�你�能把注释放在值和分隔符（ ``,`` 或 ``;`` ）之间。如下�置语法是错误的::
+
+ key = 1 # comment
+       ,2
+
+
+/proc/bootconfig
+================
+
+/proc/bootconfig是引导�置的用户空间接�。与/proc/cmdline��，此文件内容以
+键值列表样�显示。
+�个键值对一行，样�如下::
+
+ KEY[.WORDS...] = "[VALUE]"[,"VALUE2"...]
+
+
+用引导�置引导内核
+==================
+
+用引导�置引导内核有两�方法：将引导�置附加到initrd镜�或直接嵌入内核中。
+
+*initrd: initial RAM disk，�始内存�盘*
+
+将引导�置附加到initrd
+----------------------
+
+由于默认情况下引导�置文件是用initrd加载的，因此它将被添加到initrd（initramfs）
+镜�文件的末尾，其中包�填充�大��校验值和12字节幻数，如下所示::
+
+ [initrd][bootconfig][padding][size(le32)][checksum(le32)][#BOOTCONFIG\n]
+
+大�和校验值为�端�存放的32�无符�值。
+
+当引导�置被加到initrd镜�时，整个文件大�会对�到4字节。空字符（ ``\0`` ）
+会填补对�空隙。因此 ``size`` 就是引导�置文件的长度+填充的字节。
+
+Linux内核在内存中解�initrd镜�的最�部分以获�引导�置数�。由于这�“背负��
+的方法，��引导加载器传递了正确的initrd文件大�，就无需更改或更新引导加载器
+和内核镜�本身。如果引导加载器�外传递了更长的大�，内核将无法找到引导�置数
+�。
+
+Linux内核在tools/bootconfig下�供了 ``bootconfig`` 命令�完�此�作，管�员
+�以用它从initrd镜�中删除或追加�置文件。你�以用以下命令�构建它::
+
+ # make -C tools/bootconfig
+
+��initrd镜�添加你的引导�置文件，请按如下命令�作（旧数�会自动移除）::
+
+ # tools/bootconfig/bootconfig -a your-config /boot/initrd.img-X.Y.Z
+
+�从镜�中移除�置，�以使用-d选项::
+
+ # tools/bootconfig/bootconfig -d /boot/initrd.img-X.Y.Z
+
+然�在内核命令行上添加 ``bootconfig`` 告诉内核去initrd文件末尾寻找内核�置。
+
+将引导�置嵌入内核
+------------------
+
+如果你�能使用initrd，也�以通过Kconfig选项将引导�置文件嵌入内核中。在此情
+况下，你需�用以下选项�新编译内核::
+
+ CONFIG_BOOT_CONFIG_EMBED=y
+ CONFIG_BOOT_CONFIG_EMBED_FILE="/引导�置/文件/的/路径"
+
+``CONFIG_BOOT_CONFIG_EMBED_FILE`` 需�从��树或对象树开始的引导�置文件的
+�对/相对路径。内核会将其嵌入作为默认引导�置。
+
+与将引导�置附加到initrd一样，你也需�在内核命令行上添加 ``bootconfig`` 告诉
+内核去�用内嵌的引导�置。
+
+注�，�使你已�设置了此选项，��用附加到initrd的其他引导�置覆盖内嵌的引导
+�置。
+
+通过引导�置传递内核�数
+========================
+
+除了内核命令行，引导�置也�以用于传递内核�数。所有 ``kernel`` 关键字下的键
+值对都将直接传递给内核命令行。此外， ``init`` 下的键值对将通过命令行传递给
+init进程。�数按以下顺�与用户给定的内核命令行字符串相连，因此命令行�数�以
+覆盖引导�置�数（这�决于�系统如何处��数，但通常��的�数将被��的�数
+覆盖）::
+
+ [bootconfig params][cmdline params] -- [bootconfig init params][cmdline init params]
+
+如果引导�置文件给出的kernel/init�数是::
+
+ kernel {
+   root = 01234567-89ab-cdef-0123-456789abcd
+ }
+ init {
+  splash
+ }
+
+这将被�制到内核命令行字符串中，如下所示::
+
+ root="01234567-89ab-cdef-0123-456789abcd" -- splash
+
+如果用户给出的其他命令行是::
+
+ ro bootconfig -- quiet
+
+则最�的内核命令行如下::
+
+ root="01234567-89ab-cdef-0123-456789abcd" ro bootconfig -- splash quiet
+
+
+�置文件的�制
+==============
+
+当�最大的�置大�是32KB，关键字总数（�是键值�目）必须少于1024个节点。
+注�：这�是�目数而是节点数，�目必须消耗超过2个节点（一个关键字和一个值）。
+所以从�论上讲最多512个键值对。如果关键字平�包�3个��，则�有256个键值对。
+在大多数情况下，�置项的数�将少于100个�目，�于8KB，因此这应该足够了。如果
+节点数超过1024，解�器将返回错误，�使文件大��于32KB。（请注�，此最大尺寸
+�包括填充的空字符。）
+无论如何，因为 ``bootconfig`` 命令在附加�动�置到initrd映�时会验�它，用户
+�以在引导之�注�到它。
+
+
+引导�置API
+===========
+
+用户�以查询或�历键值对，也�以查找（�缀）根关键字节点，并在查找该节点下的
+键值。
+
+如果您有一个关键字字符串，则�以直接使用 xbc_find_value() 查询该键的值。如果
+你想知�引导�置里有哪些关键字，�以使用 xbc_for_each_key_value() 迭代键值对。
+请注�，您需�使用 xbc_array_for_each_value() 访问数组的值，例如::
+
+ vnode = NULL;
+ xbc_find_value("key.word", &vnode);
+ if (vnode && xbc_node_is_array(vnode))
+    xbc_array_for_each_value(vnode, value) {
+      printk("%s ", value);
+    }
+
+如果您想查找具有�缀字符串的键，�以使用 xbc_find_node() 通过�缀字符串查找
+节点，然�用 xbc_node_for_each_key_value() 迭代�缀节点下的键。
+
+但最典型的用法是获��缀下的命�值或�缀下的命�数组，例如::
+
+ root = xbc_find_node("key.prefix");
+ value = xbc_node_find_value(root, "option", &vnode);
+ ...
+ xbc_node_for_each_array_value(root, "array-option", value, anode) {
+    ...
+ }
+
+这将访问值“key.prefix.option�的值和“key.prefix.array-option�的数组。
+
+�是�需�的，因为在�始化之��置�读。如果需�修改，必须�制所有数�和关键字。
+
+
+函数与结构体
+============
+
+相关定义的kernel-doc��：
+
+ - include/linux/bootconfig.h
+ - lib/bootconfig.c
diff --git a/Documentation/translations/zh_CN/admin-guide/index.rst b/Documentation/translations/zh_CN/admin-guide/index.rst
index 2f6970d0a032..ac2960da33e6 100644
--- a/Documentation/translations/zh_CN/admin-guide/index.rst
+++ b/Documentation/translations/zh_CN/admin-guide/index.rst
@@ -63,6 +63,7 @@ Todolist:
 .. toctree::
    :maxdepth: 1
 
+   bootconfig
    clearing-warn-once
    cpu-load
    cputopology
@@ -80,7 +81,6 @@ Todolist:
 *   binderfs
 *   binfmt-misc
 *   blockdev/index
-*   bootconfig
 *   braille-console
 *   btmrvl
 *   cgroup-v1/index
diff --git a/Documentation/translations/zh_CN/core-api/circular-buffers.rst b/Documentation/translations/zh_CN/core-api/circular-buffers.rst
new file mode 100644
index 000000000000..694ad8e61070
--- /dev/null
+++ b/Documentation/translations/zh_CN/core-api/circular-buffers.rst
@@ -0,0 +1,210 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: Documentation/core-api/circular-buffers.rst
+
+:翻译:
+
+ 周彬彬 Binbin Zhou <zhoubinbin@loongson.cn>
+
+:校译:
+
+ �延腾 Yanteng Si <siyanteng@loongson.cn>
+ �想� Wu Xiangcheng <bobwxc@email.cn>
+ 时奎亮 Alex Shi <alexs@kernel.org>
+
+==========
+环形缓冲区
+==========
+
+:作者: David Howells <dhowells@redhat.com>
+:作者: Paul E. McKenney <paulmck@linux.ibm.com>
+
+
+Linux �供了许多�用于实现循环缓冲的特性。有两组这样的特性：
+
+ (1) 用于确定2次方大�的缓冲区信�的便利函数。
+
+ (2) �以代替缓冲区中对象的生产者和消费者共享�的内存�障。
+
+如下所述，�使用这些设施，�需�一个生产者和一个消费者。�以通过�列化�处�多个
+生产者，并通过�列化�处�多个消费者。
+
+.. Contents:
+
+ (*) 什么是环形缓冲区？
+
+ (*) 测�2次幂缓冲区
+
+ (*) 内存�障与环形缓冲区的结�使用
+     - 生产者
+     - 消费者
+
+ (*) 延伸阅读
+
+
+
+什么是环形缓冲区？
+==================
+
+首先，什么是环形缓冲区？环形缓冲区是具有固定的有�大�的缓冲区，它有两个索引：
+
+ (1) 'head'索引 - 生产者将元素�入缓冲区的�置。
+
+ (2) 'tail'索引 - 消费者在缓冲区中找到下一个元素的�置。
+
+通常，当tail指针等于head指针时，表明缓冲区是空的；而当head指针比tail指针少一个时，
+表明缓冲区是满的。
+
+添加元素时，递增head索引；删除元素时，递增tail索引。tail索引�应该跳过head索引，
+两个索引在到达缓冲区末端时都应该被赋值为0，从而�许海�的数��过缓冲区。
+
+通常情况下，元素都有相�的�元大�，但这并�是使用以下技术的严格�求。如果�在缓
+冲区中包�多个元素或��大�的元素，则索引�以增加超过1，��是两个索引都没有超过
+�一个。然而，实现者必须�心，因为超过一个��大�的区域�能会覆盖缓冲区的末端并
+且缓冲区会被分�两段。
+
+测�2次幂缓冲区
+===============
+
+计算任�大�的环形缓冲区的�用或剩余容�通常是一个费时的�作，需�使用模（除法）
+指令。但是如果缓冲区的大�为2次幂，则�以使用更快的按�与指令代替。
+
+Linux�供了一组用于处�2次幂环形缓冲区的�。�以通过以下方�使用::
+
+	#include <linux/circ_buf.h>
+
+这些�包括：
+
+ (#) 测�缓冲区的剩余容�::
+
+	CIRC_SPACE(head_index, tail_index, buffer_size);
+
+     返回缓冲区[1]中��入元素的剩余空间大�。
+
+
+ (#) 测�缓冲区中的最大连续立��用空间::
+
+	CIRC_SPACE_TO_END(head_index, tail_index, buffer_size);
+
+     返回缓冲区[1]中剩余的连续空间的大�，元素�以立��入其中，而�必绕回到缓冲
+     区的开头。
+
+
+ (#) 测�缓冲区的使用数::
+
+	CIRC_CNT(head_index, tail_index, buffer_size);
+
+     返回当��用缓冲区[2]的元素数�。
+
+
+ (#) 测�缓冲区的连续使用数::
+
+	CIRC_CNT_TO_END(head_index, tail_index, buffer_size);
+
+     返回�以从缓冲区中��的连续元素[2]的数�，而�必绕回到缓冲区的开头。
+
+这里的�一个��义上都会返回一个介于0和buffer_size-1之间的值，但是：
+
+ (1) CIRC_SPACE*()是为了在生产者中使用。对生产者�说，它们将返回一个下�，因为生
+     产者控制�head索引，但消费者�能�然在�一个CPU上耗尽缓冲区并移动tail索引。
+
+     对消费者�说，它将显示一个上�，因为生产者�能正忙于耗尽空间。
+
+ (2) CIRC_CNT*()是为了在消费者中使用。对消费者�说，它们将返回一个下�，因为消费
+     者控制�tail索引，但生产者�能�然在�一个CPU上填充缓冲区并移动head索引。
+
+     对于生产者，它将显示一个上�，因为消费者�能正忙于清空缓冲区。
+
+ (3) 对于第三方�说，生产者和消费者对索引的写入顺�是无法��的，因为它们是独立的，
+     而且�能是在��的CPU上进行的，所以在这�情况下的结果�是一�猜测，甚至�能
+     是错误的。
+
+内存�障与环形缓冲区的结�使用
+==============================
+
+通过将内存�障与环形缓冲区结�使用，�以��以下需求：
+
+ (1) 使用�个��控制对缓冲区两端的访问，从而�许�时填充和清空缓冲区；以�
+
+ (2) 使用原�计数器�作。
+
+这有两个方�：填充缓冲区的生产者和清空缓冲区的消费者。在任何时候，�应有一个生产
+者在填充缓冲区，�样的也�应有一个消费者在清空缓冲区，但�方�以�时�作。
+
+
+生产者
+------
+
+生产者看起��这样::
+
+	spin_lock(&producer_lock);
+
+	unsigned long head = buffer->head;
+	/* spin_unlock()和下一个spin_lock()�供必�的排�。 */
+	unsigned long tail = READ_ONCE(buffer->tail);
+
+	if (CIRC_SPACE(head, tail, buffer->size) >= 1) {
+		/* 添加一个元素到缓冲区 */
+		struct item *item = buffer[head];
+
+		produce_item(item);
+
+		smp_store_release(buffer->head,
+				  (head + 1) & (buffer->size - 1));
+
+		/* wake_up()将确�在唤醒任何人之��交head */
+		wake_up(consumer);
+	}
+
+	spin_unlock(&producer_lock);
+
+这将表明CPU必须在head索引使其对消费者�用之�写入新项目的内容，�时CPU必须在唤醒
+消费者之�写入修改�的head索引。
+
+请注�，wake_up()并���任何形�的�障，除�确实唤醒了�些东西。因此我们�能��
+它�进行排�。但是数组中始终有一个元素留空，因此生产者必须产生两个元素，然���
+能破�消费者当�正在读�的元素。�时，消费者连续调用之间�对的解�-加��供了索引
+读�（指示消费者已清空给定元素）和生产者对该相�元素的写入之间的必�顺�。
+
+
+消费者
+------
+
+消费者看起��这样::
+
+	spin_lock(&consumer_lock);
+
+	/* 读�该索引处的内容之�，先读�索引 */
+	unsigned long head = smp_load_acquire(buffer->head);
+	unsigned long tail = buffer->tail;
+
+	if (CIRC_CNT(head, tail, buffer->size) >= 1) {
+
+		/* 从缓冲区中��一个元素 */
+		struct item *item = buffer[tail];
+
+		consume_item(item);
+
+		/* 在递增tail之�完�对�述符的读�。 */
+		smp_store_release(buffer->tail,
+				  (tail + 1) & (buffer->size - 1));
+	}
+
+	spin_unlock(&consumer_lock);
+
+这表明CPU在读�新元素之�确�索引是最新的，然�在写入新的尾指针之�应确�CPU已完
+�读�该元素，这将擦除该元素。
+
+请注�，使用READ_ONCE()和smp_load_acquire()�读���（head）索引。这�以防止编译
+器丢弃并�新加载其缓存值。如果您能确定��（head）索引将仅使用一次，则这�是必须
+的。smp_load_acquire()还�以强制CPU对�续的内存引用进行排�。类似地，两�算法都使
+用smp_store_release()�写入线程的索引。这记录了我们正在写入�以并�读�的内容的事
+实，以防止编译器破�存储，并强制对以�的访问进行排�。
+
+
+延伸阅读
+========
+
+关于Linux的内存�障设施的�述，请查看Documentation/memory-barriers.txt。
diff --git a/Documentation/translations/zh_CN/core-api/generic-radix-tree.rst b/Documentation/translations/zh_CN/core-api/generic-radix-tree.rst
new file mode 100644
index 000000000000..eacd1d2ebddc
--- /dev/null
+++ b/Documentation/translations/zh_CN/core-api/generic-radix-tree.rst
@@ -0,0 +1,23 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: Documentation/core-api/generic-radix-tree.rst
+
+:翻译:
+
+ 周彬彬 Binbin Zhou <zhoubinbin@loongson.cn>
+
+===================
+通用基数树/稀�数组
+===================
+
+通用基数树/稀�数组的相关内容请�include/linux/generic-radix-tree.h文件中的
+“DOC: Generic radix trees/sparse arrays�。
+
+通用基数树函数
+--------------
+
+该API在以下内核代�中:
+
+include/linux/generic-radix-tree.h
diff --git a/Documentation/translations/zh_CN/core-api/idr.rst b/Documentation/translations/zh_CN/core-api/idr.rst
new file mode 100644
index 000000000000..97a16e76b81b
--- /dev/null
+++ b/Documentation/translations/zh_CN/core-api/idr.rst
@@ -0,0 +1,80 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: Documentation/core-api/idr.rst
+
+:翻译:
+
+ 周彬彬 Binbin Zhou <zhoubinbin@loongson.cn>
+
+:校译:
+
+ �延腾 Yanteng Si <siyanteng@loongson.cn>
+ �想� Wu Xiangcheng <bobwxc@email.cn>
+ 时奎亮 Alex Shi <alexs@kernel.org>
+
+======
+ID分�
+======
+
+:作者: Matthew Wilcox
+
+概述
+====
+
+�解决的一个常�问题是分�标识符（IDs）；它通常是标识事物的数字。比如包括文件�述
+符�进程ID�网络�议中的数�包标识符�SCSI标记和设备实例编�。IDR和IDA为这个问题
+�供了一个��的解决方案，以���个人都自创。IDR�供将ID映射到指针的能力，而IDA
+仅�供ID分�，因此内存效率更高。
+
+IDR接�已�被废弃，请使用 ``XArray`` 。
+
+IDR的用法
+=========
+
+首先�始化一个IDR，对于��分�的IDR使用DEFINE_IDR()，或者对于动�分�的IDR使用
+idr_init()。
+
+您�以调用idr_alloc()�分�一个未使用的ID。通过调用idr_find()查询与该ID相关的指针，
+并通过调用idr_remove()释放该ID。
+
+如果需�更改与一个ID相关�的指针，�以调用idr_replace()。这样�的一个常�原因是通
+过将 ``NULL`` 指针传递给分�函数��留ID；用�留的ID�始化对象，最�将�始化的对
+象�入IDR。
+
+一些用户需�分�大于 ``INT_MAX`` 的ID。到目�为止，所有这些用户都满足 ``UINT_MAX``
+的�制，他们使用idr_alloc_u32()。如果您需�超出u32的ID，我们将与您�作以满足您的
+需求。
+
+如果需�按顺�分�ID，�以使用idr_alloc_cyclic()。处�较大数�的ID时，IDR的效率会
+�低，所以使用这个函数会有一点代价。
+
+�对IDR使用的所有指针进行�作，您�以使用基于回调的idr_for_each()或迭代器样�的
+idr_for_each_entry()。您�能需�使用idr_for_each_entry_continue()�继续迭代。如果
+迭代器�符�您的需求，您也�以使用idr_get_next()。
+
+当使用完IDR�，您�以调用idr_destroy()�释放IDR�用的内存。这并�会释放IDR指�的
+对象；如果您想这样�，请使用其中一个迭代器�执行此�作。
+
+您�以使用idr_is_empty()�查看当�是�分�了任何ID。
+
+如果在从IDR分�一个新ID时需�带�，您�能需�传递一组�制性的GFP标志，但这�能导
+致IDR无法分�内存。为了解决该问题，您�以在获��之�调用idr_preload()，然�在分
+�之�调用idr_preload_end()。
+
+IDR�步的相关内容请�include/linux/idr.h文件中的“DOC: idr sync�。
+
+IDA的用法
+=========
+
+IDA的用法的相关内容请�lib/idr.c文件中的“DOC: IDA description�。
+
+函数和数�结构
+==============
+
+该API在以下内核代�中:
+
+include/linux/idr.h
+
+lib/idr.c
diff --git a/Documentation/translations/zh_CN/core-api/index.rst b/Documentation/translations/zh_CN/core-api/index.rst
index 8a94ad87465d..37756d240b5e 100644
--- a/Documentation/translations/zh_CN/core-api/index.rst
+++ b/Documentation/translations/zh_CN/core-api/index.rst
@@ -44,15 +44,15 @@
    assoc_array
    xarray
    rbtree
+   idr
+   circular-buffers
+   generic-radix-tree
+   packing
 
 Todolist:
 
 
 
-   idr
-   circular-buffers
-   generic-radix-tree
-   packing
    this_cpu_ops
    timekeeping
    errseq
diff --git a/Documentation/translations/zh_CN/core-api/packing.rst b/Documentation/translations/zh_CN/core-api/packing.rst
new file mode 100644
index 000000000000..c0aab3a349d0
--- /dev/null
+++ b/Documentation/translations/zh_CN/core-api/packing.rst
@@ -0,0 +1,160 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: Documentation/core-api/packing.rst
+
+:翻译:
+
+ 周彬彬 Binbin Zhou <zhoubinbin@loongson.cn>
+
+:校译:
+
+ �延腾 Yanteng Si <siyanteng@loongson.cn>
+ �想� Wu Xiangcheng <bobwxc@email.cn>
+ 时奎亮 Alex Shi <alexs@kernel.org>
+
+========================
+通用的�域打包和解包函数
+========================
+
+问题陈述
+--------
+
+使用硬件时，必须在几�与其交互的方法之间进行选择。
+
+�以将指针映射到在硬件设备的内存区上精心设计的结构体，并将其字段作为结构�员（�
+能声明为�域）访问。但是由于CPU和硬件设备之间潜在的字节顺��匹�，以这�方�编写
+代�会�低其�移�性。
+
+此外，必须密切注�将硬件文档中的寄存器定义转�为结构的�域索引。此外，一些硬件
+（通常是网络设备）倾�于以��任何��字边界（有时甚至是64�）的方�对其寄存器字
+段进行分组。这就造�了�得�在结构中定义寄存器字段的“高�和“低�部分的�便。
+
+结构域定义的更��的替代方法是通过移动适当数�的����所需的字段。但这�然�能
+防止字节顺��匹�，除�所有内存访问都是�字节执行的。此外，代�很容易�得�乱无
+章，�时�能会在所需的许多�移�作中丢失一些高层次的想法。
+
+许多驱动程�采用了�移的方法，然�试图用定制的���少�乱无章的东西，但更多的时
+候，这些�所采用的�径�旧妨�了代�真正的�移�性。
+
+解决方案
+--------
+
+该API涉�2个基本�作：
+
+  - 将一个CPU�使用的数字打包到内存缓冲区中（具有硬件约�/特殊性）。
+  - 将内存缓冲区（具有硬件约�/特殊性）解压缩为一个CPU�使用的数字。
+
+该API�供了对所述硬件约�和特殊性以�CPU字节�的抽象，因此这两者之间�能�匹�。
+
+这些API函数的基本�元是u64。从CPU的角度�看，�63总是�味�字节7的��移�7，尽管
+�是逻辑上的。问题是：我们将这个比特放在内存的什么�置？
+
+以下示例介�了打包u64字段的内存布局。打包缓冲区中的字节�移�始终默认为0，1...7。
+示例显示的是逻辑字节和�所在的�置。
+
+1. 通常情况下（无特殊性），我们会这样�：
+
+::
+
+  63 62 61 60 59 58 57 56 55 54 53 52 51 50 49 48 47 46 45 44 43 42 41 40 39 38 37 36 35 34 33 32
+  7                       6                       5                        4
+  31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16 15 14 13 12 11 10  9  8  7  6  5  4  3  2  1  0
+  3                       2                       1                        0
+
+也就是说，CPU�使用的u64的MSByte(7)�于内存�移�0处，而u64的LSByte(0)�于内存�移�7处。
+
+这对应于大多数人认为的“大端�，其中�i对应于数字2^i。这在代�注释中也称为“逻辑�符�。
+
+
+2. 如果设置了QUIRK_MSB_ON_THE_RIGHT，我们按如下方��作：
+
+::
+
+  56 57 58 59 60 61 62 63 48 49 50 51 52 53 54 55 40 41 42 43 44 45 46 47 32 33 34 35 36 37 38 39
+  7                       6                        5                       4
+  24 25 26 27 28 29 30 31 16 17 18 19 20 21 22 23  8  9 10 11 12 13 14 15  0  1  2  3  4  5  6  7
+  3                       2                        1                       0
+
+也就是说，QUIRK_MSB_ON_THE_RIGHT�会影�字节定�，但会�转字节内的��移�。
+
+
+3. 如果设置了QUIRK_LITTLE_ENDIAN，我们按如下方��作：
+
+::
+
+  39 38 37 36 35 34 33 32 47 46 45 44 43 42 41 40 55 54 53 52 51 50 49 48 63 62 61 60 59 58 57 56
+  4                       5                       6                       7
+  7  6  5  4  3  2  1  0  15 14 13 12 11 10  9  8 23 22 21 20 19 18 17 16 31 30 29 28 27 26 25 24
+  0                       1                       2                       3
+
+因此，QUIRK_LITTLE_ENDIAN�味�在内存区域内，�个4字节的字的�个字节都被放置在与
+该字的边界相比的镜��置。
+
+
+4. 如果设置了QUIRK_MSB_ON_THE_RIGHT和QUIRK_LITTLE_ENDIAN，我们这样�：
+
+::
+
+  32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63
+  4                       5                       6                       7
+  0  1  2  3  4  5  6  7  8   9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
+  0                       1                       2                       3
+
+
+5. 如果�设置了QUIRK_LSW32_IS_FIRST，我们这样�：
+
+::
+
+  31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16 15 14 13 12 11 10  9  8  7  6  5  4  3  2  1  0
+  3                       2                       1                        0
+  63 62 61 60 59 58 57 56 55 54 53 52 51 50 49 48 47 46 45 44 43 42 41 40 39 38 37 36 35 34 33 32
+  7                       6                       5                        4
+
+在这�情况下，8字节内存区域解释如下：�4字节对应最���的4字节的字，�4字节对应
+更��的4字节的字。
+
+6. 如果设置了QUIRK_LSW32_IS_FIRST和QUIRK_MSB_ON_THE_RIGHT，我们这样�：
+
+::
+
+  24 25 26 27 28 29 30 31 16 17 18 19 20 21 22 23  8  9 10 11 12 13 14 15  0  1  2  3  4  5  6  7
+  3                       2                        1                       0
+  56 57 58 59 60 61 62 63 48 49 50 51 52 53 54 55 40 41 42 43 44 45 46 47 32 33 34 35 36 37 38 39
+  7                       6                        5                       4
+
+
+7. 如果设置了QUIRK_LSW32_IS_FIRST和QUIRK_LITTLE_ENDIAN，则如下所示：
+
+::
+
+  7  6  5  4  3  2  1  0  15 14 13 12 11 10  9  8 23 22 21 20 19 18 17 16 31 30 29 28 27 26 25 24
+  0                       1                       2                       3
+  39 38 37 36 35 34 33 32 47 46 45 44 43 42 41 40 55 54 53 52 51 50 49 48 63 62 61 60 59 58 57 56
+  4                       5                       6                       7
+
+
+8. 如果设置了QUIRK_LSW32_IS_FIRST，QUIRK_LITTLE_ENDIAN和QUIRK_MSB_ON_THE_RIGHT，
+   则如下所示：
+
+::
+
+  0  1  2  3  4  5  6  7  8   9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
+  0                       1                       2                       3
+  32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63
+  4                       5                       6                       7
+
+
+我们总是认为我们的�移�好�没有特殊性，然�在访问内存区域之�翻译它们。
+
+预期用途
+--------
+
+选择使用该API的驱动程�首先需�确定上述3�quirk组�（共8�）中的哪一�与硬件文档
+中�述的相匹�。然�，他们应该�装packing()函数，创建一个新的xxx_packing()，使用
+适当的QUIRK_* one-hot �集��调用它。
+
+packing()函数返回一个int类型的错误�，以防止程�员使用�正确的API。这些错误预计�
+会在�行时�生，因此xxx_packing()返回void并简�地接�这些错误是��的。它�以选择
+转储栈或打�错误�述。
diff --git a/Documentation/translations/zh_CN/devicetree/changesets.rst b/Documentation/translations/zh_CN/devicetree/changesets.rst
new file mode 100644
index 000000000000..2ace05f3c377
--- /dev/null
+++ b/Documentation/translations/zh_CN/devicetree/changesets.rst
@@ -0,0 +1,37 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: Documentation/Devicetree/changesets.rst
+
+:翻译:
+
+ �延腾 Yanteng Si <siyanteng@loongson.cn>
+
+:校译:
+
+
+============
+设备树�更集
+============
+
+设备树�更集是一�方法，它�许人们以这样一�方�在实时树中使用�化，��么使用全部的
+�化，�么�使用。如果在使用�更集的过程中�生错误，那么树将被回滚到之�的状�。一个
+�更集也�以在使用�被删除。
+
+当一个�更集被使用时，所有的改�在�出OF_RECONFIG通知器之�被一次性使用到树上。这是
+为了让接收者在收到通知时看到一个完整的�一致的树的状�。
+
+一个�化集的顺�如下。
+
+1. of_changeset_init() - �始化一个�更集。
+
+2. 一些DT树�化的调用，of_changeset_attach_node(), of_changeset_detach_node(),
+   of_changeset_add_property(), of_changeset_remove_property,
+   of_changeset_update_property()�准备一组�更。此时�会对活动树�任何�更。所有
+   的�更�作都记录在of_changeset的 `entries` 列表中。
+
+3. of_changeset_apply() - 将�更使用到树上。�么整个�更集被使用，�么如果有错误，
+   树会被��到之�的状�。核心通过�确�正确的顺�。如果需�的�，�以使用一个解�的
+   __of_changeset_apply版本。
+
+如果一个�功使用的�更集需�被删除，�以用of_changeset_revert()�完�。
diff --git a/Documentation/translations/zh_CN/devicetree/dynamic-resolution-notes.rst b/Documentation/translations/zh_CN/devicetree/dynamic-resolution-notes.rst
new file mode 100644
index 000000000000..115190341305
--- /dev/null
+++ b/Documentation/translations/zh_CN/devicetree/dynamic-resolution-notes.rst
@@ -0,0 +1,31 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: Documentation/Devicetree/dynamic-resolution-notes.rst
+
+:翻译:
+
+ �延腾 Yanteng Si <siyanteng@loongson.cn>
+
+:校译:
+
+========================
+Devicetree动�解�器说明
+========================
+
+本文�述了内核内DeviceTree解�器的实现，它�于drivers/of/resolver.c中。
+
+解�器如何工作？
+----------------
+
+解�器被赋予一个任�的树作为输入，该树用适当的dtc选项编译，并有一个/plugin/标签。这就产
+生了适当的__fixups__和__local_fixups__节点。
+
+解�器�次通过以下步骤工作:
+
+1. 从实时树中获�最大的设备树phandle值 + 1.
+2. 调整树的所有本地 phandles，以解决这个�。
+3. 使用 __local__fixups__ 节点信�以相�的�调整所有本地引用。
+4. 对于__fixups__节点中的�个属性，找到它在实时树中引用的节点。这是用�标记该节点的标签。
+5. 检索fixup的目标的phandle。
+6. 对于属性中的�个fixup，找到节点:属性:�移的�置，并用phandle值替�它。
diff --git a/Documentation/translations/zh_CN/devicetree/index.rst b/Documentation/translations/zh_CN/devicetree/index.rst
index 3fc355fe0037..7451dbfdd3e5 100644
--- a/Documentation/translations/zh_CN/devicetree/index.rst
+++ b/Documentation/translations/zh_CN/devicetree/index.rst
@@ -24,21 +24,16 @@ Open Firmware 和 Devicetree
 
    usage-model
    of_unittest
-
-Todolist:
-
-*   kernel-api
+   kernel-api
 
 Devicetree Overlays
 ===================
 .. toctree::
    :maxdepth: 1
 
-Todolist:
-
-*   changesets
-*   dynamic-resolution-notes
-*   overlay-notes
+   changesets
+   dynamic-resolution-notes
+   overlay-notes
 
 Devicetree Bindings
 ===================
diff --git a/Documentation/translations/zh_CN/devicetree/kernel-api.rst b/Documentation/translations/zh_CN/devicetree/kernel-api.rst
new file mode 100644
index 000000000000..6aa3b685494e
--- /dev/null
+++ b/Documentation/translations/zh_CN/devicetree/kernel-api.rst
@@ -0,0 +1,58 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: Documentation/Devicetree/kernel-api.rst
+
+:翻译:
+
+ �延腾 Yanteng Si <siyanteng@loongson.cn>
+
+:校译:
+
+
+=================
+内核中的设备树API
+=================
+
+核心函数
+--------
+
+该API在以下内核代�中:
+
+drivers/of/base.c
+
+include/linux/of.h
+
+drivers/of/property.c
+
+include/linux/of_graph.h
+
+drivers/of/address.c
+
+drivers/of/irq.c
+
+drivers/of/fdt.c
+
+驱动模型函数
+------------
+
+该API在以下内核代�中:
+
+include/linux/of_device.h
+
+drivers/of/device.c
+
+include/linux/of_platform.h
+
+drivers/of/platform.c
+
+覆盖和动�DT函数
+----------------
+
+该API在以下内核代�中:
+
+drivers/of/resolver.c
+
+drivers/of/dynamic.c
+
+drivers/of/overlay.c
diff --git a/Documentation/translations/zh_CN/devicetree/overlay-notes.rst b/Documentation/translations/zh_CN/devicetree/overlay-notes.rst
new file mode 100644
index 000000000000..1bd482cb0a1b
--- /dev/null
+++ b/Documentation/translations/zh_CN/devicetree/overlay-notes.rst
@@ -0,0 +1,140 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: Documentation/Devicetree/overlay-notes.rst
+
+:翻译:
+
+ �延腾 Yanteng Si <siyanteng@loongson.cn>
+
+:校译:
+
+==============
+设备树覆盖说明
+==============
+
+本文档�述了drivers/of/overlay.c中的内核内设备树覆盖功能的实现，是
+Documentation/devicetree/dynamic-resolution-notes.rst[1]的�套文档。
+
+覆盖如何工作
+------------
+
+设备树覆盖的目的是修改内核的实时树，并使修改以�映�化的方�影�内核的状�。
+由于内核主�处�的是设备，任何新的设备节点如果导致一个活动的设备，就应该创建它，
+而如果设备节点被�用或被全部删除，�影�的设备应该被�消注册。
+
+让我们举个例�，我们有一个foo�，它的基本树形图如下::
+
+    ---- foo.dts ---------------------------------------------------------------
+	/* FOO平� */
+	/dts-v1/;
+	/ {
+		compatible = "corp,foo";
+
+		/* 共享的资� */
+		res: res {
+		};
+
+		/* 芯片上的外围设备 */
+		ocp: ocp {
+			/* 总是被实例化的外围设备 */
+			peripheral1 { ... };
+		};
+	};
+    ---- foo.dts ---------------------------------------------------------------
+
+覆盖bar.dts,
+::
+
+    ---- bar.dts - 按标签覆盖目标�置 ----------------------------
+	/dts-v1/;
+	/�件/;
+	&ocp {
+		/* bar外围 */
+		bar {
+			compatible = "corp,bar";
+			... /* ��属性和�节点 */
+		};
+	};
+    ---- bar.dts ---------------------------------------------------------------
+
+当加载（并按照[1]中�述的方�解决）时，应该产生foo+bar.dts::
+
+    ---- foo+bar.dts -----------------------------------------------------------
+	/* FOO平� + bar外围 */
+	/ {
+		compatible = "corp,foo";
+
+		/* 共享资� */
+		res: res {
+		};
+
+		/* 芯片上的外围设备 */
+		ocp: ocp {
+			/* 总是被实例化的外围设备 */
+			peripheral1 { ... };
+
+			/* bar外围 */
+			bar {
+				compatible = "corp,bar";
+				... /* ��属性和�节点 */
+			};
+		};
+	};
+    ---- foo+bar.dts -----------------------------------------------------------
+
+作为覆盖的结果，已�创建了一个新的设备节点（bar），因此将注册一个bar平�设备，
+如果加载了匹�的设备驱动程�，将按预期创建设备。
+
+如果基础DT�是用-@选项编译的，那么“&ocp�标签将�能用于将覆盖节点解�到基础
+DT中的适当�置。在这�情况下，�以�供目标路径。通过标签的目标�置的语法是比
+较好的，因为�管标签在DT中出现在哪里，覆盖都�以被应用到任何包�标签的基础DT上。
+
+上�的bar.dts例�被修改为使用目标路径语法，�为::
+
+    ---- bar.dts - 通过明确的路径覆盖目标�置 --------------------
+	/dts-v1/;
+	/�件/;
+	&{/ocp} {
+		/* bar外围 */
+		bar {
+			compatible = "corp,bar";
+			... /* ��外围设备和�节点 */
+		}
+	};
+    ---- bar.dts ---------------------------------------------------------------
+
+
+内核中关于覆盖的API
+-------------------
+
+该API相当容易使用。
+
+1) 调用of_overlay_fdt_apply()�创建和应用一个覆盖的�更集。返回值是一个
+   错误或一个识别这个覆盖的cookie。
+
+2) 调用of_overlay_remove()�删除和清�先�通过调用of_overlay_fdt_apply()
+   而创建的覆盖�更集。��许删除一个被�一个覆盖的覆盖�化集。
+
+最�，如果你需�一次性删除所有的覆盖，�需调用of_overlay_remove_all()，
+它将以正确的顺�删除�一个覆盖。
+
+你�以选择注册在覆盖�作中被调用的通知器。详�
+of_overlay_notifier_register/unregister和enum of_overlay_notify_action。
+
+OF_OVERLAY_PRE_APPLY�OF_OVERLAY_POST_APPLY或OF_OVERLAY_PRE_REMOVE
+的通知器回调�以存储指�覆盖层中的设备树节点或其内容的指针，但这些指针�能�
+续到OF_OVERLAY_POST_REMOVE的通知器回调。在OF_OVERLAY_POST_REMOVE通
+知器被调用�，包�覆盖层的内存将被kfree()ed。请注�，�使OF_OVERLAY_POST_REMOVE
+的通知器返回错误，内存也会被kfree()ed。
+
+drivers/of/dynamic.c中的�更集通知器是第二�类型的通知器，�以通过应用或移除
+覆盖层�触�。这些通知器��许在覆盖层或其内容中存储指�设备树节点的指针。当包�
+覆盖层的内存因移除覆盖层而被释放时，覆盖层代�并�能防止这类指针�然有效。
+
+任何其他�留指�覆盖层节点或数�的指针的代�都被认为是一个错误，因为在移除覆盖层
+�，该指针将指�已释放的内存。
+
+覆盖层的用户必须特别注�系统上�生的整体�作，以确�其他内核代���留任何指�覆
+盖层节点或数�的指针。任何无�中使用这�指针的例�是，如果一个驱动或�系统模�在
+应用了覆盖�被加载，并且该驱动或�系统扫�了整个设备树或其大部分，包括覆盖节点。
diff --git a/Documentation/translations/zh_CN/driver-api/gpio/index.rst b/Documentation/translations/zh_CN/driver-api/gpio/index.rst
new file mode 100644
index 000000000000..9ab64e94aced
--- /dev/null
+++ b/Documentation/translations/zh_CN/driver-api/gpio/index.rst
@@ -0,0 +1,69 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+.. include:: ../../disclaimer-zh_CN.rst
+
+:Original: Documentation/driver-api/gpio/index.rst
+
+:翻译:
+
+ �延腾 Yanteng Si <siyanteng@loongson.cn>
+
+:校译:
+
+=======================
+通用型输入/输出（GPIO）
+=======================
+
+目录:
+
+.. toctree::
+   :maxdepth: 2
+
+   legacy
+
+Todolist:
+
+*   intro
+*   using-gpio
+*   driver
+*   consumer
+*   board
+*   drivers-on-gpio
+*   bt8xxgpio
+
+核心
+====
+
+该API在以下内核代�中:
+
+include/linux/gpio/driver.h
+
+drivers/gpio/gpiolib.c
+
+ACPI支�
+========
+
+该API在以下内核代�中:
+
+drivers/gpio/gpiolib-acpi.c
+
+设备树支�
+==========
+
+该API在以下内核代�中:
+
+drivers/gpio/gpiolib-of.c
+
+设备管�支�
+============
+
+该API在以下内核代�中:
+
+drivers/gpio/gpiolib-devres.c
+
+sysfs帮助（函数）
+=================
+
+该API在以下内核代�中:
+
+drivers/gpio/gpiolib-sysfs.c
diff --git a/Documentation/translations/zh_CN/gpio.txt b/Documentation/translations/zh_CN/driver-api/gpio/legacy.rst
index a23ee14fc927..6399521d0548 100644
--- a/Documentation/translations/zh_CN/gpio.txt
+++ b/Documentation/translations/zh_CN/driver-api/gpio/legacy.rst
@@ -1,39 +1,28 @@
-Chinese translated version of Documentation/admin-guide/gpio
+.. SPDX-License-Identifier: GPL-2.0
 
-If you have any comment or update to the content, please contact the
-original document maintainer directly.  However, if you have a problem
-communicating in English you can also ask the Chinese maintainer for
-help.  Contact the Chinese maintainer if this translation is outdated
-or if there is a problem with the translation.
+.. include:: ../../disclaimer-zh_CN.rst
 
-Maintainer: Grant Likely <grant.likely@secretlab.ca>
-		Linus Walleij <linus.walleij@linaro.org>
-Chinese maintainer: Fu Wei <tekkamanninja@gmail.com>
----------------------------------------------------------------------
-Documentation/admin-guide/gpio 的中文翻译
+:Original: Documentation/driver-api/gpio/legacy.rst
 
-如果想评论或更新本文的内容，请直接�系原文档的维护者。如果你使用英文
-交�有困难的�，也�以�中文版维护者求助。如果本翻译更新��时或者翻
-译存在问题，请�系中文版维护者。
-英文版维护者： Grant Likely <grant.likely@secretlab.ca>
-		Linus Walleij <linus.walleij@linaro.org>
-中文版维护者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
-中文版翻译者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
-中文版校译者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
+:翻译:
 
+ 傅炜 Fu Wei <tekkamanninja@gmail.com>
+ �延腾 Yanteng Si <siyanteng@loongson.cn>
 
-以下为正文
----------------------------------------------------------------------
-GPIO 接�
+:校译:
 
-本文档�供了一个在Linux下访问GPIO的公约概述。
+
+传统GPIO接�
+============
+
+本文档概述了Linux下的GPIO访问公约。
 
 这些函数以 gpio_* 作为�缀。其他的函数��许使用这样的�缀或相关的
 __gpio_* �缀。
 
 
-什么是GPIO?
-==========
+什么是GPIO？
+============
 "通用输入/输出�"(GPIO)是一个�活的由软件控制的数字信�。他们�
 由多�芯片�供,且对于从事嵌入�和定制硬件的 Linux 开�者�说是
 比较熟悉。�个GPIO 都代表一个连接到特定引脚或�栅阵列(BGA)�装中
@@ -99,6 +88,7 @@ GPIO 公约
 
 标识 GPIO
 ---------
+
 GPIO 是通过无符�整型�标识的,范围是 0 到 MAX_INT。�留“负�数
 用于其他目的,例如标识信�“在这个��上��用�或指示错误。未接触底层
 硬件的代�会忽略这些整数。
@@ -115,7 +105,7 @@ FPGA 的特定æ�¿å­�上使用 80-95。编å�·ä¸�一定è¦�è¿žç»­,那些平å�°ä¸­ï¼
 
 如果你��始化一个带有无效 GPIO 编�的结构体,�以使用一些负编�
 (如"-EINVAL")，那将使其永远�会是有效。�测试这样一个结构体中的编�
-是�关�一个 GPIO，你�使用以下断言:
+是�关�一个 GPIO，你�使用以下断言::
 
 	int gpio_is_valid(int number);
 
@@ -128,11 +118,12 @@ FPGA 的特定æ�¿å­�上使用 80-95。编å�·ä¸�一定è¦�è¿žç»­,那些平å�°ä¸­ï¼
 
 使用 GPIO
 ---------
+
 对于一个 GPIO，系统应该�的第一件事情就是通过 gpio_request()
 函数分�它，�下文。
 
 接下�是设置I/O方�，这通常是在�级�动代�中为所使用的 GPIO 设置
-platform_device 时完�。
+platform_device 时完�::
 
 	/* 设置为输入或输出, 返回 0 或负的错误代� */
 	int gpio_direction_input(unsigned gpio);
@@ -157,12 +148,13 @@ get/set(获�/设置)函数调用没法返回错误,且有�能是�置错误
 
 
 访问自旋�安全的 GPIO
--------------------
+---------------------
+
 大多数 GPIO 控制器�以通过内存读/写指令�访问。这些指令�会休眠,�以
 安全地在硬(�线程)中断例程和类似的上下文中完�。
 
 对于那些用 gpio_cansleep()测试总是返回失败的 GPIO(�下文)，使用
-以下的函数访问:
+以下的函数访问::
 
 	/* GPIO 输入:返回零或�零 */
 	int gpio_get_value(unsigned gpio);
@@ -188,17 +180,18 @@ GPIO值是布尔值，零表示低电平，é�žé›¶è¡¨ç¤ºé«˜ç”µå¹³ã€‚当读å�–一ä
 
 
 访问�能休眠的 GPIO
------------------
+-------------------
+
 �些 GPIO 控制器必须通过基于总线(如 I2C 或 SPI)的消�访问。读或写这些
 GPIO 值的命令需�等待其信�排到队首���命令，�获得其�馈。期间需�
 休眠，这�能在 IRQ 例程(中断上下文)中执行。
 
 支�此类 GPIO 的平�通过以下函数返回�零值�区分出这� GPIO。(此函数需�
-一个之�通过 gpio_request 分�到的有效 GPIO 编�):
+一个之�通过 gpio_request 分�到的有效 GPIO 编�)::
 
 	int gpio_cansleep(unsigned gpio);
 
-为了访问这� GPIO,内核定义了一套��的函数:
+为了访问这� GPIO,内核定义了一套��的函数::
 
 	/* GPIO 输入:返回零或�零 ,�能会休眠 */
 	int gpio_get_value_cansleep(unsigned gpio);
@@ -214,25 +207,26 @@ GPIO 值的命令需�等待其信�排到队首���命令，�获得其
 事实，这些处�例程实际上和自旋�安全的函数是一样的。
 
 ** 除此之外 ** 调用设置和�置此类 GPIO 的函数也必须在�许休眠的上下文中，
-因为它们�能也需�访问 GPIO 控制器芯片: (这些设置函数通常在�级�动代�或者
-驱动探测/断开代�中，所以这是一个容易满足的约��件。)
+因为它们�能也需�访问 GPIO 控制器芯片 (这些设置函数通常在�级�动代�或者
+驱动探测/断开代�中，所以这是一个容易满足的约��件。) ::
 
-	gpio_direction_input()
-	gpio_direction_output()
-	gpio_request()
+                gpio_direction_input()
+                gpio_direction_output()
+                gpio_request()
 
-## 	gpio_request_one()
-##	gpio_request_array()
-## 	gpio_free_array()
+        ## 	gpio_request_one()
+        ##	gpio_request_array()
+        ## 	gpio_free_array()
 
-	gpio_free()
-	gpio_set_debounce()
+                gpio_free()
+                gpio_set_debounce()
 
 
 
 声明和释放 GPIO
-----------------------------
-为了有助于�获系统�置错误,定义了两个函数。
+----------------
+
+为了有助于�获系统�置错误,定义了两个函数::
 
 	/* 申请 GPIO, 返回 0 或负的错误代�.
 	 * �空标签�能有助于诊断.
@@ -256,9 +250,9 @@ GPIO 值的命令需�等待其信�排到队首���命令，�获得其
 �些平��能也使用 GPIO 作为电�管�激活信�(例如通过关闭未使用芯片区和
 简�地关闭未使用时钟)。
 
-对于 GPIO 使用 pinctrl �系统已知的引脚，�系统应该被告知其使用情况；
+对于 GPIO 使用引脚控制�系统已知的引脚，�系统应该被告知其使用情况；
 一个 gpiolib 驱动的 .request()�作应调用 pinctrl_gpio_request()，
-而 gpiolib 驱动的 .free()�作应调用 pinctrl_gpio_free()。pinctrl
+而 gpiolib 驱动的 .free()�作应调用 pinctrl_gpio_free()。引脚控制
 �系统�许 pinctrl_gpio_request()在�个引脚或引脚组以�用形�“属于�
 一个设备时都�功返回。
 
@@ -270,7 +264,7 @@ GPIO 值的命令需�等待其信�排到队首���命令，�获得其
 
 �些平��许部分或所有 GPIO 信�使用��的引脚。类似的，GPIO 或引脚的
 其他方�也需��置，如上拉/下拉。平�软件应该在对这些 GPIO 调用
-gpio_request()�将这类细节�置好，例如使用 pinctrl �系统的映射表，
+gpio_request()�将这类细节�置好，例如使用引脚控制�系统的映射表，
 使得 GPIO 的用户无须关注这些细节。
 
 还有一个值得注�的是在释放 GPIO �，你必须�止使用它。
@@ -278,7 +272,7 @@ gpio_request()�将这类细节�置好，例如使用 pinctrl �系统的映
 
 注�:申请一个 GPIO 并没有以任何方��置它，��过标识那个 GPIO 处于使用
 状�。必须有�外的代��处�引脚�置(如控制 GPIO 使用的引脚�上拉/下拉)。
-考虑到大多数情况下声明 GPIO 之�就会立��置它们,所以定义了以下三个辅助函数:
+考虑到大多数情况下声明 GPIO 之�就会立��置它们,所以定义了以下三个辅助函数::
 
 	/* 申请一个 GPIO 信�, �时通过特定的'flags'�始化�置,
 	 * 其他和 gpio_request()的�数和返回值相�
@@ -326,7 +320,7 @@ gpio_request()�将这类细节�置好，例如使用 pinctrl �系统的映
 将�这些标志�能扩展到支�更多的属性。
 
 更进一步,为了更简�地声明/释放多个 GPIO,'struct gpio'被引进��装所有
-这三个领域:
+这三个领域::
 
 	struct gpio {
 		unsigned	gpio;
@@ -334,7 +328,7 @@ gpio_request()�将这类细节�置好，例如使用 pinctrl �系统的映
 		const char	*label;
 	};
 
-一个典型的用例:
+一个典型的用例::
 
 	static struct gpio leds_gpios[] = {
 		{ 32, GPIOF_OUT_INIT_HIGH, "Power LED" }, /* 默认开� */
@@ -356,9 +350,10 @@ gpio_request()�将这类细节�置好，例如使用 pinctrl �系统的映
 
 
 GPIO 映射到 IRQ
---------------------
+----------------
+
 GPIO 编�是无符�整数;IRQ 编�也是。这些构�了两个逻辑上��的命�空间
-(GPIO 0 �一定使用 IRQ 0)。你�以通过以下函数在它们之间实现映射:
+(GPIO 0 �一定使用 IRQ 0)。你�以通过以下函数在它们之间实现映射::
 
 	/* 映射 GPIO 编�到 IRQ 编� */
 	int gpio_to_irq(unsigned gpio);
@@ -384,7 +379,8 @@ irq_to_gpio()返回的é�žé”™è¯¯å€¼å¤§å¤šæ•°é€šå¸¸å�¯ä»¥è¢« gpio_get_value()所ä½
 
 
 模拟开�信�
-----------------------------
+------------
+
 有时在�有低电平信�作为实际驱动结果(译者注:多个输出连接于一点，逻辑电平
 结果为所有输出的逻辑与)的时候,共享的信�线需�使用“开��信�。(该术语
 适用于 CMOS 管；而 TTL 用“集电�开路�。)一个上拉电阻使信�为高电平。这
@@ -408,9 +404,44 @@ irq_to_gpio()返回的é�žé”™è¯¯å€¼å¤§å¤šæ•°é€šå¸¸å�¯ä»¥è¢« gpio_get_value()所ä½
 这�一定是错误的。一个常�的例�就是 I2C 时钟的延长：一个需�较慢时钟的
 从设备延迟 SCK 的上�沿，而 I2C 主设备相应地调整其信�传输速率。
 
+GPIO控制器和引脚控制�系统
+--------------------------
+
+SOC上的GPIO控制器�能与引脚控制�系统紧密结�，�引脚�以与�选的gpio功
+能一起被其他功能使用。我们已�涵盖了这样的情况，例如一个GPIO控制器需��
+留一个引脚或通过调用以下任何一个引脚�设置其方�::
+
+  pinctrl_gpio_request()
+  pinctrl_gpio_free()
+  pinctrl_gpio_direction_input()
+  pinctrl_gpio_direction_output()
+
+但是，引脚控制�系统是如何将GPIO��（这是一个全局事项）与�个引脚控制器
+上的�个引脚交�关�的？
+
+这是通过注册引脚的“范围��实现的，这基本上是交��考表。这些�述是在
+Documentation/driver-api/pin-control.rst
+
+虽然引脚分�完全由引脚控制�系统管�，但gpio（在gpiolib下）�由gpio驱动
+维护。�能�生的情况是，SoC中的��引脚范围由��的gpio驱动器管�。
+
+这使得在调用 "pinctrl_gpio_request" 之�，让gpio驱动�pin ctrl�系
+统宣布它们的引脚范围是��的，以便在使用任何gpio之��求引脚控制�系统准
+备相应的引脚。
+
+为此，gpio控制器�以用引脚控制�系统注册其引脚范围。目�有两�方法：有或
+无DT。
+
+关于对DT的支�，请�考 Documentation/devicetree/bindings/gpio/gpio.txt.
+
+对于�DT支�，用户�以用适当的�数调用gpiochip_add_pin_range()，将一
+系列的gpio引脚注册到引脚控制驱动上。为此，必须将引脚控制设备的�称字符串
+作为�数之一传给这个程�。
+
+
+这些公约忽略了什么？
+====================
 
-这些公约忽略了什么?
-================
 这些公约忽略的最大一件事就是引脚�用，因为这属于高度芯片特定的属性且
 没有�移�性。�个平��能�需�明确的�用信�；有的对于任�给定的引脚
 �能�有两个功能选项；有的�能�个引脚有八个功能选项；有的�能�以将
@@ -433,8 +464,9 @@ Linux 的系统。)
 当�，动�定义 GPIO 并�是标准的，例如作为�置一个带有�些 GPIO 扩展器的
 附加电路�的副作用。
 
-GPIO 实现者的框架 (�选)
-=====================
+GPIO 实现者的框架（�选）
+=========================
+
 ���到了，有一个�选的实现框架，让平�使用相�的编程接�，更加简�地支�
 ���类的 GPIO 控制器。这个框架称为"gpiolib"。
 
@@ -444,15 +476,16 @@ GPIO 实现者的框架 (�选)
 
 
 控制器驱动: gpio_chip
--------------------
+---------------------
+
 在框架中�个 GPIO 控制器都包装为一个 "struct gpio_chip"，他包�了
 该类型的�个控制器的常用信�:
 
- - 设置 GPIO 方�的方法
- - 用于访问 GPIO 值的方法
- - 告知调用其方法是��能休眠的标志
- - �选的 debugfs 信�导出方法 (显示类似上拉�置一样的�外状�)
- - 诊断标签
+	- 设置 GPIO 方�的方法
+	- 用于访问 GPIO 值的方法
+	- 告知调用其方法是��能休眠的标志
+	- �选的 debugfs 信�导出方法 (显示类似上拉�置一样的�外状�)
+	- 诊断标签
 
 也包�了�自 device.platform_data 的�个实例的数�：它第一个 GPIO 的
 编�和它�用的 GPIO 的数�。
@@ -471,7 +504,8 @@ GPIO 实现者的框架 (�选)
 
 
 平�支�
--------
+--------
+
 为了支�这个框架，一个平�的 Kconfig 文件将会 "select"(选择)
 ARCH_REQUIRE_GPIOLIB 或 ARCH_WANT_OPTIONAL_GPIOLIB，并让它的
 <asm/gpio.h> 包� <asm-generic/gpio.h>，�时定义三个方法:
@@ -489,7 +523,7 @@ ARCH_WANT_OPTIONAL_GPIOLIB �味� gpiolib 核心默认关闭,且用户�以
 如果这些选项都没被选择,该平�就�通过 GPIO-lib 支� GPIO,且代���以
 被用户使能。
 
-以下这些方法的实现�以直接使用框架代�,并总是通过 gpio_chip 调度:
+以下这些方法的实现�以直接使用框架代�,并总是通过 gpio_chip 调度::
 
   #define gpio_get_value	__gpio_get_value
   #define gpio_set_value	__gpio_set_value
@@ -508,7 +542,8 @@ arch_initcall()或者更早的地方集�进平��始化代�，使这些 G
 且他们通常�以作为 IRQ 使用。
 
 �级支�
--------
+--------
+
 对于外部 GPIO 控制器(例如 I2C 或 SPI 扩展器�专用芯片�多功能器件�FPGA
 或 CPLD)，大多数常用�级特定代�都�以注册控制器设备，并��他们的驱动知�
 gpiochip_add()所使用的 GPIO 编�。他们的起始编�通常跟在平�特定的 GPIO
@@ -526,8 +561,9 @@ GPIO �以工作之���被注册。解决这类�赖的的一�方法是
 设备��无效时移除它们。
 
 
-用户空间的 Sysfs 接�(�选)
-========================
+用户空间的 Sysfs 接�（�选）
+=============================
+
 使用“gpiolib�实现框架的平��以选择�置一个 GPIO 的 sysfs 用户接�。
 这��于 debugfs 接�，因为它�供的是对 GPIO方�和值的控制，而��显示
 一个GPIO 的状�摘�。此外,它�以出现在没有调试支�的产�级系统中。
@@ -548,6 +584,7 @@ GPIO �以工作之���被注册。解决这类�赖的的一�方法是
 
 Sysfs 中的路径
 --------------
+
 在/sys/class/gpio 中有 3 类入�:
 
    -	用于在用户空间控制 GPIO 的控制接�;
@@ -625,8 +662,9 @@ GPIO 控制器的路径类似 /sys/class/gpio/gpiochip42/ (对于从#42 GPIO
 
 
 从内核代�中导出
--------------
-内核代��以明确地管�那些已通过 gpio_request()申请的 GPIO 的导出:
+----------------
+
+内核代��以明确地管�那些已通过 gpio_request()申请的 GPIO 的导出::
 
 	/* 导出 GPIO 到用户空间 */
 	int gpio_export(unsigned gpio, bool direction_may_change);
@@ -648,3 +686,9 @@ GPIO 控制器的路径类似 /sys/class/gpio/gpiochip42/ (对于从#42 GPIO
 在 GPIO 被导出之�，gpio_export_link()�许在 sysfs 文件系统的任何地方
 创建一个到这个 GPIO sysfs 节点的符�链接。这样驱动就�以通过一个�述性的
 �字，在 sysfs 中他们所拥有的设备下�供一个(到这个 GPIO sysfs 节点的)接�。
+
+
+API�考
+=======
+
+本节中列出的函数已被废弃。在新的代�中应该使用基于GPIO�述符的API。
diff --git a/Documentation/translations/zh_CN/driver-api/index.rst b/Documentation/translations/zh_CN/driver-api/index.rst
new file mode 100644
index 000000000000..ba354e1f4e6d
--- /dev/null
+++ b/Documentation/translations/zh_CN/driver-api/index.rst
@@ -0,0 +1,132 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: Documentation/driver-api/index.rst
+
+:翻译:
+
+ �延腾 Yanteng Si <siyanteng@loongson.cn>
+
+:校译:
+
+========================
+Linux驱动实现者的API指�
+========================
+
+内核�供了���样的接��支�设备驱动的开�。这份文档�是对其中一些接�进行了
+一定程度的整�——希望��时间的推移，它能�得更好��用的�节�以在下�看到。
+
+.. class:: toc-title
+
+	   目录列表：
+
+.. toctree::
+   :maxdepth: 2
+
+   gpio/index
+   io_ordering
+
+Todolist:
+
+*   driver-model/index
+*   basics
+*   infrastructure
+*   ioctl
+*   early-userspace/index
+*   pm/index
+*   clk
+*   device-io
+*   dma-buf
+*   device_link
+*   component
+*   message-based
+*   infiniband
+*   aperture
+*   frame-buffer
+*   regulator
+*   reset
+*   iio/index
+*   input
+*   usb/index
+*   firewire
+*   pci/index
+*   cxl/index
+*   spi
+*   i2c
+*   ipmb
+*   ipmi
+*   i3c/index
+*   interconnect
+*   devfreq
+*   hsi
+*   edac
+*   scsi
+*   libata
+*   target
+*   mailbox
+*   mtdnand
+*   miscellaneous
+*   mei/index
+*   mtd/index
+*   mmc/index
+*   nvdimm/index
+*   w1
+*   rapidio/index
+*   s390-drivers
+*   vme
+*   80211/index
+*   uio-howto
+*   firmware/index
+*   pin-control
+*   md/index
+*   media/index
+*   misc_devices
+*   nfc/index
+*   dmaengine/index
+*   slimbus
+*   soundwire/index
+*   thermal/index
+*   fpga/index
+*   acpi/index
+*   auxiliary_bus
+*   backlight/lp855x-driver.rst
+*   connector
+*   console
+*   dcdbas
+*   eisa
+*   isa
+*   isapnp
+*   io-mapping
+*   generic-counter
+*   memory-devices/index
+*   men-chameleon-bus
+*   ntb
+*   nvmem
+*   parport-lowlevel
+*   pps
+*   ptp
+*   phy/index
+*   pwm
+*   pldmfw/index
+*   rfkill
+*   serial/index
+*   sm501
+*   surface_aggregator/index
+*   switchtec
+*   sync_file
+*   tty/index
+*   vfio-mediated-device
+*   vfio
+*   vfio-pci-device-specific-driver-acceptance
+*   xilinx/index
+*   xillybus
+*   zorro
+*   hte/index
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`
diff --git a/Documentation/translations/zh_CN/driver-api/io_ordering.rst b/Documentation/translations/zh_CN/driver-api/io_ordering.rst
new file mode 100644
index 000000000000..4dbfa4ce92a0
--- /dev/null
+++ b/Documentation/translations/zh_CN/driver-api/io_ordering.rst
@@ -0,0 +1,60 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: Documentation/driver-api/io_ordering.rst
+
+:翻译:
+
+ 林永� Lin Yongting <linyongting@gmail.com>
+ �延腾 Yanteng Si <siyanteng@loongson.cn>
+
+:校译:
+
+===========================
+对内存映射地�的I/O写入排�
+===========================
+
+在�些平�上，所谓的内存映射I/O是弱顺�。在这些平�上，驱动开�者有责任
+��I/O内存映射地�的写�作按程�图�的顺�达到设备。通常读�一个“安全�
+设备寄存器或桥寄存器，触�IO芯片清刷未处�的写�作到达设备��处�读�作，
+而达到��目的。驱动程�通常在spinlock�护的临界区退出之�使用这�技术。
+这也�以����的写�作�在��的写�作之�到达设备（这�常类似于内存
+�障�作，mb()，�过仅适用于I/O）。
+
+�设一个设备驱动程的具体例�::
+
+                ...
+        CPU A:  spin_lock_irqsave(&dev_lock, flags)
+        CPU A:  val = readl(my_status);
+        CPU A:  ...
+        CPU A:  writel(newval, ring_ptr);
+        CPU A:  spin_unlock_irqrestore(&dev_lock, flags)
+                ...
+        CPU B:  spin_lock_irqsave(&dev_lock, flags)
+        CPU B:  val = readl(my_status);
+        CPU B:  ...
+        CPU B:  writel(newval2, ring_ptr);
+        CPU B:  spin_unlock_irqrestore(&dev_lock, flags)
+                ...
+
+上述例�中，设备�能会先接收到newval2的值，然�接收到newval的值，问题就
+�生了。�过很容易通过下�方法�修�::
+
+                ...
+        CPU A:  spin_lock_irqsave(&dev_lock, flags)
+        CPU A:  val = readl(my_status);
+        CPU A:  ...
+        CPU A:  writel(newval, ring_ptr);
+        CPU A:  (void)readl(safe_register); /* �置寄存器？*/
+        CPU A:  spin_unlock_irqrestore(&dev_lock, flags)
+                ...
+        CPU B:  spin_lock_irqsave(&dev_lock, flags)
+        CPU B:  val = readl(my_status);
+        CPU B:  ...
+        CPU B:  writel(newval2, ring_ptr);
+        CPU B:  (void)readl(safe_register); /* �置寄存器？*/
+        CPU B:  spin_unlock_irqrestore(&dev_lock, flags)
+
+在解决方案中，读�safe_register寄存器，触�IO芯片清刷未处�的写�作，
+�处���的读�作，防止引�数��一致问题。
diff --git a/Documentation/translations/zh_CN/index.rst b/Documentation/translations/zh_CN/index.rst
index bf85baca8b3e..2fc60e60feb4 100644
--- a/Documentation/translations/zh_CN/index.rst
+++ b/Documentation/translations/zh_CN/index.rst
@@ -108,6 +108,7 @@ TODOList:
    :maxdepth: 2
 
    core-api/index
+   driver-api/index
    locking/index
    accounting/index
    cpu-freq/index
@@ -120,10 +121,10 @@ TODOList:
    scheduler/index
    mm/index
    peci/index
+   PCI/index
 
 TODOList:
 
-* driver-api/index
 * block/index
 * cdrom/index
 * ide/index
@@ -148,7 +149,6 @@ TODOList:
 * crypto/index
 * bpf/index
 * usb/index
-* PCI/index
 * scsi/index
 * misc-devices/index
 * mhi/index
diff --git a/Documentation/translations/zh_CN/io_ordering.txt b/Documentation/translations/zh_CN/io_ordering.txt
deleted file mode 100644
index 7bb3086227ae..000000000000
--- a/Documentation/translations/zh_CN/io_ordering.txt
+++ /dev/null
@@ -1,67 +0,0 @@
-Chinese translated version of Documentation/driver-api/io_ordering.rst
-
-If you have any comment or update to the content, please contact the
-original document maintainer directly.  However, if you have a problem
-communicating in English you can also ask the Chinese maintainer for
-help.  Contact the Chinese maintainer if this translation is outdated
-or if there is a problem with the translation.
-
-Chinese maintainer: Lin Yongting <linyongting@gmail.com>
----------------------------------------------------------------------
-Documentation/driver-api/io_ordering.rst 的中文翻译
-
-如果想评论或更新本文的内容，请直接�系原文档的维护者。如果你使用英文
-交�有困难的�，也�以�中文版维护者求助。如果本翻译更新��时或者翻
-译存在问题，请�系中文版维护者。
-
-中文版维护者： 林永� Lin Yongting <linyongting@gmail.com>
-中文版翻译者： 林永� Lin Yongting <linyongting@gmail.com>
-中文版校译者： 林永� Lin Yongting <linyongting@gmail.com>
-
-
-以下为正文
----------------------------------------------------------------------
-
-在�些平�上，所谓的内存映射I/O是弱顺�。在这些平�上，驱动开�者有责任
-��I/O内存映射地�的写�作按程�图�的顺�达到设备。通常读�一个“安全�
-设备寄存器或桥寄存器，触�IO芯片清刷未处�的写�作到达设备��处�读�作，
-而达到��目的。驱动程�通常在spinlock�护的临界区退出之�使用这�技术。
-这也�以����的写�作�在��的写�作之�到达设备（这�常类似于内存
-�障�作，mb()，�过仅适用于I/O）。
-
-�设一个设备驱动程的具体例�：
-
-        ...
-CPU A:  spin_lock_irqsave(&dev_lock, flags)
-CPU A:  val = readl(my_status);
-CPU A:  ...
-CPU A:  writel(newval, ring_ptr);
-CPU A:  spin_unlock_irqrestore(&dev_lock, flags)
-        ...
-CPU B:  spin_lock_irqsave(&dev_lock, flags)
-CPU B:  val = readl(my_status);
-CPU B:  ...
-CPU B:  writel(newval2, ring_ptr);
-CPU B:  spin_unlock_irqrestore(&dev_lock, flags)
-        ...
-
-上述例�中，设备�能会先接收到newval2的值，然�接收到newval的值，问题就
-�生了。�过很容易通过下�方法�修�：
-
-        ...
-CPU A:  spin_lock_irqsave(&dev_lock, flags)
-CPU A:  val = readl(my_status);
-CPU A:  ...
-CPU A:  writel(newval, ring_ptr);
-CPU A:  (void)readl(safe_register); /* �置寄存器？*/
-CPU A:  spin_unlock_irqrestore(&dev_lock, flags)
-        ...
-CPU B:  spin_lock_irqsave(&dev_lock, flags)
-CPU B:  val = readl(my_status);
-CPU B:  ...
-CPU B:  writel(newval2, ring_ptr);
-CPU B:  (void)readl(safe_register); /* �置寄存器？*/
-CPU B:  spin_unlock_irqrestore(&dev_lock, flags)
-
-在解决方案中，读�safe_register寄存器，触�IO芯片清刷未处�的写�作，
-�处���的读�作，防止引�数��一致问题。
diff --git a/Documentation/translations/zh_CN/oops-tracing.txt b/Documentation/translations/zh_CN/oops-tracing.txt
deleted file mode 100644
index c5f3bda7abcb..000000000000
--- a/Documentation/translations/zh_CN/oops-tracing.txt
+++ /dev/null
@@ -1,212 +0,0 @@
-Chinese translated version of Documentation/admin-guide/bug-hunting.rst
-
-If you have any comment or update to the content, please contact the
-original document maintainer directly.  However, if you have a problem
-communicating in English you can also ask the Chinese maintainer for
-help.  Contact the Chinese maintainer if this translation is outdated
-or if there is a problem with the translation.
-
-Chinese maintainer: Dave Young <hidave.darkstar@gmail.com>
----------------------------------------------------------------------
-Documentation/admin-guide/bug-hunting.rst 的中文翻译
-
-如果想评论或更新本文的内容，请直接�系原文档的维护者。如果你使用英文
-交�有困难的�，也�以�中文版维护者求助。如果本翻译更新��时或者翻
-译存在问题，请�系中文版维护者。
-
-中文版维护者： �瑞 Dave Young <hidave.darkstar@gmail.com>
-中文版翻译者： �瑞 Dave Young <hidave.darkstar@gmail.com>
-中文版校译者： �阳 Li Yang <leoyang.li@nxp.com>
-               王� Wang Cong <xiyou.wangcong@gmail.com>
-
-以下为正文
----------------------------------------------------------------------
-
-注�： ksymoops 在2.6中是没有用的。 请以原有格�使用Oops(�自dmesg，等等)。
-忽略任何这样那样关于“解�Oops�或者“通过ksymoops�行�的文档。 如果你贴出�行过
-ksymoops的�自2.6的Oops，人们�会让你�贴一次。
-
-快速总结
--------------
-
-�现Oops并��给看似相关的内核领域的维护者。别太担心对�上�。如果你�确定就�给
-和你所�的事情相关的代�的负责人。 如果��现试��述怎样�构。 那甚至比oops更有
-价值。
-
-如果你对于��给�一无所知， �给linux-kernel@vger.kernel.org。感谢你帮助Linux
-尽�能地稳定。
-
-Oops在哪里?
-----------------------
-
-通常Oops文本由klogd从内核缓冲区里读�并传给syslogd，由syslogd写到syslog文件中，
-典型地是/var/log/messages(�赖于/etc/syslog.conf)。有时klogd崩溃了,这�情况下你
-能够�行dmesg > file�从内核缓冲区中读�数�并�存下�。 �则你�以
-cat /proc/kmsg > file， 然而你必须介入中止传输， kmsg是一个“永�结�的文件�。如
-果机器崩溃�到你�能输入命令或者�盘��用那么你有三�选择:-
-
-（1） 手抄�幕上的文本待机器����输入计算机。 麻烦但如果没有针对崩溃的准备，
-这是仅有的选择。 �外，你�以用数�相机把�幕�下�-�太好，但比没有强。 如果信
-�滚动到了终端的上�，你会�现以高分辩率�动（比如，vga=791）会让你读到更多的文
-本。（注�：这需�vesafb，所以对‘早期’的oops没有帮助）
-
-（2）用串�终端�动（请�看Documentation/admin-guide/serial-console.rst），�行一个null
-modem到�一�机器并用你喜欢的通讯工具获�输出。Minicom工作地很好。
-
-（3）使用Kdump（请�看Documentation/admin-guide/kdump/kdump.rst），
-使用在Documentation/admin-guide/kdump/gdbmacros.txt中定义的dmesg gdb�，从旧的内存中��内核
-环形缓冲区。
-
-完整信�
-----------------
-
-注�：以下�自于Linus的邮件适用于2.4内核。 我因为历�原因�留了它，并且因为其中
-一些信��然适用。 特别注�的是，请忽略任何ksymoops的引用。
-
-From: Linus Torvalds <torvalds@osdl.org>
-
-怎样跟踪Oops.. [原�到linux-kernel的一�邮件]
-
-主�的�门是有五年和这些烦人的oops消�打交�的�验;-)
-
-实际上，你有办法使它更简�。我有两个��的方法：
-
-	gdb /usr/src/linux/vmlinux
-	gdb> disassemble <offending_function>
-
-那是�现问题的简�办法，至少如果bug报告�的好的情况下（象这个一样-�行ksymoops
-得到oops�生的函数�函数内的�移）。
-
-哦，如果报告�生的内核以相�的编译器和相似的�置编译它会有帮助的。
-
-�一件��的事是�汇编bug报告的“Code�部分：ksymoops也会用正确的工具��这件事，
-但如果没有那些工具你�以写一个傻程�：
-
-	char str[] = "\xXX\xXX\xXX...";
-	main(){}
-
-并用gcc -g编译它然�执行“disassemble str�（XX部分是由Oops报告的值-你�以仅剪切
-粘贴并用“\x�替�空格-我就是这么�的，因为我懒得写程�自动�这一切）。
-
-�外，你�以用scripts/decodecode这个shell脚本。它的使用方法是：
-decodecode < oops.txt
-
-“Code�之�的�六进制字节�能（在�些架构上）有一些当�指令之�的指令字节以�
-当�和之�的指令字节
-
-Code: f9 0f 8d f9 00 00 00 8d 42 0c e8 dd 26 11 c7 a1 60 ea 2b f9 8b 50 08 a1
-64 ea 2b f9 8d 34 82 8b 1e 85 db 74 6d 8b 15 60 ea 2b f9 <8b> 43 04 39 42 54
-7e 04 40 89 42 54 8b 43 04 3b 05 00 f6 52 c0
-
-最�，如果你想知�代��自哪里，你�以：
-
-	cd /usr/src/linux
-	make fs/buffer.s 	# 或任何产生BUG的文件
-
-然�你会比gdb�汇编更清楚的知��生了什么。
-
-现在，问题是把你所拥有的所有数�结�起�：C��（关于它应该怎样的一般知识），
-汇编代��其�汇编得到的代�（�外还有从“oops�消�得到的寄存器状�-对了解��的
-指针有用，而且当你有了汇编代�你也能拿其它的寄存器和任何它们对应的C表达��匹�
-）。
-
-实际上，你仅需看看哪里�匹�（这个例�是“Code��汇编和编译器生�的代��匹�）。
-然�你须�找出为什么�匹�。通常很简�-你看到代�使用了空指针然�你看代�想知�
-空指针是怎么出现的，还有检查它是��法..
-
-现在，如果明白这是一项耗时的工作而且需�一�点儿的专心，没错。这就是我为什么大多
-�是忽略那些没有符�表信�的崩溃报告的原因：简�的说太难查找了（我有一些
-程�用于在内核代�段中�索特定的模�，而且有时我也已�能找出那些崩溃的地方，但是
-仅仅是找出正确的�列也确实需�相当扎实的内核知识）
-
-_有时_会�生这�情况，我仅看到崩溃中的�汇编代��列， 然�我马上就明白问题出在
-哪里。这时我��识到自己干这个工作已�太长时间了;-)
-
-		Linus
-
-
----------------------------------------------------------------------------
-关于Oops跟踪的注解：
-
-为了帮助Linus和其它内核开�者，klogd纳入了大�的支��处��护错误。为了拥有对
-地�解�的完整支�至少应该使用1.3-pl3的sysklogd包。
-
-当�护错误�生时，klogd守护进程自动把内核日志信�中的��地�翻译�它们相应的符
-�。
-
-klogd执行两�类型的地�解�。首先是��翻译其次是动�翻译。��翻译和ksymoops
-一样使用System.map文件。为了���翻译klogd守护进程必须在�始化时能找到system
-map文件。关于klogd怎样�索map文件请�看klogd手册页。
-
-动�地�翻译在使用内核�装载模�时很��。 因为内核模�的内存是从内核动�内存池
-里分�的，所以�管是模�开始�置还是模�中函数和符�的�置都�是固定的。
-
-内核支��许程�决定装载哪些模�和它们在内存中�置的系统调用。使用这些系统调用
-klogd守护进程生�一张符�表用于调试�生在�装载模�中的�护错误。
-
-至少klogd会�供产生�护错误的模��。还�有�外的符�信�供�装载模�开�者选择
-以从模�中输出符�信�。
-
-因为内核模�环境�能是动�的，所以必须有一�机制当模�环境�生改�时�通知klogd
-守护进程。 有一些�用的命令行选项�许klogd�当�执行中的守护进程��信�，告知符
-�信�应该被刷新了。 更多信�请�看klogd手册页。
-
-sysklogd�布时包�一个补�修改了modules-2.0.0包，无论何时一个模�装载或者�载都
-会自动�klogd��信�。打上这个补��供了必�的对调试�生于内核�装载模�的�护
-错误的无�支�。
-
-以下是被klogd处�过的�生在�装载模�中的一个�护错误例�：
----------------------------------------------------------------------------
-Aug 29 09:51:01 blizard kernel: Unable to handle kernel paging request at virtual address f15e97cc
-Aug 29 09:51:01 blizard kernel: current->tss.cr3 = 0062d000, %cr3 = 0062d000
-Aug 29 09:51:01 blizard kernel: *pde = 00000000
-Aug 29 09:51:01 blizard kernel: Oops: 0002
-Aug 29 09:51:01 blizard kernel: CPU:    0
-Aug 29 09:51:01 blizard kernel: EIP:    0010:[oops:_oops+16/3868]
-Aug 29 09:51:01 blizard kernel: EFLAGS: 00010212
-Aug 29 09:51:01 blizard kernel: eax: 315e97cc   ebx: 003a6f80   ecx: 001be77b   edx: 00237c0c
-Aug 29 09:51:01 blizard kernel: esi: 00000000   edi: bffffdb3   ebp: 00589f90   esp: 00589f8c
-Aug 29 09:51:01 blizard kernel: ds: 0018   es: 0018   fs: 002b   gs: 002b   ss: 0018
-Aug 29 09:51:01 blizard kernel: Process oops_test (pid: 3374, process nr: 21, stackpage=00589000)
-Aug 29 09:51:01 blizard kernel: Stack: 315e97cc 00589f98 0100b0b4 bffffed4 0012e38e 00240c64 003a6f80 00000001
-Aug 29 09:51:01 blizard kernel:        00000000 00237810 bfffff00 0010a7fa 00000003 00000001 00000000 bfffff00
-Aug 29 09:51:01 blizard kernel:        bffffdb3 bffffed4 ffffffda 0000002b 0007002b 0000002b 0000002b 00000036
-Aug 29 09:51:01 blizard kernel: Call Trace: [oops:_oops_ioctl+48/80] [_sys_ioctl+254/272] [_system_call+82/128]
-Aug 29 09:51:01 blizard kernel: Code: c7 00 05 00 00 00 eb 08 90 90 90 90 90 90 90 90 89 ec 5d c3
----------------------------------------------------------------------------
-
-Dr. G.W. Wettstein           Oncology Research Div. Computing Facility
-Roger Maris Cancer Center    INTERNET: greg@wind.rmcc.com
-820 4th St. N.
-Fargo, ND  58122
-Phone: 701-234-7556
-
-
----------------------------------------------------------------------------
-�污染的内核
-
-一些oops报告在程�记数器之�包�字符串'Tainted: '。这表明内核已�被一些东西给污
-染了。 该字符串之�紧跟�一系列的�置�感的字符，�个代表一个特定的污染值。
-
-  1：'G'如果所有装载的模�都有GPL或相容的许��，'P'如果装载了任何的专有模�。
-没有模�MODULE_LICENSE或者带有insmod认为是与GPL�相容的的MODULE_LICENSE的模�被
-认定是专有的。
-
-  2：'F'如果有任何通过“insmod -f�被强制装载的模�，' '如果所有模�都被正常装载。
-
-  3：'S'如果oops�生在SMP内核中，�行于没有�明安全�行多处�器的硬件。 当�这�
-情况仅�于几��支�SMP的速龙处�器。
-
-  4：'R'如果模�通过“insmod -f�被强制装载，' '如果所有模�都被正常装载。
-
-  5：'M'如果任何处�器报告了机器检查异常，' '如果没有�生机器检查异常。
-
-  6：'B'如果页释放函数�现了一个错误的页引用或者一些�预期的页标志。
-
-  7：'U'如果用户或者用户应用程�特别请求设置污染标志，�则' '。
-
-  8：'D'如果内核刚刚死掉，比如有OOPS或者BUG。
-
-使用'Tainted: '字符串的主�原因是�告诉内核调试者，这是�是一个干净的内核亦或�
-生了任何的�正常的事。污染是永久的：�使出错的模�已�被�载了，污染值�然存在，
-以表明内核��值得信任。
diff --git a/Documentation/translations/zh_CN/process/coding-style.rst b/Documentation/translations/zh_CN/process/coding-style.rst
index 638d714bec83..fa28ef0a7fee 100644
--- a/Documentation/translations/zh_CN/process/coding-style.rst
+++ b/Documentation/translations/zh_CN/process/coding-style.rst
@@ -1,21 +1,23 @@
 .. include:: ../disclaimer-zh_CN.rst
 
-:Original: :ref:`Documentation/process/coding-style.rst <codingstyle>`
+:Original: Documentation/process/coding-style.rst
 
 .. _cn_codingstyle:
 
-译者::
+:译者:
+ - 张� Zhang Le <r0bertz@gentoo.org>
+ - Andy Deng <theandy.deng@gmail.com>
+ - �想� <bobwxc@email.cn>
 
-  中文版维护者： 张� Zhang Le <r0bertz@gentoo.org>
-  中文版翻译者： 张� Zhang Le <r0bertz@gentoo.org>
-  中文版校译者： 王� Wang Cong <xiyou.wangcong@gmail.com>
-                 wheelz <kernel.zeng@gmail.com>
-                 管旭东 Xudong Guan <xudong.guan@gmail.com>
-                 Li Zefan <lizf@cn.fujitsu.com>
-                 Wang Chen <wangchen@cn.fujitsu.com>
+:校译:
+ - 王� Wang Cong <xiyou.wangcong@gmail.com>
+ - wheelz <kernel.zeng@gmail.com>
+ - 管旭东 Xudong Guan <xudong.guan@gmail.com>
+ - Li Zefan <lizf@cn.fujitsu.com>
+ - Wang Chen <wangchen@cn.fujitsu.com>
 
 Linux 内核代�风格
-=========================
+==================
 
 这是一个简短的文档，�述了 linux 内核的首选代�风格。代�风格是因人而异的，
 而且我�愿�把自己的观点强加给任何人，但这就�我去�任何事情都必须�循的原则
@@ -29,7 +31,7 @@ Linux 内核代�风格
 
 
 1) 缩进
---------------
+-------
 
 制表符是 8 个字符，所以缩进也是 8 个字符。有些异端�动试图将缩进�为 4 (甚至
 2�) 字符深，这几乎相当于�试将圆周率的值定义为 3。
@@ -73,6 +75,22 @@ Linux 内核代�风格
 	if (condition) do_this;
 	  do_something_everytime;
 
+��使用逗����使用大括�：
+
+.. code-block:: c
+
+	if (condition)
+		do_this(), do_that();
+
+使用大括�包裹多语�：
+
+.. code-block:: c
+
+	if (condition) {
+		do_this();
+		do_that();
+	}
+
 也��在一行里放多个赋值语�。内核代�风格超级简�。就是���能导致别人误读
 的表达�。
 
@@ -83,20 +101,25 @@ Linux 内核代�风格
 
 
 2) 把长的行和字符串打散
-------------------------------
+-----------------------
 
 代�风格的�义就在于使用平常使用的工具�维�代�的�读性和�维护性。
 
 �一行的长度的�制是 80 列，我们强烈建议您�守这个惯例。
 
 长于 80 列的语��打散�有�义的片段。除�超过 80 列能显著增加�读性，并且�
-会��信�。�片段�明显短于�片段，并明显��。这�样适用于有�很长�数列表
-的函数头。然而，�对��打散对用户��的字符串，例如 printk 信�，因为这样就
+会��信�。
+
+�片段�明显短于�片段，并明显��。一��常常用的样�是将�体与函数左括�对�。
+
+这�样适用于有�很长�数列表的函数头。
+
+然而，�对��打散对用户��的字符串，例如 printk 信�，因为这样就
 很难对它们 grep。
 
 
 3) 大括�和空格的放置
-------------------------------
+---------------------
 
 C 语言风格中�外一个常�问题是大括�的放置。和缩进大���，选择或弃用��放
 置策略并没有多少技术上的原因，�过首选的方�，就� Kernighan 和 Ritchie 展示
@@ -132,12 +155,12 @@ C 语言风格中�外一个常�问题是大括�的放置。和缩进大�
 		body of function
 	}
 
-全世界的异端�能会抱怨这个�一致性是... 呃... �一致的，�过所有�维�全的人
+全世界的异端�能会抱怨这个�一致性是……呃……�一致，�过所有�维�全的人
 都知� (a) K&R 是 **正确的** 并且 (b) K&R 是正确的。此外，�管怎样函数都是特
 殊的 (C 函数是�能嵌套的)。
 
 注�结�大括�独自��一行，除�它��跟��一个语�的剩余部分，也就是 do 语
-�中的 "while" 或者 if 语�中的 "else"，�这样：
+�中的 ``while`` 或者 if 语�中的 ``else`` ，�这样：
 
 .. code-block:: c
 
@@ -191,7 +214,7 @@ C 语言风格中�外一个常�问题是大括�的放置。和缩进大�
 	}
 
 3.1) 空格
-********************
+*********
 
 Linux 内核的空格使用方� (主�) �决于它是用于函数还是关键字。(大多数) 关键字
 ��加一个空格。值得注�的例外是 sizeof, typeof, alignof 和 __attribute__，这
@@ -254,7 +277,7 @@ Linux 内核的空格使用方å¼� (主è¦�) å�–决于它是用于函数还是关é
 
 
 4) 命�
-------------------------------
+-------
 
 C 是一个简朴的语言，你的命�也应该这样。和 Modula-2 和 Pascal 程�员��，
 C 程�员�使用类似 ThisVariableIsATemporaryCounter 这样�丽的�字。C 程�员会
@@ -275,11 +298,31 @@ C 程�员�使用类似 ThisVariableIsATemporaryCounter 这样�丽的�字
 �能的�。类似的， ``tmp`` �以用�称呼任�类型的临时��。
 
 如果你怕混淆了你的本地���，你就�到�一个问题了，��函数增长�尔蒙失衡综
-�症。请看第六章 (函数)。
+��。请看第六章 (函数)。
 
+对于符��称和文档，��引入新的“master/slave�（或独立于“master�的“slave�）
+和“blacklist/whitelist�。
+
+“master/slave�推�替�为：
+    '{primary,main} / {secondary,replica,subordinate}'
+    '{initiator,requester} / {target,responder}'
+    '{controller,host} / {device,worker,proxy}'
+    'leader/follower'
+    'director/performer'
+
+“blacklist/whitelist�推�替�为：
+    'denylist/allowlist'
+    'blocklist/passlist'
+
+引入新用法的例外情况是：维护用户空间ABI/API，或更新现有（截至2020年）硬件或
+�议规范的代�时�求这些术语。对于新规范，尽�能将术语的规范用法转�为内核
+编�标准。
+
+.. warning::
+	以上主从�黑白��规则�适用于中文文档，请勿更改中文术语�
 
 5) Typedef
------------
+----------
 
 ��使用类似 ``vps_t`` 之类的东西。
 
@@ -308,7 +351,7 @@ C 程�员�使用类似 ThisVariableIsATemporaryCounter 这样�丽的�字
 
      .. note::
 
-       ��明性和 "访问函数" 本身是�好的。我们使用 pte_t 等类型的原因在于真
+       ��明性和“访问函数�本身是�好的。我们使用 pte_t 等类型的原因在于真
        的是完全没有任何共用的�访问信�。
 
  (b) 清楚的整数类型，如此，这层抽象就�以 **帮助** 消除到底是 ``int`` 还是
@@ -353,7 +396,7 @@ C 程�员�使用类似 ThisVariableIsATemporaryCounter 这样�丽的�字
 
 
 6) 函数
-------------------------------
+-------
 
 函数应该简短而漂亮，并且�完�一件事情。函数应该�以一�或者两�显示完 (我们
 都知� ISO/ANSI �幕大�是 80x24)，��一件事情，而且把它�好。
@@ -383,12 +426,46 @@ C 程�员�使用类似 ThisVariableIsATemporaryCounter 这样�丽的�字
 	}
 	EXPORT_SYMBOL(system_is_up);
 
-在函数原型中，包�函数�和它们的数�类型。虽然 C 语言里没有这样的�求，在
+6.1) 函数原型
+*************
+
+在函数原型中包��数�和它们的数�类型。虽然 C 语言里没有这样的�求，但在
 Linux 里这是�倡的�法，因为这样�以很简�的给读者�供更多的有价值的信�。
 
+��在函数声明里使用 ``extern`` 关键字，因为这会导致代�行�长，并且�是严格
+必需的。
+
+写函数原型时，请�� `元素顺�规则 <https://lore.kernel.org/mm-commits/CAHk-=wiOCLRny5aifWNhr621kYrJwhfURsa0vFPeUEm8mF0ufg@mail.gmail.com/>`_ 。
+例如下列函数声明::
+
+ __init void * __must_check action(enum magic value, size_t size, u8 count,
+				   char *fmt, ...) __printf(4, 5) __malloc;
+
+推�的函数原型元素顺�是：
+
+- 储存类型（下方的 ``static __always_inline`` ，注� ``__always_inline``
+  技术上�讲是个属性但被当� ``inline`` ）
+- 储存类型属性（上方的 ``__init`` ——�节声明，但也� ``__cold`` ）
+- 返回类型（上方的 ``void *`` ）
+- 返回类型属性（上方的 ``__must_check`` ）
+- 函数�（上方的 ``action`` ）
+- 函数�数（上方的 ``(enum magic value, size_t size, u8 count, char *fmt, ...)`` ，
+  注�必须写上�数�）
+- 函数�数属性（上方的 ``__printf(4, 5)`` ）
+- 函数行为属性（上方的 ``__malloc`` ）
+
+请注�，对于函数 **定义** （�实际函数体），编译器��许在函数�数之�添加函
+数�数属性。在这�情况下，它们应该跟�存储类型属性（例如，与上�的 **声明**
+示例相比，请注�下�的 ``__printf(4, 5)`` 的�置�生了�化）::
+
+ static __always_inline __init __printf(4, 5) void * __must_check action(enum magic value,
+		size_t size, u8 count, char *fmt, ...) __malloc
+ {
+	...
+ }
 
 7) 集中的函数退出途径
-------------------------------
+---------------------
 
 虽然被�些人声称已�过时，但是 goto 语�的等价物还是�常被编译器所使用，具体
 形�是无�件跳转指令。
@@ -432,7 +509,7 @@ Linux 里这是æ��倡的å�šæ³•ï¼Œå› ä¸ºè¿™æ ·å�¯ä»¥å¾ˆç®€å�•çš„给读者æ��ä¾›æ›
 		return result;
 	}
 
-一个需�注�的常�错误是 ``一个 err 错误`` ，就�这样：
+一个需�注�的常�错误是 ``� err 错误`` ，就�这样：
 
 .. code-block:: c
 
@@ -456,19 +533,19 @@ Linux 里这是æ��倡的å�šæ³•ï¼Œå› ä¸ºè¿™æ ·å�¯ä»¥å¾ˆç®€å�•çš„给读者æ��ä¾›æ›
 
 
 8) 注释
-------------------------------
+-------
 
 注释是好的，�过有过度注释的�险。永远��在注释里解释你的代�是如何�作的：
 更好的�法是让别人一看你的代�就�以明白，解释写的很差的代�是浪费时间。
 
-一般的，你想�你的注释告诉别人你的代��了什么，而�是怎么�的。也请你��把
+一般�说你用注释告诉别人你的代��了什么，而�是怎么�的。也请你��把
 注释放在一个函数体内部：如果函数��到你需�独立的注释其中的一部分，你很�能
 需�回到第六章看一看。你�以�一些�注释�注明或警告�些很�明 (或者槽糕) 的
 �法，但��加太多。你应该�的，是把注释放在函数的头部，告诉人们它�了什么，
 也�以加上它�这些事情的原因。
 
-当注释内核 API 函数时，请使用 kernel-doc 格�。请看
-Documentation/doc-guide/ 和 scripts/kernel-doc 以获得详细信�。
+当注释内核 API 函数时，请使用 kernel-doc 格�。详�
+Documentation/translations/zh_CN/doc-guide/index.rst 和 scripts/kernel-doc 。
 
 长 (多行) 注释的首选风格是：
 
@@ -500,17 +577,18 @@ Documentation/doc-guide/ 和 scripts/kernel-doc 以获得详细信�。
 
 
 9) 你已�把事情弄糟了
-------------------------------
+---------------------
 
-这没什么，我们都是这样。�能你的使用了很长时间 Unix 的朋�已�告诉你
+这没什么，我们都是这样。�能你长期使用 Unix 的朋�已�告诉你
 ``GNU emacs`` 能自动帮你格�化 C �代�，而且你也注�到了，确实是这样，�过它
 所使用的默认值和我们想�的相去甚远 (实际上，甚至比�机打的还�差——无数个猴�
-在 GNU emacs 里打字永远�会创造出一个好程�) (译注：Infinite Monkey Theorem)
+在 GNU emacs 里打字永远�会创造出一个好程�)
+*(译注：Infinite Monkey Theorem)*
 
 所以你�么放弃 GNU emacs，�么改�它让它使用更��的设定。�采用�一个方案，
 你�以把下�这段粘贴到你的 .emacs 文件里。
 
-.. code-block:: none
+.. code-block:: elisp
 
   (defun c-lineup-arglist-tabs-only (ignored)
     "Line up argument lists by tabs, not spaces"
@@ -529,7 +607,7 @@ Documentation/doc-guide/ 和 scripts/kernel-doc 以获得详细信�。
           (c-offsets-alist . (
                   (arglist-close         . c-lineup-arglist-tabs-only)
                   (arglist-cont-nonempty .
-		      (c-lineup-gcc-asm-reg c-lineup-arglist-tabs-only))
+                      (c-lineup-gcc-asm-reg c-lineup-arglist-tabs-only))
                   (arglist-intro         . +)
                   (brace-list-intro      . +)
                   (c                     . c-lineup-C-comments)
@@ -573,9 +651,14 @@ Documentation/doc-guide/ 和 scripts/kernel-doc 以获得详细信�。
 ``indent`` 有很多选项，特别是�新格�化注释的时候，你�能需�看一下它的手册。
 �过记�： ``indent`` �能修正�的编程习惯。
 
+请注�，您还�以使用 ``clang-format`` 工具帮助您处�这些规则，快速自动�新格
+�化部分代�，并审阅整个文件以�现代�风格错误�打字错误和�能的改进。它还�
+以方便地排� ``#include`` ，对���/�，�排文本和其他类似任务。
+详� Documentation/process/clang-format.rst 。
+
 
 10) Kconfig �置文件
-------------------------------
+--------------------
 
 对于�布��树的所有 Kconfig* �置文件�说，它们缩进方�有所��。紧挨�
 ``config`` 定义的行，用一个制表符缩进，然而 help 信�的缩进则�外增加 2 个空
@@ -598,11 +681,11 @@ Documentation/doc-guide/ 和 scripts/kernel-doc 以获得详细信�。
 	depends on ADFS_FS
 	...
 
-�查看�置文件的完整文档，请看 Documentation/kbuild/kconfig-language.rst。
+�查看�置文件的完整文档，请看 Documentation/kbuild/kconfig-language.rst 。
 
 
 11) 数�结构
-------------------------------
+------------
 
 如果一个数�结构，在创建和销�它的�线执行环境之外��，那么它必须�有一个引
 用计数器。内核里没有垃圾收集 (并且内核之外的垃圾收集慢且效率低下)，这�味�你
@@ -626,7 +709,7 @@ mm_count)，和文件系统 (``struct super_block``: s_count å’Œ s_active) 中æ‰
 
 
 12) �，枚举和RTL
-------------------------------
+-----------------
 
 用于定义常�的�的�字�枚举里的标签需�大写。
 
@@ -638,7 +721,7 @@ mm_count)，和文件系统 (``struct super_block``: s_count å’Œ s_active) 中æ‰
 
 �的�字请用大写字�，�过形如函数的�的�字�以用�写字�。
 
-一般的，如果能写�内�函数就��写��函数的�。
+通常如果能写�内�函数就��写��函数的�。
 
 �有多个语�的�应该被包�在一个 do-while 代��里：
 
@@ -696,18 +779,18 @@ mm_count)，和文件系统 (``struct super_block``: s_count å’Œ s_active) 中æ‰
 		(ret);				\
 	})
 
-ret 是本地��的通用�字 - __foo_ret 更�容易与一个已存在的��冲�。
+ret 是本地��的通用�字—— __foo_ret 更�容易与一个已存在的��冲�。
 
 cpp 手册对�的讲解很详细。gcc internals 手册也详细讲解了 RTL，内核里的汇编语
 言�常用到它。
 
 
 13) 打�内核消�
-------------------------------
+----------------
 
-内核开�者应该是�过良好教育的。请一定注�内核信�的拼写，以给人以好的�象。
+内核开�者应该看起�有文化。请一定注�内核信�的拼写，以给人良好的�象。
 ��用�规范的��比如 ``dont``，而�用 ``do not`` 或者 ``don't`` 。��这些信
-�简�明了,无歧义。
+�简�明了�无歧义。
 
 内核信��必以英文��结�。
 
@@ -724,17 +807,18 @@ dev_info() 等等。对于那些�和�个特定设备相关连的信�，<li
 或设定了 CONFIG_DYNAMIC_DEBUG。实际这�样是为了 dev_dbg()，一个相关约定是在一
 个已�开�了 DEBUG 时，使用 VERBOSE_DEBUG �添加 dev_vdbg()。
 
-许多�系统拥有 Kconfig 调试选项�开� -DDEBUG 在对应的 Makefile 里�；在其他
+许多�系统拥有 Kconfig 调试选项�开�对应 Makefile 里�的 -DDEBUG；在其他
 情况下，特殊文件使用 #define DEBUG。当一�调试信�需�被无�件打�时，例如，
 如果已�包�一个调试相关的 #ifdef �件，printk(KERN_DEBUG ...) 就�被使用。
 
 
 14) 分�内存
-------------------------------
+------------
 
 内核�供了下�的一般用途的内存分�函数：
 kmalloc(), kzalloc(), kmalloc_array(), kcalloc(), vmalloc() 和 vzalloc()。
-请�考 API 文档以获�有关它们的详细信�。
+请�考 API 文档以获�有关它们的详细信�：
+Documentation/translations/zh_CN/core-api/memory-allocation.rst 。
 
 传递结构体大�的首选形�是这样的：
 
@@ -761,11 +845,13 @@ kmalloc(), kzalloc(), kmalloc_array(), kcalloc(), vmalloc() 和 vzalloc()。
 
 	p = kcalloc(n, sizeof(...), ...);
 
-两�形�检查分�大� n * sizeof(...) 的溢出，如果溢出返回 NULL。
+两�形�都会检查分� n * sizeof(...) 大�时内存的溢出，如果溢出返回 NULL。
 
+在没有 __GFP_NOWARN 的情况下使用时，这些通用分�函数都会在失败时�起堆栈转储，
+因此当返回NULL时，没有必��出�外的失败消�。
 
 15) 内�弊病
-------------------------------
+------------
 
 有一个常�的误解是 ``内�`` 是 gcc �供的�以让代��行更快的一个选项。虽然使
 用内�函数有时候是�当的 (比如作为一�替代�的方�，请看第�二章)，�过很多情
@@ -786,7 +872,7 @@ inline gcc 也�以自动使其内�。而且其他用户�能会�求移除
 
 
 16) 函数返回值�命�
-------------------------------
+--------------------
 
 函数�以返回多���类型的值，最常�的一�是表明函数执行�功或者失败的值。这样
 的一个值�以表示为一个错误代�整数 (-Exxx�失败，0��功) 或者一个 ``�功``
@@ -797,7 +883,7 @@ inline gcc 也�以自动使其内�。而且其他用户�能会�求移除
 产生这� bug，请�循下�的惯例::
 
 	如果函数的�字是一个动作或者强制性的命令，那么这个函数应该返回错误代
-	�整数。如果是一个判断，那么函数应该返回一个 "�功" 布尔值。
+	�整数。如果是一个判断，那么函数应该返回一个“�功�布尔值。
 
 比如， ``add work`` 是一个命令，所以 add_work() 在�功时返回 0，在失败时返回
 -EBUSY。类似的，因为 ``PCI device present`` 是一个判断，所以 pci_dev_present()
@@ -806,13 +892,35 @@ inline gcc 也�以自动使其内�。而且其他用户�能会�求移除
 所有 EXPORTed 函数都必须�守这个惯例，所有的公共函数也都应该如此。�有
 (static) 函数�需�如此，但是我们也推�这样�。
 
-返回值是实际计算结果而�是计算是��功的标志的函数��此惯例的�制。一般的，
+返回值是实际计算结果而�是计算是��功的标志的函数��此惯例的�制。通常
 他们通过返回一些正常值范围之外的结果�表示出错。典型的例�是返回指针的函数，
 他们使用 NULL 或者 ERR_PTR 机制�报告错误。
 
+17) 使用布尔类型
+----------------
+
+Linux内核布尔（bool）类型是C99 _Bool类型的别�。布尔值�能为0或1，而对布尔的
+��或显�转�将自动将值转�为true或false。在使用布尔类型时 **�需�** 构造，
+它会消除一类错误。
+
+使用布尔值时，应使用true和false定义，而�是1和0。
 
-17) ���新�明内核�
-------------------------------
+布尔函数返回类型和堆栈��总是�以在适当的时候使用。鼓励使用布尔��高�读性，
+并且布尔值在存储时通常比“int�更好。
+
+如果缓存行布局或值的大�很��，请��使用布尔，因为其大�和对�方�根�编译
+的体系结构而��。针对对�和大�进行优化的结构体�应使用布尔。
+
+如果一个结构体有多个true/false值，请考虑将它们�并为具有1比特�员的�域，或使
+用适当的固定宽度类型，如u8。
+
+类似地，对于函数�数，多个true/false值�以�并为�个按�的“标志��数，如果调
+用点具有裸true/false常�，“标志��数通常是更具�读性的替代方法。
+
+总之，在结构体和�数中有�地使用布尔�以�高�读性。
+
+18) ���新�明内核�
+----------------------
 
 头文件 include/linux/kernel.h 包�了一些�，你应该使用它们，而��自己写一些
 它们的��。比如，如果你需�计算一个数组的长度，使用这个�
@@ -832,11 +940,11 @@ inline gcc 也�以自动使其内�。而且其他用户�能会�求移除
 在你的代�里自己�新定义。
 
 
-18) 编辑器模�行和其他需�罗嗦的事情
---------------------------------------------------
+19) 编辑器模�行和其他需�罗嗦的事情
+------------------------------------
 
 有一些编辑器�以解释嵌入在�文件里的由一些特殊标记标明的�置信�。比如，emacs
-能够解释被标记�这样的行：
+能够解�被标记�这样的行：
 
 .. code-block:: c
 
@@ -852,7 +960,7 @@ inline gcc 也�以自动使其内�。而且其他用户�能会�求移除
 	End:
 	*/
 
-Vim 能够解释这样的标记：
+Vim 能够解�这样的标记：
 
 .. code-block:: c
 
@@ -863,8 +971,8 @@ Vim 能够解释这样的标记：
 的模�，或者使用其他�以产生正确的缩进的巧妙方法。
 
 
-19) 内�汇编
-------------------------------
+20) 内�汇编
+------------
 
 在特定架构的代�中，你�能需�内�汇编与 CPU 和平�相关功能连接。需�这么�时
 就��犹豫。然而，当 C �以完�工作时，��平白无故地使用内�汇编。在�能的情
@@ -880,8 +988,8 @@ Vim 能够解释这样的标记：
 移除了。你�必总是这样�，尽管，这�必�的举动会�制优化。
 
 在写一个包�多�指令的�个内�汇编语�时，把��指令用引�分割而且��一行，
-除了最�一�指令外，在�个指令结尾加上 \n\t，让汇编输出时�以正确地缩进下一�
-指令：
+除了最�一�指令外，在�个指令结尾加上 ``\n\t`` ，让汇编输出时�以正确地缩进
+下一�指令：
 
 .. code-block:: c
 
@@ -890,10 +998,10 @@ Vim 能够解释这样的标记：
 	     : /* outputs */ : /* inputs */ : /* clobbers */);
 
 
-20) �件编译
-------------------------------
+21) �件编译
+------------
 
-���能，就��在 .c 文件里�使用预处��件 (#if, #ifdef)；这样�让代�更难
+���能，就��在 .c 文件里�使用预处��件 (#if, #ifdef)；这样�会让代�更难
 阅读并且更难去跟踪逻辑。替代方案是，在头文件中用预处��件�供给那些 .c 文件
 使用，�给 #else �供一个空桩 (no-op stub) 版本，然�在 .c 文件内无�件地调用
 那些 (定义在头文件内的) 函数。这样�，编译器会��为桩函数 (stub) 的调用生�
@@ -904,8 +1012,8 @@ Vim 能够解释这样的标记：
 �件到这个辅助函数内。
 
 如果你有一个在特定�置中，�能��未使用的函数或��，编译器会警告它定义了但
-未使用，把它标记为 __maybe_unused 而�是将它包�在一个预处��件中。(然而，如
-果一个函数或��总是未使用，就直接删除它。)
+未使用，请把它标记为 __maybe_unused 而�是将它包�在一个预处��件中。(然而，
+如果一个函数或��总是未使用，就直接删除它。)
 
 在代�中，尽�能地使用 IS_ENABLED ��转化�个 Kconfig 标记为 C 的布尔
 表达�，并在一般的 C �件中使用它：
@@ -931,23 +1039,45 @@ Vim 能够解释这样的标记：
 	#endif /* CONFIG_SOMETHING */
 
 
-附录 I) �考
--------------------
+附录 I) �考资料
+----------------
 
-The C Programming Language, 第二版
+The C Programming Language, 2nd Edition
 作者：Brian W. Kernighan 和 Denni M. Ritchie.
 Prentice Hall, Inc., 1988.
-ISBN 0-13-110362-8 (软皮), 0-13-110370-9 (硬皮).
+ISBN 0-13-110362-8 (平装), 0-13-110370-9 (精装).
+
+.. note::
+
+    《C程�设计语言（第2版）》
+    作者：[美] Brian W. Kernighan / [美] Dennis M. Ritchie
+    译者：��文 / �志 / 尤晋元（审校）
+    出版社：机械工业出版社，2019
+    ISBN：9787111617945
 
 The Practice of Programming
 作者：Brian W. Kernighan 和 Rob Pike.
 Addison-Wesley, Inc., 1999.
 ISBN 0-201-61586-X.
 
+.. note::
+
+    《程�设计实践》
+    作者：[美] Brian W. Kernighan / [美] Rob Pike
+    出版社：机械工业出版社，2005
+    ISBN：9787111091578
+
+    《程�设计实践》
+    作者：[美] Brian W. Kernighan / Rob Pike
+    译者：裘宗燕
+    出版社：机械工业出版社，2000
+    ISBN：9787111075738
+
 GNU 手册 - �循 K&R 标准和此文本 - cpp, gcc, gcc internals and indent,
 都�以从 https://www.gnu.org/manual/ 找到
 
 WG14 是 C 语言的国际标准化工作组，URL: http://www.open-std.org/JTC1/SC22/WG14/
 
-Kernel process/coding-style.rst，作者 greg@kroah.com �表于 OLS 2002：
+内核文档 Documentation/process/coding-style.rst，
+作者 greg@kroah.com �表于 OLS 2002：
 http://www.kroah.com/linux/talks/ols_2002_kernel_codingstyle_talk/html/
diff --git a/Documentation/translations/zh_CN/process/email-clients.rst b/Documentation/translations/zh_CN/process/email-clients.rst
index 102023651118..34d51cdadc7b 100644
--- a/Documentation/translations/zh_CN/process/email-clients.rst
+++ b/Documentation/translations/zh_CN/process/email-clients.rst
@@ -1,17 +1,20 @@
-.. _cn_email_clients:
+.. SPDX-License-Identifier: GPL-2.0-or-later
 
 .. include:: ../disclaimer-zh_CN.rst
 
-:Original: :ref:`Documentation/process/email-clients.rst <email_clients>`
+.. _cn_email_clients:
 
-译者::
+:Original: Documentation/process/email-clients.rst
 
-        中文版维护者： 贾��  Harry Wei <harryxiyou@gmail.com>
-        中文版翻译者： 贾��  Harry Wei <harryxiyou@gmail.com>
-                       时奎亮  Alex Shi <alex.shi@linux.alibaba.com>
-        中文版校译者： Yinglin Luan <synmyth@gmail.com>
-        	       Xiaochen Wang <wangxiaochen0@gmail.com>
-                       yaxinsn <yaxinsn@163.com>
+:译者:
+ - 贾��  Harry Wei <harryxiyou@gmail.com>
+ - 时奎亮  Alex Shi <alexs@kernel.org>
+ - �想�  Wu XiangCheng <bobwxc@email.cn>
+
+:校译:
+ - Yinglin Luan <synmyth@gmail.com>
+ - Xiaochen Wang <wangxiaochen0@gmail.com>
+ - yaxinsn <yaxinsn@163.com>
 
 Linux邮件客户端�置信�
 =======================
@@ -27,12 +30,17 @@ Git
 改日志。如果工作正常，�将补���到相应的邮件列表。
 
 
-普通�置
+通用�置
 --------
+
 Linux内核补�是通过邮件被�交的，最好把补�作为邮件体的内嵌文本。有些维护者
 接收附件，但是附件的内容格�应该是"text/plain"。然而，附件一般是�赞�的，
 因为这会使补�的引用部分在评论过程中�的很困难。
 
+�时也强烈建议在补�或其他邮件的正文中使用纯文本格�。https://useplaintext.email
+有助于了解如何�置你喜欢的邮件客户端，并在您还没有首选的情况下列出一些推�的
+客户端。
+
 用���Linux内核补�的邮件客户端在��补�时应该处于文本的原始状�。例如，
 他们�能改�或者删除制表符或者空格，甚至是在�一行的开头或者结尾。
 
@@ -40,17 +48,17 @@ Linux内核补�是通过邮件被�交的，最好把补�作为邮件体的
 
 ��让你的邮件客户端进行自动�行。这样也会破�你的补�。
 
-邮件客户端�能改�文本的字符集编�方�。���的补��能是ASCII或者UTF-8编�方�，
-如果你使用UTF-8编�方���邮件，那么你将会��一些�能�生的字符集问题。
+邮件客户端�能改�文本的字符集编�方�。���的补��能是ASCII或者UTF-8编�
+方�，如果你使用UTF-8编�方���邮件，那么你将会��一些�能�生的字符集问题。
 
-邮件客户端应该形�并且�� References: 或者 In-Reply-To: 标题，那么
-邮件�题就�会中断。
+邮件客户端应该生�并且��“References:�或者“In-Reply-To:�邮件头，这样邮件会�
+就�会中断。
 
-�制粘帖(或者剪贴粘帖)通常�能用于补�，因为制表符会转�为空格。使用xclipboard, xclip
-或者xcutsel也许�以，但是最好测试一下或者��使用�制粘帖。
+�制粘帖(或者剪贴粘帖)通常�能用于补�，因为制表符会转�为空格。使用xclipboard,
+xclip或者xcutsel也许�以，但是最好测试一下或者��使用�制粘帖。
 
-��在使用PGP/GPG署�的邮件中包�补�。这样会使得很多脚本�能读�和适用于你的补�。
-（这个问题应该是�以修�的）
+��在使用PGP/GPG签�的邮件中包�补�。这样会使得很多脚本�能读�和适用于你的
+补�。（这个问题应该是�以修�的）
 
 在给内核邮件列表��补�之�，给自己��一个补�是个�错的主�，�存接收到的
 邮件，将补�用'patch'命令打上，如果�功了，�给内核邮件列表��。
@@ -58,98 +66,133 @@ Linux内核补�是通过邮件被�交的，最好把补�作为邮件体的
 
 一些邮件客户端�示
 ------------------
+
 这里给出一些详细的MUA�置�示，�以用于给Linux内核��补�。这些并��味是
 所有的软件包�置总结。
 
 说明：
-TUI = 以文本为基础的用户接�
-GUI = 图形界�用户接�
+
+- TUI = 以文本为基础的用户接�
+- GUI = 图形界�用户接�
 
 Alpine (TUI)
-~~~~~~~~~~~~
+************
 
 �置选项：
-在"Sending Preferences"部分：
 
-- "Do Not Send Flowed Text"必须开�
-- "Strip Whitespace Before Sending"必须关闭
+在 :menuselection:`Sending Preferences` ��：
+
+- :menuselection:`Do Not Send Flowed Text` 必须开�
+- :menuselection:`Strip Whitespace Before Sending` 必须关闭
+
+当写邮件时，光标应该放在补�会出现的地方，然�按下 :kbd:`CTRL-R` 组�键，使指
+定的补�文件嵌入到邮件中。
+
+Claws Mail (GUI)
+****************
+
+�以用，有人用它�功地�过补�。
 
-当写邮件时，光标应该放在补�会出现的地方，然�按下CTRL-R组�键，使指定的
-补�文件嵌入到邮件中。
+用 :menuselection:`Message-->Insert File` (:kbd:`CTRL-I`) 或外置编辑器�入补�。
+
+若�在Claws编辑窗��修改�入的补�，需关闭
+:menuselection:`Configuration-->Preferences-->Compose-->Wrapping`
+的 `Auto wrapping` 。
 
 Evolution (GUI)
-~~~~~~~~~~~~~~~
+***************
 
-一些开�者�功的使用它��补�
+一些开�者�功的使用它��补�。
 
-当选择邮件选项：Preformat
-  从Format->Heading->Preformatted (Ctrl-7)或者工具�
+撰写邮件时：
+从 :menuselection:`格�-->段�样�-->预格�化` (:kbd:`CTRL-7`)
+或工具�选择 :menuselection:`预格�化` ；
 
 然�使用：
-  Insert->Text File... (Alt-n x)�入补�文件。
+:menuselection:`�入-->文本文件...` (:kbd:`ALT-N x`) �入补�文件。
 
-你还�以"diff -Nru old.c new.c | xclip"，选择Preformat，然�使用中间键进行粘帖。
+你还�以 ``diff -Nru old.c new.c | xclip`` ，选择 :menuselection:`预格�化` ，
+然�使用鼠标中键进行粘帖。
 
 Kmail (GUI)
-~~~~~~~~~~~
+***********
 
 一些开�者�功的使用它��补�。
 
-默认设置�为HTML格�是�适的；���用它。
+默认撰写设置�用HTML格�是�适的；���用它。
 
-当书写一�邮件的时候，在选项下���选择自动�行。唯一的缺点就是你在邮件中输入的任何文本
-都�会被自动�行，因此你必须在��补�之�手动�行。最简�的方法就是�用自动�行�书写邮件，
-然�把它�存为�稿。一旦你在�稿中�次打开它，它已�全部自动�行了，那么你的邮件虽然没有
-选择自动�行，但是还�会失去已有的自动�行。
+当书写一�邮件的时候，在选项下���选择自动�行。唯一的缺点就是你在邮件中输
+入的任何文本都�会被自动�行，因此你必须在��补�之�手动�行。最简�的方法
+就是�用自动�行�书写邮件，然�把它�存为�稿。一旦你在�稿中�次打开它，它
+已�全部自动�行了，那么你的邮件虽然没有选择自动�行，但是还�会失去已有的自
+动�行。
 
-在邮件的底部，�入补�之�，放上常用的补�定界符：三个连字�(---)。
+在邮件的底部，�入补�之�，放上常用的补�定界符：三个连字符(``---``)。
 
-然�在"Message"���目，选择�入文件，接�选�你的补�文件。还有一个�外的选项，你�以
-通过它�置你的邮件建立工具���，还�以带上"insert file"图标。
+然�在 :menuselection:`信件` ��，选择 :menuselection:`�入文本文件` ，接
+�选�你的补�文件。还有一个�外的选项，你�以通过它�置你的创建新邮件工具�，
+加上 :menuselection:`�入文本文件` 图标。
 
-你�以安全地通过GPG标记附件，但是内嵌补�最好��使用GPG标记它们。作为内嵌文本的签�补�，
-当从GPG中��7�编�时会使他们�的更加��。
+将编辑器窗�拉到足够宽��折行。对于KMail 1.13.5 (KDE 4.5.4)，它会在��邮件
+时对编辑器窗�中显示折行的地方自动�行。在选项��中�消自动�行��能解决。
+因此，如果你的补�中有�常长的行，必须在��之�把编辑器窗�拉得�常宽。
+��：https://bugs.kde.org/show_bug.cgi?id=174034
 
-如果你��以附件的形���补�，那么就�键点击附件，然�选中属性，�出"Suggest automatic
-display"，这样内嵌附件更容易让读者看到。
+你�以安全地用GPG签�附件，但是内嵌补�最好��使用GPG签�它们。作为内嵌文本
+�入的签�补�将使其难以从7-bit编�中��。
 
-当你��存将���的内嵌文本补�，你�以从消�列表窗格选择包�补�的邮件，然��击选择
-"save as"。你�以使用一个没有更改的包�补�的邮件，如果它是以正确的形�组�。当你正真在它
-自己的窗�之下察看，那时没有选项�以�存邮件--已�有一个这样的bug被汇报到了kmail的bugzilla
-并且希望这将会被处�。邮件是以�针对�个用户�读写的��被�存的，所以如果你想把邮件�制到其他地方，
-你�得�把他们的��改为组或者整体�读。
+如果你��以附件的形���补�，那么就�键点击附件，然�选择
+:menuselection:`属性` ，打开 :menuselection:`建议自动显示` ，使附件内�更容
+易让读者看到。
+
+当你��存将���的内嵌文本补�，你�以从消�列表窗格选择包�补�的邮件，然
+��键选择 :menuselection:`�存为` 。如果整个电�邮件的组�正确，您�直接将
+其作为补�使用。电�邮件以当�用户�读写���存，因此您必须 ``chmod`` ，以
+使其在�制到别处时用户组和其他人�读。
 
 Lotus Notes (GUI)
-~~~~~~~~~~~~~~~~~
+*****************
 
 ��使用它。
 
+IBM Verse (Web GUI)
+*******************
+
+�上�。
+
 Mutt (TUI)
-~~~~~~~~~~
+**********
+
+很多Linux开�人员使用mutt客户端，这�明它肯定工作得�常漂亮。
 
-很多Linux开�人员使用mutt客户端，所以�明它肯定工作的�常漂亮。
+Mutt�自带编辑器，所以�管你使用什么编辑器，�自动断行就行。大多数编辑器都有
+:menuselection:`�入文件` 选项，它�以在�改�文件内容的情况下�入文件。
 
-Mutt�自带编辑器，所以�管你使用什么编辑器都�应该带有自动断行。大多数编辑器都带有
-一个"insert file"选项，它�以通过�改�文件内容的方��入文件。
+用 ``vim`` 作为mutt的编辑器::
 
-'vim'作为mutt的编辑器：
   set editor="vi"
 
-  如果使用xclip，敲入以下命令
+如果使用xclip，敲入以下命令::
+
   :set paste
-  按中键之�或者shift-insert或者使用
+
+然��按中键或者shift-insert或者使用::
+
   :r filename
 
-如果想�把补�作为内嵌文本。
-(a)ttach工作的很好，�带有"set paste"。
+把补��入为内嵌文本。
+在未设置  ``set paste`` 时(a)ttach工作的很好。
 
 你�以通过 ``git format-patch`` 生�补�，然�用 Mutt��它们::
 
-        $ mutt -H 0001-some-bug-fix.patch
+    $ mutt -H 0001-some-bug-fix.patch
 
 �置选项：
+
 它应该以默认设置的形�工作。
-然而，把"send_charset"设置为"us-ascii::utf-8"也是一个�错的主�。
+然而，把 ``send_charset`` 设置一下也是一个�错的主�::
+
+  set send_charset="us-ascii:utf-8"
 
 Mutt 是高度��置的。 这里是个使用mutt通过 Gmail ��的补�的最��置::
 
@@ -178,71 +221,107 @@ Mutt 是高度��置的。 这里是个使用mutt通过 Gmail ��的补�
   set from = "username@gmail.com"
   set use_from = yes
 
-Mutt文档�有更多信�:
+Mutt文档�有更多信�：
 
-    http://dev.mutt.org/trac/wiki/UseCases/Gmail
+    https://gitlab.com/muttmua/mutt/-/wikis/UseCases/Gmail
 
-    http://dev.mutt.org/doc/manual.html
+    http://www.mutt.org/doc/manual/
 
 Pine (TUI)
-~~~~~~~~~~
+**********
 
 Pine过去有一些空格删�问题，但是这些现在应该都被修�了。
 
-如果�以，请使用alpine(pine的继承者)
+如果�以，请使用alpine（pine的继承者）。
 
 �置选项：
-- 最近的版本需�消除�程文本
-- "no-strip-whitespace-before-send"选项也是需�的。
+
+- 最近的版本需� ``quell-flowed-text``
+- ``no-strip-whitespace-before-send`` 选项也是需�的。
 
 
 Sylpheed (GUI)
-~~~~~~~~~~~~~~
+**************
 
 - 内嵌文本�以很好的工作（或者使用附件）。
 - �许使用外部的编辑器。
-- 对于目录较多时�常慢。
+- 收件箱较多时�常慢。
 - 如果通过non-SSL连接，无法使用TLS SMTP授�。
-- 在组�窗�中有一个很有用的ruler bar。
-- 给地�本中添加地�就�会正确的了解显示�。
+- 撰写窗�的标尺很有用。
+- 将地�添加到通讯簿时无法正确�解显示的�称。
 
 Thunderbird (GUI)
-~~~~~~~~~~~~~~~~~
+*****************
+
+Thunderbird是Outlook的克隆版本，它很容易��文本，但也有一些方法强制修正。
+
+在完�修改�（包括安装扩展），您需��新�动Thunderbird。
+
+- �许使用外部编辑器：
+
+  使用Thunderbird�补�最简�的方法是使用扩展�打开您最喜欢的外部编辑器。
+
+  下�是一些能够�到这一点的扩展样例。
+
+  - “External Editor Revived�
+
+    https://github.com/Frederick888/external-editor-revived
+
+    https://addons.thunderbird.net/en-GB/thunderbird/addon/external-editor-revived/
+
+    它需�安装“本地消�主机（native messaging host）�。
+    ��以下文档:
+    https://github.com/Frederick888/external-editor-revived/wiki
+
+  - “External Editor�
+
+    https://github.com/exteditor/exteditor
+
+    下载并安装此扩展，然�打开 :menuselection:`新建消�` 窗�, 用
+    :menuselection:`查看-->工具�-->自定义...` 给它增加一个按钮，直接点击此
+    按钮��使用外置编辑器。
+
+    请注�，“External Editor��求你的编辑器�能fork，���说，编辑器必须在
+    关闭��返回。你�能需�传递�外的�数或修改编辑器设置。最值得注�的是，
+    如果您使用的是gvim，那么您必须将 :menuselection:`external editor` 设置的
+    编辑器字段设置为 ``/usr/bin/gvim --nofork"`` （�设�执行文件在
+    ``/usr/bin`` ），以传递 ``-f`` �数。如果您正在使用其他编辑器，请阅读其
+    手册了解如何处�。
 
-默认情况下，thunderbird很容易��文本，但是还有一些方法�以强制它�得更好。
+若�修正内部编辑器，请执行以下�作：
 
-- 在用户��设置里，组�和寻�，��选择"Compose messages in HTML format"。
+- 修改你的Thunderbird设置，��使用 ``format=flowed`` �
+  回到主窗�，按照
+  :menuselection:`主��-->首选项-->常规-->�置编辑器...`
+  打开Thunderbird的�置编辑器。
 
-- 编辑你的Thunderbird�置设置�使它��拆行使用：user_pref("mailnews.wraplength", 0);
+  - 将 ``mailnews.send_plaintext_flowed`` 设为 ``false``
 
-- 编辑你的Thunderbird�置设置，使它��使用"format=flowed"格�：user_pref("mailnews.
-  send_plaintext_flowed", false);
+  - 将 ``mailnews.wraplength`` 从 ``72`` 改为 ``0``
 
-- 你需�使Thunderbird�为预先格�方�：
-  如果默认情况下你书写的是HTML格�，那�是很难。仅仅从标题�的下拉框中选择"Preformat"格�。
-  如果默认情况下你书写的是文本格�，你�得把它改为HTML格�（仅仅作为一次性的）�书写新的消�，
-  然�强制使它回到文本格�，�则它就会拆行。�实现它，在写信的图标上使用shift键�使它�为HTML
-  格�，然�标题�的下拉框中选择"Preformat"格�。
+- ��写HTML邮件�
+  回到主窗�，打开
+  :menuselection:`主��-->账户设置-->你的@邮件.地�-->通讯录/编写&地�簿` ，
+  关掉 ``以HTML格�编写消�`` 。
 
-- �许使用外部的编辑器：
-  针对Thunderbird打补�最简�的方法就是使用一个"external editor"扩展，然�使用你最喜欢的
-  $EDITOR�读�或者�并补�到文本中。�实现它，�以下载并且安装这个扩展，然�添加一个使用它的
-  按键View->Toolbars->Customize...最�当你书写信�的时候仅仅点击它就�以了。
+- �用纯文本格�查看邮件�
+  回到主窗�， :menuselection:`主��-->查看-->消�体为-->纯文本` �
 
 TkRat (GUI)
-~~~~~~~~~~~
+***********
 
 �以使用它。使用"Insert file..."或者外部的编辑器。
 
 Gmail (Web GUI)
-~~~~~~~~~~~~~~~
+***************
 
 ��使用它��补�。
 
 Gmail网页客户端自动地把制表符转�为空格。
 
-虽然制表符转�为空格问题�以被外部编辑器解决，�时它还会使用回车�行把�行拆分为78个字符。
+虽然制表符转�为空格问题�以被外部编辑器解决，但它�时还会使用回车�行把�行
+拆分为78个字符。
 
-�一个问题是Gmail还会把任何�是ASCII的字符的信�改为base64编�。它把东西�的�欧洲人的�字。
+�一个问题是Gmail还会把任何�有�ASCII的字符的消�改用base64编�，如欧洲人的
+�字。
 
-                                ###
diff --git a/Documentation/translations/zh_CN/process/submit-checklist.rst b/Documentation/translations/zh_CN/process/submit-checklist.rst
index a64858d321fc..3d6ee21c74ae 100644
--- a/Documentation/translations/zh_CN/process/submit-checklist.rst
+++ b/Documentation/translations/zh_CN/process/submit-checklist.rst
@@ -1,105 +1,111 @@
 .. include:: ../disclaimer-zh_CN.rst
 
-:Original: :ref:`Documentation/process/submit-checklist.rst <submitchecklist>`
-:Translator: Alex Shi <alex.shi@linux.alibaba.com>
+:Original: Documentation/process/submit-checklist.rst
+:Translator:
+ - Alex Shi <alexs@kernel.org>
+ - Wu XiangCheng <bobwxc@email.cn>
 
 .. _cn_submitchecklist:
 
-Linux内核补��交清�
-~~~~~~~~~~~~~~~~~~~~~
+Linux内核补��交检查�
+~~~~~~~~~~~~~~~~~~~~~~~
 
 如果开�人员希望看到他们的内核补��交更快地被接�，那么他们应该�一些基本
 的事情。
 
-这些都是在
-:ref:`Documentation/translations/zh_CN/process/submitting-patches.rst <cn_submittingpatches>`
+这些都是在 Documentation/translations/zh_CN/process/submitting-patches.rst
 和其他有关�交Linux内核补�的文档中�供的。
 
-1) 如果使用工具，则包括定义/声明该工具的文件。���赖于其他头文件拉入您使用
+1) 如果使用工具，则包括定义/声明该工具的文件。���赖其他头文件�引入您使用
    的头文件。
 
 2) 干净的编译：
 
-   a) 使用适用或修改的 ``CONFIG`` 选项 ``=y``�``=m`` 和 ``=n`` 。没有GCC
+   a) 使用�适的 ``CONFIG`` 选项 ``=y``�``=m`` 和 ``=n`` 。没有 ``gcc``
       警告/错误，没有链接器警告/错误。
 
-   b) 通过allnoconfig�allmodconfig
+   b) 通过 ``allnoconfig`` � ``allmodconfig``
 
    c) 使用 ``O=builddir`` 时�以�功编译
 
-3) 通过使用本地交�编译工具或其他一些构建场在多个CPU体系结构上构建。
+   d) 任何 Doucmentation/ 下的�更都能�功构建且�引入新警告/错误。
+      用 ``make htmldocs`` 或 ``make pdfdocs`` 检验构建情况并修�问题。
+
+3) 通过使用本地交�编译工具或其他一些构建设施在多个CPU体系结构上构建。
 
 4) PPC64是一�很好的交�编译检查体系结构，因为它倾�于对64�的数使用无符�
    长整型。
 
-5) 如下所述 :ref:`Documentation/translations/zh_CN/process/coding-style.rst <cn_codingstyle>`.
-   检查您的补�是�为常规样�。在�交（ ``scripts/check patch.pl`` ）之�，
-   使用补�样�检查器检查是�有轻微的冲�。您应该能够处�您的补�中存在的所有
+5) 按 Documentation/translations/zh_CN/process/coding-style.rst 所述检查您的
+   补�是�为常规样�。在�交之�使用补�样�检查器 ``scripts/checkpatch.pl``
+   检查是�有轻微的冲�。您应该能够处�您的补�中存在的所有
    �规行为。
 
-6) 任何新的或修改过的 ``CONFIG`` 选项都�会弄��置��，并默认为关闭，除�
-   它们符� ``Documentation/kbuild/kconfig-language.rst`` 中记录的异常�件,
-   ��属性：默认值.
+6) 任何新的或修改过的 ``CONFIG`` 选项都�应�乱�置��，并默认为关闭，除�
+   它们符� ``Documentation/kbuild/kconfig-language.rst`` ��属性：默认值中
+   记录的例外�件。
 
 7) 所有新的 ``kconfig`` 选项都有帮助文本。
 
 8) 已仔细审查了相关的 ``Kconfig`` 组�。这很难用测试�纠正——脑力在这里是有
    回报的。
 
-9) 用 sparse 检查干净。
+9) 通过 sparse 清查。
+   （�� Documentation/translations/zh_CN/dev-tools/sparse.rst ）
 
 10) 使用 ``make checkstack`` 和 ``make namespacecheck`` 并修�他们�现的任何
     问题。
 
     .. note::
 
-        ``checkstack`` 并没有明确指出问题，但是任何一个在堆栈上使用超过512
+        ``checkstack`` 并�会明确指出问题，但是任何一个在堆栈上使用超过512
         字节的函数都�以进行更改。
 
-11) 包括 :ref:`kernel-doc <kernel_doc>` 内核文档以记录全局内核API。（��函数
-    �需�，但也�以。）使用 ``make htmldocs`` 或 ``make pdfdocs`` 检查
-    :ref:`kernel-doc <kernel_doc>` 并修�任何问题。
+11) 包括 :ref:`kernel-doc <kernel_doc_zh>` 内核文档以记录全局内核API。（��
+    函数�需�，但也�以。）使用 ``make htmldocs`` 或 ``make pdfdocs`` 检查
+    :ref:`kernel-doc <kernel_doc_zh>` 并修�任何问题。
 
-12) 通过以下选项�时�用的测试 ``CONFIG_PREEMPT``, ``CONFIG_DEBUG_PREEMPT``,
+12) 通过以下选项�时�用的测试： ``CONFIG_PREEMPT``, ``CONFIG_DEBUG_PREEMPT``,
     ``CONFIG_DEBUG_SLAB``, ``CONFIG_DEBUG_PAGEALLOC``, ``CONFIG_DEBUG_MUTEXES``,
     ``CONFIG_DEBUG_SPINLOCK``, ``CONFIG_DEBUG_ATOMIC_SLEEP``,
-    ``CONFIG_PROVE_RCU`` and ``CONFIG_DEBUG_OBJECTS_RCU_HEAD``
-
-13) 已�过构建和�行时测试，包括有或没有 ``CONFIG_SMP``, ``CONFIG_PREEMPT``.
+    ``CONFIG_PROVE_RCU`` 和 ``CONFIG_DEBUG_OBJECTS_RCU_HEAD`` 。
 
-14) 如果补�程�影�IO/�盘等：使用或�使用 ``CONFIG_LBDAF`` 进行测试。
+13) 在 ``CONFIG_SMP``, ``CONFIG_PREEMPT`` 开�和关闭的情况下都进行构建和�行
+    时测试。
 
-15) 所有代�路径都已在�用所有lockdep功能的情况下�行。
+14) 所有代�路径都已在�用所有死�检测（lockdep）功能的情况下�行。
 
-16) 所有新的/proc�目都记录在 ``Documentation/``
+15) 所有新的 ``/proc`` �目都记录在 ``Documentation/``
 
-17) 所有新的内核引导�数都记录在
+16) 所有新的内核引导�数都记录在
     Documentation/admin-guide/kernel-parameters.rst 中。
 
-18) 所有新的模��数都记录在 ``MODULE_PARM_DESC()``
+17) 所有新的模��数都记录在 ``MODULE_PARM_DESC()``
 
-19) 所有新的用户空间接�都记录在 ``Documentation/ABI/`` 中。有关详细信�，
+18) 所有新的用户空间接�都记录在 ``Documentation/ABI/`` 中。有关详细信�，
     请�阅 ``Documentation/ABI/README`` 。更改用户空间接�的补�应该抄�
     linux-api@vger.kernel.org。
 
-20) 已通过至少注入slab和page分�失败进行检查。请�阅 ``Documentation/fault-injection/``
+19) 已通过至少注入slab和page分�失败进行检查。请�阅 ``Documentation/fault-injection/`` 。
     如果新代�是实质性的，那么添加�系统特定的故障注入�能是�适的。
 
-21) 新添加的代�已�用 ``gcc -W`` 编译（使用 ``make EXTRA-CFLAGS=-W`` ）。这
+20) 新添加的代�已�用 ``gcc -W`` 编译（使用 ``make EXTRA-CFLAGS=-W`` ）。这
     将产生大�噪声，但对于查找诸如“警告：有符�和无符�之间的比较�之类的错误
     很有用。
 
-22) 在它被�并到-mm补�集中之�进行测试，以确�它�然与所有其他排队的补�以
+21) 在它被�并到-mm补�集中之�进行测试，以确�它�然与所有其他排队的补�以
     �VM�VFS和其他�系统中的��更改一起工作。
 
-23) 所有内存�障例如 ``barrier()``, ``rmb()``, ``wmb()`` 都需��代�中的注
+22) 所有内存�障（例如 ``barrier()``, ``rmb()``, ``wmb()`` ）都需��代�注
     释�解释它们正在执行的�作�其原因的逻辑。
 
-24) 如果补�添加了任何ioctl，那么也�更新 ``Documentation/userspace-api/ioctl/ioctl-number.rst``
+23) 如果补�添加了任何ioctl，那么也�更新
+    ``Documentation/userspace-api/ioctl/ioctl-number.rst`` 。
 
-25) 如果修改�的�代��赖或使用与以下 ``Kconfig`` 符�相关的任何内核API或
+24) 如果修改�的�代��赖或使用与以下 ``Kconfig`` 符�相关的任何内核API或
     功能，则在�用相关 ``Kconfig`` 符�和/或 ``=m`` （如果该选项�用）的情况
     下测试以下多个构建[并�所有这些都�时存在，�是它们的��/�机组�]：
 
-    ``CONFIG_SMP``, ``CONFIG_SYSFS``, ``CONFIG_PROC_FS``, ``CONFIG_INPUT``, ``CONFIG_PCI``, ``CONFIG_BLOCK``, ``CONFIG_PM``, ``CONFIG_MAGIC_SYSRQ``,
-    ``CONFIG_NET``, ``CONFIG_INET=n`` (但是�者伴� ``CONFIG_NET=y``).
+    ``CONFIG_SMP``, ``CONFIG_SYSFS``, ``CONFIG_PROC_FS``, ``CONFIG_INPUT``,
+    ``CONFIG_PCI``, ``CONFIG_BLOCK``, ``CONFIG_PM``, ``CONFIG_MAGIC_SYSRQ``,
+    ``CONFIG_NET``, ``CONFIG_INET=n`` （但是最�一个需� ``CONFIG_NET=y`` ）。
diff --git a/Documentation/translations/zh_CN/process/submitting-patches.rst b/Documentation/translations/zh_CN/process/submitting-patches.rst
index ebb7f37575c1..f8978f02057c 100644
--- a/Documentation/translations/zh_CN/process/submitting-patches.rst
+++ b/Documentation/translations/zh_CN/process/submitting-patches.rst
@@ -1,142 +1,92 @@
-.. _cn_submittingpatches:
+.. SPDX-License-Identifier: GPL-2.0-or-later
 
 .. include:: ../disclaimer-zh_CN.rst
 
-:Original: :ref:`Documentation/process/submitting-patches.rst <submittingpatches>`
+.. _cn_submittingpatches:
+
+:Original: Documentation/process/submitting-patches.rst
 
-译者::
+:译者:
+ - 钟宇 TripleX Chung <xxx.phy@gmail.com>
+ - 时奎亮 Alex Shi <alexs@kernel.org>
+ - �想� Wu XiangCheng <bobwxc@email.cn>
 
-        中文版维护者： 钟宇 TripleX Chung <xxx.phy@gmail.com>
-        中文版翻译者： 钟宇 TripleX Chung <xxx.phy@gmail.com>
-                       时奎亮 Alex Shi <alex.shi@linux.alibaba.com>
-        中文版校译者： �阳 Li Yang <leoyang.li@nxp.com>
-                       王� Wang Cong <xiyou.wangcong@gmail.com>
+:校译:
+ - �阳 Li Yang <leoyang.li@nxp.com>
+ - 王� Wang Cong <xiyou.wangcong@gmail.com>
 
 
-如何让你的改动进入内核
-======================
+�交补�：如何让你的改动进入内核
+================================
 
 对于想�将改动�交到 Linux 内核的个人或者公��说，如果�熟悉“规矩�，
-�交的�程会让人�惧。本文档收集了一系列建议，这些建议�以大大的�高你
+�交的�程会让人�惧。本文档包�了一系列建议，�以大大�高你
 的改动被接�的机会.
 
-以下文档�有大�简�的建议， 具体请�：
-:ref:`Documentation/process <development_process_main>`
-�样，:ref:`Documentation/translations/zh_CN/process/submit-checklist.rst <cn_submitchecklist>`
-给出在�交代��需�检查的项目的列表。
+本文档以较为简�的行文给出了大�建议。关于内核开��程如何进行的详细信�，
+��： Documentation/translations/zh_CN/process/development-process.rst 。
+Documentation/translations/zh_CN/process/submit-checklist.rst 给出了一系列
+�交补�之��检查的事项。设备树相关的补�，请�阅
+Documentation/devicetree/bindings/submitting-patches.rst 。
 
-其中许多步骤�述了Git版本控制系统的默认行为；如果您使用Git�准备补�，
-您将�现它为您完�的大部分机械工作，尽管您�然需�准备和记录一组��的
-补�。一般�说，使用git将使您作为内核开�人员的生活更轻�。
+本文档�设您正在使用 ``git`` 准备你的补�。如果您�熟悉 ``git`` ，最好学习
+如何使用它，这将使您作为内核开�人员的生活�得更加轻�。
 
+部分�系统和维护人员的树有一些关于其工作�程和�求的�外信�，请�阅
+Documentation/process/maintainer-handbooks.rst 。
 
-0) 获�当���树
------------------
+获�当���树
+--------------
 
-如果您没有一个�以使用当�内核�代�的存储库，请使用git获�一个。您将�
-从主线存储库开始，它�以通过以下方�获�::
+如果您手头没有当�内核�代�的存储库，请使用 ``git`` 获�一份。您需�先获�
+主线存储库，它�以通过以下命令拉�::
 
-        git clone git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
+    git clone git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
 
-但是，请注�，您�能�希望直接针对主线树进行开�。大多数�系统维护人员�
+但是，请注�，您�能�想直接针对主线树进行开�。大多数�系统维护人员�
 行自己的树，并希望看到针对这些树准备的补�。请��MAINTAINERS文件中�系
-统的 **T:** 项以查找该树，或者简�地询问维护者该树是�未在其中列出。
-
-�然�以通过tarballs下载内核版本（如下一节所述），但这是进行内核开�的
-一�困难的方�。
-
-1) "diff -up"
--------------
-
-使用 "diff -up" 或者 "diff -uprN" �创建补�。
-
-所有内核的改动，都是以补�的形�呈现的，补�由 diff(1) 生�。创建补�的
-时候，�确认它是以 "unified diff" 格�创建的，这�格�由 diff(1) 的 '-u'
-�数生�。而且，请使用 '-p' �数，那样会显示�个改动所在的C函数，使得
-产生的补�容易读得多。补�应该基于内核�代�树的根目录，而�是里边的任
-何�目录。
-
-为一个�独的文件创建补�，一般�说这样�就够了::
-
-        SRCTREE=linux
-        MYFILE=drivers/net/mydriver.c
+统的 **T:** 项以查找该树，或者直接询问维护者该树是�未在其中列出。
 
-        cd $SRCTREE
-        cp $MYFILE $MYFILE.orig
-        vi $MYFILE      # make your change
-        cd ..
-        diff -up $SRCTREE/$MYFILE{.orig,} > /tmp/patch
+.. _zh_describe_changes:
 
-为多个文件创建补�，你�以解开一个没有修改过的内核�代�树，然�和你自
-己的代�树之间� diff 。例如::
-
-        MYSRC=/devel/linux
-
-        tar xvfz linux-3.19.tar.gz
-        mv linux-3.19 linux-3.19-vanilla
-        diff -uprN -X linux-3.19-vanilla/Documentation/dontdiff \
-                linux-3.19-vanilla $MYSRC > /tmp/patch
-
-"dontdiff" 是内核在编译的时候产生的文件的列表，列表中的文件在 diff(1)
-产生的补�里会被跳过。
-
-确定你的补�里没有包�任何�属于这次补��交的�外文件。记得在用diff(1)
-生�补�之�，审阅一次补�，以确�准确。
-
-如果你的改动很散乱，你应该研究一下如何将补�分割�独立的部分，将改动分
-割�一系列�乎逻辑的步骤。这样更容易让其他内核开�者审核，如果你想你的
-补�被接�，这是很��的。请�阅：
-:ref:`cn_split_changes`
-
-如果你用 ``git`` , ``git rebase -i`` �以帮助你这一点。如果你�用 ``git``,
-``quilt`` <https://savannah.nongnu.org/projects/quilt> �外一个�行的选择。
-
-.. _cn_describe_changes:
-
-2) �述你的改动
----------------
+�述你的改动
+------------
 
 �述你的问题。无论您的补�是一行错误修�还是5000行新功能，都必须有一个潜在
-的问题激励您完�这项工作。让审稿人相信有一个问题值得解决，让他们读完第一段
-是有�义的。
+的问题激励您完�这项工作。说�审阅者相信有一个问题值得解决，让他们读完第一段
+�就能明白这一点。
 
 �述用户��的影�。直接崩溃和�定是相当有说�力的，但并�是所有的错误都那么
-明目张胆。�使在代�审查期间�现了这个问题，也��述一下您认为它�能对用户产
+明目张胆。�使在代�审阅期间�现了这个问题，也��述一下您认为它�能对用户产
 生的影�。请记�，大多数Linux安装�行的内核�自二级稳定树或特定于供应商/产�
 的树，�从上游精选特定的补�，因此请包�任何�以帮助您将更改定�到下游的内容：
 触�的场景�DMESG的摘录�崩溃�述�性能回归�延迟尖峰��定等。
 
-�化优化和�衡。如果您声称在性能�内存消耗�堆栈�用空间或二进制大�方�有所
-改进，请包括支�它们的数字。但也��述�明显的�本。优化通常�是�费的，而是
-在CPU�内存和�读性之间进行�衡；或者，探索性的工作，在��的工作负载之间进
+质�优化和�衡。如果您声称在性能�内存消耗�堆栈�用空间或二进制大�方�有所
+改进，请包括支�它们的数�。但也��述�明显的�本。优化通常�是零�本的，而是
+在CPU�内存和�读性之间进行�衡；或者，�探索性的工作，在��的工作负载之间进
 行�衡。请�述优化的预期缺点，以便审阅者�以�衡�本和收益。
 
-一旦问题建立起�，就�详细地�述一下您实际在�什么。对于审阅者�说，用简�的
-英语�述代�的�化是很��的，以验�代�的行为是�符�您的�愿。
+�出问题之�，就�详细地�述一下您实际在�的技术细节。对于审阅者�说，用简练的
+英语�述代�的�化是很��的，以验�代�的行为是�符�您的�图。
 
-如果您将补��述写在一个表�中，这个表��以很容易地作为“�交日志�放入Linux
-的�代�管�系统git中，那么维护人员将�常感谢您。� :ref:`cn_explicit_in_reply_to`.
+如果您将补��述写�“标准格��，�以很容易地作为“�交日志�放入Linux的�代
+�管�系统 ``git`` 中，那么维护人员将�常感谢您。
+�� :ref:`zh_the_canonical_patch_format` 。
 
 �个补��解决一个问题。如果你的�述开始�长，这就表明你�能需�拆分你的补�。
-请� :ref:`cn_split_changes`
+请� :ref:`zh_split_changes` 。
 
-�交或�新�交修补程�或修补程�系列时，请包括完整的修补程�说明和�由。��
+�交或�新�交补�或补�系列时，请包括完整的补�说明和�由。��
 �说这是补�（系列）的第几版。��期望�系统维护人员引用更早的补�版本或引用
 URL�查找补��述并将其放入补�中。也就是说，补�（系列）�其�述应该是独立的。
-这对维护人员和审查人员都有好处。一些评审者�能甚至没有收到补�的早期版本。
+这对维护人员和审阅者都有好处。一些审阅者�能甚至没有收到补�的早期版本。
 
-�述你在命令语气中的�化，例如“make xyzzy do frotz�而�是“[This patch]make
+用祈使��述你的�更，例如“make xyzzy do frotz�而�是“[This patch]make
 xyzzy do frotz�或“[I]changed xyzzy to do frotz�，就好�你在命令代�库改�
 它的行为一样。
 
-如果修补程�修�了一个记录的bug�目，请按编�和URL引用该bug�目。如果补��
-自邮件列表讨论，请给出邮件列表存档的URL；使用带有 ``Message-ID`` 的
-https://lore.kernel.org/ �定�，以确�链接�会过时。
-
-但是，在没有外部资�的情况下，尽�让你的解释��解。除了�供邮件列表存档或
-bug的URL之外，还�总结需��交补�的相关讨论�点。
-
-如果您想�引用一个特定的�交，���引用�交的 SHA-1 ID。还请包括�交的一行
+如果您想�引用一个特定的�交，���引用�交的SHA-1 ID。还请包括�交的一行
 摘�，以便于审阅者了解它是关于什么的。例如::
 
         Commit e21d2170f36602ae2708 ("video: remove unnecessary
@@ -144,82 +94,104 @@ bug的URL之外，还�总结需��交补�的相关讨论�点。
         platform_set_drvdata(), but left the variable "dev" unused,
         delete it.
 
-您还应该确�至少使用�12� SHA-1 ID. 内核存储库包�*许多*对象，使与较短的ID
+您还应该确�至少使用�12�SHA-1 ID。内核存储库包� *许多* 对象，使较短的ID
 �生冲�的�能性很大。记�，�使现在�会与您的六个字符ID�生冲�，这�情况
-�能五年�改�。
+也�能在五年�改�。
+
+如果该�更的相关讨论或背景信��以在网上查阅，请加上“Link:�标签指�它。例如
+你的补�修�了一个缺陷，需�添加一个带有URL的标签指�邮件列表存档或缺陷跟踪器
+的相关报告；如果该补�是由一些早先邮件列表讨论或网络上的记录引起的，请指�它。
+
+当链接到邮件列表存档时，请首选lore.kernel.org邮件存档�务。用邮件中的
+``Message-ID`` 头（去掉尖括�）�以创建链接URL。例如::
+
+    Link: https://lore.kernel.org/r/30th.anniversary.repost@klaava.Helsinki.FI/
+
+请检查该链接以确��用且指�正确的邮件。
 
-如果修补程�修�了特定�交中的错误，例如，使用 ``git bisct`` ，请使用带有�
-12个字符SHA-1 ID 的"Fixes:"标记和�行摘�。为了简化��将标记拆分为多个，
-行�标记��分�脚本“75列�行�规则的�制。例如::
+�过，在没有外部资�的情况下，也�尽�让你的解释��解。除了�供邮件列表存档或
+缺陷的URL之外，还�需�总结该补�的相关讨论�点。
 
-        Fixes: 54a4f0239f2e ("KVM: MMU: make kvm_mmu_zap_page() return the number of pages it actually freed")
+如果补�修�了特定�交中的错误，例如使用 ``git bisct`` �现了一个问题，请使用
+带有�12个字符SHA-1 ID的“Fixes:�标签和�行摘�。为了简化解�脚本，��将该
+标签拆分为多行，标签��“75列�行�规则的�制。例如::
 
-下列 ``git config`` 设置�以添加让 ``git log``, ``git show`` 漂亮的显示格�::
+  Fixes: 54a4f0239f2e ("KVM: MMU: make kvm_mmu_zap_page() return the number of pages it actually freed")
+
+下列 ``git config`` 设置�以让 ``git log``, ``git show`` 增加上述风格的显示格�::
 
 	[core]
 		abbrev = 12
 	[pretty]
 		fixes = Fixes: %h (\"%s\")
 
-.. _cn_split_changes:
+使用示例::
+
+	$ git log -1 --pretty=fixes 54a4f0239f2e
+	Fixes: 54a4f0239f2e ("KVM: MMU: make kvm_mmu_zap_page() return the number of pages it actually freed")
 
-3) 拆分你的改动
----------------
+.. _zh_split_changes:
 
-将�个逻辑更改分隔�一个�独的补�。
+拆分你的改动
+------------
+
+将�个 **逻辑更改** 拆分�一个�独的补�。
 
 例如，如果你的改动里�时有bug修正和性能优化，那么把这些改动拆分到两个或
-者更多的补�文件中。如果你的改动包�对API的修改，并且修改了驱动程��适
-应这些新的API，那么把这些修改分�两个补�。
+者更多的补�文件中。如果你的改动包�对API的修改，并且增加了一个使用该新API
+的驱动，那么把这些修改分�两个补�。
 
 �一方�，如果你将一个�独的改动��多个补�文件，那么将它们�并�一个
 �独的补�文件。这样一个逻辑上�独的改动�被包�在一个补�文件里。
 
-如果有一个补��赖�外一个补��完�它的改动，那没问题。简�的在你的补
-��述里指出“这个补��赖�补��就好了。
+需�记�的一点是，�个补�的更改都应易于�解，以便审阅者验�。�个补�都应该
+对其价值进行�述。
+
+如果有一个补��赖�外一个补��完�它的改动，那没问题。直接在你的补
+��述里指出 **“这个补��赖�补��** 就好了。
 
-在将您的更改划分为一系列补�时，�特别注�确�内核在系列中的�个补�之�
-都能正常构建和�行。使用 ``git bisect`` �追踪问题的开�者�能会在任何时
-候分割你的补�系列；如果你在中间引入错误，他们�会感谢你。
+在将您的更改划分为一系列补�时，�特别注�确�内核在应用系列中的�个补�之�
+都能正常构建和�行。使用 ``git bisect`` �追踪问题的开�者�能会在任何地方分
+割你的补�系列；如果你在中间引入错误，他们�会感谢你。
 
-如果你�能将补�浓缩�更少的文件，那么�次大约��出15个，然�等待审查
+如果你�能将补�系列浓缩得更�，那么�次大约��出15个补�，然�等待审阅
 和集�。
 
-4) 检查你的更改风格
--------------------
+检查你的更改风格
+----------------
 
-检查您的补�是�存在基本样�冲�，详细信��在
-:ref:`Documentation/translations/zh_CN/process/coding-style.rst <cn_codingstyle>`
-中找到。如果�这样�，�会浪费审稿人的时间，并且会导致你的补�被拒�，甚至
+检查您的补�是���了基本样�规定，详细信���
+Documentation/translations/zh_CN/process/coding-style.rst
+中找到。如果�这样�，�会浪费审阅者的时间，并且会导致你的补�被拒�，甚至
 �能没有被阅读。
 
 一个��的例外是在将代�从一个文件移动到�一个文件时——在这�情况下，您�应
 该在移动代�的�一个补�中修改移动的代�。这清楚地�述了移动代�和您的更改
-的行为。这大大有助于审查实际差异，并�许工具更好地跟踪代�本身的历�。
+的行为。这大大有助于审阅实际差异，并�许工具更好地跟踪代�本身的历�。
 
 在�交之�，使用补�样�检查程�检查补�（scripts/check patch.pl）。�过，
 请注�，样�检查程�应该被视为一个指�，而�是作为人类判断的替代�。如果您
-的代�看起�更好，但有�规行为，那么最好��使用它。
+的代�看起�更好，但有�规行为，那么最好别管它。
 
 检查者报告三个级别：
 
  - ERROR：很�能出错的事情
- - WARNING：需�仔细审查的事项
+ - WARNING：需�仔细审阅的事项
  - CHECK：需��考的事情
 
 您应该能够判断您的补�中存在的所有�规行为。
 
-5) 选择补�收件人
------------------
+选择补�收件人
+--------------
 
-您应该总是在任何补�上�制相应的�系统维护人员，以获得他们维护的代�；查看
+您应该总是知会任何补�相应代�的�系统维护人员；查看
 维护人员文件和�代�修订历�记录，以了解这些维护人员是�。脚本
-scripts/get_Maintainer.pl在这个步骤中�常有用。如果您找�到正在工作的�系统
+scripts/get_maintainer.pl在这个步骤中�常有用。如果您找�到正在工作的�系统
 的维护人员，那么Andrew Morton（akpm@linux-foundation.org）将充当最�的维护
 人员。
 
-您通常还应该选择至少一个邮件列表�接收补�集的。linux-kernel@vger.kernel.org
-作为最�一个解决办法的列表，但是这个列表上的体积已�引起了许多开�人员的拒�。
+您通常还应该选择至少一个邮件列表�接收补�集的副本。linux-kernel@vger.kernel.org
+是所有补�的默认列表，但是这个列表的��已�导致了许多开�人员��看它。
 在MAINTAINERS文件中查找�系统特定的列表；您的补��能会在那里得到更多的关注。
 �过，请����垃圾邮件到无关的列表。
 
@@ -229,189 +201,170 @@ http://vger.kernel.org/vger-lists.html 上找到它们的列表。ä¸�过，也æœ
 
 ��一次��超过15个补�到vger邮件列表����
 
-Linus Torvalds 是决定改动能�进入 Linux 内核的最终�决者。他的 e-mail
-地�是 <torvalds@linux-foundation.org> 。他收到的 e-mail 很多，所以一般
-的说，最好别给他� e-mail。
-
-如果您有修��利用安全�洞的补�，请将该补���到 security@kernel.org。对于
-严�的bug，�以考虑短期暂�以�许分销商�用户�布补�；在这�情况下，显然�应
-将补���到任何公共列表。
+Linus Torvalds是决定改动能�进入 Linux 内核的最终�决者。他的邮件地�是
+torvalds@linux-foundation.org 。他收到的邮件很多，所以一般�说最好 **别**
+给他�邮件。
 
-修�已�布内核中严�错误的补�程�应该指�稳定版维护人员，方法是放这样的一行::
+如果您有修��利用安全�洞的补�，请将该补���到 security@kernel.org 。对于
+严�的bug，�以考虑短期�令以�许分销商（有时间）�用户�布补�；在这�情况下，
+显然�应将补���到任何公共列表。
+�� Documentation/translations/zh_CN/admin-guide/security-bugs.rst 。
 
-        Cc: stable@vger.kernel.org
+修�已�布内核中严�错误的补�程�应该抄�给稳定版维护人员，方法是把以下列行
+放进补�的签准区（注�，�是电�邮件收件人）::
 
-进入补�的签准区（注�，�是电�邮件收件人）。除了这个文件之外，您还应该阅读
-:ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`
+  Cc: stable@vger.kernel.org
 
-但是，请注�，一些�系统维护人员希望得出他们自己的结论，�哪些补�应该被放到
-稳定的树上。尤其是网络维护人员，�希望看到�个开�人员在补�中添加�上�这样
-的行。
+除了本文件之外，您还应该阅读
+Documentation/translations/zh_CN/process/stable-kernel-rules.rst 。
 
-如果更改影�到用户和内核接�，请�手册页维护人员（如维护人员文件中所列）��
+如果更改影�到用户侧内核接�，请�手册页维护人员（如维护人员文件中所列）��
 手册页补�，或至少��更改通知，以便一些信�进入手册页。还应将用户空间API
-更改�制到 linux-api@vger.kernel.org。
+更改抄�到 linux-api@vger.kernel.org 。
 
 
-6) 没有 MIME 编�，没有链接，没有压缩，没有附件，�有纯文本
------------------------------------------------------------
+��MIME编�，��链接，��压缩，��附件，��纯文本
+------------------------------------------------------
 
 Linus 和其他的内核开�者需�阅读和评论你�交的改动。对于内核开�者�说
-，�以“引用�你的改动很��，使用一般的 e-mail 工具，他们就�以在你的
+，�以“引用�你的改动很��，使用一般的邮件工具，他们就�以在你的
 代�的任何�置添加评论。
 
-因为这个原因，所有的�交的补�都是 e-mail 中“内嵌�的。
+因为这个原因，所有的�交的补�都是邮件中“内嵌�的。最简�（和推�）的方法就
+是使用 ``git send-email`` 。https://git-send-email.io 有 ``git send-email``
+的交互�教程。
+
+如果你选择�用 ``git send-email`` ：
 
 .. warning::
-   如果你使用剪切-粘贴你的补�，�心你的编辑器的自动�行功能破�你的补�
 
-��将补�作为 MIME 编�的附件，�管是�压缩。很多�行的 e-mail 软件�
-是任何时候都将 MIME 编�的附件当作纯文本��的，这会使得别人无法在你的
-代�中加评论。�外，MIME 编�的附件会让 Linus 多花一点时间�处�，这就
-�低了你的改动被接�的�能性。
+  如果你使用剪切-粘贴你的补�，�心你的编辑器的自动�行功能破�你的补�
 
-例外：如果你的邮递员弄�了补�，那么有人�能会�求你使用mime�新��补�
+��将补�作为MIME编�的附件，�管是�压缩。很多�行的邮件软件�
+是任何时候都将MIME编�的附件当作纯文本��的，这会使得别人无法在你的
+代�中加评论。�外，MIME编�的附件会让Linus多花一点时间�处�，这就
+�低了你的改动被接�的�能性。
 
-请�阅 :ref:`Documentation/translations/zh_CN/process/email-clients.rst <cn_email_clients>`
-以获�有关�置电�邮件客户端以使其��影�地��修补程�的�示。
+例外：如果你的邮路��了补�，那么有人�能会�求你使用MIME�新��补�。
 
-7) e-mail 的大�
-----------------
+请�阅 Documentation/translations/zh_CN/process/email-clients.rst
+以获�有关�置电�邮件客户端以使其��影�地��补�的�示。
 
-大的改动对邮件列表��适，对�些维护者也��适。如果你的补�，在�压缩
-的情况下，超过了300kB，那么你最好将补�放在一个能通过 internet 访问的�
-务器上，然�用指�你的补�的 URL 替代。但是请注�，如果您的补�超过了
-300kb，那么它几乎肯定需�被破�。
+回�审阅��
+------------
 
-8）回�评审��
----------------
+你的补�几乎肯定会得到审阅者对补�改进方法的评论（以回�邮件的形�）。您必须
+对这些评论作出回应；让补�被忽略的一个好办法就是忽略审阅者的��。直接回�邮
+件�回应����。�会导致代�更改的��或问题几乎肯定会带�注释或�更日志的
+改�，以便下一个审阅者更好地了解正在�生的事情。
 
-你的补�几乎肯定会得到评审者对补�改进方法的评论。您必须对这些评论作出
-回应；让补�被忽略的一个好办法就是忽略审阅者的��。�会导致代�更改的
-��或问题几乎肯定会带�注释或�更日志的改�，以便下一个评审者更好地了解
-正在�生的事情。
+一定�告诉审阅者你在�什么改�，并感谢他们的时间。代�审阅是一个累人且耗时的
+过程，审阅者有时会�得暴�。�使在这�情况下，也�礼貌地回应并解决他们指出的
+问题。当��下一版时，在��邮件或独立补�里加上 ``patch changelog`` 说明与
+�一版本的��之处（�� :ref:`zh_the_canonical_patch_format` ）。
 
-一定�告诉审稿人你在�什么改�，并感谢他们的时间。代�审查是一个累人且
-耗时的过程，审查人员有时会�得暴�。�使在这�情况下，也�礼貌地回应并
-解决他们指出的问题。
+.. _zh_resend_reminders:
 
-9）��泄气或��烦
--------------------
+��泄气或��烦
+----------------
 
-�交更改�，请�心等待。审阅者是忙碌的人，�能无法立�访问您的修补程�。
+�交更改�，请�心等待。审阅者是大忙人，�能无法立�审阅您的补�。
 
-曾几何时，补�曾在没有评论的情况下消失在空白中，但开�过程比现在更加顺利。
+曾几何时，补�曾在没收到评论的情况下消失在虚空中，但现在开�过程应该更加顺利了。
 您应该在一周左�的时间内收到评论；如果没有收到评论，请确�您已将补���
-到正确的�置。在�新�交或�系审阅者之�至少等待一周-在诸如�并窗�之类的
+到正确的�置。在�新�交或�系审阅者之�至少等待一周——在诸如�并窗�之类的
 �忙时间�能更长。
 
-10）主题中包� PATCH
---------------------
+在等了几个星期�，用带RESEND的主题��补�也是�以的::
 
-由于到linus和linux内核的电�邮件��很高，通常会在主题行��加上[PATCH]
-�缀. 这使Linus和其他内核开�人员更容易将补�与其他电�邮件讨论区分开。
+   [PATCH Vx RESEND] sub/sys: Condensed patch summary
 
-11）签署你的作�-开�者原始认�
--------------------------------
+当你�布补�（系列）修改版的时候，��加上“RESEND�——“RESEND��适用于�
+新�交之�未�修改的补�（系列）。
 
-为了加强对��了何事的追踪，尤其是对那些�过好几层的维护者的补�，我们
-建议在��出去的补�上加一个 “sign-off� 的过程。
+主题中包� PATCH
+----------------
 
-"sign-off" 是在补�的注释的最�的简�的一行文字，认�你编写了它或者其他
+由于到Linus和linux-kernel的电�邮件��很高，通常会在主题行��加上[PATCH]
+�缀。这使Linus和其他内核开�人员更容易将补�与其他电�邮件讨论区分开。
+
+``git send-email`` 会自动为你加上。
+
+签署你的作�——开�者��认�
+------------------------------
+
+为了加强对��了何事的追踪，尤其是对那些�过好几层维护者�最终到达的补�，我
+们在通过邮件��的补�上引入了“签署（sign-off）��程。
+
+“签署�是在补�注释最�的一行简�文字，认�你编写了它或者其他
 人有�力将它作为开放�代�的补�传递。规则很简�：如果你能认�如下信�:
 
-开�者���书 1.1
+开�者��认� 1.1
 ^^^^^^^^^^^^^^^^^^
 
 对于本项目的贡献，我认�如下信�：
 
-      （a）这些贡献是完全或者部分的由我创建，我有�利以文件中指出
+       (a) 这些贡献是完全或者部分的由我创建，我有�利以文件中指出
            的开放�代�许���交它；或者
-      （b）这些贡献基于以�的工作，�我所知，这些以�的工作��当的开放
-           �代�许���护，而且，根�许��，我有��交修改�的贡献，
+
+       (b) 这些贡献基于以�的工作，�我所知，这些以�的工作��当的开放
+           �代�许���护，而且，根�文件中指出的许��，我有��交修改�的贡献，
            无论是完全还是部分由我创造，这些贡献都使用�一个开放�代�许��
-           （除�我被�许用其它的许��），正如文件中指出的；或者
-      （c）这些贡献由认�（a），（b）或者（c）的人直接�供给我，而
+           （除�我被�许用其它的许��）；或者
+
+       (c) 这些贡献由认�（a），（b）或者（c）的人直接�供给我，而
            且我没有修改它。
-      （d）我�解并��这个项目和贡献是公开的，贡献的记录（包括我
-           一起�交的个人记录，包括 sign-off ）被永久维护并且�以和这个项目
+
+       (d) 我�解并��这个项目和贡献是公开的，贡献的记录（包括我
+           一起�交的个人记录，包括sign-off）被永久维护并且�以和这个项目
            或者开放�代�的许���步地��行。
 
 那么加入这样一行::
 
-       Signed-off-by: Random J Developer <random@developer.example.org>
-
-使用你的真�（抱歉，�能使用��或者匿�。）
-
-有人在最�加上标签。现在这些东西会被忽略，但是你�以这样�，�标记公�
-内部的过程，或者�是指出关于 sign-off 的一些特殊细节。
-
-如果您是�系统或分支维护人员，有时需��微修改收到的补�，以便�并它们，
-因为树和�交者中的代��完全相�。如果你严格�守规则（c），你应该�求�交者
-�新�布，但这完全是在浪费时间和精力。规则（b）�许您调整代�，但是更改一个
-�交者的代�并让他认�您的错误是�常�礼貌的。�解决此问题，建议在最�一个
-由签�行和您的行之间添加一行，指示更改的性质。虽然这并�是强制性的，但似乎
-在�述�加上您的邮件和/或姓�（全部用方括�括起�），这足以让人注�到您对最
-�一分钟的更改负有责任。例如::
-
-	Signed-off-by: Random J Developer <random@developer.example.org>
-	[lucky@maintainer.example.org: struct foo moved from foo.c to foo.h]
-	Signed-off-by: Lucky K Maintainer <lucky@maintainer.example.org>
-
-如果您维护一个稳定的分支机构，�时希望对作者进行致谢�跟踪更改��并修�并
-�护�交者��投诉，那么这��法尤其有用。请注�，在任何情况下都�能更改作者
-的ID（From 头），因为它是出现在更改日志中的标识。
-
-对回�（back-porters）的特别说明：在�交消�的顶部（主题行之�）�入一个补�
-的起�指示似乎是一�常�且有用的实践，以便于跟踪。例如，下�是我们在3.x稳定
-版本中看到的内容::
-
-  Date:   Tue Oct 7 07:26:38 2014 -0400
-
-    libata: Un-break ATA blacklist
-
-    commit 1c40279960bcd7d52dbdf1d466b20d24b99176c8 upstream.
-
-还有， 这里是一个旧版内核中的一个回�补�::
+  Signed-off-by: Random J Developer <random@developer.example.org>
 
-    Date:   Tue May 13 22:12:27 2008 +0200
+使用你的真�（抱歉，�能使用��或者匿�。）如果使用 ``git commit -s`` 的�
+将会自动完�。撤销也应当包�“Signed-off-by�， ``git revert -s`` 会帮你�定。
 
-        wireless, airo: waitbusy() won't delay
+有些人会在最�加上�外的标签。现在这些东西会被忽略，但是你�以这样�，�标记
+公�内部的过程，或者�是指出关于签署的一些特殊细节。
 
-        [backport of 2.6 commit b7acbdfbd1f277c1eb23f344f899cfa4cd0bf36a]
+作者签署之�的任何其他签署（Signed-off-by:'s）��自处�和传递补�的人员，但
+未�与其开�。签署链应当�映补�传播到维护者并最终传播到Linus所�过的 **真实**
+路径，首个签署指明�个作者的主�作者身份。
 
-12）何时使用Acked-by:，CC:，和Co-Developed by:
-----------------------------------------------
+何时使用Acked-by:，CC:，和Co-Developed by:
+------------------------------------------
 
-Singed-off-by: 标记表示签�者�与了补�的开�，或者他/她在补�的传递路径中。
+Singed-off-by: 标签表示签�者�与了补�的开�，或者他/她在补�的传递路径中。
 
-如果一个人没有直接�与补�的准备或处�，但希望表示并记录他们对补�的批准，
-那么他们�以�求在补�的�更日志中添加一个 Acked-by:
+如果一个人没有直接�与补�的准备或处�，但希望表示并记录他们对补�的批准/赞�，
+那么他们�以�求在补�的�更日志中添加一个Acked-by:。
 
-Acked-by：通常由�影�代�的维护者使用，当该维护者既没有贡献也没有转�补�时。
+Acked-by: 通常由�影�代�的维护者使用，当该维护者既没有贡献也没有转�补�时。
 
-Acked-by: ��签字人那样正�。这是一个记录，确认人至少审查了补�，并表示接�。
-因此，补��并有时会手动将Acker的“Yep，looks good to me�转�为 Acked-By：（但
+Acked-by: ��签署那样正�。这是一个记录，确认人至少审阅了补�，并表示接�。
+因此，补��并有时会手动将Acker的“Yep，looks good to me�转�为 Acked-By:（但
 请注�，通常最好�求一个明确的Ack）。
 
 Acked-by：�一定表示对整个补�的确认。例如，如果一个补�影�多个�系统，并且
-有一个：�自一个�系统维护者，那么这通常表示�确认影�维护者代�的部分。这里
-应该仔细判断。如有疑问，应�考邮件列表档案中的原始讨论。
+有一个�自�个�系统维护者的Acked-By:，那么这通常表示�确认影�维护者代�的部
+分。这里应该仔细判断。如有疑问，应�考邮件列表存档中的原始讨论。
 
-如果�人有机会对补�进行评论，但没有�供此类评论，您�以选择在补�中添加 ``Cc:``
-这是唯一一个标签，它�以在没有被它命�的人显��作的情况下添加，但它应该表明
-这个人是在补�上抄�的。讨论中包�了潜在利益相关方。
+如果�人本应有机会对补�进行评论，但没有�供此类评论，您�以选择在补�中添加
+``Cc:`` 这是唯一�以在没有被该人明确��的情况下添加的标签——但它应该表明
+这个人是在补�上抄�的。此标签记录了讨论中包�的潜在利益相关方。
 
 Co-developed-by: 声明补�是由多个开�人员共�创建的；当几个人在一个补�上工
-作时，它用于将属性赋予共�作者（除了 From: 所赋予的作者之外）。因为
-Co-developed-by: 表示作者身份，所以�个共�开�人：必须紧跟在相关�作作者的
-签�之�。标准的签核程��求：标记的签核顺�应尽�能�映补�的时间历�，而�
-管作者是通过 From ：还是由 Co-developed-by: 共�开�的。值得注�的是，最�一
-个签字人：必须始终是�交补�的开�人员。
+作时，它用于给出共�作者（除了From:所给出的作者之外）。因为Co-developed-by:
+表示作者身份，所以�个Co-developed-by:必须紧跟在相关�作作者的签署之�。标准
+签署程��求Singed-off-by:标签的顺�应尽�能�映补�的时间历�，无论作者是通
+过From:还是Co-developed-by:表明。值得注�的是，最�一个Singed-off-by:必须是
+�交补�的开�人员。
 
-注�，当作者也是电�邮件标题“�件人：�行中列出的人时，“From: � 标记是�选的。
+注�，如果From:作者也是电�邮件标题的From:行中列出的人，则From:标签是�选的。
 
-作者�交的补�程�示例::
+被From:作者�交的补�示例::
 
 	<changelog>
 
@@ -421,7 +374,7 @@ Co-developed-by: 表示作者身份，所以�个共�开�人：必须紧跟
 	Signed-off-by: Second Co-Author <second@coauthor.example.org>
 	Signed-off-by: From Author <from@author.example.org>
 
-�作开�者�交的补�示例::
+被�作开�者�交的补�示例::
 
 	From: From Author <from@author.example.org>
 
@@ -434,76 +387,85 @@ Co-developed-by: 表示作者身份，所以�个共�开�人：必须紧跟
 	Signed-off-by: Submitting Co-Author <sub@coauthor.example.org>
 
 
-13）使用报告人：�测试人：�审核人：�建议人：�修�人：
---------------------------------------------------------
+使用Reported-by:�Tested-by:�Reviewed-by:�Suggested-by:和Fixes:
+-----------------------------------------------------------------
 
 Reported-by: 给那些�现错误并报告错误的人致谢，它希望激励他们在将��次帮助
-我们。请注�，如果bug是以�有方�报告的，那么在使用Reported-by标记之�，请
-先请求��。
+我们。请注�，如果bug是以�有方�报告的，那么在使用Reported-by标签之�，请
+先请求许�。此标签是为Bug设计的；请��将其用于感谢功能请求。
 
-Tested-by: 标记表示补�已由指定的人（在�些环境中）�功测试。这个标签通知
-维护人员已�执行了一些测试，为将�的补��供了一�定�测试人员的方法，并确
-�测试人员的信誉。
+Tested-by: 标签表示补�已由指定的人（在�些环境中）�功测试。这个标签通知
+维护人员已�执行了一些测试，为将�的补��供了一�定�测试人员的方法，并彰显测试人员的功劳。
 
-Reviewed-by：相�，根�审查人的声明，表明该补�已被审查并被认为是�接�的：
+Reviewed-by：根�审阅者的监�声明，表明该补�已被审阅并被认为是�接�的：
 
 
-审查人的监�声明
+审阅者的监�声明
 ^^^^^^^^^^^^^^^^
 
-通过�供我的 Reviewed-by，我声明：
+通过�供我的Reviewed-by:标签，我声明：
 
-        (a) 我已�对这个补�进行了一次技术审查，以评估它是�适�被包�到
+        (a) 我已�对这个补�进行了一次技术审阅，以评估它是�适�被包�到
             主线内核中。
 
         (b) 与补�相关的任何问题�顾虑或问题都已�馈给�交者。我对�交者对
             我的评论的回应感到满�。
 
-        (c) 虽然这一�交�能会改进一些东西，但我相信，此时，（1）对内核
+        (c) 虽然这一�交�能��被改进，但我相信，此时，（1）对内核
             进行了有价值的修改，（2）没有包�争论中涉�的已知问题。
 
-        (d) 虽然我已�审查了补�并认为它是�全的，但我�会（除��有明确
-            说明）作出任何��或��它将在任何给定情况下实现其规定的目的
+        (d) 虽然我已�审阅了补�并认为它是�全的，但我�会（除��有明确
+            说明）作出任何��或担�它会在任何给定情况下实现其规定的目的
             或正常�行。
 
-Reviewed-by 是一�观点声明，�补�是对内核的适当修改，没有任何�留的严�技术
-问题。任何感兴趣的审阅者（完�工作的人）都�以为一个补��供一个 Review-by
-标签。此标签用于�审阅者�供致谢，并通知维护者已在修补程�上完�的审阅程度。
-Reviewed-by: 当由已知了解主题区域并执行彻底检查的审阅者�供时，通常会增加
+Reviewed-by是一�观点声明，�补�是对内核的适当修改，没有任何�留的严�技术
+问题。任何感兴趣的审阅者（完�工作的人）都�以为一个补��供一个Reviewed-by
+标签。此标签用于�审阅者�供致谢，并通知维护者补�的审阅进度。
+当Reviewed-by:标签由已知了解主题区域并执行彻底检查的审阅者�供时，通常会增加
 补�进入内核的�能性。
 
+一旦从测试人员或审阅者的“Tested-by�和“Reviewed-by�标签出现在邮件列表中，
+作者应在��下一个版本时将其添加到适用的补�中。但是，如果补�在以下版本中�
+生了实质性更改，这些标签�能��适用，因此应该删除。通常，在补�更改日志中
+（在 ``---`` 分隔符之�）应该�到删除�人的测试者或审阅者标签。
+
 Suggested-by: 表示补�的想法是由指定的人�出的，并确�将此想法归功于指定的
 人。请注�，未�许�，�得添加此标签，特别是如果该想法未在公共论�上�布。
-这就是说，如果我们勤快地致谢我们的创�者，他们很有希望在未�得到鼓舞，�次
+也就是说，如果我们勤快地致谢创��供者，他们将�到鼓舞，很有希望在未��次
 帮助我们。
 
-Fixes: 指示补�在以�的�交中修�了一个问题。它�以很容易地确定错误的��，
-这有助于检查错误修�。这个标记还帮助稳定内核团队确定应该接收修�的稳定内核
-版本。这是指示补�修�的错误的首选方法。请�阅 :ref:`cn_describe_changes`
-�述您的更改以了解更多详细信�。
+Fixes: 指示补�修�了之��交的一个问题。它�以便于确定错误的��，这有助于
+检查错误修�。这个标签还帮助稳定内核团队确定应该接收修�的稳定内核版本。这是
+指示补�修�的错误的首选方法。请�阅 :ref:`zh_describe_changes` 了解更多信�。
 
-.. _cn_the_canonical_patch_format:
+.. note::
 
-12）标准补�格�
-----------------
+  附加Fixes:标签�会改�稳定内核规则�程，也�改�所有稳定版补�抄�
+  stable@vger.kernel.org的�求。有关更多信�，请阅读
+  Documentation/translations/zh_CN/process/stable-kernel-rules.rst 。
+
+.. _zh_the_canonical_patch_format:
+
+标准补�格�
+------------
 
 本节�述如何格�化补�本身。请注�，如果您的补�存储在 ``Git`` 存储库中，则
-�以使用 ``git format-patch`` 进行正确的补�格�设置。但是，这些工具无法创建
+�以使用 ``git format-patch`` 进行正确的补�格�化。但是，这些工具无法创建
 必�的文本，因此请务必阅读下�的说明。
 
-标准的补�，标题行是::
+标准的补�标题行是::
 
     Subject: [PATCH 001/123] �系统:一��概述
 
-标准补�的信体存在如下部分：
+标准补�的信体包�如下部分：
 
-  - 一个 "from" 行指出补�作者。�跟空行（仅当��修补程�的人�是作者时�需�）。
+  - 一个 ``from`` 行指出补�作者。�跟空行（仅当��补�的人�是作者时�需�）。
 
-  - 解释的正文，行以75列包装，这将被�制到永久�更日志��述这个补�。
+  - 说明文字，�行最长75列，这将被�制到永久�更日志��述这个补�。
 
   - 一个空行
 
-  - 上��述的“Signed-off-by� 行，也将出现在更改日志中。
+  - 上述的 ``Signed-off-by:`` 行，也将出现在更改日志中。
 
   - �包� ``---`` 的标记线。
 
@@ -511,29 +473,29 @@ Fixes: 指示补ä¸�在以å‰�çš„æ��交中修å¤�了一个问题。它å�¯ä»¥å¾ˆå®¹æ
 
   - 实际补�（ ``diff`` 输出）。
 
-标题行的格�，使得对标题行按字��排��常的容易 - 很多 e-mail 客户端都
-�以支� - 因为�列�是用零填充的，所以按数字排�和按字�排�是一样的。
+标题行的格�，使得对标题行按字��排��常的容易——很多邮件客户端都
+�以支�——因为�列�是用零填充的，所以按数字排�和按字�排�是一样的。
 
-e-mail 标题中的“�系统�标识哪个内核�系统将被打补�。
+邮件标题中的“�系统�标识哪个内核�系统将被打补�。
 
-e-mail 标题中的“一��概述�扼�的�述 e-mail 中的补�。“一��概述�
+邮件标题中的“一��概述�扼�的�述邮件中的补�。“一��概述�
 �应该是一个文件�。对于一个补�系列（“补�系列�指一系列的多个相关补
 �），��对�个补�都使用�样的“一��概述�。
 
-记� e-mail 的“一��概述�会�为该补�的全局唯一标识。它会蔓延到 git
+记�邮件的“一��概述�会�为该补�的全局唯一标识。它会进入 ``git``
 的改动记录里。然�“一��概述�会被用在开�者的讨论里，用�指代这个补
-�。用户将希望通过 google ��索"一��概述"�找到那些讨论这个补�的文
+�。用户将希望通过�索引擎�索“一��概述��找到那些讨论这个补�的文
 章。当人们在两三个月�使用诸如 ``gitk`` 或 ``git log --oneline`` 之类
 的工具查看数�个补�时，也会很快看到它。
 
 出于这些原因，概述必须�超过70-75个字符，并且必须�述补�的更改以�为
-什么需�补�。既�简����述性很有挑战性，但写得好的概述应该这样�。
+什么需�补�。既�简����述性很有挑战性，但写得好的概述应该这样。
 
 概述的�缀�以用方括�括起�：“Subject: [PATCH <tag>...] <概述>�。标记
 �被视为概述的一部分，而是�述应该如何处�补�。如果补�的多个版本已�
-�出�以�应评审（�“v1，v2，v3�）或“rfc�，以指示评审请求，那么通用标记
-�能包括版本�述符。如果一个补�系列中有四个补�，那么�个补��以这样
-编�：1/4�2/4�3/4�4/4。这�以确�开�人员了解补�应用的顺�，并且他们
+�出�以�应评审（�“v1，v2，v3�）则必须包�版本�，或包�“RFC�以指示
+评审请求。如果一个补�系列中有四个补�，那么�个补��以这样编�：1/4�2/4�
+3/4�4/4。这�以确�开�人员了解补�应用的顺�，且
 已�查看或应用了补�系列中的所有补�。
 
 一些标题的例�::
@@ -541,95 +503,134 @@ e-mail 标题中的“一å�¥è¯�概述â€�扼è¦�çš„æ��è¿° e-mail 中的补ä¸�。â€
     Subject: [patch 2/5] ext2: improve scalability of bitmap searching
     Subject: [PATCHv2 001/207] x86: fix eflags tracking
 
-"From" 行是信体里的最上�一行，具有如下格�：
+``From`` 行是信体里的最上�一行，具有如下格�::
+
         From: Patch Author <author@example.com>
 
-"From" 行指明在永久改动日志里，�会被确认为作者。如果没有 "From" 行，那
-么邮件头里的 "From: " 行会被用�决定改动日志中的作者。
+``From`` 行指明在永久改动日志里，�会被确认为作者。如果没有 ``From`` 行，那
+么邮件头里的 ``From:`` 行会被用�决定改动日志中的作者。
 
-说明的主题将会被�交到永久的�代�改动日志里，因此对那些早已��记得和
-这个补�相关的讨论细节的有能力的读者�说，是有�义的。包括补�程�定�
-错误的（内核日志消��OOPS消�等）症状，对于�索�交日志以寻找适用补�的人
-尤其有用。如果一个补�修�了一个编译失败，那么�能�需�包�所有编译失败；
+说明文字将会被�交到永久的�代�改动日志里，因此应针对那些早已��记得和这
+个补�相关的讨论细节的读者。包括补�处�的故障症状（内核日志消��oops消�
+等），这对于�能正在�索�交日志以查找适用补�的人特别有用。文本应该写得如
+此详细，以便在数周�数月甚至数年�阅读时，能够为读者�供所需的细节信�，以
+掌�创建补�的 **原因** 。
+
+如果一个补�修�了一个编译失败，那么�能�需�包� *所有* 编译失败；
 ��足够让�索补�的人能够找到它就行了。与概述一样，既�简����述性。
 
-"---" 标记行对于补�处�工具�找到哪里是改动日志信�的结�，是��缺少
+``---`` 标记行对于补�处�工具�找到哪里是改动日志信�的结�，是��缺少
 的。
 
-对于 "---" 标记之�的�外注解，一个好的用途就是用�写 diffstat，用�显
-示修改了什么文件和�个文件都增加和删除了多少行。diffstat 对于比较大的补
-�特别有用。其余那些�是和时刻或者开�者相关的注解，��适放到永久的改
-动日志里的，也应该放这里。
-使用 diffstat的选项 "-p 1 -w 70" 这样文件�就会从内核�代�树的目录开始
+对于 ``---`` 标记之�的�外注解，一个好的用途就是用�写 ``diffstat`` ，用�显
+示修改了什么文件和�个文件都增加和删除了多少行。 ``diffstat`` 对于比较大的补
+�特别有用。
+使用 ``diffstat`` 的选项 ``-p 1 -w 70`` 这样文件�就会从内核�代�树的目录开始
 ，�会�用太宽的空间（很容易适�80列的宽度，也许会有一些缩进。）
+（ ``git`` 默认会生��适的diffstat。）
+
+其余那些�适用于当时或者与维护者相关的注解，��适放到永久的改动日志里的，也
+应该放这里。较好的例�就是 ``补�更改记录`` ，记录了v1和v2版本补�之间的差异。
+
+请将此信�放在将�更日志与补�的其余部分分隔开的 ``---`` 行 **之�** 。版本
+信��是�交到git树的�更日志的一部分。�是供审阅人员使用的附加信�。如果将
+其放置在�交标记上方，则需�手动交互�能将其删除。如果它�于分隔线以下，则在
+应用补�时会自动剥离::
+
+  <commit message>
+  ...
+  Signed-off-by: Author <author@mail>
+  ---
+  V2 -> V3: Removed redundant helper function
+  V1 -> V2: Cleaned up coding style and addressed review comments
 
-在��的�考资料中能看到适当的补�格�的更多细节。
+  path/to/file | 5+++--
+  ...
 
-.. _cn_explicit_in_reply_to:
+在��的�考资料中能看到正确补�格�的更多细节。
 
-15) 明确回�邮件头(In-Reply-To)
--------------------------------
+.. _zh_backtraces:
 
-手动添加回�补�的的标题头(In-Reply_To:) 是有帮助的（例如，使用 ``git send-email`` ）
-将补�与以�的相关讨论关�起�，例如，将bug修�程�链接到电�邮件和bug报告。
+�交消�中的回溯（Backtraces）
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+回溯有助于记录导致问题的调用链。然而，并�所有回溯都有帮助。例如，早期引导调
+用链是独特而明显的。而�字�制完整的dmesg输出则会增加时间戳�模�列表�寄存
+器和堆栈转储等分散注�力的信�。
+
+因此，最有用的回溯应该从转储中��相关信�，以更容易集中在真实问题上。下�是
+一个剪�良好的回溯示例::
+
+  unchecked MSR access error: WRMSR to 0xd51 (tried to write 0x0000000000000064)
+  at rIP: 0xffffffffae059994 (native_write_msr+0x4/0x20)
+  Call Trace:
+  mba_wrmsr
+  update_domains
+  rdtgroup_mkdir
+
+.. _zh_explicit_in_reply_to:
+
+明确回�邮件头（In-Reply-To）
+-----------------------------
+
+手动添加回�补�的的邮件头（In-Reply_To:）是有用的（例如，使用 ``git send-email`` ），
+�以将补�与以�的相关讨论关�起�，例如，将bug补�链接到电�邮件和bug报告。
 但是，对于多补�系列，最好��在回�时使用链接到该系列的旧版本。这样，
-补�的多个版本就�会�为电�邮件客户端中无法管�的引用�列。如果链接有用，
+补�的多个版本就�会�为电�邮件客户端中无法管�的引用树。如果链接有用，
 �以使用 https://lore.kernel.org/ �定�器（例如，在��电�邮件文本中）
 链接到补�系列的早期版本。
 
-16) ��git pull请求
---------------------
-
-如果您有一系列补�，那么让维护人员通过git pull�作将它们直接拉入�系统存储
-库�能是最方便的。但是，请注�，从开�人员那里获�补�比从邮件列表中获�补
-�需�更高的信任度。因此，许多�系统维护人员�愿�接�请求，特别是�自新的
-未知开�人员的请求。如果有疑问，您�以在��邮件中使用pull 请求作为补�系列
-正常�布的一个选项，让维护人员�以选择使用其中之一。
-
-pull 请求的主题行中应该有[Git Pull]。请求本身应该在一行中包�存储库�称和
-感兴趣的分支；它应该看起��::
+给出基础树信�
+--------------
 
-  Please pull from
+当其他开�人员收到您的补�并开始审阅时，知�应该将您的工作放到代�树历�记录
+中的什么�置通常很有用。这对于自动化�续集��水（CI）特别有用，这些�水线试
+图�行一系列测试，以便在维护人员开始审阅之�确定�交的质�。
 
-      git://jdelvare.pck.nerim.net/jdelvare-2.6 i2c-for-linus
+如果您使用 ``git format-patch`` 生�补�，则�以通过 ``--base`` 标志在�交中
+自动包�基础树信�。使用此选项最简��最方便的方法是��主题分支::
 
-  to get these changes:
+    $ git checkout -t -b my-topical-branch master
+    Branch 'my-topical-branch' set up to track local branch 'master'.
+    Switched to a new branch 'my-topical-branch'
 
+    [perform your edits and commits]
 
-pull 请求还应该包�一�整体消�，说明请求中将包�什么，一个补�本身的 ``Git shortlog``
-以�一个显示补�系列整体效果的 ``diffstat`` 。当然，将所有这些信�收集在一起
-的最简�方法是让 ``git`` 使用 ``git request-pull`` 命令为您完�这些工作。
+    $ git format-patch --base=auto --cover-letter -o outgoing/ master
+    outgoing/0000-cover-letter.patch
+    outgoing/0001-First-Commit.patch
+    outgoing/...
 
-一些维护人员（包括Linus）希望看到�自已签��交的请求；这增加了他们对你的
-请求信心。特别是，在没有签�标签的情况下，Linus �会从� Github 这样的公共
-托管站点拉请求。
+当你编辑 ``outgoing/0000-cover-letter.patch`` 时，您会注�到在它的最底部有一
+行 ``base-commit:`` 尾注，它为审阅者和CI工具�供了足够的信�以正确执行
+``git am`` 而�必担心冲�::
 
-创建此类签�的第一步是生�一个 GNRPG 密钥，并由一个或多个核心内核开�人员对
-其进行签�。这一步对新开�人员�说�能很困难，但没有办法绕过它。�加会议是
-找到�以签署您的密钥的开�人员的好方法。
+    $ git checkout -b patch-review [base-commit-id]
+    Switched to a new branch 'patch-review'
+    $ git am patches.mbox
+    Applying: First Commit
+    Applying: ...
 
-一旦您在Git 中准备了一个您希望有人拉的补�系列，就用 ``git tag -s`` 创建一
-个签�标记。这将创建一个新标记，标识该系列中的最�一次�交，并包�用您的�
-钥创建的签�。您还�以将changelog样�的消�添加到标记中；这是一个�述拉请求
-整体效果的�想�置。
+有关此选项的更多信�，请�阅 ``man git-format-patch`` 。
 
-如果维护人员将�从中��的树�是您正在使用的存储库，请��忘记将已签�的标记
-显�推�到公共树。
+.. note::
 
-生�拉请求时，请使用已签�的标记作为目标。这样的命令�以实现::
+    ``--base`` 功能是在2.9.0版git中引入的。
 
-  git request-pull master git://my.public.tree/linux.git my-signed-tag
+如果您�使用git格�化补�，�然�以包�相�的 ``base-commit`` 尾注，以指示您
+的工作所基于的树的�交哈希。你应该在��邮件或系列的第一个补�中添加它，它应
+该放在 ``---`` 行的下�或所有其他内容之�，��在你的电�邮件签�之�。
 
 �考文献
 --------
 
-Andrew Morton, "The perfect patch" (tpp).
+Andrew Morton，“完美的补��（tpp）
   <https://www.ozlabs.org/~akpm/stuff/tpp.txt>
 
-Jeff Garzik, "Linux kernel patch submission format".
+Jeff Garzik，“Linux内核补��交格��
   <https://web.archive.org/web/20180829112450/http://linux.yyz.us/patch-format.html>
 
-Greg Kroah-Hartman, "How to piss off a kernel subsystem maintainer".
+Greg Kroah-Hartman，“如何惹�内核�系统维护人员�
   <http://www.kroah.com/log/linux/maintainer.html>
 
   <http://www.kroah.com/log/linux/maintainer-02.html>
@@ -642,16 +643,15 @@ Greg Kroah-Hartman, "How to piss off a kernel subsystem maintainer".
 
   <http://www.kroah.com/log/linux/maintainer-06.html>
 
-NO!!!! No more huge patch bombs to linux-kernel@vger.kernel.org people!
+����别��巨型补�炸弹给linux-kernel@vger.kernel.org的人们了�
   <https://lore.kernel.org/r/20050711.125305.08322243.davem@davemloft.net>
 
-Kernel Documentation/process/coding-style.rst:
-  :ref:`Documentation/translations/zh_CN/process/coding-style.rst <cn_codingstyle>`
+内核 Documentation/translations/zh_CN/process/coding-style.rst
 
-Linus Torvalds's mail on the canonical patch format:
+Linus Torvalds关于标准补�格�的邮件
   <https://lore.kernel.org/r/Pine.LNX.4.58.0504071023190.28951@ppc970.osdl.org>
 
-Andi Kleen, "On submitting kernel patches"
-  Some strategies to get difficult or controversial changes in.
+Andi Kleen，“�交补�之路�
+  一些帮助�入困难或有争议的�更的策略。
 
   http://halobates.de/on-submitting-patches.pdf
diff --git a/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst b/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst
index 26b0f36f793d..3076402406c4 100644
--- a/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst
+++ b/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst
@@ -80,7 +80,7 @@ p->se.vruntime。一旦p->se.vruntimeå�˜å¾—足够大，其它的任务将æˆ�为æ
 CFS使用纳秒粒度的计时，��赖于任何jiffies或HZ的细节。因此CFS并��之�的调度器那样
 有“时间片�的概念，也没有任何���的设计。唯一�调的�数（你需�打开CONFIG_SCHED_DEBUG）是：
 
-   /proc/sys/kernel/sched_min_granularity_ns
+   /sys/kernel/debug/sched/min_granularity_ns
 
 它�以用�将调度器从“桌��模�（也就是低时延）调节为“�务器�（也就是高批处�）模�。
 它的默认设置是适�桌�的工作负载。SCHED_BATCH也被CFS调度器模�处�。
diff --git a/Documentation/translations/zh_TW/oops-tracing.txt b/Documentation/translations/zh_TW/oops-tracing.txt
deleted file mode 100644
index be8e59f2abaf..000000000000
--- a/Documentation/translations/zh_TW/oops-tracing.txt
+++ /dev/null
@@ -1,212 +0,0 @@
-Chinese translated version of Documentation/admin-guide/bug-hunting.rst
-
-If you have any comment or update to the content, please contact the
-original document maintainer directly.  However, if you have a problem
-communicating in English you can also ask the Chinese maintainer for
-help.  Contact the Chinese maintainer if this translation is outdated
-or if there is a problem with the translation.
-
-Traditional Chinese maintainer:  Hu Haowen <src.res@email.cn>
----------------------------------------------------------------------
-Documentation/admin-guide/bug-hunting.rst 的�體中文版翻譯
-
-如果想評論或更新本文的內容，請直接�繫原文檔的維護者。如果你使用英文
-交�有困難的話，也�以��體中文版維護者求助。如果本翻譯更新��時或
-者翻譯存在�題，請�繫�體中文版維護者。
-
-�體中文版維護者： 胡皓文 Hu Haowen <src.res@email.cn>
-�體中文版翻譯者： 胡皓文 Hu Haowen <src.res@email.cn>
-�體中文版校譯者： 胡皓文 Hu Haowen <src.res@email.cn>
-
-以下爲正文
----------------------------------------------------------------------
-
-注�： ksymoops 在2.6中是沒有用的。 請以原有格�使用Oops(來自dmesg，等等)。
-忽略任何這樣那樣關於「解碼Oops�或者「通�ksymoops�行�的文檔。 如果你貼出�行�
-ksymoops的來自2.6的Oops，人們�會讓你�貼一次。
-
-快速總�
--------------
-
-發�Oops並發�給看似相關的內核領域的維護者。別太擔心��上號。如果你�確定就發給
-和你所�的事情相關的代碼的負責人。 如果���試著�述怎樣�構。 那甚至比oops更有
-價值。
-
-如果你�於發�給誰一無所知， 發給linux-kernel@vger.kernel.org。感�你幫助Linux
-儘�能地穩定。
-
-Oops在哪裡?
-----------------------
-
-通常Oops文本由klogd從內核緩��里讀�並傳給syslogd，由syslogd寫到syslog文件中，
-典型地是/var/log/messages(�賴於/etc/syslog.conf)。有時klogd崩潰了,這種情�下你
-能夠�行dmesg > file來從內核緩��中讀�數據並�存下來。 �則你�以
-cat /proc/kmsg > file， 然而你必須介入中止傳輸， kmsg是一個「永���的文件�。如
-果機器崩潰壞到你�能輸入命令或者�碟��用那麼你有三種�擇:-
-
-（1） 手抄�幕上的文本待機器�啓後�輸入計算機。 麻煩但如果沒有��崩潰的準備，
-這是僅有的�擇。 �外，你�以用數�相機把�幕�下來-�太好，但比沒有強。 如果信
-�滾動到了終端的上�，你會發�以高分辯率啓動（比如，vga=791）會讓你讀到更多的文
-本。（注�：這需�vesafb，所以�『早期�的oops沒有幫助）
-
-（2）用串�終端啓動（請�看Documentation/admin-guide/serial-console.rst），�行一個null
-modem到�一�機器並用你喜歡的通訊工具��輸出。Minicom工作地很好。
-
-（3）使用Kdump（請�看Documentation/admin-guide/kdump/kdump.rst），
-使用在Documentation/admin-guide/kdump/gdbmacros.txt中定義的dmesg gdb�，從舊的內存中��內核
-環形緩��。
-
-完整信�
-----------------
-
-注�：以下來自於Linus的郵件�用於2.4內核。 我因爲歷�原因�留了它，並且因爲其中
-一些信��然�用。 特別注�的是，請忽略任何ksymoops的引用。
-
-From: Linus Torvalds <torvalds@osdl.org>
-
-怎樣跟蹤Oops.. [原發到linux-kernel的一�郵件]
-
-主�的竅門是有五年和這些煩人的oops消�打交�的經驗;-)
-
-實際上，你有辦法使它更簡單。我有兩個��的方法：
-
-	gdb /usr/src/linux/vmlinux
-	gdb> disassemble <offending_function>
-
-那是發��題的簡單辦法，至少如果bug報告�的好的情�下（象這個一樣-�行ksymoops
-得到oops發生的函數�函數內的�移）。
-
-哦，如果報告發生的內核以相�的編譯器和相似的�置編譯它會有幫助的。
-
-�一件��的事是�彙編bug報告的「Code�部分：ksymoops也會用正確的工具來�這件事，
-但如果沒有那些工具你�以寫一個傻程�：
-
-	char str[] = "\xXX\xXX\xXX...";
-	main(){}
-
-並用gcc -g編譯它然後執行「disassemble str�（XX部分是由Oops報告的值-你�以僅剪切
-粘貼並用「\x�替�空格-我就是這麼�的，因爲我懶得寫程�自動�這一切）。
-
-�外，你�以用scripts/decodecode這個shell腳本。它的使用方法是：
-decodecode < oops.txt
-
-「Code�之後的�六進�字節�能（在�些架構上）有一些當�指令之�的指令字節以�
-當�和之後的指令字節
-
-Code: f9 0f 8d f9 00 00 00 8d 42 0c e8 dd 26 11 c7 a1 60 ea 2b f9 8b 50 08 a1
-64 ea 2b f9 8d 34 82 8b 1e 85 db 74 6d 8b 15 60 ea 2b f9 <8b> 43 04 39 42 54
-7e 04 40 89 42 54 8b 43 04 3b 05 00 f6 52 c0
-
-最後，如果你想知�代碼來自哪裡，你�以：
-
-	cd /usr/src/linux
-	make fs/buffer.s 	# 或任何產生BUG的文件
-
-然後你會比gdb�彙編更清楚的知�發生了什麼。
-
-�在，�題是把你所�有的所有數據��起來：C�碼（關於它應該怎樣的一般知識），
-彙編代碼�其�彙編得到的代碼（�外還有從「oops�消�得到的寄存器狀態-�了解毀壞的
-指�有用，而且當你有了彙編代碼你也能拿其它的寄存器和任何它們�應的C表���匹�
-）。
-
-實際上，你僅需看看哪裡�匹�（這個例�是「Code��彙編和編譯器生�的代碼�匹�）。
-然後你須�找出爲什麼�匹�。通常很簡單-你看到代碼使用了空指�然後你看代碼想知�
-空指�是怎麼出�的，還有檢查它是��法..
-
-�在，如果明白這是一項耗時的工作而且需�一�點兒的專心，沒錯。這就是我爲什麼大多
-�是忽略那些沒有符號表信�的崩潰報告的原因：簡單的說太難查找了（我有一些
-程�用於在內核代碼段中�索特定的模�，而且有時我也已經能找出那些崩潰的地方，但是
-僅僅是找出正確的�列也確實需�相當紮實的內核知識）
-
-_有時_會發生這種情�，我僅看到崩潰中的�彙編代碼�列， 然後我馬上就明白�題出在
-哪裡。這時我��識到自己幹這個工作已經太長時間了;-)
-
-		Linus
-
-
----------------------------------------------------------------------------
-關於Oops跟蹤的註解：
-
-爲了幫助Linus和其它內核開發者，klogd�入了大�的支�來處��護錯誤。爲了�有�
-地�解�的完整支�至少應該使用1.3-pl3的sysklogd包。
-
-當�護錯誤發生時，klogd守護進程自動把內核日誌信�中的��地�翻譯�它們相應的符
-號。
-
-klogd執行兩種類型的地�解�。首先是�態翻譯其次是動態翻譯。�態翻譯和ksymoops
-一樣使用System.map文件。爲了��態翻譯klogd守護進程必須在�始化時能找到system
-map文件。關於klogd怎樣�索map文件請�看klogd手冊�。
-
-動態地�翻譯在使用內核��載模塊時很��。 因爲內核模塊的內存是從內核動態內存池
-里分�的，所以�管是模塊開始�置還是模塊中函數和符號的�置都�是固定的。
-
-內核支��許程�決定�載哪些模塊和它們在內存中�置的系統調用。使用這些系統調用
-klogd守護進程生�一張符號表用於調試發生在��載模塊中的�護錯誤。
-
-至少klogd會�供產生�護錯誤的模塊�。還�有�外的符號信�供��載模塊開發者�擇
-以從模塊中輸出符號信�。
-
-因爲內核模塊環境�能是動態的，所以必須有一種機制當模塊環境發生改變時來通知klogd
-守護進程。 有一些�用的命令行�項�許klogd�當�執行中的守護進程發�信號，告知符
-號信�應該被刷新了。 更多信�請�看klogd手冊�。
-
-sysklogd發布時包�一個補�修改了modules-2.0.0包，無論何時一個模塊�載或者�載都
-會自動�klogd發�信號。打上這個補��供了必�的�調試發生於內核��載模塊的�護
-錯誤的無縫支�。
-
-以下是被klogd處��的發生在��載模塊中的一個�護錯誤例�：
----------------------------------------------------------------------------
-Aug 29 09:51:01 blizard kernel: Unable to handle kernel paging request at virtual address f15e97cc
-Aug 29 09:51:01 blizard kernel: current->tss.cr3 = 0062d000, %cr3 = 0062d000
-Aug 29 09:51:01 blizard kernel: *pde = 00000000
-Aug 29 09:51:01 blizard kernel: Oops: 0002
-Aug 29 09:51:01 blizard kernel: CPU:    0
-Aug 29 09:51:01 blizard kernel: EIP:    0010:[oops:_oops+16/3868]
-Aug 29 09:51:01 blizard kernel: EFLAGS: 00010212
-Aug 29 09:51:01 blizard kernel: eax: 315e97cc   ebx: 003a6f80   ecx: 001be77b   edx: 00237c0c
-Aug 29 09:51:01 blizard kernel: esi: 00000000   edi: bffffdb3   ebp: 00589f90   esp: 00589f8c
-Aug 29 09:51:01 blizard kernel: ds: 0018   es: 0018   fs: 002b   gs: 002b   ss: 0018
-Aug 29 09:51:01 blizard kernel: Process oops_test (pid: 3374, process nr: 21, stackpage=00589000)
-Aug 29 09:51:01 blizard kernel: Stack: 315e97cc 00589f98 0100b0b4 bffffed4 0012e38e 00240c64 003a6f80 00000001
-Aug 29 09:51:01 blizard kernel:        00000000 00237810 bfffff00 0010a7fa 00000003 00000001 00000000 bfffff00
-Aug 29 09:51:01 blizard kernel:        bffffdb3 bffffed4 ffffffda 0000002b 0007002b 0000002b 0000002b 00000036
-Aug 29 09:51:01 blizard kernel: Call Trace: [oops:_oops_ioctl+48/80] [_sys_ioctl+254/272] [_system_call+82/128]
-Aug 29 09:51:01 blizard kernel: Code: c7 00 05 00 00 00 eb 08 90 90 90 90 90 90 90 90 89 ec 5d c3
----------------------------------------------------------------------------
-
-Dr. G.W. Wettstein           Oncology Research Div. Computing Facility
-Roger Maris Cancer Center    INTERNET: greg@wind.rmcc.com
-820 4th St. N.
-Fargo, ND  58122
-Phone: 701-234-7556
-
-
----------------------------------------------------------------------------
-�汙染的內核
-
-一些oops報告在程�記數器之後包�字符串'Tainted: '。這表明內核已經被一些�西給汙
-染了。 該字符串之後緊跟著一系列的�置�感的字符，�個代表一個特定的汙染值。
-
-  1：'G'如果所有�載的模塊都有GPL或相容的許�證，'P'如果�載了任何的專有模塊。
-沒有模塊MODULE_LICENSE或者帶有insmod�爲是與GPL�相容的的MODULE_LICENSE的模塊被
-�定是專有的。
-
-  2：'F'如果有任何通�「insmod -f�被強制�載的模塊，' '如果所有模塊都被正常�載。
-
-  3：'S'如果oops發生在SMP內核中，�行於沒有證明安全�行多處�器的硬體。 當�這種
-情�僅�於幾種�支�SMP的速�處�器。
-
-  4：'R'如果模塊通�「insmod -f�被強制�載，' '如果所有模塊都被正常�載。
-
-  5：'M'如果任何處�器報告了機器檢查異常，' '如果沒有發生機器檢查異常。
-
-  6：'B'如果�釋放函數發�了一個錯誤的�引用或者一些��期的�標誌。
-
-  7：'U'如果用戶或者用戶應用程�特別請求設置汙染標誌，�則' '。
-
-  8：'D'如果內核剛剛死掉，比如有OOPS或者BUG。
-
-使用'Tainted: '字符串的主�原因是�告訴內核調試者，這是�是一個乾淨的內核亦或發
-生了任何的�正常的事。汙染是永久的：�使出錯的模塊已經被�載了，汙染值�然存在，
-以表明內核��值得信任。
-
diff --git a/Documentation/virt/kvm/x86/mmu.rst b/Documentation/virt/kvm/x86/mmu.rst
index 8739120f4300..8364afa228ec 100644
--- a/Documentation/virt/kvm/x86/mmu.rst
+++ b/Documentation/virt/kvm/x86/mmu.rst
@@ -377,7 +377,7 @@ Emulating cr0.wp
 ================
 
 If tdp is not enabled, the host must keep cr0.wp=1 so page write protection
-works for the guest kernel, not guest guest userspace.  When the guest
+works for the guest kernel, not guest userspace.  When the guest
 cr0.wp=1, this does not present a problem.  However when the guest cr0.wp=0,
 we cannot map the permissions for gpte.u=1, gpte.w=0 to any spte (the
 semantics require allowing any guest kernel access plus user read access).
diff --git a/Documentation/w1/masters/ds2490.rst b/Documentation/w1/masters/ds2490.rst
index 7e5b50f9c0f5..842e7ae80424 100644
--- a/Documentation/w1/masters/ds2490.rst
+++ b/Documentation/w1/masters/ds2490.rst
@@ -52,7 +52,7 @@ Notes and limitations.
   clear the entire bulk in buffer.  It would be possible to read the
   maximum buffer size to not run into this error condition, only extra
   bytes in the buffer is a logic error in the driver.  The code should
-  should match reads and writes as well as data sizes.  Reads and
+  match reads and writes as well as data sizes.  Reads and
   writes are serialized and the status verifies that the chip is idle
   (and data is available) before the read is executed, so it should
   not happen.
diff --git a/Documentation/w1/w1-generic.rst b/Documentation/w1/w1-generic.rst
index da4e8b4e9b01..99255b6d0e53 100644
--- a/Documentation/w1/w1-generic.rst
+++ b/Documentation/w1/w1-generic.rst
@@ -113,7 +113,7 @@ generally only make sense when searching is disabled, as a search will
 redetect manually removed devices that are present and timeout manually
 added devices that aren't on the bus.
 
-Bus searches occur at an interval, specified as a summ of timeout and
+Bus searches occur at an interval, specified as a sum of timeout and
 timeout_us module parameters (either of which may be 0) for as long as
 w1_master_search remains greater than 0 or is -1.  Each search attempt
 decrements w1_master_search by 1 (down to 0) and increments
diff --git a/Documentation/x86/entry_64.rst b/Documentation/x86/entry_64.rst
index e433e08f7018..0afdce3c06f4 100644
--- a/Documentation/x86/entry_64.rst
+++ b/Documentation/x86/entry_64.rst
@@ -33,8 +33,8 @@ Some of these entries are:
  - interrupt: An array of entries.  Every IDT vector that doesn't
    explicitly point somewhere else gets set to the corresponding
    value in interrupts.  These point to a whole array of
-   magically-generated functions that make their way to do_IRQ with
-   the interrupt number as a parameter.
+   magically-generated functions that make their way to common_interrupt()
+   with the interrupt number as a parameter.
 
  - APIC interrupts: Various special-purpose interrupts for things
    like TLB shootdown.
diff --git a/Documentation/x86/microcode.rst b/Documentation/x86/microcode.rst
index a320d37982ed..b627c6f36bcf 100644
--- a/Documentation/x86/microcode.rst
+++ b/Documentation/x86/microcode.rst
@@ -6,6 +6,7 @@ The Linux Microcode Loader
 
 :Authors: - Fenghua Yu <fenghua.yu@intel.com>
           - Borislav Petkov <bp@suse.de>
+	  - Ashok Raj <ashok.raj@intel.com>
 
 The kernel has a x86 microcode loading facility which is supposed to
 provide microcode loading methods in the OS. Potential use cases are
@@ -92,15 +93,8 @@ vendor's site.
 Late loading
 ============
 
-There are two legacy user space interfaces to load microcode, either through
-/dev/cpu/microcode or through /sys/devices/system/cpu/microcode/reload file
-in sysfs.
-
-The /dev/cpu/microcode method is deprecated because it needs a special
-userspace tool for that.
-
-The easier method is simply installing the microcode packages your distro
-supplies and running::
+You simply install the microcode packages your distro supplies and
+run::
 
   # echo 1 > /sys/devices/system/cpu/microcode/reload
 
@@ -110,6 +104,110 @@ The loading mechanism looks for microcode blobs in
 /lib/firmware/{intel-ucode,amd-ucode}. The default distro installation
 packages already put them there.
 
+Since kernel 5.19, late loading is not enabled by default.
+
+The /dev/cpu/microcode method has been removed in 5.19.
+
+Why is late loading dangerous?
+==============================
+
+Synchronizing all CPUs
+----------------------
+
+The microcode engine which receives the microcode update is shared
+between the two logical threads in a SMT system. Therefore, when
+the update is executed on one SMT thread of the core, the sibling
+"automatically" gets the update.
+
+Since the microcode can "simulate" MSRs too, while the microcode update
+is in progress, those simulated MSRs transiently cease to exist. This
+can result in unpredictable results if the SMT sibling thread happens to
+be in the middle of an access to such an MSR. The usual observation is
+that such MSR accesses cause #GPs to be raised to signal that former are
+not present.
+
+The disappearing MSRs are just one common issue which is being observed.
+Any other instruction that's being patched and gets concurrently
+executed by the other SMT sibling, can also result in similar,
+unpredictable behavior.
+
+To eliminate this case, a stop_machine()-based CPU synchronization was
+introduced as a way to guarantee that all logical CPUs will not execute
+any code but just wait in a spin loop, polling an atomic variable.
+
+While this took care of device or external interrupts, IPIs including
+LVT ones, such as CMCI etc, it cannot address other special interrupts
+that can't be shut off. Those are Machine Check (#MC), System Management
+(#SMI) and Non-Maskable interrupts (#NMI).
+
+Machine Checks
+--------------
+
+Machine Checks (#MC) are non-maskable. There are two kinds of MCEs.
+Fatal un-recoverable MCEs and recoverable MCEs. While un-recoverable
+errors are fatal, recoverable errors can also happen in kernel context
+are also treated as fatal by the kernel.
+
+On certain Intel machines, MCEs are also broadcast to all threads in a
+system. If one thread is in the middle of executing WRMSR, a MCE will be
+taken at the end of the flow. Either way, they will wait for the thread
+performing the wrmsr(0x79) to rendezvous in the MCE handler and shutdown
+eventually if any of the threads in the system fail to check in to the
+MCE rendezvous.
+
+To be paranoid and get predictable behavior, the OS can choose to set
+MCG_STATUS.MCIP. Since MCEs can be at most one in a system, if an
+MCE was signaled, the above condition will promote to a system reset
+automatically. OS can turn off MCIP at the end of the update for that
+core.
+
+System Management Interrupt
+---------------------------
+
+SMIs are also broadcast to all CPUs in the platform. Microcode update
+requests exclusive access to the core before writing to MSR 0x79. So if
+it does happen such that, one thread is in WRMSR flow, and the 2nd got
+an SMI, that thread will be stopped in the first instruction in the SMI
+handler.
+
+Since the secondary thread is stopped in the first instruction in SMI,
+there is very little chance that it would be in the middle of executing
+an instruction being patched. Plus OS has no way to stop SMIs from
+happening.
+
+Non-Maskable Interrupts
+-----------------------
+
+When thread0 of a core is doing the microcode update, if thread1 is
+pulled into NMI, that can cause unpredictable behavior due to the
+reasons above.
+
+OS can choose a variety of methods to avoid running into this situation.
+
+
+Is the microcode suitable for late loading?
+-------------------------------------------
+
+Late loading is done when the system is fully operational and running
+real workloads. Late loading behavior depends on what the base patch on
+the CPU is before upgrading to the new patch.
+
+This is true for Intel CPUs.
+
+Consider, for example, a CPU has patch level 1 and the update is to
+patch level 3.
+
+Between patch1 and patch3, patch2 might have deprecated a software-visible
+feature.
+
+This is unacceptable if software is even potentially using that feature.
+For instance, say MSR_X is no longer available after an update,
+accessing that MSR will cause a #GP fault.
+
+Basically there is no way to declare a new microcode update suitable
+for late-loading. This is another one of the problems that caused late
+loading to be not enabled by default.
+
 Builtin microcode
 =================
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 8a5012ba6ff9..66ef84d8b304 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -348,7 +348,6 @@ M:	"Rafael J. Wysocki" <rafael@kernel.org>
 R:	Len Brown <lenb@kernel.org>
 L:	linux-acpi@vger.kernel.org
 S:	Supported
-W:	https://01.org/linux-acpi
 Q:	https://patchwork.kernel.org/project/linux-acpi/list/
 B:	https://bugzilla.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
@@ -427,7 +426,6 @@ M:	Rafael J. Wysocki <rafael@kernel.org>
 R:	Zhang Rui <rui.zhang@intel.com>
 L:	linux-acpi@vger.kernel.org
 S:	Supported
-W:	https://01.org/linux-acpi
 B:	https://bugzilla.kernel.org
 F:	drivers/acpi/*thermal*
 
@@ -671,7 +669,8 @@ F:	fs/afs/
 F:	include/trace/events/afs.h
 
 AGPGART DRIVER
-M:	David Airlie <airlied@linux.ie>
+M:	David Airlie <airlied@redhat.com>
+L:	dri-devel@lists.freedesktop.org
 S:	Maintained
 T:	git git://anongit.freedesktop.org/drm/drm
 F:	drivers/char/agp/
@@ -1010,7 +1009,6 @@ F:	drivers/spi/spi-amd.c
 
 AMD MP2 I2C DRIVER
 M:	Elie Morisse <syniurge@gmail.com>
-M:	Nehal Shah <nehal-bakulchandra.shah@amd.com>
 M:	Shyam Sundar S K <shyam-sundar.s-k@amd.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
@@ -1803,7 +1801,7 @@ N:	sun[x456789]i
 N:	sun50i
 
 ARM/Amlogic Meson SoC CLOCK FRAMEWORK
-M:	Neil Armstrong <narmstrong@baylibre.com>
+M:	Neil Armstrong <neil.armstrong@linaro.org>
 M:	Jerome Brunet <jbrunet@baylibre.com>
 L:	linux-amlogic@lists.infradead.org
 S:	Maintained
@@ -1828,7 +1826,7 @@ F:	Documentation/devicetree/bindings/sound/amlogic*
 F:	sound/soc/meson/
 
 ARM/Amlogic Meson SoC support
-M:	Neil Armstrong <narmstrong@baylibre.com>
+M:	Neil Armstrong <neil.armstrong@linaro.org>
 M:	Kevin Hilman <khilman@baylibre.com>
 R:	Jerome Brunet <jbrunet@baylibre.com>
 R:	Martin Blumenstingl <martin.blumenstingl@googlemail.com>
@@ -2178,7 +2176,7 @@ M:	Jean-Marie Verdun <verdun@hpe.com>
 M:	Nick Hawkins <nick.hawkins@hpe.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/arm/hpe,gxp.yaml
-F:	Documentation/devicetree/bindings/spi/hpe,gxp-spi.yaml
+F:	Documentation/devicetree/bindings/spi/hpe,gxp-spifi.yaml
 F:	Documentation/devicetree/bindings/timer/hpe,gxp-timer.yaml
 F:	arch/arm/boot/dts/hpe-bmc*
 F:	arch/arm/boot/dts/hpe-gxp*
@@ -2531,7 +2529,7 @@ W:	http://www.digriz.org.uk/ts78xx/kernel
 F:	arch/arm/mach-orion5x/ts78xx-*
 
 ARM/OXNAS platform support
-M:	Neil Armstrong <narmstrong@baylibre.com>
+M:	Neil Armstrong <neil.armstrong@linaro.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-oxnas@groups.io (moderated for non-subscribers)
 S:	Maintained
@@ -2579,7 +2577,7 @@ W:	http://www.armlinux.org.uk/
 
 ARM/QUALCOMM SUPPORT
 M:	Andy Gross <agross@kernel.org>
-M:	Bjorn Andersson <bjorn.andersson@linaro.org>
+M:	Bjorn Andersson <andersson@kernel.org>
 R:	Konrad Dybcio <konrad.dybcio@somainline.org>
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
@@ -2670,7 +2668,6 @@ M:	Russell King <linux@armlinux.org.uk>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 W:	http://www.armlinux.org.uk/
-F:	arch/arm/include/asm/hardware/entry-macro-iomd.S
 F:	arch/arm/include/asm/hardware/ioc.h
 F:	arch/arm/include/asm/hardware/iomd.h
 F:	arch/arm/include/asm/hardware/memc.h
@@ -3612,6 +3609,7 @@ F:	include/linux/find.h
 F:	include/linux/nodemask.h
 F:	lib/bitmap.c
 F:	lib/cpumask.c
+F:	lib/cpumask_kunit.c
 F:	lib/find_bit.c
 F:	lib/find_bit_benchmark.c
 F:	lib/test_bitmap.c
@@ -3679,6 +3677,7 @@ F:	Documentation/networking/bonding.rst
 F:	drivers/net/bonding/
 F:	include/net/bond*
 F:	include/uapi/linux/if_bonding.h
+F:	tools/testing/selftests/drivers/net/bonding/
 
 BOSCH SENSORTEC BMA400 ACCELEROMETER IIO DRIVER
 M:	Dan Robertson <dan@dlrobertson.com>
@@ -5145,6 +5144,7 @@ T:	git git://git.samba.org/sfrench/cifs-2.6.git
 F:	Documentation/admin-guide/cifs/
 F:	fs/cifs/
 F:	fs/smbfs_common/
+F:	include/uapi/linux/cifs
 
 COMPACTPCI HOTPLUG CORE
 M:	Scott Murray <scott@spiteful.org>
@@ -5242,6 +5242,7 @@ F:	block/blk-throttle.c
 F:	include/linux/blk-cgroup.h
 
 CONTROL GROUP - CPUSET
+M:	Waiman Long <longman@redhat.com>
 M:	Zefan Li <lizefan.x@bytedance.com>
 L:	cgroups@vger.kernel.org
 S:	Maintained
@@ -6750,7 +6751,7 @@ F:	Documentation/devicetree/bindings/display/panel/samsung,lms380kf01.yaml
 F:	drivers/gpu/drm/panel/panel-widechips-ws2401.c
 
 DRM DRIVERS
-M:	David Airlie <airlied@linux.ie>
+M:	David Airlie <airlied@gmail.com>
 M:	Daniel Vetter <daniel@ffwll.ch>
 L:	dri-devel@lists.freedesktop.org
 S:	Maintained
@@ -6789,7 +6790,7 @@ F:	Documentation/devicetree/bindings/display/allwinner*
 F:	drivers/gpu/drm/sun4i/
 
 DRM DRIVERS FOR AMLOGIC SOCS
-M:	Neil Armstrong <narmstrong@baylibre.com>
+M:	Neil Armstrong <neil.armstrong@linaro.org>
 L:	dri-devel@lists.freedesktop.org
 L:	linux-amlogic@lists.infradead.org
 S:	Supported
@@ -6811,7 +6812,7 @@ F:	drivers/gpu/drm/atmel-hlcdc/
 
 DRM DRIVERS FOR BRIDGE CHIPS
 M:	Andrzej Hajda <andrzej.hajda@intel.com>
-M:	Neil Armstrong <narmstrong@baylibre.com>
+M:	Neil Armstrong <neil.armstrong@linaro.org>
 M:	Robert Foss <robert.foss@linaro.org>
 R:	Laurent Pinchart <Laurent.pinchart@ideasonboard.com>
 R:	Jonas Karlman <jonas@kwiboo.se>
@@ -7684,7 +7685,6 @@ R:	Kees Cook <keescook@chromium.org>
 L:	linux-mm@kvack.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve
-F:	arch/alpha/kernel/binfmt_loader.c
 F:	fs/*binfmt_*.c
 F:	fs/exec.c
 F:	include/linux/binfmts.h
@@ -8001,6 +8001,7 @@ L:	linux-hardening@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening
 F:	include/linux/fortify-string.h
+F:	lib/fortify_kunit.c
 F:	lib/test_fortify/*
 F:	scripts/test_fortify.sh
 K:	\b__NO_FORTIFY\b
@@ -8649,8 +8650,8 @@ F:	drivers/input/touchscreen/goodix*
 
 GOOGLE ETHERNET DRIVERS
 M:	Jeroen de Borst <jeroendb@google.com>
-R:	Catherine Sullivan <csully@google.com>
-R:	David Awogbemila <awogbemila@google.com>
+M:	Catherine Sullivan <csully@google.com>
+R:	Shailend Chand <shailend@google.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	Documentation/networking/device_drivers/ethernet/google/gve.rst
@@ -8940,7 +8941,7 @@ F:	include/linux/hw_random.h
 
 HARDWARE SPINLOCK CORE
 M:	Ohad Ben-Cohen <ohad@wizery.com>
-M:	Bjorn Andersson <bjorn.andersson@linaro.org>
+M:	Bjorn Andersson <andersson@kernel.org>
 R:	Baolin Wang <baolin.wang7@gmail.com>
 L:	linux-remoteproc@vger.kernel.org
 S:	Maintained
@@ -9119,7 +9120,7 @@ S:	Maintained
 F:	drivers/dma/hisi_dma.c
 
 HISILICON GPIO DRIVER
-M:	Luo Jiaxing <luojiaxing@huawei.com>
+M:	Jay Fang <f.fangjian@huawei.com>
 L:	linux-gpio@vger.kernel.org
 S:	Maintained
 F:	drivers/gpio/gpio-hisi.c
@@ -9205,8 +9206,8 @@ F:	Documentation/ABI/testing/debugfs-hisi-zip
 F:	drivers/crypto/hisilicon/zip/
 
 HISILICON ROCE DRIVER
+M:	Haoyue Xu <xuhaoyue1@hisilicon.com>
 M:	Wenpeng Liang <liangwenpeng@huawei.com>
-M:	Weihang Li <liweihang@huawei.com>
 L:	linux-rdma@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt
@@ -9780,7 +9781,7 @@ M:	Christian Brauner <brauner@kernel.org>
 M:	Seth Forshee <sforshee@kernel.org>
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux.git
+T:	git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping.git
 F:	Documentation/filesystems/idmappings.rst
 F:	tools/testing/selftests/mount_setattr/
 F:	include/linux/mnt_idmapping.h
@@ -10029,6 +10030,7 @@ F:	Documentation/devicetree/bindings/input/
 F:	Documentation/devicetree/bindings/serio/
 F:	Documentation/input/
 F:	drivers/input/
+F:	include/dt-bindings/input/
 F:	include/linux/input.h
 F:	include/linux/input/
 F:	include/uapi/linux/input-event-codes.h
@@ -10374,7 +10376,6 @@ INTEL MENLOW THERMAL DRIVER
 M:	Sujith Thomas <sujith.thomas@intel.com>
 L:	linux-pm@vger.kernel.org
 S:	Supported
-W:	https://01.org/linux-acpi
 F:	drivers/thermal/intel/intel_menlow.c
 
 INTEL P-Unit IPC DRIVER
@@ -10657,6 +10658,7 @@ T:	git git://git.kernel.dk/linux-block
 T:	git git://git.kernel.dk/liburing
 F:	io_uring/
 F:	include/linux/io_uring.h
+F:	include/linux/io_uring_types.h
 F:	include/uapi/linux/io_uring.h
 F:	tools/io_uring/
 
@@ -10823,7 +10825,7 @@ F:	drivers/media/tuners/it913x*
 
 ITE IT66121 HDMI BRIDGE DRIVER
 M:	Phong LE <ple@baylibre.com>
-M:	Neil Armstrong <narmstrong@baylibre.com>
+M:	Neil Armstrong <neil.armstrong@linaro.org>
 S:	Maintained
 T:	git git://anongit.freedesktop.org/drm/drm-misc
 F:	Documentation/devicetree/bindings/display/bridge/ite,it66121.yaml
@@ -11342,7 +11344,7 @@ F:	kernel/debug/
 F:	kernel/module/kdb.c
 
 KHADAS MCU MFD DRIVER
-M:	Neil Armstrong <narmstrong@baylibre.com>
+M:	Neil Armstrong <neil.armstrong@linaro.org>
 L:	linux-amlogic@lists.infradead.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/mfd/khadas,mcu.yaml
@@ -13213,7 +13215,7 @@ S:	Maintained
 F:	drivers/watchdog/menz69_wdt.c
 
 MESON AO CEC DRIVER FOR AMLOGIC SOCS
-M:	Neil Armstrong <narmstrong@baylibre.com>
+M:	Neil Armstrong <neil.armstrong@linaro.org>
 L:	linux-media@vger.kernel.org
 L:	linux-amlogic@lists.infradead.org
 S:	Supported
@@ -13224,7 +13226,7 @@ F:	drivers/media/cec/platform/meson/ao-cec-g12a.c
 F:	drivers/media/cec/platform/meson/ao-cec.c
 
 MESON GE2D DRIVER FOR AMLOGIC SOCS
-M:	Neil Armstrong <narmstrong@baylibre.com>
+M:	Neil Armstrong <neil.armstrong@linaro.org>
 L:	linux-media@vger.kernel.org
 L:	linux-amlogic@lists.infradead.org
 S:	Supported
@@ -13240,7 +13242,7 @@ F:	Documentation/devicetree/bindings/mtd/amlogic,meson-nand.txt
 F:	drivers/mtd/nand/raw/meson_*
 
 MESON VIDEO DECODER DRIVER FOR AMLOGIC SOCS
-M:	Neil Armstrong <narmstrong@baylibre.com>
+M:	Neil Armstrong <neil.armstrong@linaro.org>
 L:	linux-media@vger.kernel.org
 L:	linux-amlogic@lists.infradead.org
 S:	Supported
@@ -14444,6 +14446,7 @@ M:	Willy Tarreau <w@1wt.eu>
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/wtarreau/nolibc.git
 F:	tools/include/nolibc/
+F:	tools/testing/selftests/nolibc/
 
 NSDEPS
 M:	Matthias Maennich <maennich@google.com>
@@ -16120,7 +16123,7 @@ F:	drivers/gpio/gpio-sama5d2-piobu.c
 F:	drivers/pinctrl/pinctrl-at91*
 
 PIN CONTROLLER - QUALCOMM
-M:	Bjorn Andersson <bjorn.andersson@linaro.org>
+M:	Bjorn Andersson <andersson@kernel.org>
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/pinctrl/qcom,*.txt
@@ -16813,7 +16816,7 @@ F:	Documentation/devicetree/bindings/media/*camss*
 F:	drivers/media/platform/qcom/camss/
 
 QUALCOMM CLOCK DRIVERS
-M:	Bjorn Andersson <bjorn.andersson@linaro.org>
+M:	Bjorn Andersson <andersson@kernel.org>
 L:	linux-arm-msm@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/qcom/linux.git
@@ -16852,6 +16855,7 @@ F:	drivers/net/ethernet/qualcomm/emac/
 
 QUALCOMM ETHQOS ETHERNET DRIVER
 M:	Vinod Koul <vkoul@kernel.org>
+R:	Bhupesh Sharma <bhupesh.sharma@linaro.org>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/qcom,ethqos.txt
@@ -17302,7 +17306,7 @@ S:	Supported
 F:	fs/reiserfs/
 
 REMOTE PROCESSOR (REMOTEPROC) SUBSYSTEM
-M:	Bjorn Andersson <bjorn.andersson@linaro.org>
+M:	Bjorn Andersson <andersson@kernel.org>
 M:	Mathieu Poirier <mathieu.poirier@linaro.org>
 L:	linux-remoteproc@vger.kernel.org
 S:	Maintained
@@ -17315,7 +17319,7 @@ F:	include/linux/remoteproc.h
 F:	include/linux/remoteproc/
 
 REMOTE PROCESSOR MESSAGING (RPMSG) SUBSYSTEM
-M:	Bjorn Andersson <bjorn.andersson@linaro.org>
+M:	Bjorn Andersson <andersson@kernel.org>
 M:	Mathieu Poirier <mathieu.poirier@linaro.org>
 L:	linux-remoteproc@vger.kernel.org
 S:	Maintained
@@ -17527,9 +17531,19 @@ M:	Conor Dooley <conor.dooley@microchip.com>
 M:	Daire McNamara <daire.mcnamara@microchip.com>
 L:	linux-riscv@lists.infradead.org
 S:	Supported
+F:	Documentation/devicetree/bindings/clock/microchip,mpfs.yaml
+F:	Documentation/devicetree/bindings/gpio/microchip,mpfs-gpio.yaml
+F:	Documentation/devicetree/bindings/i2c/microchip,corei2c.yaml
+F:	Documentation/devicetree/bindings/mailbox/microchip,mpfs-mailbox.yaml
+F:	Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml
+F:	Documentation/devicetree/bindings/pwm/microchip,corepwm.yaml
+F:	Documentation/devicetree/bindings/soc/microchip/microchip,mpfs-sys-controller.yaml
+F:	Documentation/devicetree/bindings/spi/microchip,mpfs-spi.yaml
+F:	Documentation/devicetree/bindings/usb/microchip,mpfs-musb.yaml
 F:	arch/riscv/boot/dts/microchip/
 F:	drivers/char/hw_random/mpfs-rng.c
 F:	drivers/clk/microchip/clk-mpfs.c
+F:	drivers/i2c/busses/i2c-microchip-core.c
 F:	drivers/mailbox/mailbox-mpfs.c
 F:	drivers/pci/controller/pcie-microchip-host.c
 F:	drivers/rtc/rtc-mpfs.c
@@ -17730,6 +17744,35 @@ L:	linux-rdma@vger.kernel.org
 S:	Maintained
 F:	drivers/infiniband/ulp/rtrs/
 
+RUNTIME VERIFICATION (RV)
+M:	Daniel Bristot de Oliveira <bristot@kernel.org>
+M:	Steven Rostedt <rostedt@goodmis.org>
+L:	linux-trace-devel@vger.kernel.org
+S:	Maintained
+F:	Documentation/trace/rv/
+F:	include/linux/rv.h
+F:	include/rv/
+F:	kernel/trace/rv/
+F:	tools/verification/
+
+RUST
+M:	Miguel Ojeda <ojeda@kernel.org>
+M:	Alex Gaynor <alex.gaynor@gmail.com>
+M:	Wedson Almeida Filho <wedsonaf@gmail.com>
+R:	Boqun Feng <boqun.feng@gmail.com>
+R:	Gary Guo <gary@garyguo.net>
+R:	Björn Roy Baron <bjorn3_gh@protonmail.com>
+L:	rust-for-linux@vger.kernel.org
+S:	Supported
+W:	https://github.com/Rust-for-Linux/linux
+B:	https://github.com/Rust-for-Linux/linux/issues
+T:	git https://github.com/Rust-for-Linux/linux.git rust-next
+F:	Documentation/rust/
+F:	rust/
+F:	samples/rust/
+F:	scripts/*rust*
+K:	\b(?i:rust)\b
+
 RXRPC SOCKETS (AF_RXRPC)
 M:	David Howells <dhowells@redhat.com>
 M:	Marc Dionne <marc.dionne@auristor.com>
@@ -19933,6 +19976,7 @@ S:	Supported
 F:	drivers/net/team/
 F:	include/linux/if_team.h
 F:	include/uapi/linux/if_team.h
+F:	tools/testing/selftests/drivers/net/team/
 
 TECHNOLOGIC SYSTEMS TS-5500 PLATFORM SUPPORT
 M:	"Savoir-faire Linux Inc." <kernel@savoirfairelinux.com>
@@ -20596,6 +20640,7 @@ F:	include/*/ftrace.h
 F:	include/linux/trace*.h
 F:	include/trace/
 F:	kernel/trace/
+F:	scripts/tracing/
 F:	tools/testing/selftests/ftrace/
 
 TRACING MMIO ACCESSES (MMIOTRACE)
@@ -20760,6 +20805,7 @@ UBLK USERSPACE BLOCK DRIVER
 M:	Ming Lei <ming.lei@redhat.com>
 L:	linux-block@vger.kernel.org
 S:	Maintained
+F:	Documentation/block/ublk.rst
 F:	drivers/block/ublk_drv.c
 F:	include/uapi/linux/ublk_cmd.h
 
@@ -21537,7 +21583,7 @@ F:	drivers/gpio/gpio-virtio.c
 F:	include/uapi/linux/virtio_gpio.h
 
 VIRTIO GPU DRIVER
-M:	David Airlie <airlied@linux.ie>
+M:	David Airlie <airlied@redhat.com>
 M:	Gerd Hoffmann <kraxel@redhat.com>
 R:	Gurchetan Singh <gurchetansingh@chromium.org>
 R:	Chia-I Wu <olvaffe@gmail.com>
@@ -22301,7 +22347,7 @@ M:	Shubhrajyoti Datta <shubhrajyoti.datta@xilinx.com>
 R:	Srinivas Neeli <srinivas.neeli@xilinx.com>
 R:	Michal Simek <michal.simek@xilinx.com>
 S:	Maintained
-F:	Documentation/devicetree/bindings/gpio/gpio-xilinx.txt
+F:	Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml
 F:	Documentation/devicetree/bindings/gpio/gpio-zynq.yaml
 F:	drivers/gpio/gpio-xilinx.c
 F:	drivers/gpio/gpio-zynq.c
diff --git a/Makefile b/Makefile
index f09673b6c11d..f659d3085121 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION =
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*
@@ -120,6 +120,15 @@ endif
 
 export KBUILD_CHECKSRC
 
+# Enable "clippy" (a linter) as part of the Rust compilation.
+#
+# Use 'make CLIPPY=1' to enable it.
+ifeq ("$(origin CLIPPY)", "command line")
+  KBUILD_CLIPPY := $(CLIPPY)
+endif
+
+export KBUILD_CLIPPY
+
 # Use make M=dir or set the environment variable KBUILD_EXTMOD to specify the
 # directory of external module to build. Setting M= takes precedence.
 ifeq ("$(origin M)", "command line")
@@ -270,14 +279,14 @@ no-dot-config-targets := $(clean-targets) \
 			 cscope gtags TAGS tags help% %docs check% coccicheck \
 			 $(version_h) headers headers_% archheaders archscripts \
 			 %asm-generic kernelversion %src-pkg dt_binding_check \
-			 outputmakefile
+			 outputmakefile rustavailable rustfmt rustfmtcheck
 # Installation targets should not require compiler. Unfortunately, vdso_install
 # is an exception where build artifacts may be updated. This must be fixed.
 no-compiler-targets := $(no-dot-config-targets) install dtbs_install \
 			headers_install modules_install kernelrelease image_name
 no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease \
 			  image_name
-single-targets := %.a %.i %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/
+single-targets := %.a %.i %.rsi %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/
 
 config-build	:=
 mixed-build	:=
@@ -439,6 +448,7 @@ else
 HOSTCC	= gcc
 HOSTCXX	= g++
 endif
+HOSTRUSTC = rustc
 HOSTPKG_CONFIG	= pkg-config
 
 KBUILD_USERHOSTCFLAGS := -Wall -Wmissing-prototypes -Wstrict-prototypes \
@@ -447,8 +457,26 @@ KBUILD_USERHOSTCFLAGS := -Wall -Wmissing-prototypes -Wstrict-prototypes \
 KBUILD_USERCFLAGS  := $(KBUILD_USERHOSTCFLAGS) $(USERCFLAGS)
 KBUILD_USERLDFLAGS := $(USERLDFLAGS)
 
+# These flags apply to all Rust code in the tree, including the kernel and
+# host programs.
+export rust_common_flags := --edition=2021 \
+			    -Zbinary_dep_depinfo=y \
+			    -Dunsafe_op_in_unsafe_fn -Drust_2018_idioms \
+			    -Dunreachable_pub -Dnon_ascii_idents \
+			    -Wmissing_docs \
+			    -Drustdoc::missing_crate_level_docs \
+			    -Dclippy::correctness -Dclippy::style \
+			    -Dclippy::suspicious -Dclippy::complexity \
+			    -Dclippy::perf \
+			    -Dclippy::let_unit_value -Dclippy::mut_mut \
+			    -Dclippy::needless_bitwise_bool \
+			    -Dclippy::needless_continue \
+			    -Wclippy::dbg_macro
+
 KBUILD_HOSTCFLAGS   := $(KBUILD_USERHOSTCFLAGS) $(HOST_LFS_CFLAGS) $(HOSTCFLAGS)
 KBUILD_HOSTCXXFLAGS := -Wall -O2 $(HOST_LFS_CFLAGS) $(HOSTCXXFLAGS)
+KBUILD_HOSTRUSTFLAGS := $(rust_common_flags) -O -Cstrip=debuginfo \
+			-Zallow-features= $(HOSTRUSTFLAGS)
 KBUILD_HOSTLDFLAGS  := $(HOST_LFS_LDFLAGS) $(HOSTLDFLAGS)
 KBUILD_HOSTLDLIBS   := $(HOST_LFS_LIBS) $(HOSTLDLIBS)
 
@@ -473,6 +501,12 @@ OBJDUMP		= $(CROSS_COMPILE)objdump
 READELF		= $(CROSS_COMPILE)readelf
 STRIP		= $(CROSS_COMPILE)strip
 endif
+RUSTC		= rustc
+RUSTDOC		= rustdoc
+RUSTFMT		= rustfmt
+CLIPPY_DRIVER	= clippy-driver
+BINDGEN		= bindgen
+CARGO		= cargo
 PAHOLE		= pahole
 RESOLVE_BTFIDS	= $(objtree)/tools/bpf/resolve_btfids/resolve_btfids
 LEX		= flex
@@ -498,9 +532,11 @@ CHECKFLAGS     := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \
 		  -Wbitwise -Wno-return-void -Wno-unknown-attribute $(CF)
 NOSTDINC_FLAGS :=
 CFLAGS_MODULE   =
+RUSTFLAGS_MODULE =
 AFLAGS_MODULE   =
 LDFLAGS_MODULE  =
 CFLAGS_KERNEL	=
+RUSTFLAGS_KERNEL =
 AFLAGS_KERNEL	=
 LDFLAGS_vmlinux =
 
@@ -529,15 +565,43 @@ KBUILD_CFLAGS   := -Wall -Wundef -Werror=strict-prototypes -Wno-trigraphs \
 		   -Werror=return-type -Wno-format-security \
 		   -std=gnu11
 KBUILD_CPPFLAGS := -D__KERNEL__
+KBUILD_RUSTFLAGS := $(rust_common_flags) \
+		    --target=$(objtree)/rust/target.json \
+		    -Cpanic=abort -Cembed-bitcode=n -Clto=n \
+		    -Cforce-unwind-tables=n -Ccodegen-units=1 \
+		    -Csymbol-mangling-version=v0 \
+		    -Crelocation-model=static \
+		    -Zfunction-sections=n \
+		    -Dclippy::float_arithmetic
+
 KBUILD_AFLAGS_KERNEL :=
 KBUILD_CFLAGS_KERNEL :=
+KBUILD_RUSTFLAGS_KERNEL :=
 KBUILD_AFLAGS_MODULE  := -DMODULE
 KBUILD_CFLAGS_MODULE  := -DMODULE
+KBUILD_RUSTFLAGS_MODULE := --cfg MODULE
 KBUILD_LDFLAGS_MODULE :=
 KBUILD_LDFLAGS :=
 CLANG_FLAGS :=
 
+ifeq ($(KBUILD_CLIPPY),1)
+	RUSTC_OR_CLIPPY_QUIET := CLIPPY
+	RUSTC_OR_CLIPPY = $(CLIPPY_DRIVER)
+else
+	RUSTC_OR_CLIPPY_QUIET := RUSTC
+	RUSTC_OR_CLIPPY = $(RUSTC)
+endif
+
+ifdef RUST_LIB_SRC
+	export RUST_LIB_SRC
+endif
+
+# Allows the usage of unstable features in stable compilers.
+export RUSTC_BOOTSTRAP := 1
+
 export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE LD CC HOSTPKG_CONFIG
+export RUSTC RUSTDOC RUSTFMT RUSTC_OR_CLIPPY_QUIET RUSTC_OR_CLIPPY BINDGEN CARGO
+export HOSTRUSTC KBUILD_HOSTRUSTFLAGS
 export CPP AR NM STRIP OBJCOPY OBJDUMP READELF PAHOLE RESOLVE_BTFIDS LEX YACC AWK INSTALLKERNEL
 export PERL PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX
 export KGZIP KBZIP2 KLZOP LZMA LZ4 XZ ZSTD
@@ -546,9 +610,10 @@ export KBUILD_USERCFLAGS KBUILD_USERLDFLAGS
 
 export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS KBUILD_LDFLAGS
 export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE
+export KBUILD_RUSTFLAGS RUSTFLAGS_KERNEL RUSTFLAGS_MODULE
 export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE
-export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE
-export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL
+export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_RUSTFLAGS_MODULE KBUILD_LDFLAGS_MODULE
+export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL KBUILD_RUSTFLAGS_KERNEL
 export PAHOLE_FLAGS
 
 # Files to ignore in find ... statements
@@ -729,7 +794,7 @@ $(KCONFIG_CONFIG):
 #
 # Do not use $(call cmd,...) here. That would suppress prompts from syncconfig,
 # so you cannot notice that Kconfig is waiting for the user input.
-%/config/auto.conf %/config/auto.conf.cmd %/generated/autoconf.h: $(KCONFIG_CONFIG)
+%/config/auto.conf %/config/auto.conf.cmd %/generated/autoconf.h %/generated/rustc_cfg: $(KCONFIG_CONFIG)
 	$(Q)$(kecho) "  SYNC    $@"
 	$(Q)$(MAKE) -f $(srctree)/Makefile syncconfig
 else # !may-sync-config
@@ -758,10 +823,17 @@ KBUILD_CFLAGS	+= $(call cc-disable-warning, address-of-packed-member)
 
 ifdef CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE
 KBUILD_CFLAGS += -O2
+KBUILD_RUSTFLAGS += -Copt-level=2
 else ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
 KBUILD_CFLAGS += -Os
+KBUILD_RUSTFLAGS += -Copt-level=s
 endif
 
+# Always set `debug-assertions` and `overflow-checks` because their default
+# depends on `opt-level` and `debug-assertions`, respectively.
+KBUILD_RUSTFLAGS += -Cdebug-assertions=$(if $(CONFIG_RUST_DEBUG_ASSERTIONS),y,n)
+KBUILD_RUSTFLAGS += -Coverflow-checks=$(if $(CONFIG_RUST_OVERFLOW_CHECKS),y,n)
+
 # Tell gcc to never replace conditional load with a non-conditional one
 ifdef CONFIG_CC_IS_GCC
 # gcc-10 renamed --param=allow-store-data-races=0 to
@@ -792,6 +864,9 @@ KBUILD_CFLAGS-$(CONFIG_WERROR) += -Werror
 KBUILD_CFLAGS-$(CONFIG_CC_NO_ARRAY_BOUNDS) += -Wno-array-bounds
 KBUILD_CFLAGS += $(KBUILD_CFLAGS-y) $(CONFIG_CC_IMPLICIT_FALLTHROUGH)
 
+KBUILD_RUSTFLAGS-$(CONFIG_WERROR) += -Dwarnings
+KBUILD_RUSTFLAGS += $(KBUILD_RUSTFLAGS-y)
+
 ifdef CONFIG_CC_IS_CLANG
 KBUILD_CPPFLAGS += -Qunused-arguments
 # The kernel builds with '-std=gnu11' so use of GNU extensions is acceptable.
@@ -812,12 +887,15 @@ KBUILD_CFLAGS += $(call cc-disable-warning, dangling-pointer)
 
 ifdef CONFIG_FRAME_POINTER
 KBUILD_CFLAGS	+= -fno-omit-frame-pointer -fno-optimize-sibling-calls
+KBUILD_RUSTFLAGS += -Cforce-frame-pointers=y
 else
 # Some targets (ARM with Thumb2, for example), can't be built with frame
 # pointers.  For those, we don't have FUNCTION_TRACER automatically
 # select FRAME_POINTER.  However, FUNCTION_TRACER adds -pg, and this is
 # incompatible with -fomit-frame-pointer with current GCC, so we don't use
 # -fomit-frame-pointer with FUNCTION_TRACER.
+# In the Rust target specification, "frame-pointer" is set explicitly
+# to "may-omit".
 ifndef CONFIG_FUNCTION_TRACER
 KBUILD_CFLAGS	+= -fomit-frame-pointer
 endif
@@ -831,8 +909,8 @@ endif
 # Initialize all stack variables with a zero value.
 ifdef CONFIG_INIT_STACK_ALL_ZERO
 KBUILD_CFLAGS	+= -ftrivial-auto-var-init=zero
-ifdef CONFIG_CC_IS_CLANG
-# https://bugs.llvm.org/show_bug.cgi?id=45497
+ifdef CONFIG_CC_HAS_AUTO_VAR_INIT_ZERO_ENABLER
+# https://github.com/llvm/llvm-project/issues/44842
 KBUILD_CFLAGS	+= -enable-trivial-auto-var-init-zero-knowing-it-will-be-removed-from-clang
 endif
 endif
@@ -882,8 +960,10 @@ ifdef CONFIG_DEBUG_SECTION_MISMATCH
 KBUILD_CFLAGS += -fno-inline-functions-called-once
 endif
 
+# `rustc`'s `-Zfunction-sections` applies to data too (as of 1.59.0).
 ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
 KBUILD_CFLAGS_KERNEL += -ffunction-sections -fdata-sections
+KBUILD_RUSTFLAGS_KERNEL += -Zfunction-sections=y
 LDFLAGS_vmlinux += --gc-sections
 endif
 
@@ -921,18 +1001,7 @@ export CC_FLAGS_LTO
 endif
 
 ifdef CONFIG_CFI_CLANG
-CC_FLAGS_CFI	:= -fsanitize=cfi \
-		   -fsanitize-cfi-cross-dso \
-		   -fno-sanitize-cfi-canonical-jump-tables \
-		   -fno-sanitize-trap=cfi \
-		   -fno-sanitize-blacklist
-
-ifdef CONFIG_CFI_PERMISSIVE
-CC_FLAGS_CFI	+= -fsanitize-recover=cfi
-endif
-
-# If LTO flags are filtered out, we must also filter out CFI.
-CC_FLAGS_LTO	+= $(CC_FLAGS_CFI)
+CC_FLAGS_CFI	:= -fsanitize=kcfi
 KBUILD_CFLAGS	+= $(CC_FLAGS_CFI)
 export CC_FLAGS_CFI
 endif
@@ -1026,10 +1095,11 @@ include $(addprefix $(srctree)/, $(include-y))
 # Do not add $(call cc-option,...) below this line. When you build the kernel
 # from the clean source tree, the GCC plugins do not exist at this point.
 
-# Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments
+# Add user supplied CPPFLAGS, AFLAGS, CFLAGS and RUSTFLAGS as the last assignments
 KBUILD_CPPFLAGS += $(KCPPFLAGS)
 KBUILD_AFLAGS   += $(KAFLAGS)
 KBUILD_CFLAGS   += $(KCFLAGS)
+KBUILD_RUSTFLAGS += $(KRUSTFLAGS)
 
 KBUILD_LDFLAGS_MODULE += --build-id=sha1
 LDFLAGS_vmlinux += --build-id=sha1
@@ -1104,6 +1174,7 @@ ifeq ($(KBUILD_EXTMOD),)
 core-y			+= kernel/ certs/ mm/ fs/ ipc/ security/ crypto/
 core-$(CONFIG_BLOCK)	+= block/
 core-$(CONFIG_IO_URING)	+= io_uring/
+core-$(CONFIG_RUST)	+= rust/
 
 vmlinux-dirs	:= $(patsubst %/,%,$(filter %/, \
 		     $(core-y) $(core-m) $(drivers-y) $(drivers-m) \
@@ -1113,13 +1184,11 @@ vmlinux-alldirs	:= $(sort $(vmlinux-dirs) Documentation \
 		     $(patsubst %/,%,$(filter %/, $(core-) \
 			$(drivers-) $(libs-))))
 
-subdir-modorder := $(addsuffix modules.order,$(filter %/, \
-			$(core-y) $(core-m) $(libs-y) $(libs-m) \
-			$(drivers-y) $(drivers-m)))
-
 build-dirs	:= $(vmlinux-dirs)
 clean-dirs	:= $(vmlinux-alldirs)
 
+subdir-modorder := $(addsuffix /modules.order, $(build-dirs))
+
 # Externally visible symbols (used by link-vmlinux.sh)
 KBUILD_VMLINUX_OBJS := $(head-y) $(patsubst %/,%/built-in.a, $(core-y))
 KBUILD_VMLINUX_OBJS += $(addsuffix built-in.a, $(filter %/, $(libs-y)))
@@ -1208,6 +1277,10 @@ prepare0: archprepare
 
 # All the preparing..
 prepare: prepare0
+ifdef CONFIG_RUST
+	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh -v
+	$(Q)$(MAKE) $(build)=rust
+endif
 
 PHONY += remove-stale-files
 remove-stale-files:
@@ -1289,8 +1362,7 @@ hdr-inst := -f $(srctree)/scripts/Makefile.headersinst obj
 
 PHONY += headers
 headers: $(version_h) scripts_unifdef uapi-asm-generic archheaders archscripts
-	$(if $(wildcard $(srctree)/arch/$(SRCARCH)/include/uapi/asm/Kbuild),, \
-	  $(error Headers not exportable for the $(SRCARCH) architecture))
+	$(if $(filter um, $(SRCARCH)), $(error Headers not exportable for UML))
 	$(Q)$(MAKE) $(hdr-inst)=include/uapi
 	$(Q)$(MAKE) $(hdr-inst)=arch/$(SRCARCH)/include/uapi
 
@@ -1502,7 +1574,7 @@ endif # CONFIG_MODULES
 # Directories & files removed with 'make clean'
 CLEAN_FILES += include/ksym vmlinux.symvers modules-only.symvers \
 	       modules.builtin modules.builtin.modinfo modules.nsdeps \
-	       compile_commands.json .thinlto-cache
+	       compile_commands.json .thinlto-cache rust/test rust/doc
 
 # Directories & files removed with 'make mrproper'
 MRPROPER_FILES += include/config include/generated          \
@@ -1513,7 +1585,8 @@ MRPROPER_FILES += include/config include/generated          \
 		  certs/signing_key.pem \
 		  certs/x509.genkey \
 		  vmlinux-gdb.py \
-		  *.spec
+		  *.spec \
+		  rust/target.json rust/libmacros.so
 
 # clean - Delete most, but leave enough to build external modules
 #
@@ -1538,6 +1611,9 @@ $(mrproper-dirs):
 
 mrproper: clean $(mrproper-dirs)
 	$(call cmd,rmfiles)
+	@find . $(RCS_FIND_IGNORE) \
+		\( -name '*.rmeta' \) \
+		-type f -print | xargs rm -f
 
 # distclean
 #
@@ -1625,6 +1701,24 @@ help:
 	@echo  '  kselftest-merge   - Merge all the config dependencies of'
 	@echo  '		      kselftest to existing .config.'
 	@echo  ''
+	@echo  'Rust targets:'
+	@echo  '  rustavailable   - Checks whether the Rust toolchain is'
+	@echo  '		    available and, if not, explains why.'
+	@echo  '  rustfmt	  - Reformat all the Rust code in the kernel'
+	@echo  '  rustfmtcheck	  - Checks if all the Rust code in the kernel'
+	@echo  '		    is formatted, printing a diff otherwise.'
+	@echo  '  rustdoc	  - Generate Rust documentation'
+	@echo  '		    (requires kernel .config)'
+	@echo  '  rusttest        - Runs the Rust tests'
+	@echo  '                    (requires kernel .config; downloads external repos)'
+	@echo  '  rust-analyzer	  - Generate rust-project.json rust-analyzer support file'
+	@echo  '		    (requires kernel .config)'
+	@echo  '  dir/file.[os]   - Build specified target only'
+	@echo  '  dir/file.rsi    - Build macro expanded source, similar to C preprocessing.'
+	@echo  '                    Run with RUSTFMT=n to skip reformatting if needed.'
+	@echo  '                    The output is not intended to be compilable.'
+	@echo  '  dir/file.ll     - Build the LLVM assembly file'
+	@echo  ''
 	@$(if $(dtstree), \
 		echo 'Devicetree:'; \
 		echo '* dtbs             - Build device tree blobs for enabled boards'; \
@@ -1697,6 +1791,52 @@ PHONY += $(DOC_TARGETS)
 $(DOC_TARGETS):
 	$(Q)$(MAKE) $(build)=Documentation $@
 
+
+# Rust targets
+# ---------------------------------------------------------------------------
+
+# "Is Rust available?" target
+PHONY += rustavailable
+rustavailable:
+	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh -v && echo "Rust is available!"
+
+# Documentation target
+#
+# Using the singular to avoid running afoul of `no-dot-config-targets`.
+PHONY += rustdoc
+rustdoc: prepare
+	$(Q)$(MAKE) $(build)=rust $@
+
+# Testing target
+PHONY += rusttest
+rusttest: prepare
+	$(Q)$(MAKE) $(build)=rust $@
+
+# Formatting targets
+PHONY += rustfmt rustfmtcheck
+
+# We skip `rust/alloc` since we want to minimize the diff w.r.t. upstream.
+#
+# We match using absolute paths since `find` does not resolve them
+# when matching, which is a problem when e.g. `srctree` is `..`.
+# We `grep` afterwards in order to remove the directory entry itself.
+rustfmt:
+	$(Q)find $(abs_srctree) -type f -name '*.rs' \
+		-o -path $(abs_srctree)/rust/alloc -prune \
+		-o -path $(abs_objtree)/rust/test -prune \
+		| grep -Fv $(abs_srctree)/rust/alloc \
+		| grep -Fv $(abs_objtree)/rust/test \
+		| grep -Fv generated \
+		| xargs $(RUSTFMT) $(rustfmt_flags)
+
+rustfmtcheck: rustfmt_flags = --check
+rustfmtcheck: rustfmt
+
+# IDE support targets
+PHONY += rust-analyzer
+rust-analyzer:
+	$(Q)$(MAKE) $(build)=rust $@
+
 # Misc
 # ---------------------------------------------------------------------------
 
@@ -1864,7 +2004,7 @@ $(clean-dirs):
 clean: $(clean-dirs)
 	$(call cmd,rmfiles)
 	@find $(or $(KBUILD_EXTMOD), .) $(RCS_FIND_IGNORE) \
-		\( -name '*.[aios]' -o -name '*.ko' -o -name '.*.cmd' \
+		\( -name '*.[aios]' -o -name '*.rsi' -o -name '*.ko' -o -name '.*.cmd' \
 		-o -name '*.ko.*' \
 		-o -name '*.dtb' -o -name '*.dtbo' -o -name '*.dtb.S' -o -name '*.dt.yaml' \
 		-o -name '*.dwo' -o -name '*.lst' \
diff --git a/arch/Kconfig b/arch/Kconfig
index f330410da63a..266862428a84 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -53,7 +53,6 @@ config KPROBES
 config JUMP_LABEL
 	bool "Optimize very unlikely/likely branches"
 	depends on HAVE_ARCH_JUMP_LABEL
-	depends on CC_HAS_ASM_GOTO
 	select OBJTOOL if HAVE_JUMP_LABEL_HACK
 	help
 	 This option enables a transparent branch optimization that
@@ -356,6 +355,12 @@ config HAVE_RSEQ
 	  This symbol should be selected by an architecture if it
 	  supports an implementation of restartable sequences.
 
+config HAVE_RUST
+	bool
+	help
+	  This symbol should be selected by an architecture if it
+	  supports Rust.
+
 config HAVE_FUNCTION_ARG_ACCESS_API
 	bool
 	help
@@ -739,11 +744,13 @@ config ARCH_SUPPORTS_CFI_CLANG
 	  An architecture should select this option if it can support Clang's
 	  Control-Flow Integrity (CFI) checking.
 
+config ARCH_USES_CFI_TRAPS
+	bool
+
 config CFI_CLANG
 	bool "Use Clang's Control Flow Integrity (CFI)"
-	depends on LTO_CLANG && ARCH_SUPPORTS_CFI_CLANG
-	depends on CLANG_VERSION >= 140000
-	select KALLSYMS
+	depends on ARCH_SUPPORTS_CFI_CLANG
+	depends on $(cc-option,-fsanitize=kcfi)
 	help
 	  This option enables Clang’s forward-edge Control Flow Integrity
 	  (CFI) checking, where the compiler injects a runtime check to each
@@ -755,16 +762,6 @@ config CFI_CLANG
 
 	    https://clang.llvm.org/docs/ControlFlowIntegrity.html
 
-config CFI_CLANG_SHADOW
-	bool "Use CFI shadow to speed up cross-module checks"
-	default y
-	depends on CFI_CLANG && MODULES
-	help
-	  If you select this option, the kernel builds a fast look-up table of
-	  CFI check functions in loaded modules to reduce performance overhead.
-
-	  If unsure, say Y.
-
 config CFI_PERMISSIVE
 	bool "Use CFI in permissive mode"
 	depends on CFI_CLANG
@@ -924,6 +921,9 @@ config HAVE_SOFTIRQ_ON_OWN_STACK
 	  Architecture provides a function to run __do_softirq() on a
 	  separate stack.
 
+config SOFTIRQ_ON_OWN_STACK
+	def_bool HAVE_SOFTIRQ_ON_OWN_STACK && !PREEMPT_RT
+
 config ALTERNATE_USER_ADDRESS_SPACE
 	bool
 	help
@@ -1361,7 +1361,7 @@ config HAVE_PREEMPT_DYNAMIC_CALL
 
 config HAVE_PREEMPT_DYNAMIC_KEY
 	bool
-	depends on HAVE_ARCH_JUMP_LABEL && CC_HAS_ASM_GOTO
+	depends on HAVE_ARCH_JUMP_LABEL
 	select HAVE_PREEMPT_DYNAMIC
 	help
 	   An architecture should select this if it can handle the preemption
diff --git a/arch/alpha/include/asm/a.out.h b/arch/alpha/include/asm/a.out.h
deleted file mode 100644
index d2346b7caff1..000000000000
--- a/arch/alpha/include/asm/a.out.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ALPHA_A_OUT_H__
-#define __ALPHA_A_OUT_H__
-
-#include <uapi/asm/a.out.h>
-
-
-/* Assume that start addresses below 4G belong to a TASO application.
-   Unfortunately, there is no proper bit in the exec header to check.
-   Worse, we have to notice the start address before swapping to use
-   /sbin/loader, which of course is _not_ a TASO application.  */
-#define SET_AOUT_PERSONALITY(BFPM, EX) \
-	set_personality (((BFPM->taso || EX.ah.entry < 0x100000000L \
-			   ? ADDR_LIMIT_32BIT : 0) | PER_OSF4))
-
-#endif /* __A_OUT_GNU_H__ */
diff --git a/arch/alpha/include/asm/bitops.h b/arch/alpha/include/asm/bitops.h
index 492c7713ddae..bafb1c1f0fdc 100644
--- a/arch/alpha/include/asm/bitops.h
+++ b/arch/alpha/include/asm/bitops.h
@@ -283,11 +283,8 @@ arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 	return (old & mask) != 0;
 }
 
-static __always_inline bool
-arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
-{
-	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
-}
+#define arch_test_bit generic_test_bit
+#define arch_test_bit_acquire generic_test_bit_acquire
 
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
diff --git a/arch/alpha/kernel/Makefile b/arch/alpha/kernel/Makefile
index 5a74581bf0ee..6a274c0d53a2 100644
--- a/arch/alpha/kernel/Makefile
+++ b/arch/alpha/kernel/Makefile
@@ -47,10 +47,6 @@ else
 # Misc support
 obj-$(CONFIG_ALPHA_SRM)		+= srmcons.o
 
-ifdef CONFIG_BINFMT_AOUT
-obj-y	+= binfmt_loader.o
-endif
-
 # Core logic support
 obj-$(CONFIG_ALPHA_APECS)	+= core_apecs.o
 obj-$(CONFIG_ALPHA_CIA)		+= core_cia.o
diff --git a/arch/alpha/kernel/binfmt_loader.c b/arch/alpha/kernel/binfmt_loader.c
deleted file mode 100644
index e4be7a543ecf..000000000000
--- a/arch/alpha/kernel/binfmt_loader.c
+++ /dev/null
@@ -1,46 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/init.h>
-#include <linux/fs.h>
-#include <linux/file.h>
-#include <linux/mm_types.h>
-#include <linux/binfmts.h>
-#include <linux/a.out.h>
-
-static int load_binary(struct linux_binprm *bprm)
-{
-	struct exec *eh = (struct exec *)bprm->buf;
-	unsigned long loader;
-	struct file *file;
-	int retval;
-
-	if (eh->fh.f_magic != 0x183 || (eh->fh.f_flags & 0x3000) != 0x3000)
-		return -ENOEXEC;
-
-	if (bprm->loader)
-		return -ENOEXEC;
-
-	loader = bprm->vma->vm_end - sizeof(void *);
-
-	file = open_exec("/sbin/loader");
-	retval = PTR_ERR(file);
-	if (IS_ERR(file))
-		return retval;
-
-	/* Remember if the application is TASO.  */
-	bprm->taso = eh->ah.entry < 0x100000000UL;
-
-	bprm->interpreter = file;
-	bprm->loader = loader;
-	return 0;
-}
-
-static struct linux_binfmt loader_format = {
-	.load_binary	= load_binary,
-};
-
-static int __init init_loader_binfmt(void)
-{
-	insert_binfmt(&loader_format);
-	return 0;
-}
-arch_initcall(init_loader_binfmt);
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index d257293401e2..b3ad8c44c971 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1278,45 +1278,15 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	return addr;
 }
 
-#ifdef CONFIG_OSF4_COMPAT
-/* Clear top 32 bits of iov_len in the user's buffer for
-   compatibility with old versions of OSF/1 where iov_len
-   was defined as int. */
-static int
-osf_fix_iov_len(const struct iovec __user *iov, unsigned long count)
-{
-	unsigned long i;
-
-	for (i = 0 ; i < count ; i++) {
-		int __user *iov_len_high = (int __user *)&iov[i].iov_len + 1;
-
-		if (put_user(0, iov_len_high))
-			return -EFAULT;
-	}
-	return 0;
-}
-#endif
-
 SYSCALL_DEFINE3(osf_readv, unsigned long, fd,
 		const struct iovec __user *, vector, unsigned long, count)
 {
-#ifdef CONFIG_OSF4_COMPAT
-	if (unlikely(personality(current->personality) == PER_OSF4))
-		if (osf_fix_iov_len(vector, count))
-			return -EFAULT;
-#endif
-
 	return sys_readv(fd, vector, count);
 }
 
 SYSCALL_DEFINE3(osf_writev, unsigned long, fd,
 		const struct iovec __user *, vector, unsigned long, count)
 {
-#ifdef CONFIG_OSF4_COMPAT
-	if (unlikely(personality(current->personality) == PER_OSF4))
-		if (osf_fix_iov_len(vector, count))
-			return -EFAULT;
-#endif
 	return sys_writev(fd, vector, count);
 }
 
diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c
index cb2e069dc73f..abfed1aa2baa 100644
--- a/arch/arm/boot/compressed/misc.c
+++ b/arch/arm/boot/compressed/misc.c
@@ -23,7 +23,9 @@ unsigned int __machine_arch_type;
 #include <linux/types.h>
 #include <linux/linkage.h>
 #include "misc.h"
+#ifdef CONFIG_ARCH_EP93XX
 #include "misc-ep93xx.h"
+#endif
 
 static void putstr(const char *ptr);
 
diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S
index 1bcb68ac4b01..3fcb3e62dc56 100644
--- a/arch/arm/boot/compressed/vmlinux.lds.S
+++ b/arch/arm/boot/compressed/vmlinux.lds.S
@@ -23,6 +23,7 @@ SECTIONS
     *(.ARM.extab*)
     *(.note.*)
     *(.rel.*)
+    *(.printk_index)
     /*
      * Discard any r/w data - this produces a link error if we have any,
      * which is required for PIC decompression.  Local data generates
@@ -57,6 +58,7 @@ SECTIONS
     *(.rodata)
     *(.rodata.*)
     *(.data.rel.ro)
+    *(.data.rel.ro.*)
   }
   .piggydata : {
     *(.piggydata)
diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi
index 7da42a5b959c..7e50fe633d8a 100644
--- a/arch/arm/boot/dts/am33xx-l4.dtsi
+++ b/arch/arm/boot/dts/am33xx-l4.dtsi
@@ -1502,8 +1502,7 @@
 			mmc1: mmc@0 {
 				compatible = "ti,am335-sdhci";
 				ti,needs-special-reset;
-				dmas = <&edma_xbar 24 0 0
-					&edma_xbar 25 0 0>;
+				dmas = <&edma 24 0>, <&edma 25 0>;
 				dma-names = "tx", "rx";
 				interrupts = <64>;
 				reg = <0x0 0x1000>;
diff --git a/arch/arm/boot/dts/am5748.dtsi b/arch/arm/boot/dts/am5748.dtsi
index c260aa1a85bd..a1f029e9d1f3 100644
--- a/arch/arm/boot/dts/am5748.dtsi
+++ b/arch/arm/boot/dts/am5748.dtsi
@@ -25,6 +25,10 @@
 	status = "disabled";
 };
 
+&usb4_tm {
+	status = "disabled";
+};
+
 &atl_tm {
 	status = "disabled";
 };
diff --git a/arch/arm/boot/dts/arm-realview-eb.dtsi b/arch/arm/boot/dts/arm-realview-eb.dtsi
index 2dfb32bf9d48..fbb2258b451f 100644
--- a/arch/arm/boot/dts/arm-realview-eb.dtsi
+++ b/arch/arm/boot/dts/arm-realview-eb.dtsi
@@ -399,7 +399,7 @@
 			compatible = "arm,pl022", "arm,primecell";
 			reg = <0x1000d000 0x1000>;
 			clocks = <&sspclk>, <&pclk>;
-			clock-names = "SSPCLK", "apb_pclk";
+			clock-names = "sspclk", "apb_pclk";
 		};
 
 		wdog: watchdog@10010000 {
diff --git a/arch/arm/boot/dts/arm-realview-pb1176.dts b/arch/arm/boot/dts/arm-realview-pb1176.dts
index 06b8723b09eb..efed325af88d 100644
--- a/arch/arm/boot/dts/arm-realview-pb1176.dts
+++ b/arch/arm/boot/dts/arm-realview-pb1176.dts
@@ -410,7 +410,7 @@
 			interrupt-parent = <&intc_dc1176>;
 			interrupts = <0 17 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&sspclk>, <&pclk>;
-			clock-names = "SSPCLK", "apb_pclk";
+			clock-names = "sspclk", "apb_pclk";
 		};
 
 		pb1176_serial0: serial@1010c000 {
diff --git a/arch/arm/boot/dts/arm-realview-pb11mp.dts b/arch/arm/boot/dts/arm-realview-pb11mp.dts
index 295aef448123..89103d54ecc1 100644
--- a/arch/arm/boot/dts/arm-realview-pb11mp.dts
+++ b/arch/arm/boot/dts/arm-realview-pb11mp.dts
@@ -555,7 +555,7 @@
 			interrupt-parent = <&intc_pb11mp>;
 			interrupts = <0 11 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&sspclk>, <&pclk>;
-			clock-names = "SSPCLK", "apb_pclk";
+			clock-names = "sspclk", "apb_pclk";
 		};
 
 		watchdog@1000f000 {
diff --git a/arch/arm/boot/dts/arm-realview-pbx.dtsi b/arch/arm/boot/dts/arm-realview-pbx.dtsi
index 6f61f968d689..ec1507c5147c 100644
--- a/arch/arm/boot/dts/arm-realview-pbx.dtsi
+++ b/arch/arm/boot/dts/arm-realview-pbx.dtsi
@@ -390,7 +390,7 @@
 			compatible = "arm,pl022", "arm,primecell";
 			reg = <0x1000d000 0x1000>;
 			clocks = <&sspclk>, <&pclk>;
-			clock-names = "SSPCLK", "apb_pclk";
+			clock-names = "sspclk", "apb_pclk";
 		};
 
 		wdog0: watchdog@1000f000 {
diff --git a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi
index 76b2025c67b4..83bcf9fe0152 100644
--- a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi
+++ b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi
@@ -76,8 +76,8 @@
 		regulators {
 			vdd_3v3: VDD_IO {
 				regulator-name = "VDD_IO";
-				regulator-min-microvolt = <1200000>;
-				regulator-max-microvolt = <3700000>;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
 				regulator-initial-mode = <2>;
 				regulator-allowed-modes = <2>, <4>;
 				regulator-always-on;
@@ -95,8 +95,8 @@
 
 			vddio_ddr: VDD_DDR {
 				regulator-name = "VDD_DDR";
-				regulator-min-microvolt = <600000>;
-				regulator-max-microvolt = <1850000>;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
 				regulator-initial-mode = <2>;
 				regulator-allowed-modes = <2>, <4>;
 				regulator-always-on;
@@ -118,8 +118,8 @@
 
 			vdd_core: VDD_CORE {
 				regulator-name = "VDD_CORE";
-				regulator-min-microvolt = <600000>;
-				regulator-max-microvolt = <1850000>;
+				regulator-min-microvolt = <1250000>;
+				regulator-max-microvolt = <1250000>;
 				regulator-initial-mode = <2>;
 				regulator-allowed-modes = <2>, <4>;
 				regulator-always-on;
@@ -160,8 +160,8 @@
 
 			LDO1 {
 				regulator-name = "LDO1";
-				regulator-min-microvolt = <1200000>;
-				regulator-max-microvolt = <3700000>;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
 				regulator-always-on;
 
 				regulator-state-standby {
@@ -175,9 +175,8 @@
 
 			LDO2 {
 				regulator-name = "LDO2";
-				regulator-min-microvolt = <1200000>;
-				regulator-max-microvolt = <3700000>;
-				regulator-always-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
 
 				regulator-state-standby {
 					regulator-on-in-suspend;
diff --git a/arch/arm/boot/dts/at91-sama5d2_icp.dts b/arch/arm/boot/dts/at91-sama5d2_icp.dts
index 6865be8d7787..dd1dec9d4e07 100644
--- a/arch/arm/boot/dts/at91-sama5d2_icp.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_icp.dts
@@ -196,8 +196,8 @@
 			regulators {
 				vdd_io_reg: VDD_IO {
 					regulator-name = "VDD_IO";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <3700000>;
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
 					regulator-always-on;
@@ -215,8 +215,8 @@
 
 				VDD_DDR {
 					regulator-name = "VDD_DDR";
-					regulator-min-microvolt = <600000>;
-					regulator-max-microvolt = <1850000>;
+					regulator-min-microvolt = <1350000>;
+					regulator-max-microvolt = <1350000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
 					regulator-always-on;
@@ -234,8 +234,8 @@
 
 				VDD_CORE {
 					regulator-name = "VDD_CORE";
-					regulator-min-microvolt = <600000>;
-					regulator-max-microvolt = <1850000>;
+					regulator-min-microvolt = <1250000>;
+					regulator-max-microvolt = <1250000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
 					regulator-always-on;
@@ -257,7 +257,6 @@
 					regulator-max-microvolt = <1850000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
-					regulator-always-on;
 
 					regulator-state-standby {
 						regulator-on-in-suspend;
@@ -272,8 +271,8 @@
 
 				LDO1 {
 					regulator-name = "LDO1";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <3700000>;
+					regulator-min-microvolt = <2500000>;
+					regulator-max-microvolt = <2500000>;
 					regulator-always-on;
 
 					regulator-state-standby {
@@ -287,8 +286,8 @@
 
 				LDO2 {
 					regulator-name = "LDO2";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <3700000>;
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
 					regulator-always-on;
 
 					regulator-state-standby {
diff --git a/arch/arm/boot/dts/at91-sama7g5ek.dts b/arch/arm/boot/dts/at91-sama7g5ek.dts
index de44da2e4aae..3b25c67795dd 100644
--- a/arch/arm/boot/dts/at91-sama7g5ek.dts
+++ b/arch/arm/boot/dts/at91-sama7g5ek.dts
@@ -244,8 +244,8 @@
 			regulators {
 				vdd_3v3: VDD_IO {
 					regulator-name = "VDD_IO";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <3700000>;
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
 					regulator-always-on;
@@ -264,8 +264,8 @@
 
 				vddioddr: VDD_DDR {
 					regulator-name = "VDD_DDR";
-					regulator-min-microvolt = <1300000>;
-					regulator-max-microvolt = <1450000>;
+					regulator-min-microvolt = <1350000>;
+					regulator-max-microvolt = <1350000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
 					regulator-always-on;
@@ -285,8 +285,8 @@
 
 				vddcore: VDD_CORE {
 					regulator-name = "VDD_CORE";
-					regulator-min-microvolt = <1100000>;
-					regulator-max-microvolt = <1850000>;
+					regulator-min-microvolt = <1150000>;
+					regulator-max-microvolt = <1150000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
 					regulator-always-on;
@@ -306,7 +306,7 @@
 				vddcpu: VDD_OTHER {
 					regulator-name = "VDD_OTHER";
 					regulator-min-microvolt = <1050000>;
-					regulator-max-microvolt = <1850000>;
+					regulator-max-microvolt = <1250000>;
 					regulator-initial-mode = <2>;
 					regulator-allowed-modes = <2>, <4>;
 					regulator-ramp-delay = <3125>;
@@ -326,8 +326,8 @@
 
 				vldo1: LDO1 {
 					regulator-name = "LDO1";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <3700000>;
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
 					regulator-always-on;
 
 					regulator-state-standby {
diff --git a/arch/arm/boot/dts/bcm63178.dtsi b/arch/arm/boot/dts/bcm63178.dtsi
index 5463443f0762..cbd094dde6d0 100644
--- a/arch/arm/boot/dts/bcm63178.dtsi
+++ b/arch/arm/boot/dts/bcm63178.dtsi
@@ -32,6 +32,7 @@
 			next-level-cache = <&L2_0>;
 			enable-method = "psci";
 		};
+
 		CA7_2: cpu@2 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a7";
@@ -39,6 +40,7 @@
 			next-level-cache = <&L2_0>;
 			enable-method = "psci";
 		};
+
 		L2_0: l2-cache0 {
 			compatible = "cache";
 		};
@@ -46,10 +48,10 @@
 
 	timer {
 		compatible = "arm,armv7-timer";
-		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-			<GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-			<GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-			<GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(3) | IRQ_TYPE_LEVEL_LOW)>,
+			<GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(3) | IRQ_TYPE_LEVEL_LOW)>,
+			<GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(3) | IRQ_TYPE_LEVEL_LOW)>,
+			<GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(3) | IRQ_TYPE_LEVEL_LOW)>;
 		arm,cpu-registers-not-fw-configured;
 	};
 
@@ -80,23 +82,23 @@
 	psci {
 		compatible = "arm,psci-0.2";
 		method = "smc";
-		cpu_off = <1>;
-		cpu_on = <2>;
 	};
 
 	axi@81000000 {
 		compatible = "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
-		ranges = <0 0x81000000 0x4000>;
+		ranges = <0 0x81000000 0x8000>;
 
 		gic: interrupt-controller@1000 {
 			compatible = "arm,cortex-a7-gic";
 			#interrupt-cells = <3>;
-			#address-cells = <0>;
 			interrupt-controller;
+			interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(3) | IRQ_TYPE_LEVEL_HIGH)>;
 			reg = <0x1000 0x1000>,
-				<0x2000 0x2000>;
+				<0x2000 0x2000>,
+				<0x4000 0x2000>,
+				<0x6000 0x2000>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/bcm6846.dtsi b/arch/arm/boot/dts/bcm6846.dtsi
index e610c102498f..8aa47a2583b2 100644
--- a/arch/arm/boot/dts/bcm6846.dtsi
+++ b/arch/arm/boot/dts/bcm6846.dtsi
@@ -40,10 +40,10 @@
 
 	timer {
 		compatible = "arm,armv7-timer";
-		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-			<GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-			<GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-			<GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			<GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			<GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			<GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>;
 		arm,cpu-registers-not-fw-configured;
 	};
 
@@ -65,23 +65,23 @@
 	psci {
 		compatible = "arm,psci-0.2";
 		method = "smc";
-		cpu_off = <1>;
-		cpu_on = <2>;
 	};
 
 	axi@81000000 {
 		compatible = "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
-		ranges = <0 0x81000000 0x4000>;
+		ranges = <0 0x81000000 0x8000>;
 
 		gic: interrupt-controller@1000 {
 			compatible = "arm,cortex-a7-gic";
 			#interrupt-cells = <3>;
-			#address-cells = <0>;
 			interrupt-controller;
+			interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>;
 			reg = <0x1000 0x1000>,
-				<0x2000 0x2000>;
+				<0x2000 0x2000>,
+				<0x4000 0x2000>,
+				<0x6000 0x2000>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/bcm6878.dtsi b/arch/arm/boot/dts/bcm6878.dtsi
index a7dff596fe1e..1e8b5fa96c25 100644
--- a/arch/arm/boot/dts/bcm6878.dtsi
+++ b/arch/arm/boot/dts/bcm6878.dtsi
@@ -32,6 +32,7 @@
 			next-level-cache = <&L2_0>;
 			enable-method = "psci";
 		};
+
 		L2_0: l2-cache0 {
 			compatible = "cache";
 		};
@@ -39,10 +40,10 @@
 
 	timer {
 		compatible = "arm,armv7-timer";
-		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-			<GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-			<GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
-			<GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			<GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			<GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			<GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>;
 		arm,cpu-registers-not-fw-configured;
 	};
 
diff --git a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi
index 095c9143d99a..6b791d515e29 100644
--- a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi
@@ -51,16 +51,6 @@
 		vin-supply = <&reg_3p3v_s5>;
 	};
 
-	reg_3p3v_s0: regulator-3p3v-s0 {
-		compatible = "regulator-fixed";
-		regulator-name = "V_3V3_S0";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-		regulator-always-on;
-		regulator-boot-on;
-		vin-supply = <&reg_3p3v_s5>;
-	};
-
 	reg_3p3v_s5: regulator-3p3v-s5 {
 		compatible = "regulator-fixed";
 		regulator-name = "V_3V3_S5";
@@ -259,7 +249,7 @@
 
 	/* default boot source: workaround #1 for errata ERR006282 */
 	smarc_flash: flash@0 {
-		compatible = "winbond,w25q16dw", "jedec,spi-nor";
+		compatible = "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <20000000>;
 	};
diff --git a/arch/arm/boot/dts/imx6qdl-vicut1.dtsi b/arch/arm/boot/dts/imx6qdl-vicut1.dtsi
index a1676b5d2980..c5a98b0110dd 100644
--- a/arch/arm/boot/dts/imx6qdl-vicut1.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-vicut1.dtsi
@@ -28,7 +28,7 @@
 		enable-gpios = <&gpio4 28 GPIO_ACTIVE_HIGH>;
 	};
 
-	backlight_led: backlight_led {
+	backlight_led: backlight-led {
 		compatible = "pwm-backlight";
 		pwms = <&pwm3 0 5000000 0>;
 		brightness-levels = <0 16 64 255>;
diff --git a/arch/arm/boot/dts/integratorap-im-pd1.dts b/arch/arm/boot/dts/integratorap-im-pd1.dts
index d47bfb66d069..cc514cf07bff 100644
--- a/arch/arm/boot/dts/integratorap-im-pd1.dts
+++ b/arch/arm/boot/dts/integratorap-im-pd1.dts
@@ -178,12 +178,12 @@
 		clock-names = "uartclk", "apb_pclk";
 	};
 
-	ssp@300000 {
+	spi@300000 {
 		compatible = "arm,pl022", "arm,primecell";
 		reg = <0x00300000 0x1000>;
 		interrupts-extended = <&impd1_vic 3>;
 		clocks = <&impd1_sspclk>, <&sysclk>;
-		clock-names = "spiclk", "apb_pclk";
+		clock-names = "sspclk", "apb_pclk";
 	};
 
 	impd1_gpio0: gpio@400000 {
@@ -249,6 +249,7 @@
 		/* 640x480 16bpp @ 25.175MHz is 36827428 bytes/s */
 		max-memory-bandwidth = <40000000>;
 		memory-region = <&impd1_ram>;
+		dma-ranges;
 
 		port@0 {
 			#address-cells = <1>;
diff --git a/arch/arm/boot/dts/integratorap.dts b/arch/arm/boot/dts/integratorap.dts
index 9b652cc27b14..9148287fa0a9 100644
--- a/arch/arm/boot/dts/integratorap.dts
+++ b/arch/arm/boot/dts/integratorap.dts
@@ -160,6 +160,7 @@
 
 	pci: pciv3@62000000 {
 		compatible = "arm,integrator-ap-pci", "v3,v360epc-pci";
+		device_type = "pci";
 		#interrupt-cells = <1>;
 		#size-cells = <2>;
 		#address-cells = <3>;
@@ -261,7 +262,7 @@
 		lm0: bus@c0000000 {
 			compatible = "simple-bus";
 			ranges = <0x00000000 0xc0000000 0x10000000>;
-			dma-ranges = <0x00000000 0x80000000 0x10000000>;
+			dma-ranges = <0x00000000 0xc0000000 0x10000000>;
 			reg = <0xc0000000 0x10000000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
@@ -269,7 +270,7 @@
 		lm1: bus@d0000000 {
 			compatible = "simple-bus";
 			ranges = <0x00000000 0xd0000000 0x10000000>;
-			dma-ranges = <0x00000000 0x80000000 0x10000000>;
+			dma-ranges = <0x00000000 0xd0000000 0x10000000>;
 			reg = <0xd0000000 0x10000000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
@@ -277,7 +278,7 @@
 		lm2: bus@e0000000 {
 			compatible = "simple-bus";
 			ranges = <0x00000000 0xe0000000 0x10000000>;
-			dma-ranges = <0x00000000 0x80000000 0x10000000>;
+			dma-ranges = <0x00000000 0xe0000000 0x10000000>;
 			reg = <0xe0000000 0x10000000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
@@ -285,7 +286,7 @@
 		lm3: bus@f0000000 {
 			compatible = "simple-bus";
 			ranges = <0x00000000 0xf0000000 0x10000000>;
-			dma-ranges = <0x00000000 0x80000000 0x10000000>;
+			dma-ranges = <0x00000000 0xf0000000 0x10000000>;
 			reg = <0xf0000000 0x10000000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
diff --git a/arch/arm/boot/dts/lan966x.dtsi b/arch/arm/boot/dts/lan966x.dtsi
index 894bf9da19a4..0bf818713422 100644
--- a/arch/arm/boot/dts/lan966x.dtsi
+++ b/arch/arm/boot/dts/lan966x.dtsi
@@ -541,13 +541,13 @@
 
 			phy0: ethernet-phy@1 {
 				reg = <1>;
-				interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
 			};
 
 			phy1: ethernet-phy@2 {
 				reg = <2>;
-				interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
 			};
 		};
diff --git a/arch/arm/boot/dts/moxart-uc7112lx.dts b/arch/arm/boot/dts/moxart-uc7112lx.dts
index eb5291b0ee3a..e07b807b4cec 100644
--- a/arch/arm/boot/dts/moxart-uc7112lx.dts
+++ b/arch/arm/boot/dts/moxart-uc7112lx.dts
@@ -79,7 +79,7 @@
 	clocks = <&ref12>;
 };
 
-&sdhci {
+&mmc {
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/moxart.dtsi b/arch/arm/boot/dts/moxart.dtsi
index f5f070a87482..764832ddfa78 100644
--- a/arch/arm/boot/dts/moxart.dtsi
+++ b/arch/arm/boot/dts/moxart.dtsi
@@ -93,8 +93,8 @@
 			clock-names = "PCLK";
 		};
 
-		sdhci: sdhci@98e00000 {
-			compatible = "moxa,moxart-sdhci";
+		mmc: mmc@98e00000 {
+			compatible = "moxa,moxart-mmc";
 			reg = <0x98e00000 0x5C>;
 			interrupts = <5 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&clk_apb>;
diff --git a/arch/arm/boot/dts/versatile-ab.dts b/arch/arm/boot/dts/versatile-ab.dts
index 79f7cc241282..a520615f4d8d 100644
--- a/arch/arm/boot/dts/versatile-ab.dts
+++ b/arch/arm/boot/dts/versatile-ab.dts
@@ -391,7 +391,7 @@
 			reg = <0x101f4000 0x1000>;
 			interrupts = <11>;
 			clocks = <&xtal24mhz>, <&pclk>;
-			clock-names = "SSPCLK", "apb_pclk";
+			clock-names = "sspclk", "apb_pclk";
 		};
 
 		fpga {
diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig
index da90ce9cd42e..e185eee18856 100644
--- a/arch/arm/configs/at91_dt_defconfig
+++ b/arch/arm/configs/at91_dt_defconfig
@@ -196,7 +196,6 @@ CONFIG_RTC_DRV_AT91SAM9=y
 CONFIG_DMADEVICES=y
 CONFIG_AT_HDMAC=y
 CONFIG_AT_XDMAC=y
-CONFIG_MICROCHIP_PIT64B=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_IIO=y
 CONFIG_AT91_ADC=y
diff --git a/arch/arm/configs/badge4_defconfig b/arch/arm/configs/badge4_defconfig
index 506f3378da07..6908032fbce8 100644
--- a/arch/arm/configs/badge4_defconfig
+++ b/arch/arm/configs/badge4_defconfig
@@ -6,7 +6,6 @@ CONFIG_UNUSED_BOARD_FILES=y
 CONFIG_CMDLINE="init=/linuxrc root=/dev/mtdblock3"
 CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
 CONFIG_FPE_NWFPE=y
-CONFIG_BINFMT_AOUT=m
 CONFIG_MODULES=y
 CONFIG_MODVERSIONS=y
 CONFIG_PARTITION_ADVANCED=y
diff --git a/arch/arm/configs/corgi_defconfig b/arch/arm/configs/corgi_defconfig
index 1f137f74050f..df84640f4f57 100644
--- a/arch/arm/configs/corgi_defconfig
+++ b/arch/arm/configs/corgi_defconfig
@@ -16,7 +16,6 @@ CONFIG_MACH_HUSKY=y
 CONFIG_UNUSED_BOARD_FILES=y
 CONFIG_CMDLINE="console=ttyS0,115200n8 console=tty1 noinitrd root=/dev/mtdblock2 rootfstype=jffs2   debug"
 CONFIG_FPE_NWFPE=y
-CONFIG_BINFMT_AOUT=m
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
diff --git a/arch/arm/configs/ezx_defconfig b/arch/arm/configs/ezx_defconfig
index 1a41391d7367..cd9ccc4e4627 100644
--- a/arch/arm/configs/ezx_defconfig
+++ b/arch/arm/configs/ezx_defconfig
@@ -25,7 +25,6 @@ CONFIG_CPU_FREQ_GOV_ONDEMAND=m
 CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m
 CONFIG_CPU_IDLE=y
 CONFIG_FPE_NWFPE=y
-CONFIG_BINFMT_AOUT=m
 CONFIG_PM=y
 CONFIG_APM_EMULATION=y
 CONFIG_MODULES=y
diff --git a/arch/arm/configs/footbridge_defconfig b/arch/arm/configs/footbridge_defconfig
index 504070812ad0..b5b56f8dda5f 100644
--- a/arch/arm/configs/footbridge_defconfig
+++ b/arch/arm/configs/footbridge_defconfig
@@ -9,7 +9,6 @@ CONFIG_ARCH_EBSA285_HOST=y
 CONFIG_ARCH_NETWINDER=y
 CONFIG_FPE_NWFPE=y
 CONFIG_FPE_NWFPE_XP=y
-CONFIG_BINFMT_AOUT=y
 CONFIG_MODULES=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_ACORN_PARTITION=y
diff --git a/arch/arm/configs/hackkit_defconfig b/arch/arm/configs/hackkit_defconfig
index b9327b2eacd3..398558c4ffa8 100644
--- a/arch/arm/configs/hackkit_defconfig
+++ b/arch/arm/configs/hackkit_defconfig
@@ -7,7 +7,6 @@ CONFIG_UNUSED_BOARD_FILES=y
 CONFIG_CMDLINE="console=ttySA0,115200 root=/dev/ram0 initrd=0xc0400000,8M init=/rootshell"
 CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
 CONFIG_FPE_NWFPE=y
-CONFIG_BINFMT_AOUT=y
 CONFIG_MODULES=y
 CONFIG_NET=y
 CONFIG_PACKET=y
diff --git a/arch/arm/configs/iop32x_defconfig b/arch/arm/configs/iop32x_defconfig
index c16e92cdfd00..19e30e790d35 100644
--- a/arch/arm/configs/iop32x_defconfig
+++ b/arch/arm/configs/iop32x_defconfig
@@ -12,7 +12,6 @@ CONFIG_MACH_N2100=y
 CONFIG_UNUSED_BOARD_FILES=y
 CONFIG_CMDLINE="console=ttyS0,115200 root=/dev/nfs ip=bootp cachepolicy=writealloc"
 CONFIG_FPE_NWFPE=y
-CONFIG_BINFMT_AOUT=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_PARTITION_ADVANCED=y
diff --git a/arch/arm/configs/jornada720_defconfig b/arch/arm/configs/jornada720_defconfig
index 3dcf89d3e1f1..1a11ee6b3e24 100644
--- a/arch/arm/configs/jornada720_defconfig
+++ b/arch/arm/configs/jornada720_defconfig
@@ -6,7 +6,6 @@ CONFIG_SA1100_JORNADA720=y
 CONFIG_SA1100_JORNADA720_SSP=y
 CONFIG_UNUSED_BOARD_FILES=y
 CONFIG_FPE_NWFPE=y
-CONFIG_BINFMT_AOUT=y
 CONFIG_PM=y
 CONFIG_MODULES=y
 CONFIG_NET=y
diff --git a/arch/arm/configs/lart_defconfig b/arch/arm/configs/lart_defconfig
index 0c2f19d756c0..00583d64d2ea 100644
--- a/arch/arm/configs/lart_defconfig
+++ b/arch/arm/configs/lart_defconfig
@@ -8,7 +8,6 @@ CONFIG_CMDLINE="console=ttySA0,9600 root=/dev/ram"
 CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_FPE_NWFPE=y
-CONFIG_BINFMT_AOUT=y
 CONFIG_PM=y
 CONFIG_MODULES=y
 CONFIG_NET=y
diff --git a/arch/arm/configs/neponset_defconfig b/arch/arm/configs/neponset_defconfig
index 907403529e30..2d16ddb0e7ff 100644
--- a/arch/arm/configs/neponset_defconfig
+++ b/arch/arm/configs/neponset_defconfig
@@ -9,7 +9,6 @@ CONFIG_ZBOOT_ROM_BSS=0xc1000000
 CONFIG_ZBOOT_ROM=y
 CONFIG_CMDLINE="console=ttySA0,38400n8 cpufreq=221200 rw root=/dev/mtdblock2 mtdparts=sa1100:512K(boot),1M(kernel),2560K(initrd),4M(root) load_ramdisk=1 prompt_ramdisk=0 mem=32M noinitrd initrd=0xc0800000,3M"
 CONFIG_FPE_NWFPE=y
-CONFIG_BINFMT_AOUT=y
 CONFIG_PM=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
diff --git a/arch/arm/configs/netwinder_defconfig b/arch/arm/configs/netwinder_defconfig
index cf7bbcf9d98a..7a14ea1faa65 100644
--- a/arch/arm/configs/netwinder_defconfig
+++ b/arch/arm/configs/netwinder_defconfig
@@ -5,7 +5,6 @@ CONFIG_ARCH_NETWINDER=y
 CONFIG_DEPRECATED_PARAM_STRUCT=y
 CONFIG_CMDLINE="root=0x801"
 CONFIG_FPE_NWFPE=y
-CONFIG_BINFMT_AOUT=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_NET=y
 CONFIG_PACKET=y
diff --git a/arch/arm/configs/rpc_defconfig b/arch/arm/configs/rpc_defconfig
index 16d74a1f027a..b667c9d4527c 100644
--- a/arch/arm/configs/rpc_defconfig
+++ b/arch/arm/configs/rpc_defconfig
@@ -7,7 +7,6 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_ARCH_RPC=y
 CONFIG_CPU_SA110=y
 CONFIG_FPE_NWFPE=y
-CONFIG_BINFMT_AOUT=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_BSD_DISKLABEL=y
 CONFIG_SLAB=y
diff --git a/arch/arm/configs/sama7_defconfig b/arch/arm/configs/sama7_defconfig
index 0384030d8b25..b2311f004618 100644
--- a/arch/arm/configs/sama7_defconfig
+++ b/arch/arm/configs/sama7_defconfig
@@ -188,7 +188,6 @@ CONFIG_RTC_DRV_AT91SAM9=y
 CONFIG_DMADEVICES=y
 CONFIG_AT_XDMAC=y
 CONFIG_STAGING=y
-CONFIG_MICROCHIP_PIT64B=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_IIO=y
 CONFIG_IIO_SW_TRIGGER=y
diff --git a/arch/arm/configs/spitz_defconfig b/arch/arm/configs/spitz_defconfig
index 1284a1d92ca3..66d74653f3fb 100644
--- a/arch/arm/configs/spitz_defconfig
+++ b/arch/arm/configs/spitz_defconfig
@@ -13,7 +13,6 @@ CONFIG_MACH_AKITA=y
 CONFIG_MACH_BORZOI=y
 CONFIG_CMDLINE="console=ttyS0,115200n8 console=tty1 noinitrd root=/dev/mtdblock2 rootfstype=jffs2   debug"
 CONFIG_FPE_NWFPE=y
-CONFIG_BINFMT_AOUT=m
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 034cb48c9eeb..fe28fc1f759d 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -70,7 +70,7 @@ static void __init init_irq_stacks(void)
 	}
 }
 
-#ifndef CONFIG_PREEMPT_RT
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
 static void ____do_softirq(void *arg)
 {
 	__do_softirq();
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index df6d673e83d5..f4501dea98b0 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -541,10 +541,42 @@ extern u32 at91_pm_suspend_in_sram_sz;
 
 static int at91_suspend_finish(unsigned long val)
 {
+	unsigned char modified_gray_code[] = {
+		0x00, 0x01, 0x02, 0x03, 0x06, 0x07, 0x04, 0x05, 0x0c, 0x0d,
+		0x0e, 0x0f, 0x0a, 0x0b, 0x08, 0x09, 0x18, 0x19, 0x1a, 0x1b,
+		0x1e, 0x1f, 0x1c, 0x1d, 0x14, 0x15, 0x16, 0x17, 0x12, 0x13,
+		0x10, 0x11,
+	};
+	unsigned int tmp, index;
 	int i;
 
 	if (soc_pm.data.mode == AT91_PM_BACKUP && soc_pm.data.ramc_phy) {
 		/*
+		 * Bootloader will perform DDR recalibration and will try to
+		 * restore the ZQ0SR0 with the value saved here. But the
+		 * calibration is buggy and restoring some values from ZQ0SR0
+		 * is forbidden and risky thus we need to provide processed
+		 * values for these (modified gray code values).
+		 */
+		tmp = readl(soc_pm.data.ramc_phy + DDR3PHY_ZQ0SR0);
+
+		/* Store pull-down output impedance select. */
+		index = (tmp >> DDR3PHY_ZQ0SR0_PDO_OFF) & 0x1f;
+		soc_pm.bu->ddr_phy_calibration[0] = modified_gray_code[index];
+
+		/* Store pull-up output impedance select. */
+		index = (tmp >> DDR3PHY_ZQ0SR0_PUO_OFF) & 0x1f;
+		soc_pm.bu->ddr_phy_calibration[0] |= modified_gray_code[index];
+
+		/* Store pull-down on-die termination impedance select. */
+		index = (tmp >> DDR3PHY_ZQ0SR0_PDODT_OFF) & 0x1f;
+		soc_pm.bu->ddr_phy_calibration[0] |= modified_gray_code[index];
+
+		/* Store pull-up on-die termination impedance select. */
+		index = (tmp >> DDR3PHY_ZQ0SRO_PUODT_OFF) & 0x1f;
+		soc_pm.bu->ddr_phy_calibration[0] |= modified_gray_code[index];
+
+		/*
 		 * The 1st 8 words of memory might get corrupted in the process
 		 * of DDR PHY recalibration; it is saved here in securam and it
 		 * will be restored later, after recalibration, by bootloader
@@ -1066,10 +1098,6 @@ static int __init at91_pm_backup_init(void)
 		of_scan_flat_dt(at91_pm_backup_scan_memcs, &located);
 		if (!located)
 			goto securam_fail;
-
-		/* DDR3PHY_ZQ0SR0 */
-		soc_pm.bu->ddr_phy_calibration[0] = readl(soc_pm.data.ramc_phy +
-							  0x188);
 	}
 
 	return 0;
diff --git a/arch/arm/mach-at91/pm_suspend.S b/arch/arm/mach-at91/pm_suspend.S
index abe4ced33eda..ffed4d949042 100644
--- a/arch/arm/mach-at91/pm_suspend.S
+++ b/arch/arm/mach-at91/pm_suspend.S
@@ -172,9 +172,15 @@ sr_ena_2:
 	/* Put DDR PHY's DLL in bypass mode for non-backup modes. */
 	cmp	r7, #AT91_PM_BACKUP
 	beq	sr_ena_3
-	ldr	tmp1, [r3, #DDR3PHY_PIR]
-	orr	tmp1, tmp1, #DDR3PHY_PIR_DLLBYP
-	str	tmp1, [r3, #DDR3PHY_PIR]
+
+	/* Disable DX DLLs. */
+	ldr	tmp1, [r3, #DDR3PHY_DX0DLLCR]
+	orr	tmp1, tmp1, #DDR3PHY_DXDLLCR_DLLDIS
+	str	tmp1, [r3, #DDR3PHY_DX0DLLCR]
+
+	ldr	tmp1, [r3, #DDR3PHY_DX1DLLCR]
+	orr	tmp1, tmp1, #DDR3PHY_DXDLLCR_DLLDIS
+	str	tmp1, [r3, #DDR3PHY_DX1DLLCR]
 
 sr_ena_3:
 	/* Power down DDR PHY data receivers. */
@@ -221,10 +227,14 @@ sr_ena_3:
 	bic	tmp1, tmp1, #DDR3PHY_DSGCR_ODTPDD_ODT0
 	str	tmp1, [r3, #DDR3PHY_DSGCR]
 
-	/* Take DDR PHY's DLL out of bypass mode. */
-	ldr	tmp1, [r3, #DDR3PHY_PIR]
-	bic	tmp1, tmp1, #DDR3PHY_PIR_DLLBYP
-	str	tmp1, [r3, #DDR3PHY_PIR]
+	/* Enable DX DLLs. */
+	ldr	tmp1, [r3, #DDR3PHY_DX0DLLCR]
+	bic	tmp1, tmp1, #DDR3PHY_DXDLLCR_DLLDIS
+	str	tmp1, [r3, #DDR3PHY_DX0DLLCR]
+
+	ldr	tmp1, [r3, #DDR3PHY_DX1DLLCR]
+	bic	tmp1, tmp1, #DDR3PHY_DXDLLCR_DLLDIS
+	str	tmp1, [r3, #DDR3PHY_DX1DLLCR]
 
 	/* Enable quasi-dynamic programming. */
 	mov	tmp1, #0
diff --git a/arch/arm/mach-ixp4xx/ixp4xx-of.c b/arch/arm/mach-ixp4xx/ixp4xx-of.c
index f9904716ec7f..f543e2adae0c 100644
--- a/arch/arm/mach-ixp4xx/ixp4xx-of.c
+++ b/arch/arm/mach-ixp4xx/ixp4xx-of.c
@@ -46,7 +46,7 @@ static void __init ixp4xx_of_map_io(void)
 }
 
 /*
- * We handle 4 differen SoC families. These compatible strings are enough
+ * We handle 4 different SoC families. These compatible strings are enough
  * to provide the core so that different boards can add their more detailed
  * specifics.
  */
diff --git a/arch/arm/mach-sunplus/Kconfig b/arch/arm/mach-sunplus/Kconfig
index 926cde5e3cd9..d0c2416e6f24 100644
--- a/arch/arm/mach-sunplus/Kconfig
+++ b/arch/arm/mach-sunplus/Kconfig
@@ -18,8 +18,8 @@ config SOC_SP7021
 	select ARM_PSCI
 	select PINCTRL
 	select PINCTRL_SPPCTL
-	select SERIAL_SUNPLUS
-	select SERIAL_SUNPLUS_CONSOLE
+	select SERIAL_SUNPLUS if TTY
+	select SERIAL_SUNPLUS_CONSOLE if TTY
 	help
 	  Support for Sunplus SP7021 SoC. It is based on ARM 4-core
 	  Cortex-A7 with various peripherals (e.g.: I2C, SPI, SDIO,
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index fb688003d156..712da6a81b23 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -346,7 +346,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
 		addr = start + i * PMD_SIZE;
 		domain = get_domain_name(pmd);
 		if (pmd_none(*pmd) || pmd_large(*pmd) || !pmd_present(*pmd))
-			note_page(st, addr, 3, pmd_val(*pmd), domain);
+			note_page(st, addr, 4, pmd_val(*pmd), domain);
 		else
 			walk_pte(st, pmd, addr, domain);
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index a49f0b9c0f75..463fc2a8448f 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -300,7 +300,11 @@ static struct mem_type mem_types[] __ro_after_init = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 			     L_PTE_XN | L_PTE_RDONLY,
 		.prot_l1   = PMD_TYPE_TABLE,
+#ifdef CONFIG_ARM_LPAE
+		.prot_sect = PMD_TYPE_SECT | L_PMD_SECT_RDONLY | PMD_SECT_AP2,
+#else
 		.prot_sect = PMD_TYPE_SECT,
+#endif
 		.domain    = DOMAIN_KERNEL,
 	},
 	[MT_ROM] = {
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 571cc234d0b3..1ce7685ad5de 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -917,6 +917,23 @@ config ARM64_ERRATUM_1902691
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_2457168
+	bool "Cortex-A510: 2457168: workaround for AMEVCNTR01 incrementing incorrectly"
+	depends on ARM64_AMU_EXTN
+	default y
+	help
+	  This option adds the workaround for ARM Cortex-A510 erratum 2457168.
+
+	  The AMU counter AMEVCNTR01 (constant counter) should increment at the same rate
+	  as the system counter. On affected Cortex-A510 cores AMEVCNTR01 increments
+	  incorrectly giving a significantly higher output value.
+
+	  Work around this problem by returning 0 when reading the affected counter in
+	  key locations that results in disabling all users of this counter. This effect
+	  is the same to firmware disabling affected counters.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
@@ -1870,6 +1887,8 @@ config ARM64_BTI_KERNEL
 	depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI
 	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697
 	depends on !CC_IS_GCC || GCC_VERSION >= 100100
+	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106671
+	depends on !CC_IS_GCC
 	# https://github.com/llvm/llvm-project/commit/a88c722e687e6780dcd6a58718350dc76fcc4cc9
 	depends on !CC_IS_CLANG || CLANG_VERSION >= 120000
 	depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi
index 8d0d45d168d1..2f27619d8abd 100644
--- a/arch/arm64/boot/dts/arm/juno-base.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-base.dtsi
@@ -26,7 +26,8 @@
 		compatible = "arm,mhu", "arm,primecell";
 		reg = <0x0 0x2b1f0000 0x0 0x1000>;
 		interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
+			     <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
 		#mbox-cells = <1>;
 		clocks = <&soc_refclk100mhz>;
 		clock-names = "apb_pclk";
diff --git a/arch/arm64/boot/dts/arm/juno-cs-r1r2.dtsi b/arch/arm64/boot/dts/arm/juno-cs-r1r2.dtsi
index ba88d1596f6f..09d2b692e9e1 100644
--- a/arch/arm64/boot/dts/arm/juno-cs-r1r2.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-cs-r1r2.dtsi
@@ -67,7 +67,6 @@
 			port@0 {
 				reg = <0>;
 				csys2_funnel_in_port0: endpoint {
-					slave-mode;
 					remote-endpoint = <&etf0_out_port>;
 				};
 			};
@@ -75,7 +74,6 @@
 			port@1 {
 				reg = <1>;
 				csys2_funnel_in_port1: endpoint {
-					slave-mode;
 					remote-endpoint = <&etf1_out_port>;
 				};
 			};
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds-65bb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds-65bb.dts
index 40d34c8384a5..b949cac03742 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds-65bb.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds-65bb.dts
@@ -25,7 +25,6 @@
 &enetc_port0 {
 	phy-handle = <&slot1_sgmii>;
 	phy-mode = "2500base-x";
-	managed = "in-band-status";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts b/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts
index c97f4e06ae5f..32f6f2f50c10 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts
@@ -152,11 +152,11 @@
 	 * CPLD_reset is RESET_SOFT in schematic
 	 */
 	gpio-line-names =
-		"CPLD_D[1]", "CPLD_int", "CPLD_reset", "",
-		"", "CPLD_D[0]", "", "",
-		"", "", "", "CPLD_D[2]",
-		"CPLD_D[3]", "CPLD_D[4]", "CPLD_D[5]", "CPLD_D[6]",
-		"CPLD_D[7]", "", "", "",
+		"CPLD_D[6]", "CPLD_int", "CPLD_reset", "",
+		"", "CPLD_D[7]", "", "",
+		"", "", "", "CPLD_D[5]",
+		"CPLD_D[4]", "CPLD_D[3]", "CPLD_D[2]", "CPLD_D[1]",
+		"CPLD_D[0]", "", "", "",
 		"", "", "", "",
 		"", "", "", "KBD_intK",
 		"", "", "", "";
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts
index 286d2df01cfa..7e0aeb2db305 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts
@@ -5,7 +5,6 @@
 
 /dts-v1/;
 
-#include <dt-bindings/phy/phy-imx8-pcie.h>
 #include "imx8mm-tqma8mqml.dtsi"
 #include "mba8mx.dtsi"
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi
index 16ee9b5179e6..f649dfacb4b6 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi
@@ -3,6 +3,7 @@
  * Copyright 2020-2021 TQ-Systems GmbH
  */
 
+#include <dt-bindings/phy/phy-imx8-pcie.h>
 #include "imx8mm.dtsi"
 
 / {
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts
index 35fb929e7bcc..d3ee6fc4baab 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts
@@ -626,24 +626,28 @@
 			lan1: port@0 {
 				reg = <0>;
 				label = "lan1";
+				phy-mode = "internal";
 				local-mac-address = [00 00 00 00 00 00];
 			};
 
 			lan2: port@1 {
 				reg = <1>;
 				label = "lan2";
+				phy-mode = "internal";
 				local-mac-address = [00 00 00 00 00 00];
 			};
 
 			lan3: port@2 {
 				reg = <2>;
 				label = "lan3";
+				phy-mode = "internal";
 				local-mac-address = [00 00 00 00 00 00];
 			};
 
 			lan4: port@3 {
 				reg = <3>;
 				label = "lan4";
+				phy-mode = "internal";
 				local-mac-address = [00 00 00 00 00 00];
 			};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi
index d1b4582f44c4..3ec0c9ac3170 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi
@@ -32,10 +32,10 @@
 	};
 
 	/* Fixed clock dedicated to SPI CAN controller */
-	clk20m: oscillator {
+	clk40m: oscillator {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
-		clock-frequency = <20000000>;
+		clock-frequency = <40000000>;
 	};
 
 	gpio-keys {
@@ -202,8 +202,8 @@
 
 	can1: can@0 {
 		compatible = "microchip,mcp251xfd";
-		clocks = <&clk20m>;
-		interrupts-extended = <&gpio1 6 IRQ_TYPE_EDGE_FALLING>;
+		clocks = <&clk40m>;
+		interrupts-extended = <&gpio1 6 IRQ_TYPE_LEVEL_LOW>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_can1_int>;
 		reg = <0>;
@@ -367,8 +367,8 @@
 				nxp,dvs-standby-voltage = <850000>;
 				regulator-always-on;
 				regulator-boot-on;
-				regulator-max-microvolt = <950000>;
-				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <1050000>;
+				regulator-min-microvolt = <805000>;
 				regulator-name = "On-module +VDD_ARM (BUCK2)";
 				regulator-ramp-delay = <3125>;
 			};
@@ -376,8 +376,8 @@
 			reg_vdd_dram: BUCK3 {
 				regulator-always-on;
 				regulator-boot-on;
-				regulator-max-microvolt = <950000>;
-				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <1000000>;
+				regulator-min-microvolt = <805000>;
 				regulator-name = "On-module +VDD_GPU_VPU_DDR (BUCK3)";
 			};
 
@@ -416,7 +416,7 @@
 			reg_vdd_snvs: LDO2 {
 				regulator-always-on;
 				regulator-boot-on;
-				regulator-max-microvolt = <900000>;
+				regulator-max-microvolt = <800000>;
 				regulator-min-microvolt = <800000>;
 				regulator-name = "On-module +V0.8_SNVS (LDO2)";
 			};
@@ -603,7 +603,7 @@
 		pinctrl-0 = <&pinctrl_gpio_9_dsi>, <&pinctrl_i2s_2_bclk_touch_reset>;
 		reg = <0x4a>;
 		/* Verdin I2S_2_BCLK (TOUCH_RESET#, SODIMM 42) */
-		reset-gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpio3 23 GPIO_ACTIVE_LOW>;
 		status = "disabled";
 	};
 
@@ -745,6 +745,7 @@
 };
 
 &usbphynop2 {
+	power-domains = <&pgc_otg2>;
 	vcc-supply = <&reg_vdd_3v3>;
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
index 0c71b740a316..cb2836bfbd95 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
@@ -672,7 +672,6 @@
 							 <&clk IMX8MN_CLK_GPU_SHADER>,
 							 <&clk IMX8MN_CLK_GPU_BUS_ROOT>,
 							 <&clk IMX8MN_CLK_GPU_AHB>;
-						resets = <&src IMX8MQ_RESET_GPU_RESET>;
 					};
 
 					pgc_dispmix: power-domain@3 {
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi
index a616eb378002..0f13ee362771 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi
@@ -70,7 +70,7 @@
 &ecspi1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_ecspi1>;
-	cs-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>;
+	cs-gpios = <&gpio5 17 GPIO_ACTIVE_LOW>;
 	status = "disabled";
 };
 
@@ -403,8 +403,8 @@
 	pinctrl-names = "default", "gpio";
 	pinctrl-0 = <&pinctrl_i2c5>;
 	pinctrl-1 = <&pinctrl_i2c5_gpio>;
-	scl-gpios = <&gpio5 26 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
-	sda-gpios = <&gpio5 27 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	scl-gpios = <&gpio3 26 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	sda-gpios = <&gpio3 27 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
 	status = "okay";
 };
 
@@ -648,10 +648,10 @@
 
 	pinctrl_ecspi1: dhcom-ecspi1-grp {
 		fsl,pins = <
-			MX8MP_IOMUXC_ECSPI1_SCLK__ECSPI1_SCLK		0x44
-			MX8MP_IOMUXC_ECSPI1_MOSI__ECSPI1_MOSI		0x44
-			MX8MP_IOMUXC_ECSPI1_MISO__ECSPI1_MISO		0x44
-			MX8MP_IOMUXC_ECSPI1_SS0__GPIO5_IO09		0x40
+			MX8MP_IOMUXC_I2C1_SCL__ECSPI1_SCLK		0x44
+			MX8MP_IOMUXC_I2C1_SDA__ECSPI1_MOSI		0x44
+			MX8MP_IOMUXC_I2C2_SCL__ECSPI1_MISO		0x44
+			MX8MP_IOMUXC_I2C2_SDA__GPIO5_IO17		0x40
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
index d8ca52976170..0e237b2f9541 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
@@ -57,13 +57,13 @@
 		switch-1 {
 			label = "S12";
 			linux,code = <BTN_0>;
-			gpios = <&gpio5 26 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio5 27 GPIO_ACTIVE_LOW>;
 		};
 
 		switch-2 {
 			label = "S13";
 			linux,code = <BTN_1>;
-			gpios = <&gpio5 27 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio5 26 GPIO_ACTIVE_LOW>;
 		};
 	};
 
@@ -394,6 +394,8 @@
 
 &pcf85063 {
 	/* RTC_EVENT# is connected on MBa8MPxL */
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pcf85063>;
 	interrupt-parent = <&gpio4>;
 	interrupts = <28 IRQ_TYPE_EDGE_FALLING>;
 };
@@ -630,6 +632,10 @@
 		fsl,pins = <MX8MP_IOMUXC_SAI5_RXC__GPIO3_IO20		0x10>; /* Power enable */
 	};
 
+	pinctrl_pcf85063: pcf85063grp {
+		fsl,pins = <MX8MP_IOMUXC_SAI3_RXFS__GPIO4_IO28		0x80>;
+	};
+
 	/* LVDS Backlight */
 	pinctrl_pwm2: pwm2grp {
 		fsl,pins = <MX8MP_IOMUXC_SAI5_RXD0__PWM2_OUT		0x14>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts
index 521215520a0f..211e6a1b296e 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts
@@ -123,8 +123,7 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_reg_can>;
 		regulator-name = "can2_stby";
-		gpio = <&gpio3 19 GPIO_ACTIVE_HIGH>;
-		enable-active-high;
+		gpio = <&gpio3 19 GPIO_ACTIVE_LOW>;
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
@@ -484,35 +483,40 @@
 			lan1: port@0 {
 				reg = <0>;
 				label = "lan1";
+				phy-mode = "internal";
 				local-mac-address = [00 00 00 00 00 00];
 			};
 
 			lan2: port@1 {
 				reg = <1>;
 				label = "lan2";
+				phy-mode = "internal";
 				local-mac-address = [00 00 00 00 00 00];
 			};
 
 			lan3: port@2 {
 				reg = <2>;
 				label = "lan3";
+				phy-mode = "internal";
 				local-mac-address = [00 00 00 00 00 00];
 			};
 
 			lan4: port@3 {
 				reg = <3>;
 				label = "lan4";
+				phy-mode = "internal";
 				local-mac-address = [00 00 00 00 00 00];
 			};
 
 			lan5: port@4 {
 				reg = <4>;
 				label = "lan5";
+				phy-mode = "internal";
 				local-mac-address = [00 00 00 00 00 00];
 			};
 
-			port@6 {
-				reg = <6>;
+			port@5 {
+				reg = <5>;
 				label = "cpu";
 				ethernet = <&fec>;
 				phy-mode = "rgmii-id";
@@ -770,10 +774,10 @@
 
 	pinctrl_sai2: sai2grp {
 		fsl,pins = <
-			MX8MP_IOMUXC_SAI2_TXFS__AUDIOMIX_SAI2_TX_SYNC
-			MX8MP_IOMUXC_SAI2_TXD0__AUDIOMIX_SAI2_TX_DATA00
-			MX8MP_IOMUXC_SAI2_TXC__AUDIOMIX_SAI2_TX_BCLK
-			MX8MP_IOMUXC_SAI2_MCLK__AUDIOMIX_SAI2_MCLK
+			MX8MP_IOMUXC_SAI2_TXFS__AUDIOMIX_SAI2_TX_SYNC	0xd6
+			MX8MP_IOMUXC_SAI2_TXD0__AUDIOMIX_SAI2_TX_DATA00	0xd6
+			MX8MP_IOMUXC_SAI2_TXC__AUDIOMIX_SAI2_TX_BCLK	0xd6
+			MX8MP_IOMUXC_SAI2_MCLK__AUDIOMIX_SAI2_MCLK	0xd6
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi
index c5987bdbb383..1c74c6a19449 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi
@@ -628,7 +628,7 @@
 		interrupts = <5 IRQ_TYPE_EDGE_FALLING>;
 		reg = <0x4a>;
 		/* Verdin GPIO_2 (SODIMM 208) */
-		reset-gpios = <&gpio1 1 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
 		status = "disabled";
 	};
 };
@@ -705,7 +705,7 @@
 		pinctrl-0 = <&pinctrl_gpio_9_dsi>, <&pinctrl_i2s_2_bclk_touch_reset>;
 		reg = <0x4a>;
 		/* Verdin I2S_2_BCLK (TOUCH_RESET#, SODIMM 42) */
-		reset-gpios = <&gpio5 0 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>;
 		status = "disabled";
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi
index 899e8e7dbc24..802ad6e5cef6 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi
@@ -204,7 +204,6 @@
 		reg = <0x51>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_rtc>;
-		interrupt-names = "irq";
 		interrupt-parent = <&gpio1>;
 		interrupts = <1 IRQ_TYPE_EDGE_FALLING>;
 		quartz-load-femtofarads = <7000>;
diff --git a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi
index 60c1b018bf03..bb56390b8f54 100644
--- a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi
@@ -172,6 +172,7 @@
 				compatible = "fsl,imx8ulp-pcc3";
 				reg = <0x292d0000 0x10000>;
 				#clock-cells = <1>;
+				#reset-cells = <1>;
 			};
 
 			tpm5: tpm@29340000 {
@@ -270,6 +271,7 @@
 				compatible = "fsl,imx8ulp-pcc4";
 				reg = <0x29800000 0x10000>;
 				#clock-cells = <1>;
+				#reset-cells = <1>;
 			};
 
 			lpi2c6: i2c@29840000 {
@@ -414,6 +416,7 @@
 				compatible = "fsl,imx8ulp-pcc5";
 				reg = <0x2da70000 0x10000>;
 				#clock-cells = <1>;
+				#reset-cells = <1>;
 			};
 		};
 
diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi
index 13d7f267b289..dac3b69e314f 100644
--- a/arch/arm64/boot/dts/qcom/sc7280.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi
@@ -3374,6 +3374,8 @@
 					<&gem_noc MASTER_APPSS_PROC 0 &cnoc2 SLAVE_USB3_0 0>;
 			interconnect-names = "usb-ddr", "apps-usb";
 
+			wakeup-source;
+
 			usb_1_dwc3: usb@a600000 {
 				compatible = "snps,dwc3";
 				reg = <0 0x0a600000 0 0xe000>;
@@ -3384,7 +3386,6 @@
 				phys = <&usb_1_hsphy>, <&usb_1_ssphy>;
 				phy-names = "usb2-phy", "usb3-phy";
 				maximum-speed = "super-speed";
-				wakeup-source;
 			};
 		};
 
diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts
index 84dc92dda0b8..4c404e2eafba 100644
--- a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts
+++ b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts
@@ -235,13 +235,13 @@
 };
 
 &remoteproc_adsp {
-	firmware-name = "qcom/sc8280xp/qcadsp8280.mbn";
+	firmware-name = "qcom/sc8280xp/LENOVO/21BX/qcadsp8280.mbn";
 
 	status = "okay";
 };
 
 &remoteproc_nsp0 {
-	firmware-name = "qcom/sc8280xp/qccdsp8280.mbn";
+	firmware-name = "qcom/sc8280xp/LENOVO/21BX/qccdsp8280.mbn";
 
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi
index 7d509ecd44da..916f12b799b7 100644
--- a/arch/arm64/boot/dts/qcom/sm8150.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi
@@ -3394,57 +3394,49 @@
 					compute-cb@1 {
 						compatible = "qcom,fastrpc-compute-cb";
 						reg = <1>;
-						iommus = <&apps_smmu 0x1401 0x2040>,
-							 <&apps_smmu 0x1421 0x0>,
-							 <&apps_smmu 0x2001 0x420>,
-							 <&apps_smmu 0x2041 0x0>;
+						iommus = <&apps_smmu 0x1001 0x0460>;
 					};
 
 					compute-cb@2 {
 						compatible = "qcom,fastrpc-compute-cb";
 						reg = <2>;
-						iommus = <&apps_smmu 0x2 0x3440>,
-							 <&apps_smmu 0x22 0x3400>;
+						iommus = <&apps_smmu 0x1002 0x0460>;
 					};
 
 					compute-cb@3 {
 						compatible = "qcom,fastrpc-compute-cb";
 						reg = <3>;
-						iommus = <&apps_smmu 0x3 0x3440>,
-							 <&apps_smmu 0x1423 0x0>,
-							 <&apps_smmu 0x2023 0x0>;
+						iommus = <&apps_smmu 0x1003 0x0460>;
 					};
 
 					compute-cb@4 {
 						compatible = "qcom,fastrpc-compute-cb";
 						reg = <4>;
-						iommus = <&apps_smmu 0x4 0x3440>,
-							 <&apps_smmu 0x24 0x3400>;
+						iommus = <&apps_smmu 0x1004 0x0460>;
 					};
 
 					compute-cb@5 {
 						compatible = "qcom,fastrpc-compute-cb";
 						reg = <5>;
-						iommus = <&apps_smmu 0x5 0x3440>,
-							 <&apps_smmu 0x25 0x3400>;
+						iommus = <&apps_smmu 0x1005 0x0460>;
 					};
 
 					compute-cb@6 {
 						compatible = "qcom,fastrpc-compute-cb";
 						reg = <6>;
-						iommus = <&apps_smmu 0x6 0x3460>;
+						iommus = <&apps_smmu 0x1006 0x0460>;
 					};
 
 					compute-cb@7 {
 						compatible = "qcom,fastrpc-compute-cb";
 						reg = <7>;
-						iommus = <&apps_smmu 0x7 0x3460>;
+						iommus = <&apps_smmu 0x1007 0x0460>;
 					};
 
 					compute-cb@8 {
 						compatible = "qcom,fastrpc-compute-cb";
 						reg = <8>;
-						iommus = <&apps_smmu 0x8 0x3460>;
+						iommus = <&apps_smmu 0x1008 0x0460>;
 					};
 
 					/* note: secure cb9 in downstream */
diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi
index e72a04411888..d9b08dfc2980 100644
--- a/arch/arm64/boot/dts/qcom/sm8350.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi
@@ -2128,7 +2128,7 @@
 
 		ufs_mem_phy: phy@1d87000 {
 			compatible = "qcom,sm8350-qmp-ufs-phy";
-			reg = <0 0x01d87000 0 0xe10>;
+			reg = <0 0x01d87000 0 0x1c4>;
 			#address-cells = <2>;
 			#size-cells = <2>;
 			ranges;
diff --git a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi
index 7cbb0de060dd..1c15726cff8b 100644
--- a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi
@@ -85,7 +85,7 @@
 				     "renesas,rcar-gen4-hscif",
 				     "renesas,hscif";
 			reg = <0 0xe6540000 0 96>;
-			interrupts = <GIC_SPI 245 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 246 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 514>,
 				 <&cpg CPG_CORE R8A779G0_CLK_S0D3_PER>,
 				 <&scif_clk>;
diff --git a/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core.dtsi b/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core.dtsi
index 7249871530ab..5eecbefa8a33 100644
--- a/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core.dtsi
@@ -2,8 +2,8 @@
 /*
  * Copyright (c) 2020 Fuzhou Rockchip Electronics Co., Ltd
  * Copyright (c) 2020 Engicam srl
- * Copyright (c) 2020 Amarula Solutons
- * Copyright (c) 2020 Amarula Solutons(India)
+ * Copyright (c) 2020 Amarula Solutions
+ * Copyright (c) 2020 Amarula Solutions(India)
  */
 
 #include <dt-bindings/gpio/gpio.h>
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts
index 31ebb4e5fd33..0f9cc042d9bf 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts
@@ -88,3 +88,8 @@
 		};
 	};
 };
+
+&wlan_host_wake_l {
+	/* Kevin has an external pull up, but Bob does not. */
+	rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_up>;
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
index cd074641884b..ee6095baba4d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
@@ -244,6 +244,14 @@
 &edp {
 	status = "okay";
 
+	/*
+	 * eDP PHY/clk don't sync reliably at anything other than 24 MHz. Only
+	 * set this here, because rk3399-gru.dtsi ensures we can generate this
+	 * off GPLL=600MHz, whereas some other RK3399 boards may not.
+	 */
+	assigned-clocks = <&cru PCLK_EDP>;
+	assigned-clock-rates = <24000000>;
+
 	ports {
 		edp_out: port@1 {
 			reg = <1>;
@@ -578,6 +586,7 @@ ap_i2c_tp: &i2c5 {
 	};
 
 	wlan_host_wake_l: wlan-host-wake-l {
+		/* Kevin has an external pull up, but Bob does not */
 		rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>;
 	};
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
index b1ac3a89f259..aa3e21bd6c8f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
@@ -62,7 +62,6 @@
 	vcc5v0_host: vcc5v0-host-regulator {
 		compatible = "regulator-fixed";
 		gpio = <&gpio4 RK_PA3 GPIO_ACTIVE_LOW>;
-		enable-active-low;
 		pinctrl-names = "default";
 		pinctrl-0 = <&vcc5v0_host_en>;
 		regulator-name = "vcc5v0_host";
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts
index d943559b157c..a05460b92415 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts
@@ -189,7 +189,6 @@
 
 	vcc3v3_sd: vcc3v3_sd {
 		compatible = "regulator-fixed";
-		enable-active-low;
 		gpio = <&gpio0 RK_PA5 GPIO_ACTIVE_LOW>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&vcc_sd_h>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts
index 02d5f5a8ca03..528bb4e8ac77 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts
@@ -506,7 +506,7 @@
 	disable-wp;
 	pinctrl-names = "default";
 	pinctrl-0 = <&sdmmc0_bus4 &sdmmc0_clk &sdmmc0_cmd &sdmmc0_det>;
-	sd-uhs-sdr104;
+	sd-uhs-sdr50;
 	vmmc-supply = <&vcc3v3_sd>;
 	vqmmc-supply = <&vccio_sd>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts
index 5e34bd0b214d..93d383b8be87 100644
--- a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts
@@ -678,7 +678,7 @@
 };
 
 &usb_host0_xhci {
-	extcon = <&usb2phy0>;
+	dr_mode = "host";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts b/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts
index 6ff89ff95ad1..674792567fa6 100644
--- a/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts
@@ -656,7 +656,7 @@
 };
 
 &usb2phy0_otg {
-	vbus-supply = <&vcc5v0_usb_otg>;
+	phy-supply = <&vcc5v0_usb_otg>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts b/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts
index 6b5093a1a6cf..b2e040dffb59 100644
--- a/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts
@@ -581,7 +581,7 @@
 };
 
 &usb2phy0_otg {
-	vbus-supply = <&vcc5v0_usb_otg>;
+	phy-supply = <&vcc5v0_usb_otg>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index d5b2d2dd4904..5b167649097e 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -48,6 +48,7 @@ CONFIG_ARCH_KEEMBAY=y
 CONFIG_ARCH_MEDIATEK=y
 CONFIG_ARCH_MESON=y
 CONFIG_ARCH_MVEBU=y
+CONFIG_ARCH_NXP=y
 CONFIG_ARCH_MXC=y
 CONFIG_ARCH_NPCM=y
 CONFIG_ARCH_QCOM=y
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index 7868330dd54e..ebe5558929b7 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -6,6 +6,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/assembler.h>
 
 	SHASH		.req	v0
@@ -350,11 +351,11 @@ CPU_LE(	rev64		T1.16b, T1.16b	)
 	 * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
 	 *			   struct ghash_key const *k, const char *head)
 	 */
-SYM_FUNC_START(pmull_ghash_update_p64)
+SYM_TYPED_FUNC_START(pmull_ghash_update_p64)
 	__pmull_ghash	p64
 SYM_FUNC_END(pmull_ghash_update_p64)
 
-SYM_FUNC_START(pmull_ghash_update_p8)
+SYM_TYPED_FUNC_START(pmull_ghash_update_p8)
 	__pmull_ghash	p8
 SYM_FUNC_END(pmull_ghash_update_p8)
 
diff --git a/arch/arm64/crypto/sm3-ce-core.S b/arch/arm64/crypto/sm3-ce-core.S
index ef97d3187cb7..ca70cfacd0d0 100644
--- a/arch/arm64/crypto/sm3-ce-core.S
+++ b/arch/arm64/crypto/sm3-ce-core.S
@@ -6,6 +6,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/assembler.h>
 
 	.irp		b, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12
@@ -73,7 +74,7 @@
 	 *                       int blocks)
 	 */
 	.text
-SYM_FUNC_START(sm3_ce_transform)
+SYM_TYPED_FUNC_START(sm3_ce_transform)
 	/* load state */
 	ld1		{v8.4s-v9.4s}, [x0]
 	rev64		v8.4s, v8.4s
diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h
index ec7720dbe2c8..6e000113e508 100644
--- a/arch/arm64/include/asm/brk-imm.h
+++ b/arch/arm64/include/asm/brk-imm.h
@@ -17,6 +17,7 @@
  * 0x401: for compile time BRK instruction
  * 0x800: kernel-mode BUG() and WARN() traps
  * 0x9xx: tag-based KASAN trap (allowed values 0x900 - 0x9ff)
+ * 0x8xxx: Control-Flow Integrity traps
  */
 #define KPROBES_BRK_IMM			0x004
 #define UPROBES_BRK_IMM			0x005
@@ -28,4 +29,9 @@
 #define KASAN_BRK_IMM			0x900
 #define KASAN_BRK_MASK			0x0ff
 
+#define CFI_BRK_IMM_TARGET		GENMASK(4, 0)
+#define CFI_BRK_IMM_TYPE		GENMASK(9, 5)
+#define CFI_BRK_IMM_BASE		0x8000
+#define CFI_BRK_IMM_MASK		(CFI_BRK_IMM_TARGET | CFI_BRK_IMM_TYPE)
+
 #endif
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index ca9b487112cc..34256bda0da9 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -71,7 +71,7 @@ static __always_inline int icache_is_vpipt(void)
 
 static inline u32 cache_type_cwg(void)
 {
-	return (read_cpuid_cachetype() >> CTR_EL0_CWG_SHIFT) & CTR_EL0_CWG_MASK;
+	return SYS_FIELD_GET(CTR_EL0, CWG, read_cpuid_cachetype());
 }
 
 #define __read_mostly __section(".data..read_mostly")
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 9bb1873f5295..6f86b7ab6c28 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -153,7 +153,7 @@ struct vl_info {
 
 #ifdef CONFIG_ARM64_SVE
 
-extern void sve_alloc(struct task_struct *task);
+extern void sve_alloc(struct task_struct *task, bool flush);
 extern void fpsimd_release_task(struct task_struct *task);
 extern void fpsimd_sync_to_sve(struct task_struct *task);
 extern void fpsimd_force_sync_to_sve(struct task_struct *task);
@@ -256,7 +256,7 @@ size_t sve_state_size(struct task_struct const *task);
 
 #else /* ! CONFIG_ARM64_SVE */
 
-static inline void sve_alloc(struct task_struct *task) { }
+static inline void sve_alloc(struct task_struct *task, bool flush) { }
 static inline void fpsimd_release_task(struct task_struct *task) { }
 static inline void sve_sync_to_fpsimd(struct task_struct *task) { }
 static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { }
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
index dbc45a4157fa..329dbbd4d50b 100644
--- a/arch/arm64/include/asm/ftrace.h
+++ b/arch/arm64/include/asm/ftrace.h
@@ -26,7 +26,7 @@
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #else
-#define MCOUNT_ADDR		((unsigned long)function_nocfi(_mcount))
+#define MCOUNT_ADDR		((unsigned long)_mcount)
 #endif
 
 /* The BL at the callsite's adjusted rec->ip */
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 02e59fa8f293..32d14f481f0c 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -64,28 +64,28 @@
 #define EARLY_KASLR	(0)
 #endif
 
-#define EARLY_ENTRIES(vstart, vend, shift) \
-	((((vend) - 1) >> (shift)) - ((vstart) >> (shift)) + 1 + EARLY_KASLR)
+#define EARLY_ENTRIES(vstart, vend, shift, add) \
+	((((vend) - 1) >> (shift)) - ((vstart) >> (shift)) + 1 + add)
 
-#define EARLY_PGDS(vstart, vend) (EARLY_ENTRIES(vstart, vend, PGDIR_SHIFT))
+#define EARLY_PGDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, PGDIR_SHIFT, add))
 
 #if SWAPPER_PGTABLE_LEVELS > 3
-#define EARLY_PUDS(vstart, vend) (EARLY_ENTRIES(vstart, vend, PUD_SHIFT))
+#define EARLY_PUDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, PUD_SHIFT, add))
 #else
-#define EARLY_PUDS(vstart, vend) (0)
+#define EARLY_PUDS(vstart, vend, add) (0)
 #endif
 
 #if SWAPPER_PGTABLE_LEVELS > 2
-#define EARLY_PMDS(vstart, vend) (EARLY_ENTRIES(vstart, vend, SWAPPER_TABLE_SHIFT))
+#define EARLY_PMDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, SWAPPER_TABLE_SHIFT, add))
 #else
-#define EARLY_PMDS(vstart, vend) (0)
+#define EARLY_PMDS(vstart, vend, add) (0)
 #endif
 
-#define EARLY_PAGES(vstart, vend) ( 1 			/* PGDIR page */				\
-			+ EARLY_PGDS((vstart), (vend)) 	/* each PGDIR needs a next level page table */	\
-			+ EARLY_PUDS((vstart), (vend))	/* each PUD needs a next level page table */	\
-			+ EARLY_PMDS((vstart), (vend)))	/* each PMD needs a next level page table */
-#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR, _end))
+#define EARLY_PAGES(vstart, vend, add) ( 1 			/* PGDIR page */				\
+			+ EARLY_PGDS((vstart), (vend), add) 	/* each PGDIR needs a next level page table */	\
+			+ EARLY_PUDS((vstart), (vend), add)	/* each PUD needs a next level page table */	\
+			+ EARLY_PMDS((vstart), (vend), add))	/* each PMD needs a next level page table */
+#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR, _end, EARLY_KASLR))
 
 /* the initial ID map may need two extra pages if it needs to be extended */
 #if VA_BITS < 48
@@ -93,7 +93,7 @@
 #else
 #define INIT_IDMAP_DIR_SIZE	(INIT_IDMAP_DIR_PAGES * PAGE_SIZE)
 #endif
-#define INIT_IDMAP_DIR_PAGES	EARLY_PAGES(KIMAGE_VADDR, _end + MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE)
+#define INIT_IDMAP_DIR_PAGES	EARLY_PAGES(KIMAGE_VADDR, _end + MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE, 1)
 
 /* Initial memory map size */
 #if ARM64_KERNEL_USES_PMD_MAPS
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f38ef299f13b..e9c9388ccc02 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -929,6 +929,10 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
 	(system_supports_mte() &&				\
 	 test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &(kvm)->arch.flags))
 
+#define kvm_supports_32bit_el0()				\
+	(system_supports_32bit_el0() &&				\
+	 !static_branch_unlikely(&arm64_mismatched_32bit_el0))
+
 int kvm_trng_call(struct kvm_vcpu *vcpu);
 #ifdef CONFIG_KVM
 extern phys_addr_t hyp_mem_base;
diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h
index 43f8c25b3fda..1436fa1cde24 100644
--- a/arch/arm64/include/asm/linkage.h
+++ b/arch/arm64/include/asm/linkage.h
@@ -39,4 +39,8 @@
 	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)		\
 	bti c ;
 
+#define SYM_TYPED_FUNC_START(name)				\
+	SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)	\
+	bti c ;
+
 #endif
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index c7ccd82db1d2..d3f8b5df0c1f 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -147,7 +147,7 @@ static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz)
  * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD,
  * avoiding the possibility of conflicting TLB entries being allocated.
  */
-static inline void __nocfi cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
+static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
 {
 	typedef void (ttbr_replace_func)(phys_addr_t);
 	extern ttbr_replace_func idmap_cpu_replace_ttbr1;
@@ -168,7 +168,7 @@ static inline void __nocfi cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
 		ttbr1 |= TTBR_CNP_BIT;
 	}
 
-	replace_phys = (void *)__pa_symbol(function_nocfi(idmap_cpu_replace_ttbr1));
+	replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
 
 	__cpu_install_idmap(idmap);
 	replace_phys(ttbr1);
diff --git a/arch/arm64/include/asm/setup.h b/arch/arm64/include/asm/setup.h
index 6437df661700..f4af547ef54c 100644
--- a/arch/arm64/include/asm/setup.h
+++ b/arch/arm64/include/asm/setup.h
@@ -3,6 +3,8 @@
 #ifndef __ARM64_ASM_SETUP_H
 #define __ARM64_ASM_SETUP_H
 
+#include <linux/string.h>
+
 #include <uapi/asm/setup.h>
 
 void *get_early_fdt_ptr(void);
@@ -14,4 +16,19 @@ void early_fdt_map(u64 dt_phys);
 extern phys_addr_t __fdt_pointer __initdata;
 extern u64 __cacheline_aligned boot_args[4];
 
+static inline bool arch_parse_debug_rodata(char *arg)
+{
+	extern bool rodata_enabled;
+	extern bool rodata_full;
+
+	if (arg && !strcmp(arg, "full")) {
+		rodata_enabled = true;
+		rodata_full = true;
+		return true;
+	}
+
+	return false;
+}
+#define arch_parse_debug_rodata arch_parse_debug_rodata
+
 #endif
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 7c71358d44c4..818df938a7ad 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -1116,6 +1116,7 @@
 
 #else
 
+#include <linux/bitfield.h>
 #include <linux/build_bug.h>
 #include <linux/types.h>
 #include <asm/alternative.h>
@@ -1209,8 +1210,6 @@
 	par;								\
 })
 
-#endif
-
 #define SYS_FIELD_GET(reg, field, val)		\
 		 FIELD_GET(reg##_##field##_MASK, val)
 
@@ -1220,4 +1219,6 @@
 #define SYS_FIELD_PREP_ENUM(reg, field, val)		\
 		 FIELD_PREP(reg##_##field##_MASK, reg##_##field##_##val)
 
+#endif
+
 #endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 3bb134355874..316917b98707 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -75,9 +75,11 @@ struct kvm_regs {
 
 /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
 #define KVM_ARM_DEVICE_TYPE_SHIFT	0
-#define KVM_ARM_DEVICE_TYPE_MASK	(0xffff << KVM_ARM_DEVICE_TYPE_SHIFT)
+#define KVM_ARM_DEVICE_TYPE_MASK	GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \
+						KVM_ARM_DEVICE_TYPE_SHIFT)
 #define KVM_ARM_DEVICE_ID_SHIFT		16
-#define KVM_ARM_DEVICE_ID_MASK		(0xffff << KVM_ARM_DEVICE_ID_SHIFT)
+#define KVM_ARM_DEVICE_ID_MASK		GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \
+						KVM_ARM_DEVICE_ID_SHIFT)
 
 /* Supported device IDs */
 #define KVM_ARM_DEVICE_VGIC_V2		0
diff --git a/arch/arm64/kernel/acpi_parking_protocol.c b/arch/arm64/kernel/acpi_parking_protocol.c
index bfeeb5319abf..b1990e38aed0 100644
--- a/arch/arm64/kernel/acpi_parking_protocol.c
+++ b/arch/arm64/kernel/acpi_parking_protocol.c
@@ -99,7 +99,7 @@ static int acpi_parking_protocol_cpu_boot(unsigned int cpu)
 	 * that read this address need to convert this address to the
 	 * Boot-Loader's endianness before jumping.
 	 */
-	writeq_relaxed(__pa_symbol(function_nocfi(secondary_entry)),
+	writeq_relaxed(__pa_symbol(secondary_entry),
 		       &mailbox->entry_point);
 	writel_relaxed(cpu_entry->gic_cpu_id, &mailbox->cpu_id);
 
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 9bcaa5eacf16..d2c66507398d 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -133,7 +133,7 @@ static void clean_dcache_range_nopatch(u64 start, u64 end)
 	} while (cur += d_size, cur < end);
 }
 
-static void __nocfi __apply_alternatives(struct alt_region *region, bool is_module,
+static void __apply_alternatives(struct alt_region *region, bool is_module,
 				 unsigned long *feature_mask)
 {
 	struct alt_instr *alt;
diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c
index 587543c6c51c..97c42be71338 100644
--- a/arch/arm64/kernel/cacheinfo.c
+++ b/arch/arm64/kernel/cacheinfo.c
@@ -45,7 +45,8 @@ static void ci_leaf_init(struct cacheinfo *this_leaf,
 
 int init_cache_level(unsigned int cpu)
 {
-	unsigned int ctype, level, leaves, fw_level;
+	unsigned int ctype, level, leaves;
+	int fw_level;
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
 
 	for (level = 1, leaves = 0; level <= MAX_CACHE_LEVEL; level++) {
@@ -63,6 +64,9 @@ int init_cache_level(unsigned int cpu)
 	else
 		fw_level = acpi_find_last_cache_level(cpu);
 
+	if (fw_level < 0)
+		return fw_level;
+
 	if (level < fw_level) {
 		/*
 		 * some external caches not specified in CLIDR_EL1
diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S
index 48a8af97faa9..6b752fe89745 100644
--- a/arch/arm64/kernel/cpu-reset.S
+++ b/arch/arm64/kernel/cpu-reset.S
@@ -8,6 +8,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/assembler.h>
 #include <asm/sysreg.h>
 #include <asm/virt.h>
@@ -28,7 +29,7 @@
  * branch to what would be the reset vector. It must be executed with the
  * flat identity mapping.
  */
-SYM_CODE_START(cpu_soft_restart)
+SYM_TYPED_FUNC_START(cpu_soft_restart)
 	mov_q	x12, INIT_SCTLR_EL1_MMU_OFF
 	pre_disable_mmu_workaround
 	/*
@@ -47,6 +48,6 @@ SYM_CODE_START(cpu_soft_restart)
 	mov	x1, x3				// arg1
 	mov	x2, x4				// arg2
 	br	x8
-SYM_CODE_END(cpu_soft_restart)
+SYM_FUNC_END(cpu_soft_restart)
 
 .popsection
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 7e6289e709fc..53b973b6059f 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -208,6 +208,8 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = {
 #ifdef CONFIG_ARM64_ERRATUM_1286807
 	{
 		ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0),
+	},
+	{
 		/* Kryo4xx Gold (rcpe to rfpe) => (r0p0 to r3p0) */
 		ERRATA_MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xe),
 	},
@@ -654,6 +656,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2)
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_2457168
+	{
+		.desc = "ARM erratum 2457168",
+		.capability = ARM64_WORKAROUND_2457168,
+		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
+
+		/* Cortex-A510 r0p0-r1p1 */
+		CAP_MIDR_RANGE(MIDR_CORTEX_A510, 0, 0, 1, 1)
+	},
+#endif
 #ifdef CONFIG_ARM64_ERRATUM_2038923
 	{
 		.desc = "ARM erratum 2038923",
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 907401e4fffb..d8361691efeb 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1685,7 +1685,7 @@ static phys_addr_t kpti_ng_pgd_alloc(int shift)
 	return kpti_ng_temp_alloc;
 }
 
-static void __nocfi
+static void
 kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 {
 	typedef void (kpti_remap_fn)(int, int, phys_addr_t, unsigned long);
@@ -1713,7 +1713,7 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 	if (arm64_use_ng_mappings)
 		return;
 
-	remap_fn = (void *)__pa_symbol(function_nocfi(idmap_kpti_install_ng_mappings));
+	remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings);
 
 	if (!cpu) {
 		alloc = __get_free_pages(GFP_ATOMIC | __GFP_ZERO, order);
@@ -1870,7 +1870,10 @@ static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap)
 		pr_info("detected CPU%d: Activity Monitors Unit (AMU)\n",
 			smp_processor_id());
 		cpumask_set_cpu(smp_processor_id(), &amu_cpus);
-		update_freq_counters_refs();
+
+		/* 0 reference values signal broken/disabled counters */
+		if (!this_cpu_has_cap(ARM64_WORKAROUND_2457168))
+			update_freq_counters_refs();
 	}
 }
 
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 254fe31c03a0..2d73b3e793b2 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -502,7 +502,7 @@ tsk	.req	x28		// current thread_info
 SYM_CODE_START(vectors)
 	kernel_ventry	1, t, 64, sync		// Synchronous EL1t
 	kernel_ventry	1, t, 64, irq		// IRQ EL1t
-	kernel_ventry	1, t, 64, fiq		// FIQ EL1h
+	kernel_ventry	1, t, 64, fiq		// FIQ EL1t
 	kernel_ventry	1, t, 64, error		// Error EL1t
 
 	kernel_ventry	1, h, 64, sync		// Synchronous EL1h
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index dd63ffc3a2fa..23834d96d1e7 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -715,10 +715,12 @@ size_t sve_state_size(struct task_struct const *task)
  * do_sve_acc() case, there is no ABI requirement to hide stale data
  * written previously be task.
  */
-void sve_alloc(struct task_struct *task)
+void sve_alloc(struct task_struct *task, bool flush)
 {
 	if (task->thread.sve_state) {
-		memset(task->thread.sve_state, 0, sve_state_size(task));
+		if (flush)
+			memset(task->thread.sve_state, 0,
+			       sve_state_size(task));
 		return;
 	}
 
@@ -1388,7 +1390,7 @@ void do_sve_acc(unsigned long esr, struct pt_regs *regs)
 		return;
 	}
 
-	sve_alloc(current);
+	sve_alloc(current, true);
 	if (!current->thread.sve_state) {
 		force_sig(SIGKILL);
 		return;
@@ -1439,7 +1441,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
 		return;
 	}
 
-	sve_alloc(current);
+	sve_alloc(current, false);
 	sme_alloc(current);
 	if (!current->thread.sve_state || !current->thread.za_state) {
 		force_sig(SIGKILL);
@@ -1460,17 +1462,6 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
 		fpsimd_bind_task_to_cpu();
 	}
 
-	/*
-	 * If SVE was not already active initialise the SVE registers,
-	 * any non-shared state between the streaming and regular SVE
-	 * registers is architecturally guaranteed to be zeroed when
-	 * we enter streaming mode.  We do not need to initialize ZA
-	 * since ZA must be disabled at this point and enabling ZA is
-	 * architecturally defined to zero ZA.
-	 */
-	if (system_supports_sve() && !test_thread_flag(TIF_SVE))
-		sve_init_regs();
-
 	put_cpu_fpsimd_context();
 }
 
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index ea5dc7c90f46..26789865748c 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -56,7 +56,7 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	unsigned long pc;
 	u32 new;
 
-	pc = (unsigned long)function_nocfi(ftrace_call);
+	pc = (unsigned long)ftrace_call;
 	new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func,
 					  AARCH64_INSN_BRANCH_LINK);
 
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index cefe6a73ee54..814b6587ccb7 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -371,7 +371,9 @@ SYM_FUNC_END(create_idmap)
 SYM_FUNC_START_LOCAL(create_kernel_mapping)
 	adrp	x0, init_pg_dir
 	mov_q	x5, KIMAGE_VADDR		// compile time __va(_text)
+#ifdef CONFIG_RELOCATABLE
 	add	x5, x5, x23			// add KASLR displacement
+#endif
 	adrp	x6, _end			// runtime __pa(_end)
 	adrp	x3, _text			// runtime __pa(_text)
 	sub	x6, x6, x3			// _end - _text
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 19c2d487cb08..ce3d40120f72 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -204,7 +204,7 @@ void machine_kexec(struct kimage *kimage)
 		typeof(cpu_soft_restart) *restart;
 
 		cpu_install_idmap();
-		restart = (void *)__pa_symbol(function_nocfi(cpu_soft_restart));
+		restart = (void *)__pa_symbol(cpu_soft_restart);
 		restart(is_hyp_nvhe(), kimage->start, kimage->arch.dtb_mem,
 			0, 0);
 	} else {
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index 889951291cc0..a11a6e14ba89 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -47,7 +47,7 @@ static int prepare_elf_headers(void **addr, unsigned long *sz)
 	u64 i;
 	phys_addr_t start, end;
 
-	nr_ranges = 1; /* for exclusion of crashkernel region */
+	nr_ranges = 2; /* for exclusion of crashkernel region */
 	for_each_mem_range(i, &start, &end)
 		nr_ranges++;
 
diff --git a/arch/arm64/kernel/pi/kaslr_early.c b/arch/arm64/kernel/pi/kaslr_early.c
index 6c3855e69395..17bff6e399e4 100644
--- a/arch/arm64/kernel/pi/kaslr_early.c
+++ b/arch/arm64/kernel/pi/kaslr_early.c
@@ -94,11 +94,9 @@ asmlinkage u64 kaslr_early_init(void *fdt)
 
 	seed = get_kaslr_seed(fdt);
 	if (!seed) {
-#ifdef CONFIG_ARCH_RANDOM
-		 if (!__early_cpu_has_rndr() ||
-		     !__arm64_rndr((unsigned long *)&seed))
-#endif
-		return 0;
+		if (!__early_cpu_has_rndr() ||
+		    !__arm64_rndr((unsigned long *)&seed))
+			return 0;
 	}
 
 	/*
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index ab7f4c476104..29a8e444db83 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -38,7 +38,7 @@ static int __init cpu_psci_cpu_prepare(unsigned int cpu)
 
 static int cpu_psci_cpu_boot(unsigned int cpu)
 {
-	phys_addr_t pa_secondary_entry = __pa_symbol(function_nocfi(secondary_entry));
+	phys_addr_t pa_secondary_entry = __pa_symbol(secondary_entry);
 	int err = psci_ops.cpu_on(cpu_logical_map(cpu), pa_secondary_entry);
 	if (err)
 		pr_err("failed to boot CPU%d (%d)\n", cpu, err);
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 21da83187a60..041d2ae5c30a 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -882,7 +882,7 @@ static int sve_set_common(struct task_struct *target,
 		 * state and ensure there's storage.
 		 */
 		if (target->thread.svcr != old_svcr)
-			sve_alloc(target);
+			sve_alloc(target, true);
 	}
 
 	/* Registers: FPSIMD-only case */
@@ -912,7 +912,7 @@ static int sve_set_common(struct task_struct *target,
 		goto out;
 	}
 
-	sve_alloc(target);
+	sve_alloc(target, true);
 	if (!target->thread.sve_state) {
 		ret = -ENOMEM;
 		clear_tsk_thread_flag(target, TIF_SVE);
@@ -1082,9 +1082,8 @@ static int za_set(struct task_struct *target,
 
 	/* Ensure there is some SVE storage for streaming mode */
 	if (!target->thread.sve_state) {
-		sve_alloc(target);
+		sve_alloc(target, false);
 		if (!target->thread.sve_state) {
-			clear_thread_flag(TIF_SME);
 			ret = -ENOMEM;
 			goto out;
 		}
@@ -1094,7 +1093,6 @@ static int za_set(struct task_struct *target,
 	sme_alloc(target);
 	if (!target->thread.za_state) {
 		ret = -ENOMEM;
-		clear_tsk_thread_flag(target, TIF_SME);
 		goto out;
 	}
 
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 3e6d0352d7d3..9ad911f1647c 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -91,7 +91,7 @@ static size_t sigframe_size(struct rt_sigframe_user_layout const *user)
  * not taken into account.  This limit is not a guarantee and is
  * NOT ABI.
  */
-#define SIGFRAME_MAXSZ SZ_64K
+#define SIGFRAME_MAXSZ SZ_256K
 
 static int __sigframe_alloc(struct rt_sigframe_user_layout *user,
 			    unsigned long *offset, size_t size, bool extend)
@@ -310,7 +310,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 	fpsimd_flush_task_state(current);
 	/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
 
-	sve_alloc(current);
+	sve_alloc(current, true);
 	if (!current->thread.sve_state) {
 		clear_thread_flag(TIF_SVE);
 		return -ENOMEM;
@@ -926,6 +926,16 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 
 	/* Signal handlers are invoked with ZA and streaming mode disabled */
 	if (system_supports_sme()) {
+		/*
+		 * If we were in streaming mode the saved register
+		 * state was SVE but we will exit SM and use the
+		 * FPSIMD register state - flush the saved FPSIMD
+		 * register state in case it gets loaded.
+		 */
+		if (current->thread.svcr & SVCR_SM_MASK)
+			memset(&current->thread.uw.fpsimd_state, 0,
+			       sizeof(current->thread.uw.fpsimd_state));
+
 		current->thread.svcr &= ~(SVCR_ZA_MASK |
 					  SVCR_SM_MASK);
 		sme_smstop();
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index 617f78ad43a1..97c9de57725d 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -101,6 +101,9 @@ SYM_FUNC_END(__cpu_suspend_enter)
 SYM_CODE_START(cpu_resume)
 	bl	init_kernel_el
 	bl	finalise_el2
+#if VA_BITS > 48
+	ldr_l	x0, vabits_actual
+#endif
 	bl	__cpu_setup
 	/* enable the MMU early - so we can access sleep_save_stash by va */
 	adrp	x1, swapper_pg_dir
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 7e1624ecab3c..49029eace3ad 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -66,7 +66,7 @@ static int smp_spin_table_cpu_init(unsigned int cpu)
 static int smp_spin_table_cpu_prepare(unsigned int cpu)
 {
 	__le64 __iomem *release_addr;
-	phys_addr_t pa_holding_pen = __pa_symbol(function_nocfi(secondary_holding_pen));
+	phys_addr_t pa_holding_pen = __pa_symbol(secondary_holding_pen);
 
 	if (!cpu_release_addr[cpu])
 		return -ENODEV;
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 869ffc4d4484..44ebf5b2fc4b 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -237,7 +237,7 @@ static void amu_fie_setup(const struct cpumask *cpus)
 	for_each_cpu(cpu, cpus) {
 		if (!freq_counters_valid(cpu) ||
 		    freq_inv_set_max_ratio(cpu,
-					   cpufreq_get_hw_max_freq(cpu) * 1000,
+					   cpufreq_get_hw_max_freq(cpu) * 1000ULL,
 					   arch_timer_get_rate()))
 			return;
 	}
@@ -296,12 +296,25 @@ core_initcall(init_amu_fie);
 
 static void cpu_read_corecnt(void *val)
 {
+	/*
+	 * A value of 0 can be returned if the current CPU does not support AMUs
+	 * or if the counter is disabled for this CPU. A return value of 0 at
+	 * counter read is properly handled as an error case by the users of the
+	 * counter.
+	 */
 	*(u64 *)val = read_corecnt();
 }
 
 static void cpu_read_constcnt(void *val)
 {
-	*(u64 *)val = read_constcnt();
+	/*
+	 * Return 0 if the current CPU is affected by erratum 2457168. A value
+	 * of 0 is also returned if the current CPU does not support AMUs or if
+	 * the counter is disabled. A return value of 0 at counter read is
+	 * properly handled as an error case by the users of the counter.
+	 */
+	*(u64 *)val = this_cpu_has_cap(ARM64_WORKAROUND_2457168) ?
+		      0UL : read_constcnt();
 }
 
 static inline
@@ -328,7 +341,22 @@ int counters_read_on_cpu(int cpu, smp_call_func_t func, u64 *val)
  */
 bool cpc_ffh_supported(void)
 {
-	return freq_counters_valid(get_cpu_with_amu_feat());
+	int cpu = get_cpu_with_amu_feat();
+
+	/*
+	 * FFH is considered supported if there is at least one present CPU that
+	 * supports AMUs. Using FFH to read core and reference counters for CPUs
+	 * that do not support AMUs, have counters disabled or that are affected
+	 * by errata, will result in a return value of 0.
+	 *
+	 * This is done to allow any enabled and valid counters to be read
+	 * through FFH, knowing that potentially returning 0 as counter value is
+	 * properly handled by the users of these counters.
+	 */
+	if ((cpu >= nr_cpu_ids) || !cpumask_test_cpu(cpu, cpu_present_mask))
+		return false;
+
+	return true;
 }
 
 int cpc_read_ffh(int cpu, struct cpc_reg *reg, u64 *val)
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index b7fed33981f7..3c026da95bbc 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -26,6 +26,7 @@
 #include <linux/syscalls.h>
 #include <linux/mm_types.h>
 #include <linux/kasan.h>
+#include <linux/cfi.h>
 
 #include <asm/atomic.h>
 #include <asm/bug.h>
@@ -991,6 +992,38 @@ static struct break_hook bug_break_hook = {
 	.imm = BUG_BRK_IMM,
 };
 
+#ifdef CONFIG_CFI_CLANG
+static int cfi_handler(struct pt_regs *regs, unsigned long esr)
+{
+	unsigned long target;
+	u32 type;
+
+	target = pt_regs_read_reg(regs, FIELD_GET(CFI_BRK_IMM_TARGET, esr));
+	type = (u32)pt_regs_read_reg(regs, FIELD_GET(CFI_BRK_IMM_TYPE, esr));
+
+	switch (report_cfi_failure(regs, regs->pc, &target, type)) {
+	case BUG_TRAP_TYPE_BUG:
+		die("Oops - CFI", regs, 0);
+		break;
+
+	case BUG_TRAP_TYPE_WARN:
+		break;
+
+	default:
+		return DBG_HOOK_ERROR;
+	}
+
+	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
+	return DBG_HOOK_HANDLED;
+}
+
+static struct break_hook cfi_break_hook = {
+	.fn = cfi_handler,
+	.imm = CFI_BRK_IMM_BASE,
+	.mask = CFI_BRK_IMM_MASK,
+};
+#endif /* CONFIG_CFI_CLANG */
+
 static int reserved_fault_handler(struct pt_regs *regs, unsigned long esr)
 {
 	pr_err("%s generated an invalid instruction at %pS!\n",
@@ -1052,6 +1085,9 @@ static struct break_hook kasan_break_hook = {
 };
 #endif
 
+
+#define esr_comment(esr) ((esr) & ESR_ELx_BRK64_ISS_COMMENT_MASK)
+
 /*
  * Initial handler for AArch64 BRK exceptions
  * This handler only used until debug_traps_init().
@@ -1059,10 +1095,12 @@ static struct break_hook kasan_break_hook = {
 int __init early_brk64(unsigned long addr, unsigned long esr,
 		struct pt_regs *regs)
 {
+#ifdef CONFIG_CFI_CLANG
+	if ((esr_comment(esr) & ~CFI_BRK_IMM_MASK) == CFI_BRK_IMM_BASE)
+		return cfi_handler(regs, esr) != DBG_HOOK_HANDLED;
+#endif
 #ifdef CONFIG_KASAN_SW_TAGS
-	unsigned long comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
-
-	if ((comment & ~KASAN_BRK_MASK) == KASAN_BRK_IMM)
+	if ((esr_comment(esr) & ~KASAN_BRK_MASK) == KASAN_BRK_IMM)
 		return kasan_handler(regs, esr) != DBG_HOOK_HANDLED;
 #endif
 	return bug_handler(regs, esr) != DBG_HOOK_HANDLED;
@@ -1071,6 +1109,9 @@ int __init early_brk64(unsigned long addr, unsigned long esr,
 void __init trap_init(void)
 {
 	register_kernel_break_hook(&bug_break_hook);
+#ifdef CONFIG_CFI_CLANG
+	register_kernel_break_hook(&cfi_break_hook);
+#endif
 	register_kernel_break_hook(&fault_break_hook);
 #ifdef CONFIG_KASAN_SW_TAGS
 	register_kernel_break_hook(&kasan_break_hook);
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index bafbf78fab77..619e2dc7ee14 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -40,7 +40,8 @@ ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
 # kernel with CONFIG_WERROR enabled.
 CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) \
 				$(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) \
-				$(CC_FLAGS_LTO) -Wmissing-prototypes -Wmissing-declarations
+				$(CC_FLAGS_LTO) $(CC_FLAGS_CFI) \
+				-Wmissing-prototypes -Wmissing-declarations
 KASAN_SANITIZE			:= n
 KCSAN_SANITIZE			:= n
 UBSAN_SANITIZE			:= n
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 986cee6fbc7f..917086be5c6b 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -757,8 +757,7 @@ static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu)
 	if (likely(!vcpu_mode_is_32bit(vcpu)))
 		return false;
 
-	return !system_supports_32bit_el0() ||
-		static_branch_unlikely(&arm64_mismatched_32bit_el0);
+	return !kvm_supports_32bit_el0();
 }
 
 /**
@@ -2115,7 +2114,7 @@ static int finalize_hyp_mode(void)
 	 * at, which would end badly once inaccessible.
 	 */
 	kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start);
-	kmemleak_free_part(__va(hyp_mem_base), hyp_mem_size);
+	kmemleak_free_part_phys(hyp_mem_base, hyp_mem_size);
 	return pkvm_drop_host_privileges();
 }
 
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 8c607199cad1..f802a3b3f8db 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -242,7 +242,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		u64 mode = (*(u64 *)valp) & PSR_AA32_MODE_MASK;
 		switch (mode) {
 		case PSR_AA32_MODE_USR:
-			if (!system_supports_32bit_el0())
+			if (!kvm_supports_32bit_el0())
 				return -EINVAL;
 			break;
 		case PSR_AA32_MODE_FIQ:
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 87f1cd0df36e..c9a13e487187 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -993,7 +993,7 @@ transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		 * THP doesn't start to split while we are adjusting the
 		 * refcounts.
 		 *
-		 * We are sure this doesn't happen, because mmu_notifier_retry
+		 * We are sure this doesn't happen, because mmu_invalidate_retry
 		 * was successful and we are holding the mmu_lock, so if this
 		 * THP is trying to split, it will be blocked in the mmu
 		 * notifier before touching any of the pages, specifically
@@ -1188,9 +1188,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			return ret;
 	}
 
-	mmu_seq = vcpu->kvm->mmu_notifier_seq;
+	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	/*
-	 * Ensure the read of mmu_notifier_seq happens before we call
+	 * Ensure the read of mmu_invalidate_seq happens before we call
 	 * gfn_to_pfn_prot (which calls get_user_pages), so that we don't risk
 	 * the page we just got a reference to gets unmapped before we have a
 	 * chance to grab the mmu_lock, which ensure that if the page gets
@@ -1246,7 +1246,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	else
 		write_lock(&kvm->mmu_lock);
 	pgt = vcpu->arch.hw_mmu->pgt;
-	if (mmu_notifier_retry(kvm, mmu_seq))
+	if (mmu_invalidate_retry(kvm, mmu_seq))
 		goto out_unlock;
 
 	/*
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index c059b259aea6..3234f50b8c4b 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -652,7 +652,7 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	 */
 	val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
 	       | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E);
-	if (!system_supports_32bit_el0())
+	if (!kvm_supports_32bit_el0())
 		val |= ARMV8_PMU_PMCR_LC;
 	__vcpu_sys_reg(vcpu, r->reg) = val;
 }
@@ -701,7 +701,7 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		val = __vcpu_sys_reg(vcpu, PMCR_EL0);
 		val &= ~ARMV8_PMU_PMCR_MASK;
 		val |= p->regval & ARMV8_PMU_PMCR_MASK;
-		if (!system_supports_32bit_el0())
+		if (!kvm_supports_32bit_el0())
 			val |= ARMV8_PMU_PMCR_LC;
 		__vcpu_sys_reg(vcpu, PMCR_EL0) = val;
 		kvm_pmu_handle_pmcr(vcpu, val);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index db7c4e6ae57b..eb489302c28a 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -331,12 +331,6 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 	}
 	BUG_ON(p4d_bad(p4d));
 
-	/*
-	 * No need for locking during early boot. And it doesn't work as
-	 * expected with KASLR enabled.
-	 */
-	if (system_state != SYSTEM_BOOTING)
-		mutex_lock(&fixmap_lock);
 	pudp = pud_set_fixmap_offset(p4dp, addr);
 	do {
 		pud_t old_pud = READ_ONCE(*pudp);
@@ -368,15 +362,13 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 	} while (pudp++, addr = next, addr != end);
 
 	pud_clear_fixmap();
-	if (system_state != SYSTEM_BOOTING)
-		mutex_unlock(&fixmap_lock);
 }
 
-static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
-				 unsigned long virt, phys_addr_t size,
-				 pgprot_t prot,
-				 phys_addr_t (*pgtable_alloc)(int),
-				 int flags)
+static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys,
+					unsigned long virt, phys_addr_t size,
+					pgprot_t prot,
+					phys_addr_t (*pgtable_alloc)(int),
+					int flags)
 {
 	unsigned long addr, end, next;
 	pgd_t *pgdp = pgd_offset_pgd(pgdir, virt);
@@ -400,8 +392,20 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 	} while (pgdp++, addr = next, addr != end);
 }
 
+static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
+				 unsigned long virt, phys_addr_t size,
+				 pgprot_t prot,
+				 phys_addr_t (*pgtable_alloc)(int),
+				 int flags)
+{
+	mutex_lock(&fixmap_lock);
+	__create_pgd_mapping_locked(pgdir, phys, virt, size, prot,
+				    pgtable_alloc, flags);
+	mutex_unlock(&fixmap_lock);
+}
+
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-extern __alias(__create_pgd_mapping)
+extern __alias(__create_pgd_mapping_locked)
 void create_kpti_ng_temp_pgd(pgd_t *pgdir, phys_addr_t phys, unsigned long virt,
 			     phys_addr_t size, pgprot_t prot,
 			     phys_addr_t (*pgtable_alloc)(int), int flags);
@@ -642,24 +646,6 @@ static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end,
 	vm_area_add_early(vma);
 }
 
-static int __init parse_rodata(char *arg)
-{
-	int ret = strtobool(arg, &rodata_enabled);
-	if (!ret) {
-		rodata_full = false;
-		return 0;
-	}
-
-	/* permit 'full' in addition to boolean options */
-	if (strcmp(arg, "full"))
-		return -EINVAL;
-
-	rodata_enabled = true;
-	rodata_full = true;
-	return 0;
-}
-early_param("rodata", parse_rodata);
-
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 static int __init map_entry_trampoline(void)
 {
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 7837a69524c5..8b9f419fcad9 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -10,6 +10,7 @@
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/pgtable.h>
+#include <linux/cfi_types.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/asm_pointer_auth.h>
@@ -185,7 +186,7 @@ SYM_FUNC_END(cpu_do_resume)
  * This is the low-level counterpart to cpu_replace_ttbr1, and should not be
  * called by anything else. It can only be executed from a TTBR0 mapping.
  */
-SYM_FUNC_START(idmap_cpu_replace_ttbr1)
+SYM_TYPED_FUNC_START(idmap_cpu_replace_ttbr1)
 	save_and_disable_daif flags=x2
 
 	__idmap_cpu_set_reserved_ttbr1 x1, x3
@@ -253,7 +254,7 @@ SYM_FUNC_END(idmap_cpu_replace_ttbr1)
 SYM_DATA(__idmap_kpti_flag, .long 1)
 	.popsection
 
-SYM_FUNC_START(idmap_kpti_install_ng_mappings)
+SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings)
 	cpu		.req	w0
 	temp_pte	.req	x0
 	num_cpus	.req	w1
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 779653771507..63b2484ce6c3 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -67,6 +67,7 @@ WORKAROUND_1902691
 WORKAROUND_2038923
 WORKAROUND_2064142
 WORKAROUND_2077057
+WORKAROUND_2457168
 WORKAROUND_TRBE_OVERWRITE_FILL_MODE
 WORKAROUND_TSB_FLUSH_FAILURE
 WORKAROUND_TRBE_WRITE_OUT_OF_RANGE
diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h
index da500471ac73..160d8f37fa1a 100644
--- a/arch/hexagon/include/asm/bitops.h
+++ b/arch/hexagon/include/asm/bitops.h
@@ -179,6 +179,21 @@ arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
 	return retval;
 }
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 /*
  * ffz - find first zero in word.
  * @word: The word to search
diff --git a/arch/ia64/include/asm/bitops.h b/arch/ia64/include/asm/bitops.h
index 9f62af7fd7c4..1accb7842f58 100644
--- a/arch/ia64/include/asm/bitops.h
+++ b/arch/ia64/include/asm/bitops.h
@@ -331,11 +331,8 @@ arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 	return (old & bit) != 0;
 }
 
-static __always_inline bool
-arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
-{
-	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
-}
+#define arch_test_bit generic_test_bit
+#define arch_test_bit_acquire generic_test_bit_acquire
 
 /**
  * ffz - find the first zero bit in a long word
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 4abc9a28aba4..551dd99e98b8 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -10,7 +10,6 @@ config LOONGARCH
 	select ARCH_ENABLE_MEMORY_HOTPLUG
 	select ARCH_ENABLE_MEMORY_HOTREMOVE
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
-	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_INLINE_READ_LOCK if !PREEMPTION
@@ -39,6 +38,7 @@ config LOONGARCH
 	select ARCH_INLINE_SPIN_UNLOCK_BH if !PREEMPTION
 	select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPTION
 	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION
+	select ARCH_KEEP_MEMBLOCK
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_SPARSEMEM_ENABLE
@@ -51,6 +51,7 @@ config LOONGARCH
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
+	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANTS_NO_INSTR
 	select BUILDTIME_TABLE_SORT
 	select COMMON_CLK
@@ -111,6 +112,7 @@ config LOONGARCH
 	select PCI_ECAM if ACPI
 	select PCI_LOONGSON
 	select PCI_MSI_ARCH_FALLBACKS
+	select PCI_QUIRKS
 	select PERF_USE_VMALLOC
 	select RTC_LIB
 	select SMP
diff --git a/arch/loongarch/include/asm/acpi.h b/arch/loongarch/include/asm/acpi.h
index c5108213876c..17162f494b9b 100644
--- a/arch/loongarch/include/asm/acpi.h
+++ b/arch/loongarch/include/asm/acpi.h
@@ -15,7 +15,7 @@ extern int acpi_pci_disabled;
 extern int acpi_noirq;
 
 #define acpi_os_ioremap acpi_os_ioremap
-void __init __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size);
+void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size);
 
 static inline void disable_acpi(void)
 {
diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h
index b91e0733b2e5..d342935e5a72 100644
--- a/arch/loongarch/include/asm/addrspace.h
+++ b/arch/loongarch/include/asm/addrspace.h
@@ -109,4 +109,20 @@ extern unsigned long vm_map_base;
  */
 #define PHYSADDR(a)		((_ACAST64_(a)) & TO_PHYS_MASK)
 
+/*
+ * On LoongArch, I/O ports mappring is following:
+ *
+ *              |         ....          |
+ *              |-----------------------|
+ *              | pci io ports(16K~32M) |
+ *              |-----------------------|
+ *              | isa io ports(0  ~16K) |
+ * PCI_IOBASE ->|-----------------------|
+ *              |         ....          |
+ */
+#define PCI_IOBASE	((void __iomem *)(vm_map_base + (2 * PAGE_SIZE)))
+#define PCI_IOSIZE	SZ_32M
+#define ISA_IOSIZE	SZ_16K
+#define IO_SPACE_LIMIT	(PCI_IOSIZE - 1)
+
 #endif /* _ASM_ADDRSPACE_H */
diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h
index 0a9b0fac1eee..ae19e33c7754 100644
--- a/arch/loongarch/include/asm/cmpxchg.h
+++ b/arch/loongarch/include/asm/cmpxchg.h
@@ -5,8 +5,9 @@
 #ifndef __ASM_CMPXCHG_H
 #define __ASM_CMPXCHG_H
 
-#include <asm/barrier.h>
+#include <linux/bits.h>
 #include <linux/build_bug.h>
+#include <asm/barrier.h>
 
 #define __xchg_asm(amswap_db, m, val)		\
 ({						\
@@ -21,10 +22,53 @@
 		__ret;				\
 })
 
+static inline unsigned int __xchg_small(volatile void *ptr, unsigned int val,
+					unsigned int size)
+{
+	unsigned int shift;
+	u32 old32, mask, temp;
+	volatile u32 *ptr32;
+
+	/* Mask value to the correct size. */
+	mask = GENMASK((size * BITS_PER_BYTE) - 1, 0);
+	val &= mask;
+
+	/*
+	 * Calculate a shift & mask that correspond to the value we wish to
+	 * exchange within the naturally aligned 4 byte integerthat includes
+	 * it.
+	 */
+	shift = (unsigned long)ptr & 0x3;
+	shift *= BITS_PER_BYTE;
+	mask <<= shift;
+
+	/*
+	 * Calculate a pointer to the naturally aligned 4 byte integer that
+	 * includes our byte of interest, and load its value.
+	 */
+	ptr32 = (volatile u32 *)((unsigned long)ptr & ~0x3);
+
+	asm volatile (
+	"1:	ll.w		%0, %3		\n"
+	"	andn		%1, %0, %z4	\n"
+	"	or		%1, %1, %z5	\n"
+	"	sc.w		%1, %2		\n"
+	"	beqz		%1, 1b		\n"
+	: "=&r" (old32), "=&r" (temp), "=ZC" (*ptr32)
+	: "ZC" (*ptr32), "Jr" (mask), "Jr" (val << shift)
+	: "memory");
+
+	return (old32 & mask) >> shift;
+}
+
 static inline unsigned long __xchg(volatile void *ptr, unsigned long x,
 				   int size)
 {
 	switch (size) {
+	case 1:
+	case 2:
+		return __xchg_small(ptr, x, size);
+
 	case 4:
 		return __xchg_asm("amswap_db.w", (volatile u32 *)ptr, (u32)x);
 
@@ -67,10 +111,62 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long x,
 	__ret;								\
 })
 
+static inline unsigned int __cmpxchg_small(volatile void *ptr, unsigned int old,
+					   unsigned int new, unsigned int size)
+{
+	unsigned int shift;
+	u32 old32, mask, temp;
+	volatile u32 *ptr32;
+
+	/* Mask inputs to the correct size. */
+	mask = GENMASK((size * BITS_PER_BYTE) - 1, 0);
+	old &= mask;
+	new &= mask;
+
+	/*
+	 * Calculate a shift & mask that correspond to the value we wish to
+	 * compare & exchange within the naturally aligned 4 byte integer
+	 * that includes it.
+	 */
+	shift = (unsigned long)ptr & 0x3;
+	shift *= BITS_PER_BYTE;
+	old <<= shift;
+	new <<= shift;
+	mask <<= shift;
+
+	/*
+	 * Calculate a pointer to the naturally aligned 4 byte integer that
+	 * includes our byte of interest, and load its value.
+	 */
+	ptr32 = (volatile u32 *)((unsigned long)ptr & ~0x3);
+
+	asm volatile (
+	"1:	ll.w		%0, %3		\n"
+	"	and		%1, %0, %z4	\n"
+	"	bne		%1, %z5, 2f	\n"
+	"	andn		%1, %0, %z4	\n"
+	"	or		%1, %1, %z6	\n"
+	"	sc.w		%1, %2		\n"
+	"	beqz		%1, 1b		\n"
+	"	b		3f		\n"
+	"2:					\n"
+	__WEAK_LLSC_MB
+	"3:					\n"
+	: "=&r" (old32), "=&r" (temp), "=ZC" (*ptr32)
+	: "ZC" (*ptr32), "Jr" (mask), "Jr" (old), "Jr" (new)
+	: "memory");
+
+	return (old32 & mask) >> shift;
+}
+
 static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 				      unsigned long new, unsigned int size)
 {
 	switch (size) {
+	case 1:
+	case 2:
+		return __cmpxchg_small(ptr, old, new, size);
+
 	case 4:
 		return __cmpxchg_asm("ll.w", "sc.w", (volatile u32 *)ptr,
 				     (u32)old, new);
diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h
index 884599739b36..999944ea1cea 100644
--- a/arch/loongarch/include/asm/io.h
+++ b/arch/loongarch/include/asm/io.h
@@ -7,35 +7,16 @@
 
 #define ARCH_HAS_IOREMAP_WC
 
-#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 
 #include <asm/addrspace.h>
-#include <asm/bug.h>
-#include <asm/byteorder.h>
 #include <asm/cpu.h>
 #include <asm/page.h>
 #include <asm/pgtable-bits.h>
 #include <asm/string.h>
 
 /*
- * On LoongArch, I/O ports mappring is following:
- *
- *              |         ....          |
- *              |-----------------------|
- *              | pci io ports(64K~32M) |
- *              |-----------------------|
- *              | isa io ports(0  ~16K) |
- * PCI_IOBASE ->|-----------------------|
- *              |         ....          |
- */
-#define PCI_IOBASE	((void __iomem *)(vm_map_base + (2 * PAGE_SIZE)))
-#define PCI_IOSIZE	SZ_32M
-#define ISA_IOSIZE	SZ_16K
-#define IO_SPACE_LIMIT	(PCI_IOSIZE - 1)
-
-/*
  * Change "struct page" to physical address.
  */
 #define page_to_phys(page)	((phys_addr_t)page_to_pfn(page) << PAGE_SHIFT)
diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h
index 4b130199ceae..d06d4542b634 100644
--- a/arch/loongarch/include/asm/irq.h
+++ b/arch/loongarch/include/asm/irq.h
@@ -81,7 +81,6 @@ extern struct acpi_vector_group msi_group[MAX_IO_PICS];
 #define GSI_MIN_PCH_IRQ		LOONGSON_PCH_IRQ_BASE
 #define GSI_MAX_PCH_IRQ		(LOONGSON_PCH_IRQ_BASE + 256 - 1)
 
-extern int find_pch_pic(u32 gsi);
 struct acpi_madt_lio_pic;
 struct acpi_madt_eio_pic;
 struct acpi_madt_ht_pic;
diff --git a/arch/loongarch/include/asm/loongson.h b/arch/loongarch/include/asm/loongson.h
index 6e8f6972ceb6..00db93edae1b 100644
--- a/arch/loongarch/include/asm/loongson.h
+++ b/arch/loongarch/include/asm/loongson.h
@@ -14,8 +14,6 @@
 #include <asm/addrspace.h>
 #include <asm/bootinfo.h>
 
-extern const struct plat_smp_ops loongson3_smp_ops;
-
 #define LOONGSON_REG(x) \
 	(*(volatile u32 *)((char *)TO_UNCACHE(LOONGSON_REG_BASE) + (x)))
 
diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h
index a37324ac460b..53f284a96182 100644
--- a/arch/loongarch/include/asm/page.h
+++ b/arch/loongarch/include/asm/page.h
@@ -95,7 +95,7 @@ static inline int pfn_valid(unsigned long pfn)
 
 #endif
 
-#define virt_to_pfn(kaddr)	PFN_DOWN(virt_to_phys((void *)(kaddr)))
+#define virt_to_pfn(kaddr)	PFN_DOWN(PHYSADDR(kaddr))
 #define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
 
 extern int __virt_addr_valid(volatile void *kaddr);
diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h
index e6569f18c6dd..0bd6b0110198 100644
--- a/arch/loongarch/include/asm/percpu.h
+++ b/arch/loongarch/include/asm/percpu.h
@@ -123,6 +123,10 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 						int size)
 {
 	switch (size) {
+	case 1:
+	case 2:
+		return __xchg_small((volatile void *)ptr, val, size);
+
 	case 4:
 		return __xchg_asm("amswap.w", (volatile u32 *)ptr, (u32)val);
 
@@ -204,9 +208,13 @@ do {									\
 #define this_cpu_write_4(pcp, val) _percpu_write(pcp, val)
 #define this_cpu_write_8(pcp, val) _percpu_write(pcp, val)
 
+#define this_cpu_xchg_1(pcp, val) _percpu_xchg(pcp, val)
+#define this_cpu_xchg_2(pcp, val) _percpu_xchg(pcp, val)
 #define this_cpu_xchg_4(pcp, val) _percpu_xchg(pcp, val)
 #define this_cpu_xchg_8(pcp, val) _percpu_xchg(pcp, val)
 
+#define this_cpu_cmpxchg_1(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_2(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
 #define this_cpu_cmpxchg_4(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
 #define this_cpu_cmpxchg_8(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
 
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index e03443abaf7d..8ea57e2f0e04 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -59,7 +59,6 @@
 #include <linux/mm_types.h>
 #include <linux/mmzone.h>
 #include <asm/fixmap.h>
-#include <asm/io.h>
 
 struct mm_struct;
 struct vm_area_struct;
@@ -145,7 +144,7 @@ static inline void set_p4d(p4d_t *p4d, p4d_t p4dval)
 	*p4d = p4dval;
 }
 
-#define p4d_phys(p4d)		virt_to_phys((void *)p4d_val(p4d))
+#define p4d_phys(p4d)		PHYSADDR(p4d_val(p4d))
 #define p4d_page(p4d)		(pfn_to_page(p4d_phys(p4d) >> PAGE_SHIFT))
 
 #endif
@@ -188,7 +187,7 @@ static inline pmd_t *pud_pgtable(pud_t pud)
 
 #define set_pud(pudptr, pudval) do { *(pudptr) = (pudval); } while (0)
 
-#define pud_phys(pud)		virt_to_phys((void *)pud_val(pud))
+#define pud_phys(pud)		PHYSADDR(pud_val(pud))
 #define pud_page(pud)		(pfn_to_page(pud_phys(pud) >> PAGE_SHIFT))
 
 #endif
@@ -221,7 +220,7 @@ static inline void pmd_clear(pmd_t *pmdp)
 
 #define set_pmd(pmdptr, pmdval) do { *(pmdptr) = (pmdval); } while (0)
 
-#define pmd_phys(pmd)		virt_to_phys((void *)pmd_val(pmd))
+#define pmd_phys(pmd)		PHYSADDR(pmd_val(pmd))
 
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_page(pmd)		(pfn_to_page(pmd_phys(pmd) >> PAGE_SHIFT))
diff --git a/arch/loongarch/include/asm/reboot.h b/arch/loongarch/include/asm/reboot.h
deleted file mode 100644
index 51151749d8f0..000000000000
--- a/arch/loongarch/include/asm/reboot.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
- */
-#ifndef _ASM_REBOOT_H
-#define _ASM_REBOOT_H
-
-extern void (*pm_restart)(void);
-
-#endif /* _ASM_REBOOT_H */
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index f1c928648a4a..335398482038 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -48,7 +48,7 @@ void __init __acpi_unmap_table(void __iomem *map, unsigned long size)
 	early_memunmap(map, size);
 }
 
-void __init __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
+void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 {
 	if (!memblock_is_memory(phys))
 		return ioremap(phys, size);
diff --git a/arch/loongarch/kernel/dma.c b/arch/loongarch/kernel/dma.c
index 8c9b5314a13e..7a9c6a9dd2d0 100644
--- a/arch/loongarch/kernel/dma.c
+++ b/arch/loongarch/kernel/dma.c
@@ -2,39 +2,29 @@
 /*
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
-#include <linux/init.h>
+#include <linux/acpi.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-map-ops.h>
-#include <linux/swiotlb.h>
 
-#include <asm/bootinfo.h>
-#include <asm/dma.h>
-#include <asm/loongson.h>
-
-/*
- * We extract 4bit node id (bit 44~47) from Loongson-3's
- * 48bit physical address space and embed it into 40bit.
- */
-
-static int node_id_offset;
-
-dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	long nid = (paddr >> 44) & 0xf;
-
-	return ((nid << 44) ^ paddr) | (nid << node_id_offset);
-}
-
-phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
+void acpi_arch_dma_setup(struct device *dev)
 {
-	long nid = (daddr >> node_id_offset) & 0xf;
+	int ret;
+	u64 mask, end = 0;
+	const struct bus_dma_region *map = NULL;
+
+	ret = acpi_dma_get_range(dev, &map);
+	if (!ret && map) {
+		const struct bus_dma_region *r = map;
+
+		for (end = 0; r->size; r++) {
+			if (r->dma_start + r->size - 1 > end)
+				end = r->dma_start + r->size - 1;
+		}
+
+		mask = DMA_BIT_MASK(ilog2(end) + 1);
+		dev->bus_dma_limit = end;
+		dev->dma_range_map = map;
+		dev->coherent_dma_mask = min(dev->coherent_dma_mask, mask);
+		*dev->dma_mask = min(*dev->dma_mask, mask);
+	}
 
-	return ((nid << node_id_offset) ^ daddr) | (nid << 44);
-}
-
-void __init plat_swiotlb_setup(void)
-{
-	swiotlb_init(true, SWIOTLB_VERBOSE);
-	node_id_offset = ((readl(LS7A_DMA_CFG) & LS7A_DMA_NODE_MASK) >> LS7A_DMA_NODE_SHF) + 36;
 }
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index c60eb66793e3..331864369e49 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -14,6 +14,8 @@
 
 	__REF
 
+	.align 12
+
 SYM_CODE_START(kernel_entry)			# kernel entry point
 
 	/* Config direct window and set PG */
diff --git a/arch/loongarch/kernel/reset.c b/arch/loongarch/kernel/reset.c
index 800c965a17ea..8c82021eb2f4 100644
--- a/arch/loongarch/kernel/reset.c
+++ b/arch/loongarch/kernel/reset.c
@@ -15,10 +15,16 @@
 #include <acpi/reboot.h>
 #include <asm/idle.h>
 #include <asm/loongarch.h>
-#include <asm/reboot.h>
 
-static void default_halt(void)
+void (*pm_power_off)(void);
+EXPORT_SYMBOL(pm_power_off);
+
+void machine_halt(void)
 {
+#ifdef CONFIG_SMP
+	preempt_disable();
+	smp_send_stop();
+#endif
 	local_irq_disable();
 	clear_csr_ecfg(ECFG0_IM);
 
@@ -30,18 +36,29 @@ static void default_halt(void)
 	}
 }
 
-static void default_poweroff(void)
+void machine_power_off(void)
 {
+#ifdef CONFIG_SMP
+	preempt_disable();
+	smp_send_stop();
+#endif
+	do_kernel_power_off();
 #ifdef CONFIG_EFI
 	efi.reset_system(EFI_RESET_SHUTDOWN, EFI_SUCCESS, 0, NULL);
 #endif
+
 	while (true) {
 		__arch_cpu_idle();
 	}
 }
 
-static void default_restart(void)
+void machine_restart(char *command)
 {
+#ifdef CONFIG_SMP
+	preempt_disable();
+	smp_send_stop();
+#endif
+	do_kernel_restart(command);
 #ifdef CONFIG_EFI
 	if (efi_capsule_pending(NULL))
 		efi_reboot(REBOOT_WARM, NULL);
@@ -55,47 +72,3 @@ static void default_restart(void)
 		__arch_cpu_idle();
 	}
 }
-
-void (*pm_restart)(void);
-EXPORT_SYMBOL(pm_restart);
-
-void (*pm_power_off)(void);
-EXPORT_SYMBOL(pm_power_off);
-
-void machine_halt(void)
-{
-#ifdef CONFIG_SMP
-	preempt_disable();
-	smp_send_stop();
-#endif
-	default_halt();
-}
-
-void machine_power_off(void)
-{
-#ifdef CONFIG_SMP
-	preempt_disable();
-	smp_send_stop();
-#endif
-	pm_power_off();
-}
-
-void machine_restart(char *command)
-{
-#ifdef CONFIG_SMP
-	preempt_disable();
-	smp_send_stop();
-#endif
-	do_kernel_restart(command);
-	pm_restart();
-}
-
-static int __init loongarch_reboot_setup(void)
-{
-	pm_restart = default_restart;
-	pm_power_off = default_poweroff;
-
-	return 0;
-}
-
-arch_initcall(loongarch_reboot_setup);
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 8f5c2f9a1a83..d97c69dbe553 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -247,7 +247,7 @@ static void __init arch_mem_init(char **cmdline_p)
 	sparse_init();
 	memblock_set_bottom_up(true);
 
-	plat_swiotlb_setup();
+	swiotlb_init(true, SWIOTLB_VERBOSE);
 
 	dma_contiguous_reserve(PFN_PHYS(max_low_pfn));
 
diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c
index 7f4889df4a17..8f5b7986374b 100644
--- a/arch/loongarch/kernel/signal.c
+++ b/arch/loongarch/kernel/signal.c
@@ -529,11 +529,11 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	signal_setup_done(ret, ksig, 0);
 }
 
-void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal)
+void arch_do_signal_or_restart(struct pt_regs *regs)
 {
 	struct ksignal ksig;
 
-	if (has_signal && get_signal(&ksig)) {
+	if (get_signal(&ksig)) {
 		/* Whee!  Actually deliver the signal.	*/
 		handle_signal(&ksig, regs);
 		return;
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index aa1c95aaf595..5010e95cef84 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -461,11 +461,9 @@ asmlinkage void noinstr do_watch(struct pt_regs *regs)
 
 asmlinkage void noinstr do_ri(struct pt_regs *regs)
 {
-	int status = -1;
+	int status = SIGILL;
 	unsigned int opcode = 0;
 	unsigned int __user *era = (unsigned int __user *)exception_era(regs);
-	unsigned long old_era = regs->csr_era;
-	unsigned long old_ra = regs->regs[1];
 	irqentry_state_t state = irqentry_enter(regs);
 
 	local_irq_enable();
@@ -477,21 +475,12 @@ asmlinkage void noinstr do_ri(struct pt_regs *regs)
 
 	die_if_kernel("Reserved instruction in kernel code", regs);
 
-	compute_return_era(regs);
-
 	if (unlikely(get_user(opcode, era) < 0)) {
 		status = SIGSEGV;
 		current->thread.error_code = 1;
 	}
 
-	if (status < 0)
-		status = SIGILL;
-
-	if (unlikely(status > 0)) {
-		regs->csr_era = old_era;		/* Undo skip-over.  */
-		regs->regs[1] = old_ra;
-		force_sig(status);
-	}
+	force_sig(status);
 
 out:
 	local_irq_disable();
diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S
index 69c76f26c1c5..f4831df5d2f9 100644
--- a/arch/loongarch/kernel/vmlinux.lds.S
+++ b/arch/loongarch/kernel/vmlinux.lds.S
@@ -77,6 +77,8 @@ SECTIONS
 	PERCPU_SECTION(1 << CONFIG_L1_CACHE_SHIFT)
 #endif
 
+	.rela.dyn : ALIGN(8) { *(.rela.dyn) *(.rela*) }
+
 	.init.bss : {
 		*(.init.bss)
 	}
diff --git a/arch/loongarch/lib/dump_tlb.c b/arch/loongarch/lib/dump_tlb.c
index cda2c6bc7f09..c2cc7ce343c9 100644
--- a/arch/loongarch/lib/dump_tlb.c
+++ b/arch/loongarch/lib/dump_tlb.c
@@ -18,11 +18,11 @@ void dump_tlb_regs(void)
 {
 	const int field = 2 * sizeof(unsigned long);
 
-	pr_info("Index    : %0x\n", read_csr_tlbidx());
-	pr_info("PageSize : %0x\n", read_csr_pagesize());
-	pr_info("EntryHi  : %0*llx\n", field, read_csr_entryhi());
-	pr_info("EntryLo0 : %0*llx\n", field, read_csr_entrylo0());
-	pr_info("EntryLo1 : %0*llx\n", field, read_csr_entrylo1());
+	pr_info("Index    : 0x%0x\n", read_csr_tlbidx());
+	pr_info("PageSize : 0x%0x\n", read_csr_pagesize());
+	pr_info("EntryHi  : 0x%0*llx\n", field, read_csr_entryhi());
+	pr_info("EntryLo0 : 0x%0*llx\n", field, read_csr_entrylo0());
+	pr_info("EntryLo1 : 0x%0*llx\n", field, read_csr_entrylo1());
 }
 
 static void dump_tlb(int first, int last)
@@ -33,8 +33,8 @@ static void dump_tlb(int first, int last)
 	unsigned int s_index, s_asid;
 	unsigned int pagesize, c0, c1, i;
 	unsigned long asidmask = cpu_asid_mask(&current_cpu_data);
-	int pwidth = 11;
-	int vwidth = 11;
+	int pwidth = 16;
+	int vwidth = 16;
 	int asidwidth = DIV_ROUND_UP(ilog2(asidmask) + 1, 4);
 
 	s_entryhi = read_csr_entryhi();
@@ -64,22 +64,22 @@ static void dump_tlb(int first, int last)
 		/*
 		 * Only print entries in use
 		 */
-		pr_info("Index: %2d pgsize=%x ", i, (1 << pagesize));
+		pr_info("Index: %4d pgsize=0x%x ", i, (1 << pagesize));
 
 		c0 = (entrylo0 & ENTRYLO_C) >> ENTRYLO_C_SHIFT;
 		c1 = (entrylo1 & ENTRYLO_C) >> ENTRYLO_C_SHIFT;
 
-		pr_cont("va=%0*lx asid=%0*lx",
+		pr_cont("va=0x%0*lx asid=0x%0*lx",
 			vwidth, (entryhi & ~0x1fffUL), asidwidth, asid & asidmask);
 
 		/* NR/NX are in awkward places, so mask them off separately */
 		pa = entrylo0 & ~(ENTRYLO_NR | ENTRYLO_NX);
 		pa = pa & PAGE_MASK;
 		pr_cont("\n\t[");
-		pr_cont("ri=%d xi=%d ",
+		pr_cont("nr=%d nx=%d ",
 			(entrylo0 & ENTRYLO_NR) ? 1 : 0,
 			(entrylo0 & ENTRYLO_NX) ? 1 : 0);
-		pr_cont("pa=%0*llx c=%d d=%d v=%d g=%d plv=%lld] [",
+		pr_cont("pa=0x%0*llx c=%d d=%d v=%d g=%d plv=%lld] [",
 			pwidth, pa, c0,
 			(entrylo0 & ENTRYLO_D) ? 1 : 0,
 			(entrylo0 & ENTRYLO_V) ? 1 : 0,
@@ -88,10 +88,10 @@ static void dump_tlb(int first, int last)
 		/* NR/NX are in awkward places, so mask them off separately */
 		pa = entrylo1 & ~(ENTRYLO_NR | ENTRYLO_NX);
 		pa = pa & PAGE_MASK;
-		pr_cont("ri=%d xi=%d ",
+		pr_cont("nr=%d nx=%d ",
 			(entrylo1 & ENTRYLO_NR) ? 1 : 0,
 			(entrylo1 & ENTRYLO_NX) ? 1 : 0);
-		pr_cont("pa=%0*llx c=%d d=%d v=%d g=%d plv=%lld]\n",
+		pr_cont("pa=0x%0*llx c=%d d=%d v=%d g=%d plv=%lld]\n",
 			pwidth, pa, c1,
 			(entrylo1 & ENTRYLO_D) ? 1 : 0,
 			(entrylo1 & ENTRYLO_V) ? 1 : 0,
diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c
index 605579b19a00..1ccd53655cab 100644
--- a/arch/loongarch/mm/fault.c
+++ b/arch/loongarch/mm/fault.c
@@ -216,6 +216,10 @@ good_area:
 		return;
 	}
 
+	/* The fault is fully completed (including releasing mmap lock) */
+	if (fault & VM_FAULT_COMPLETED)
+		return;
+
 	if (unlikely(fault & VM_FAULT_RETRY)) {
 		flags |= FAULT_FLAG_TRIED;
 
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index 7094a68c9b83..0532ed5ba43d 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -131,18 +131,6 @@ int arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params)
 	return ret;
 }
 
-#ifdef CONFIG_NUMA
-int memory_add_physaddr_to_nid(u64 start)
-{
-	int nid;
-
-	nid = pa_to_nid(start);
-	return nid;
-}
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
-#endif
-
-#ifdef CONFIG_MEMORY_HOTREMOVE
 void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
@@ -154,6 +142,13 @@ void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 		page += vmem_altmap_offset(altmap);
 	__remove_pages(start_pfn, nr_pages, altmap);
 }
+
+#ifdef CONFIG_NUMA
+int memory_add_physaddr_to_nid(u64 start)
+{
+	return pa_to_nid(start);
+}
+EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
 #endif
 
diff --git a/arch/loongarch/mm/mmap.c b/arch/loongarch/mm/mmap.c
index 52e40f0ba732..381a569635a9 100644
--- a/arch/loongarch/mm/mmap.c
+++ b/arch/loongarch/mm/mmap.c
@@ -2,16 +2,9 @@
 /*
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
-#include <linux/compiler.h>
-#include <linux/elf-randomize.h>
-#include <linux/errno.h>
+#include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
-#include <linux/export.h>
-#include <linux/personality.h>
-#include <linux/random.h>
-#include <linux/sched/signal.h>
-#include <linux/sched/mm.h>
 
 unsigned long shm_align_mask = PAGE_SIZE - 1;	/* Sane caches */
 EXPORT_SYMBOL(shm_align_mask);
@@ -120,6 +113,6 @@ int __virt_addr_valid(volatile void *kaddr)
 	if ((vaddr < PAGE_OFFSET) || (vaddr >= vm_map_base))
 		return 0;
 
-	return pfn_valid(PFN_DOWN(virt_to_phys(kaddr)));
+	return pfn_valid(PFN_DOWN(PHYSADDR(kaddr)));
 }
 EXPORT_SYMBOL_GPL(__virt_addr_valid);
diff --git a/arch/loongarch/vdso/vgetcpu.c b/arch/loongarch/vdso/vgetcpu.c
index 43a0078e4418..e02e775f5360 100644
--- a/arch/loongarch/vdso/vgetcpu.c
+++ b/arch/loongarch/vdso/vgetcpu.c
@@ -24,6 +24,8 @@ static __always_inline const struct vdso_pcpu_data *get_pcpu_data(void)
 	return (struct vdso_pcpu_data *)(get_vdso_base() - VDSO_DATA_SIZE);
 }
 
+extern
+int __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused);
 int __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused)
 {
 	int cpu_id;
diff --git a/arch/loongarch/vdso/vgettimeofday.c b/arch/loongarch/vdso/vgettimeofday.c
index b1f4548dae92..8f22863bd7ea 100644
--- a/arch/loongarch/vdso/vgettimeofday.c
+++ b/arch/loongarch/vdso/vgettimeofday.c
@@ -6,20 +6,23 @@
  */
 #include <linux/types.h>
 
-int __vdso_clock_gettime(clockid_t clock,
-			 struct __kernel_timespec *ts)
+extern
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 {
 	return __cvdso_clock_gettime(clock, ts);
 }
 
-int __vdso_gettimeofday(struct __kernel_old_timeval *tv,
-			struct timezone *tz)
+extern
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
 	return __cvdso_gettimeofday(tv, tz);
 }
 
-int __vdso_clock_getres(clockid_t clock_id,
-			struct __kernel_timespec *res)
+extern
+int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res);
+int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res)
 {
 	return __cvdso_clock_getres(clock_id, res);
 }
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index b06faf6c0b27..7bff88118507 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -87,7 +87,7 @@ config MMU_SUN3
 
 config KEXEC
 	bool "kexec system call"
-	depends on M68KCLASSIC
+	depends on M68KCLASSIC && MMU
 	select KEXEC_CORE
 	help
 	  kexec is a system call that implements the ability to shutdown your
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index a6a886a89be2..e2038d9499e4 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -84,7 +84,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
@@ -573,9 +572,9 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
@@ -594,6 +593,7 @@ CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4_GENERIC=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index bffd24c2755e..ddd201259e43 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -80,7 +80,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
@@ -530,9 +529,9 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
@@ -551,6 +550,7 @@ CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4_GENERIC=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 0013425b1e08..d9f783707387 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -87,7 +87,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
@@ -550,9 +549,9 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
@@ -571,6 +570,7 @@ CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4_GENERIC=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 42d969697f7f..68957c6bcff1 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -77,7 +77,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
@@ -522,9 +521,9 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
@@ -543,6 +542,7 @@ CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4_GENERIC=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 97d6d9acb395..825c6a02fa9d 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -79,7 +79,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
@@ -532,9 +531,9 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
@@ -553,6 +552,7 @@ CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4_GENERIC=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 8cbfc1c659a3..17f64c562bf1 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -78,7 +78,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
@@ -552,9 +551,9 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
@@ -573,6 +572,7 @@ CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4_GENERIC=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 9f45fe60757f..f5f4c572b694 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -98,7 +98,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
@@ -638,9 +637,9 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
@@ -659,6 +658,7 @@ CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4_GENERIC=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 4736cfacf6a2..b4a0bbef7e39 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -76,7 +76,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
@@ -521,9 +520,9 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
@@ -542,6 +541,7 @@ CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4_GENERIC=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 638cd38aa7d2..c6a6d5926793 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -77,7 +77,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
@@ -522,9 +521,9 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
@@ -543,6 +542,7 @@ CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4_GENERIC=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index ec8b6bb70ebd..49c9c89f0caf 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -78,7 +78,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
@@ -539,9 +538,9 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
@@ -560,6 +559,7 @@ CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4_GENERIC=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 7d8dc578d59c..9b44eeb9c07f 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -74,7 +74,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
@@ -521,9 +520,9 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
@@ -542,6 +541,7 @@ CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4_GENERIC=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 96290aee5302..d2ffb0a65b44 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -74,7 +74,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
@@ -520,9 +519,9 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
@@ -541,6 +540,7 @@ CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_SM4_GENERIC=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h
index 470aed978590..e984af71df6b 100644
--- a/arch/m68k/include/asm/bitops.h
+++ b/arch/m68k/include/asm/bitops.h
@@ -157,11 +157,8 @@ arch___change_bit(unsigned long nr, volatile unsigned long *addr)
 	change_bit(nr, addr);
 }
 
-static __always_inline bool
-arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
-{
-	return (addr[nr >> 5] & (1UL << (nr & 31))) != 0;
-}
+#define arch_test_bit generic_test_bit
+#define arch_test_bit_acquire generic_test_bit_acquire
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
diff --git a/arch/m68k/include/uapi/asm/bootinfo-virt.h b/arch/m68k/include/uapi/asm/bootinfo-virt.h
index b091ee9b06e0..7dbcd7bec103 100644
--- a/arch/m68k/include/uapi/asm/bootinfo-virt.h
+++ b/arch/m68k/include/uapi/asm/bootinfo-virt.h
@@ -13,13 +13,8 @@
 #define BI_VIRT_VIRTIO_BASE	0x8004
 #define BI_VIRT_CTRL_BASE	0x8005
 
-/*
- * A random seed used to initialize the RNG. Record format:
- *
- *   - length       [ 2 bytes, 16-bit big endian ]
- *   - seed data    [ `length` bytes, padded to preserve 2-byte alignment ]
- */
-#define BI_VIRT_RNG_SEED	0x8006
+/* No longer used -- replaced with BI_RNG_SEED -- but don't reuse this index:
+ * #define BI_VIRT_RNG_SEED	0x8006 */
 
 #define VIRT_BOOTI_VERSION	MK_BI_VERSION(2, 0)
 
diff --git a/arch/m68k/include/uapi/asm/bootinfo.h b/arch/m68k/include/uapi/asm/bootinfo.h
index 95ecf3ae4c49..024e87d7095f 100644
--- a/arch/m68k/include/uapi/asm/bootinfo.h
+++ b/arch/m68k/include/uapi/asm/bootinfo.h
@@ -64,6 +64,13 @@ struct mem_info {
 					/* (struct mem_info) */
 #define BI_COMMAND_LINE		0x0007	/* kernel command line parameters */
 					/* (string) */
+/*
+ * A random seed used to initialize the RNG. Record format:
+ *
+ *   - length       [ 2 bytes, 16-bit big endian ]
+ *   - seed data    [ `length` bytes, padded to preserve 4-byte struct alignment ]
+ */
+#define BI_RNG_SEED		0x0008
 
 
     /*
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index e62fa8f2149b..3a2bb2e8fdad 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <linux/nvram.h>
 #include <linux/initrd.h>
+#include <linux/random.h>
 
 #include <asm/bootinfo.h>
 #include <asm/byteorder.h>
@@ -109,10 +110,9 @@ extern void paging_init(void);
 
 static void __init m68k_parse_bootinfo(const struct bi_record *record)
 {
+	const struct bi_record *first_record = record;
 	uint16_t tag;
 
-	save_bootinfo(record);
-
 	while ((tag = be16_to_cpu(record->tag)) != BI_LAST) {
 		int unknown = 0;
 		const void *data = record->data;
@@ -148,10 +148,21 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 			break;
 
 		case BI_COMMAND_LINE:
-			strlcpy(m68k_command_line, data,
+			strscpy(m68k_command_line, data,
 				sizeof(m68k_command_line));
 			break;
 
+		case BI_RNG_SEED: {
+			u16 len = be16_to_cpup(data);
+			add_bootloader_randomness(data + 2, len);
+			/*
+			 * Zero the data to preserve forward secrecy, and zero the
+			 * length to prevent kexec from using it.
+			 */
+			memzero_explicit((void *)data, len + 2);
+			break;
+		}
+
 		default:
 			if (MACH_IS_AMIGA)
 				unknown = amiga_parse_bootinfo(record);
@@ -182,6 +193,8 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 		record = (struct bi_record *)((unsigned long)record + size);
 	}
 
+	save_bootinfo(first_record);
+
 	m68k_realnum_memory = m68k_num_memory;
 #ifdef CONFIG_SINGLE_MEMORY_CHUNK
 	if (m68k_num_memory > 1) {
diff --git a/arch/m68k/virt/config.c b/arch/m68k/virt/config.c
index 4ab22946ff68..632ba200ad42 100644
--- a/arch/m68k/virt/config.c
+++ b/arch/m68k/virt/config.c
@@ -2,7 +2,6 @@
 
 #include <linux/reboot.h>
 #include <linux/serial_core.h>
-#include <linux/random.h>
 #include <clocksource/timer-goldfish.h>
 
 #include <asm/bootinfo.h>
@@ -93,16 +92,6 @@ int __init virt_parse_bootinfo(const struct bi_record *record)
 		data += 4;
 		virt_bi_data.virtio.irq = be32_to_cpup(data);
 		break;
-	case BI_VIRT_RNG_SEED: {
-		u16 len = be16_to_cpup(data);
-		add_bootloader_randomness(data + 2, len);
-		/*
-		 * Zero the data to preserve forward secrecy, and zero the
-		 * length to prevent kexec from using it.
-		 */
-		memzero_explicit((void *)data, len + 2);
-		break;
-	}
 	default:
 		unknown = 1;
 		break;
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index ec21f8999249..25dd4c5a8ef5 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2669,7 +2669,6 @@ config ARCH_FLATMEM_ENABLE
 
 config ARCH_SPARSEMEM_ENABLE
 	bool
-	select SPARSEMEM_STATIC if !SGI_IP27
 
 config NUMA
 	bool "NUMA Support"
diff --git a/arch/mips/bcm47xx/prom.c b/arch/mips/bcm47xx/prom.c
index ab203e66ba0d..a9bea411d928 100644
--- a/arch/mips/bcm47xx/prom.c
+++ b/arch/mips/bcm47xx/prom.c
@@ -86,7 +86,7 @@ static __init void prom_init_mem(void)
 			pr_debug("Assume 128MB RAM\n");
 			break;
 		}
-		if (!memcmp(prom_init, prom_init + mem, 32))
+		if (!memcmp((void *)prom_init, (void *)prom_init + mem, 32))
 			break;
 	}
 	lowmem = mem;
@@ -159,7 +159,7 @@ void __init bcm47xx_prom_highmem_init(void)
 
 	off = EXTVBASE + __pa(off);
 	for (extmem = 128 << 20; extmem < 512 << 20; extmem <<= 1) {
-		if (!memcmp(prom_init, (void *)(off + extmem), 16))
+		if (!memcmp((void *)prom_init, (void *)(off + extmem), 16))
 			break;
 	}
 	extmem -= lowmem;
diff --git a/arch/mips/boot/dts/brcm/bcm63268.dtsi b/arch/mips/boot/dts/brcm/bcm63268.dtsi
index c3ce49ec675f..8926417a8fbc 100644
--- a/arch/mips/boot/dts/brcm/bcm63268.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm63268.dtsi
@@ -105,14 +105,20 @@
 			interrupts = <2>, <3>;
 		};
 
-		wdt: watchdog@1000009c {
-			compatible = "brcm,bcm7038-wdt";
-			reg = <0x1000009c 0xc>;
+		timer-mfd@10000080 {
+			compatible = "brcm,bcm7038-twd", "simple-mfd", "syscon";
+			reg = <0x10000080 0x30>;
+			ranges = <0x0 0x10000080 0x30>;
 
-			clocks = <&periph_osc>;
-			clock-names = "refclk";
+			wdt: watchdog@1c {
+				compatible = "brcm,bcm7038-wdt";
+				reg = <0x1c 0xc>;
 
-			timeout-sec = <30>;
+				clocks = <&periph_osc>;
+				clock-names = "refclk";
+
+				timeout-sec = <30>;
+			};
 		};
 
 		uart0: serial@10000180 {
diff --git a/arch/mips/boot/dts/lantiq/Makefile b/arch/mips/boot/dts/lantiq/Makefile
index f5dfc06242b9..ae6e3e21ebeb 100644
--- a/arch/mips/boot/dts/lantiq/Makefile
+++ b/arch/mips/boot/dts/lantiq/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-dtb-$(CONFIG_DT_EASY50712)	+= easy50712.dtb
+dtb-$(CONFIG_DT_EASY50712)	+= danube_easy50712.dtb
 
 obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .o, $(dtb-y))
diff --git a/arch/mips/boot/dts/lantiq/easy50712.dts b/arch/mips/boot/dts/lantiq/danube_easy50712.dts
index 1ce20b7d05cb..1ce20b7d05cb 100644
--- a/arch/mips/boot/dts/lantiq/easy50712.dts
+++ b/arch/mips/boot/dts/lantiq/danube_easy50712.dts
diff --git a/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c b/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c
index bf13e35871b2..aa7bbf8d0df5 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-cmd-queue.c
@@ -57,14 +57,11 @@ EXPORT_SYMBOL_GPL(__cvmx_cmd_queue_state_ptr);
 static cvmx_cmd_queue_result_t __cvmx_cmd_queue_init_state_ptr(void)
 {
 	char *alloc_name = "cvmx_cmd_queues";
-#if defined(CONFIG_CAVIUM_RESERVE32) && CONFIG_CAVIUM_RESERVE32
 	extern uint64_t octeon_reserve32_memory;
-#endif
 
 	if (likely(__cvmx_cmd_queue_state_ptr))
 		return CVMX_CMD_QUEUE_SUCCESS;
 
-#if defined(CONFIG_CAVIUM_RESERVE32) && CONFIG_CAVIUM_RESERVE32
 	if (octeon_reserve32_memory)
 		__cvmx_cmd_queue_state_ptr =
 		    cvmx_bootmem_alloc_named_range(sizeof(*__cvmx_cmd_queue_state_ptr),
@@ -73,7 +70,6 @@ static cvmx_cmd_queue_result_t __cvmx_cmd_queue_init_state_ptr(void)
 						   (CONFIG_CAVIUM_RESERVE32 <<
 						    20) - 1, 128, alloc_name);
 	else
-#endif
 		__cvmx_cmd_queue_state_ptr =
 		    cvmx_bootmem_alloc_named(sizeof(*__cvmx_cmd_queue_state_ptr),
 					    128,
diff --git a/arch/mips/cavium-octeon/oct_ilm.c b/arch/mips/cavium-octeon/oct_ilm.c
index 6a4694538bb6..dc05262e85ff 100644
--- a/arch/mips/cavium-octeon/oct_ilm.c
+++ b/arch/mips/cavium-octeon/oct_ilm.c
@@ -28,7 +28,7 @@ struct latency_info {
 static struct latency_info li;
 static struct dentry *dir;
 
-static int show_latency(struct seq_file *m, void *v)
+static int oct_ilm_show(struct seq_file *m, void *v)
 {
 	u64 cpuclk, avg, max, min;
 	struct latency_info curr_li = li;
@@ -43,18 +43,7 @@ static int show_latency(struct seq_file *m, void *v)
 		   curr_li.interrupt_cnt, avg, max, min);
 	return 0;
 }
-
-static int oct_ilm_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, show_latency, NULL);
-}
-
-static const struct file_operations oct_ilm_ops = {
-	.open = oct_ilm_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(oct_ilm);
 
 static int reset_statistics(void *data, u64 value)
 {
@@ -67,7 +56,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(reset_statistics_ops, NULL, reset_statistics, "%llu\n")
 static void init_debugfs(void)
 {
 	dir = debugfs_create_dir("oct_ilm", 0);
-	debugfs_create_file("statistics", 0222, dir, NULL, &oct_ilm_ops);
+	debugfs_create_file("statistics", 0222, dir, NULL, &oct_ilm_fops);
 	debugfs_create_file("reset", 0222, dir, NULL, &reset_statistics_ops);
 }
 
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 9cb9ed44bcaf..fd8043f6ff8a 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -127,6 +127,16 @@ static void octeon_irq_free_cd(struct irq_domain *d, unsigned int irq)
 static int octeon_irq_force_ciu_mapping(struct irq_domain *domain,
 					int irq, int line, int bit)
 {
+	struct device_node *of_node;
+	int ret;
+
+	of_node = irq_domain_get_of_node(domain);
+	if (!of_node)
+		return -EINVAL;
+	ret = irq_alloc_desc_at(irq, of_node_to_nid(of_node));
+	if (ret < 0)
+		return ret;
+
 	return irq_domain_associate(domain, irq, line << 6 | bit);
 }
 
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index cbd83205518d..a71727f7a608 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -284,10 +284,8 @@ void octeon_crash_smp_send_stop(void)
 
 #endif /* CONFIG_KEXEC */
 
-#ifdef CONFIG_CAVIUM_RESERVE32
 uint64_t octeon_reserve32_memory;
 EXPORT_SYMBOL(octeon_reserve32_memory);
-#endif
 
 #ifdef CONFIG_KEXEC
 /* crashkernel cmdline parameter is parsed _after_ memory setup
@@ -532,7 +530,7 @@ void octeon_user_io_init(void)
 	/* Get the current settings for CP0_CVMMEMCTL_REG */
 	cvmmemctl.u64 = read_c0_cvmmemctl();
 	/* R/W If set, marked write-buffer entries time out the same
-	 * as as other entries; if clear, marked write-buffer entries
+	 * as other entries; if clear, marked write-buffer entries
 	 * use the maximum timeout. */
 	cvmmemctl.s.dismarkwblongto = 1;
 	/* R/W If set, a merged store does not clear the write-buffer
@@ -666,9 +664,6 @@ void __init prom_init(void)
 	int i;
 	u64 t;
 	int argc;
-#ifdef CONFIG_CAVIUM_RESERVE32
-	int64_t addr = -1;
-#endif
 	/*
 	 * The bootloader passes a pointer to the boot descriptor in
 	 * $a3, this is available as fw_arg3.
@@ -783,7 +778,7 @@ void __init prom_init(void)
 		cvmx_write_csr(CVMX_LED_UDD_DATX(1), 0);
 		cvmx_write_csr(CVMX_LED_EN, 1);
 	}
-#ifdef CONFIG_CAVIUM_RESERVE32
+
 	/*
 	 * We need to temporarily allocate all memory in the reserve32
 	 * region. This makes sure the kernel doesn't allocate this
@@ -794,14 +789,16 @@ void __init prom_init(void)
 	 * Allocate memory for RESERVED32 aligned on 2MB boundary. This
 	 * is in case we later use hugetlb entries with it.
 	 */
-	addr = cvmx_bootmem_phy_named_block_alloc(CONFIG_CAVIUM_RESERVE32 << 20,
-						0, 0, 2 << 20,
-						"CAVIUM_RESERVE32", 0);
-	if (addr < 0)
-		pr_err("Failed to allocate CAVIUM_RESERVE32 memory area\n");
-	else
-		octeon_reserve32_memory = addr;
-#endif
+	if (CONFIG_CAVIUM_RESERVE32) {
+		int64_t addr =
+			cvmx_bootmem_phy_named_block_alloc(CONFIG_CAVIUM_RESERVE32 << 20,
+							   0, 0, 2 << 20,
+							   "CAVIUM_RESERVE32", 0);
+		if (addr < 0)
+			pr_err("Failed to allocate CAVIUM_RESERVE32 memory area\n");
+		else
+			octeon_reserve32_memory = addr;
+	}
 
 #ifdef CONFIG_CAVIUM_OCTEON_LOCK_L2
 	if (cvmx_read_csr(CVMX_L2D_FUS3) & (3ull << 34)) {
@@ -1079,7 +1076,6 @@ void __init plat_mem_setup(void)
 	cvmx_bootmem_unlock();
 #endif /* CONFIG_CRASH_DUMP */
 
-#ifdef CONFIG_CAVIUM_RESERVE32
 	/*
 	 * Now that we've allocated the kernel memory it is safe to
 	 * free the reserved region. We free it here so that builtin
@@ -1087,7 +1083,6 @@ void __init plat_mem_setup(void)
 	 */
 	if (octeon_reserve32_memory)
 		cvmx_bootmem_free_named("CAVIUM_RESERVE32");
-#endif /* CONFIG_CAVIUM_RESERVE32 */
 
 	if (total == 0)
 		panic("Unable to allocate memory from "
diff --git a/arch/mips/configs/ar7_defconfig b/arch/mips/configs/ar7_defconfig
index cf9c6329b807..ed4a6388791e 100644
--- a/arch/mips/configs/ar7_defconfig
+++ b/arch/mips/configs/ar7_defconfig
@@ -32,9 +32,6 @@ CONFIG_IP_ROUTE_MULTIPATH=y
 CONFIG_IP_ROUTE_VERBOSE=y
 CONFIG_IP_MROUTE=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_INET_DIAG is not set
 CONFIG_TCP_CONG_ADVANCED=y
 # CONFIG_TCP_CONG_BIC is not set
@@ -117,7 +114,6 @@ CONFIG_JFFS2_SUMMARY=y
 CONFIG_JFFS2_COMPRESSION_OPTIONS=y
 CONFIG_SQUASHFS=y
 # CONFIG_CRYPTO_HW is not set
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_FS=y
 CONFIG_CMDLINE_BOOL=y
diff --git a/arch/mips/configs/ath25_defconfig b/arch/mips/configs/ath25_defconfig
index 7143441f5476..afd1c16242e9 100644
--- a/arch/mips/configs/ath25_defconfig
+++ b/arch/mips/configs/ath25_defconfig
@@ -29,9 +29,6 @@ CONFIG_UNIX=y
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_ADVANCED_ROUTER=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
 CONFIG_CFG80211=m
 CONFIG_MAC80211=m
@@ -108,7 +105,6 @@ CONFIG_SQUASHFS_XZ=y
 # CONFIG_XZ_DEC_ARMTHUMB is not set
 # CONFIG_XZ_DEC_SPARC is not set
 CONFIG_PRINTK_TIME=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_FS=y
 # CONFIG_SCHED_DEBUG is not set
diff --git a/arch/mips/configs/ath79_defconfig b/arch/mips/configs/ath79_defconfig
index 96622a2ad333..0b741716c852 100644
--- a/arch/mips/configs/ath79_defconfig
+++ b/arch/mips/configs/ath79_defconfig
@@ -10,12 +10,6 @@ CONFIG_EMBEDDED=y
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_COMPAT_BRK is not set
 CONFIG_ATH79=y
-CONFIG_ATH79_MACH_AP121=y
-CONFIG_ATH79_MACH_AP136=y
-CONFIG_ATH79_MACH_AP81=y
-CONFIG_ATH79_MACH_DB120=y
-CONFIG_ATH79_MACH_PB44=y
-CONFIG_ATH79_MACH_UBNT_XM=y
 CONFIG_HZ_100=y
 # CONFIG_SECCOMP is not set
 CONFIG_PCI=y
@@ -29,9 +23,6 @@ CONFIG_UNIX=y
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_ADVANCED_ROUTER=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
 CONFIG_CFG80211=m
 CONFIG_MAC80211=m
@@ -92,7 +83,6 @@ CONFIG_LEDS_GPIO=y
 # CONFIG_DNOTIFY is not set
 # CONFIG_PROC_PAGE_MONITOR is not set
 CONFIG_CRC_ITU_T=m
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_FS=y
 # CONFIG_SCHED_DEBUG is not set
diff --git a/arch/mips/configs/bcm63xx_defconfig b/arch/mips/configs/bcm63xx_defconfig
index 861f680184b9..34d0ca638ef0 100644
--- a/arch/mips/configs/bcm63xx_defconfig
+++ b/arch/mips/configs/bcm63xx_defconfig
@@ -24,9 +24,6 @@ CONFIG_PCMCIA_BCM63XX=y
 CONFIG_NET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 CONFIG_CFG80211=y
diff --git a/arch/mips/configs/bigsur_defconfig b/arch/mips/configs/bigsur_defconfig
index d83e7d600b0a..d15961f00ece 100644
--- a/arch/mips/configs/bigsur_defconfig
+++ b/arch/mips/configs/bigsur_defconfig
@@ -49,8 +49,6 @@ CONFIG_IP_PIMSM_V2=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_TCP_MD5SIG=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_IPV6_ROUTE_INFO=y
@@ -59,7 +57,6 @@ CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_MIP6=m
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
 CONFIG_IPV6_SIT_6RD=y
 CONFIG_IPV6_TUNNEL=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
@@ -101,7 +98,6 @@ CONFIG_BAYCOM_SER_HDX=m
 CONFIG_YAM=m
 CONFIG_FW_LOADER=m
 CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_EEPROM_LEGACY=y
 CONFIG_EEPROM_MAX6875=y
@@ -230,12 +226,8 @@ CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
@@ -243,7 +235,6 @@ CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/mips/configs/bmips_be_defconfig b/arch/mips/configs/bmips_be_defconfig
index 032bb51defe8..daef132d000b 100644
--- a/arch/mips/configs/bmips_be_defconfig
+++ b/arch/mips/configs/bmips_be_defconfig
@@ -17,9 +17,6 @@ CONFIG_PACKET=y
 CONFIG_PACKET_DIAG=y
 CONFIG_UNIX=y
 CONFIG_INET=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_INET_DIAG is not set
 CONFIG_CFG80211=y
 CONFIG_NL80211_TESTMODE=y
diff --git a/arch/mips/configs/bmips_stb_defconfig b/arch/mips/configs/bmips_stb_defconfig
index 5956fb95c19f..cd0dc37c3d84 100644
--- a/arch/mips/configs/bmips_stb_defconfig
+++ b/arch/mips/configs/bmips_stb_defconfig
@@ -12,7 +12,6 @@ CONFIG_HIGHMEM=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=4
-CONFIG_CC_STACKPROTECTOR_STRONG=y
 # CONFIG_SECCOMP is not set
 CONFIG_MIPS_O32_FP64_SUPPORT=y
 # CONFIG_RD_GZIP is not set
@@ -21,8 +20,6 @@ CONFIG_MIPS_O32_FP64_SUPPORT=y
 CONFIG_RD_XZ=y
 # CONFIG_RD_LZO is not set
 # CONFIG_RD_LZ4 is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_PCI=y
 CONFIG_PCI_MSI=y
 CONFIG_PCIEASPM_POWERSAVE=y
@@ -30,7 +27,6 @@ CONFIG_PCIEPORTBUS=y
 CONFIG_PCIE_BRCMSTB=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_STAT=y
-CONFIG_CPU_FREQ_STAT_DETAILS=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
 CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
@@ -44,15 +40,11 @@ CONFIG_PACKET=y
 CONFIG_PACKET_DIAG=y
 CONFIG_UNIX=y
 CONFIG_INET=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_INET_DIAG is not set
 CONFIG_CFG80211=y
 CONFIG_NL80211_TESTMODE=y
 CONFIG_WIRELESS=y
 CONFIG_MAC80211=y
-CONFIG_NL80211=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_STANDALONE is not set
@@ -70,10 +62,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_IP_MROUTE=y
 CONFIG_IP_PIMSM_V1=y
 CONFIG_IP_PIMSM_V2=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 CONFIG_INET_UDP_DIAG=y
 CONFIG_TCP_CONG_ADVANCED=y
 CONFIG_TCP_CONG_BIC=y
@@ -93,7 +81,6 @@ CONFIG_NET_SWITCHDEV=y
 CONFIG_DMA_CMA=y
 CONFIG_CMA_ALIGNMENT=12
 CONFIG_SPI=y
-CONFIG_SPI_BRCMSTB=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
@@ -105,14 +92,11 @@ CONFIG_MTD_CFI_STAA=y
 CONFIG_MTD_ROM=y
 CONFIG_MTD_ABSENT=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_M25P80=y
-CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_BRCMNAND=y
 CONFIG_MTD_SPI_NOR=y
 # CONFIG_MTD_SPI_NOR_USE_4K_SECTORS is not set
 CONFIG_MTD_UBI=y
 CONFIG_MTD_UBI_GLUEBI=y
-CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
@@ -120,7 +104,6 @@ CONFIG_BLK_DEV_RAM_SIZE=8192
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_MULTI_LUN=y
 # CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_NETDEVICES=y
 CONFIG_VLAN_8021Q=y
@@ -135,7 +118,6 @@ CONFIG_INPUT_UINPUT=y
 # CONFIG_SERIO is not set
 CONFIG_VT=y
 CONFIG_VT_HW_CONSOLE_BINDING=y
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
 CONFIG_SERIAL_8250_CONSOLE=y
@@ -203,17 +185,14 @@ CONFIG_CMDLINE="earlycon"
 CONFIG_MIPS_CMDLINE_DTB_EXTEND=y
 # CONFIG_MIPS_CMDLINE_FROM_BOOTLOADER is not set
 # CONFIG_CRYPTO_HW is not set
-CONFIG_DT_BCM974XX=y
 CONFIG_FW_CFE=y
 CONFIG_ATA=y
 CONFIG_SATA_AHCI_PLATFORM=y
-CONFIG_AHCI_BRCMSTB=y
 CONFIG_GENERIC_PHY=y
 CONFIG_GPIOLIB=y
 CONFIG_GPIO_SYSFS=y
 CONFIG_PHY_BRCM_USB=y
 CONFIG_PHY_BRCM_SATA=y
-CONFIG_PM_RUNTIME=y
 CONFIG_PM_DEBUG=y
 CONFIG_SYSVIPC=y
 CONFIG_FUNCTION_GRAPH_TRACER=y
@@ -227,3 +206,5 @@ CONFIG_FTRACE_SYSCALLS=y
 CONFIG_TRACER_SNAPSHOT=y
 CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
 CONFIG_STACK_TRACER=y
+CONFIG_AHCI_BRCM=y
+CONFIG_MTD_RAW_NAND=y
diff --git a/arch/mips/configs/cavium_octeon_defconfig b/arch/mips/configs/cavium_octeon_defconfig
index 97ceaf080c0c..a2311495af79 100644
--- a/arch/mips/configs/cavium_octeon_defconfig
+++ b/arch/mips/configs/cavium_octeon_defconfig
@@ -71,7 +71,6 @@ CONFIG_NETDEVICES=y
 # CONFIG_NET_VENDOR_DEC is not set
 # CONFIG_NET_VENDOR_DLINK is not set
 # CONFIG_NET_VENDOR_EMULEX is not set
-# CONFIG_NET_VENDOR_HP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MELLANOX is not set
diff --git a/arch/mips/configs/db1xxx_defconfig b/arch/mips/configs/db1xxx_defconfig
index b8bd66300996..a8b62df3c021 100644
--- a/arch/mips/configs/db1xxx_defconfig
+++ b/arch/mips/configs/db1xxx_defconfig
@@ -61,7 +61,6 @@ CONFIG_INET6_AH=y
 CONFIG_INET6_ESP=y
 CONFIG_INET6_IPCOMP=y
 CONFIG_IPV6_MIP6=y
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=y
 CONFIG_IPV6_VTI=y
 CONFIG_IPV6_SIT_6RD=y
 CONFIG_IPV6_GRE=y
diff --git a/arch/mips/configs/decstation_64_defconfig b/arch/mips/configs/decstation_64_defconfig
index 0021427a1bbe..4f74c4bde9f6 100644
--- a/arch/mips/configs/decstation_64_defconfig
+++ b/arch/mips/configs/decstation_64_defconfig
@@ -37,9 +37,6 @@ CONFIG_SYN_COOKIES=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_TCP_MD5SIG=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_IPV6_ROUTE_INFO=y
@@ -47,7 +44,6 @@ CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_MIP6=m
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_IPV6_SUBTREES=y
 CONFIG_NETWORK_SECMARK=y
@@ -79,7 +75,6 @@ CONFIG_NETDEVICES=y
 CONFIG_DECLANCE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_VENDOR_AURORA is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_CADENCE is not set
 # CONFIG_NET_VENDOR_CAVIUM is not set
@@ -193,12 +188,8 @@ CONFIG_CRYPTO_CRC32=m
 CONFIG_CRYPTO_CRCT10DIF=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_ARC4=m
@@ -208,7 +199,6 @@ CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/mips/configs/decstation_defconfig b/arch/mips/configs/decstation_defconfig
index 7a97a0818ce4..f0d0546ea1e5 100644
--- a/arch/mips/configs/decstation_defconfig
+++ b/arch/mips/configs/decstation_defconfig
@@ -33,9 +33,6 @@ CONFIG_SYN_COOKIES=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_TCP_MD5SIG=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_IPV6_ROUTE_INFO=y
@@ -43,7 +40,6 @@ CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_MIP6=m
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_IPV6_SUBTREES=y
 CONFIG_NETWORK_SECMARK=y
@@ -75,7 +71,6 @@ CONFIG_NETDEVICES=y
 CONFIG_DECLANCE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_VENDOR_AURORA is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_CADENCE is not set
 # CONFIG_NET_VENDOR_CAVIUM is not set
@@ -188,12 +183,8 @@ CONFIG_CRYPTO_CRC32=m
 CONFIG_CRYPTO_CRCT10DIF=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_ARC4=m
@@ -203,7 +194,6 @@ CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/mips/configs/decstation_r4k_defconfig b/arch/mips/configs/decstation_r4k_defconfig
index a0643363526d..df5ff9ddf8f4 100644
--- a/arch/mips/configs/decstation_r4k_defconfig
+++ b/arch/mips/configs/decstation_r4k_defconfig
@@ -32,9 +32,6 @@ CONFIG_SYN_COOKIES=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_TCP_MD5SIG=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_IPV6_ROUTE_INFO=y
@@ -42,7 +39,6 @@ CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_MIP6=m
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_IPV6_SUBTREES=y
 CONFIG_NETWORK_SECMARK=y
@@ -74,7 +70,6 @@ CONFIG_NETDEVICES=y
 CONFIG_DECLANCE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_VENDOR_AURORA is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_CADENCE is not set
 # CONFIG_NET_VENDOR_CAVIUM is not set
@@ -188,12 +183,8 @@ CONFIG_CRYPTO_CRC32=m
 CONFIG_CRYPTO_CRCT10DIF=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_ARC4=m
@@ -203,7 +194,6 @@ CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig
index ba47c5e929b7..843d6a5a4f61 100644
--- a/arch/mips/configs/fuloong2e_defconfig
+++ b/arch/mips/configs/fuloong2e_defconfig
@@ -35,8 +35,6 @@ CONFIG_IP_MULTICAST=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_NET_IPIP=m
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 CONFIG_NETFILTER=y
@@ -92,7 +90,6 @@ CONFIG_MTD_CFI_AMDSTD=m
 CONFIG_MTD_CFI_STAA=m
 CONFIG_MTD_PHYSMAP=m
 CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_RAM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
@@ -159,7 +156,6 @@ CONFIG_USB_MOUSE=y
 CONFIG_USB=y
 CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
 CONFIG_USB_OTG_PRODUCTLIST=y
-CONFIG_USB_WUSB_CBAF=m
 CONFIG_USB_C67X00_HCD=m
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_ROOT_HUB_TT=y
@@ -219,15 +215,10 @@ CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_HMAC=y
-CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
-CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_DEFLATE=m
 CONFIG_CRYPTO_LZO=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC_CCITT=y
 CONFIG_CRC7=m
-# CONFIG_ENABLE_MUST_CHECK is not set
diff --git a/arch/mips/configs/generic/board-ocelot.config b/arch/mips/configs/generic/board-ocelot.config
index 510709565404..8cfbafa532e0 100644
--- a/arch/mips/configs/generic/board-ocelot.config
+++ b/arch/mips/configs/generic/board-ocelot.config
@@ -25,7 +25,6 @@ CONFIG_NETDEVICES=y
 CONFIG_NET_SWITCHDEV=y
 CONFIG_NET_DSA=y
 CONFIG_MSCC_OCELOT_SWITCH=y
-CONFIG_MSCC_OCELOT_SWITCH_OCELOT=y
 CONFIG_MDIO_MSCC_MIIM=y
 CONFIG_MICROSEMI_PHY=y
 
diff --git a/arch/mips/configs/gpr_defconfig b/arch/mips/configs/gpr_defconfig
index d82f4ebf687f..7cd321b47d01 100644
--- a/arch/mips/configs/gpr_defconfig
+++ b/arch/mips/configs/gpr_defconfig
@@ -29,9 +29,6 @@ CONFIG_IP_ROUTE_VERBOSE=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
 CONFIG_NETWORK_SECMARK=y
 CONFIG_NETFILTER=y
@@ -220,9 +217,6 @@ CONFIG_HDLC_X25=m
 CONFIG_PCI200SYN=m
 CONFIG_WANXL=m
 CONFIG_FARSYNC=m
-CONFIG_DSCC4=m
-CONFIG_DSCC4_PCISYNC=y
-CONFIG_DSCC4_PCI_RST=y
 CONFIG_LAPBETHER=m
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
@@ -288,7 +282,6 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
@@ -299,7 +292,6 @@ CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_DEFLATE=m
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="console=ttyS0,115200 root=/dev/nfs rw ip=auto"
diff --git a/arch/mips/configs/ip22_defconfig b/arch/mips/configs/ip22_defconfig
index 70a4ba90f491..13df29901237 100644
--- a/arch/mips/configs/ip22_defconfig
+++ b/arch/mips/configs/ip22_defconfig
@@ -36,9 +36,6 @@ CONFIG_IP_PNP_BOOTP=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_TCP_MD5SIG=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_IPV6_ROUTE_INFO=y
@@ -47,7 +44,6 @@ CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_MIP6=m
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
 CONFIG_IPV6_TUNNEL=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_IPV6_SUBTREES=y
@@ -226,7 +222,6 @@ CONFIG_SERIO_RAW=m
 CONFIG_VT_HW_CONSOLE_BINDING=y
 CONFIG_SERIAL_IP22_ZILOG=m
 # CONFIG_HW_RANDOM is not set
-CONFIG_RAW_DRIVER=m
 # CONFIG_HWMON is not set
 CONFIG_THERMAL=y
 CONFIG_WATCHDOG=y
@@ -320,11 +315,7 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_XCBC=m
-CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
@@ -333,7 +324,6 @@ CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig
index 821630ac1be7..3e86f8106ba0 100644
--- a/arch/mips/configs/ip27_defconfig
+++ b/arch/mips/configs/ip27_defconfig
@@ -33,9 +33,6 @@ CONFIG_NET_KEY_MIGRATE=y
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_PNP=y
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_TCP_MD5SIG=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_IPV6_ROUTE_INFO=y
@@ -44,10 +41,6 @@ CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_MIP6=m
-CONFIG_INET6_XFRM_MODE_TRANSPORT=m
-CONFIG_INET6_XFRM_MODE_TUNNEL=m
-CONFIG_INET6_XFRM_MODE_BEET=m
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
 CONFIG_IPV6_SIT=m
 CONFIG_IPV6_SIT_6RD=y
 CONFIG_IPV6_TUNNEL=m
@@ -92,7 +85,6 @@ CONFIG_CFG80211=m
 CONFIG_MAC80211=m
 CONFIG_RFKILL=m
 CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_SCSI=y
@@ -115,7 +107,6 @@ CONFIG_SCSI_AIC94XX=m
 # CONFIG_AIC94XX_DEBUG is not set
 CONFIG_SCSI_MVSAS=m
 # CONFIG_SCSI_MVSAS_DEBUG is not set
-CONFIG_SCSI_DPT_I2O=m
 CONFIG_SCSI_MPT2SAS=m
 CONFIG_LIBFC=m
 CONFIG_SCSI_QLOGIC_1280=y
@@ -126,8 +117,6 @@ CONFIG_SCSI_DH_RDAC=m
 CONFIG_SCSI_DH_HP_SW=m
 CONFIG_SCSI_DH_EMC=m
 CONFIG_SCSI_DH_ALUA=m
-CONFIG_SCSI_OSD_INITIATOR=m
-CONFIG_SCSI_OSD_ULD=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 CONFIG_MD_LINEAR=m
@@ -166,7 +155,6 @@ CONFIG_JME=m
 CONFIG_MLX4_EN=m
 # CONFIG_MLX4_DEBUG is not set
 CONFIG_KS8851_MLL=m
-CONFIG_VXGE=m
 CONFIG_AX88796=m
 CONFIG_AX88796_93CX6=y
 CONFIG_ETHOC=m
@@ -264,7 +252,6 @@ CONFIG_I2C_VIAPRO=m
 CONFIG_I2C_OCORES=m
 CONFIG_I2C_PCA_PLATFORM=m
 CONFIG_I2C_SIMTEC=m
-CONFIG_I2C_PARPORT_LIGHT=m
 CONFIG_I2C_TAOS_EVM=m
 CONFIG_I2C_STUB=m
 # CONFIG_HWMON is not set
@@ -309,7 +296,6 @@ CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_SQUASHFS=m
 CONFIG_OMFS_FS=m
-CONFIG_EXOFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_SECURITYFS=y
 CONFIG_CRYPTO_CRYPTD=m
@@ -321,12 +307,8 @@ CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_MD4=m
-CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
@@ -335,7 +317,6 @@ CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/mips/configs/ip28_defconfig b/arch/mips/configs/ip28_defconfig
index 0921ef38e9fb..ba13eea0509f 100644
--- a/arch/mips/configs/ip28_defconfig
+++ b/arch/mips/configs/ip28_defconfig
@@ -29,9 +29,6 @@ CONFIG_IP_MULTICAST=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 CONFIG_TCP_MD5SIG=y
 # CONFIG_IPV6 is not set
 CONFIG_SCSI=y
diff --git a/arch/mips/configs/ip32_defconfig b/arch/mips/configs/ip32_defconfig
index 74020aa3440b..8ced2224c328 100644
--- a/arch/mips/configs/ip32_defconfig
+++ b/arch/mips/configs/ip32_defconfig
@@ -43,7 +43,6 @@ CONFIG_IPV6_TUNNEL=m
 CONFIG_NETWORK_SECMARK=y
 CONFIG_CONNECTOR=y
 CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_RAID_ATTRS=y
 CONFIG_SCSI=y
@@ -165,7 +164,6 @@ CONFIG_CRYPTO_MICHAEL_MIC=y
 CONFIG_CRYPTO_SHA1=y
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
-CONFIG_CRYPTO_TGR192=y
 CONFIG_CRYPTO_WP512=y
 CONFIG_CRYPTO_ANUBIS=y
 CONFIG_CRYPTO_ARC4=y
diff --git a/arch/mips/configs/jazz_defconfig b/arch/mips/configs/jazz_defconfig
index 843f360da5f2..106b21cb677f 100644
--- a/arch/mips/configs/jazz_defconfig
+++ b/arch/mips/configs/jazz_defconfig
@@ -32,7 +32,6 @@ CONFIG_PARPORT_1284=y
 CONFIG_DEVTMPFS=y
 CONFIG_BLK_DEV_FD=m
 CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=m
 CONFIG_CDROM_PKTCDVD=m
diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig
index 791894c4d8fb..7e598d338979 100644
--- a/arch/mips/configs/lemote2f_defconfig
+++ b/arch/mips/configs/lemote2f_defconfig
@@ -43,9 +43,6 @@ CONFIG_IP_MROUTE=y
 CONFIG_IP_PIMSM_V1=y
 CONFIG_IP_PIMSM_V2=y
 CONFIG_SYN_COOKIES=y
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_TCP_CONG_ADVANCED=y
 CONFIG_TCP_CONG_BIC=y
 CONFIG_DEFAULT_BIC=y
@@ -77,7 +74,6 @@ CONFIG_MAC80211_LEDS=y
 CONFIG_RFKILL=m
 CONFIG_RFKILL_INPUT=y
 CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
 CONFIG_BLK_DEV_SD=y
@@ -312,12 +308,8 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA1=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
@@ -326,7 +318,6 @@ CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SEED=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m
diff --git a/arch/mips/configs/loongson1b_defconfig b/arch/mips/configs/loongson1b_defconfig
index 25e70423e17d..68207b31dc20 100644
--- a/arch/mips/configs/loongson1b_defconfig
+++ b/arch/mips/configs/loongson1b_defconfig
@@ -28,9 +28,6 @@ CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
@@ -115,7 +112,6 @@ CONFIG_NLS_ISO8859_1=m
 # CONFIG_CRYPTO_ECHAINIV is not set
 # CONFIG_CRYPTO_HW is not set
 CONFIG_DYNAMIC_DEBUG=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_DEBUG_FS=y
 CONFIG_MAGIC_SYSRQ=y
 # CONFIG_SCHED_DEBUG is not set
diff --git a/arch/mips/configs/loongson1c_defconfig b/arch/mips/configs/loongson1c_defconfig
index 3a158d4d2fab..c3910a9dee9e 100644
--- a/arch/mips/configs/loongson1c_defconfig
+++ b/arch/mips/configs/loongson1c_defconfig
@@ -29,9 +29,6 @@ CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
@@ -116,7 +113,6 @@ CONFIG_NLS_ISO8859_1=m
 # CONFIG_CRYPTO_ECHAINIV is not set
 # CONFIG_CRYPTO_HW is not set
 CONFIG_DYNAMIC_DEBUG=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_DEBUG_FS=y
 CONFIG_MAGIC_SYSRQ=y
 # CONFIG_SCHED_DEBUG is not set
diff --git a/arch/mips/configs/loongson2k_defconfig b/arch/mips/configs/loongson2k_defconfig
index e948ca487e2d..728bef666f7a 100644
--- a/arch/mips/configs/loongson2k_defconfig
+++ b/arch/mips/configs/loongson2k_defconfig
@@ -95,7 +95,6 @@ CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_MTD=m
 CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
 CONFIG_RAID_ATTRS=m
@@ -229,7 +228,6 @@ CONFIG_SERIAL_8250_RSA=y
 CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_NONSTANDARD=y
 CONFIG_HW_RANDOM=y
-CONFIG_RAW_DRIVER=m
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_PIIX4=y
 CONFIG_GPIO_LOONGSON=y
@@ -336,7 +334,6 @@ CONFIG_DEFAULT_SECURITY_DAC=y
 CONFIG_CRYPTO_SEQIV=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAST5=m
diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig
index 25ecd15bc952..aca66a5f330d 100644
--- a/arch/mips/configs/loongson3_defconfig
+++ b/arch/mips/configs/loongson3_defconfig
@@ -143,7 +143,6 @@ CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_MTD=m
 CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
 CONFIG_VIRTIO_BLK=y
@@ -268,7 +267,6 @@ CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_NONSTANDARD=y
 CONFIG_VIRTIO_CONSOLE=y
 CONFIG_HW_RANDOM=y
-CONFIG_RAW_DRIVER=m
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_PIIX4=y
 CONFIG_GPIO_LOONGSON=y
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index 7a5bdd236a2a..265d38dffbf6 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -42,8 +42,6 @@ CONFIG_SYN_COOKIES=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_TCP_MD5SIG=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_IPV6_ROUTE_INFO=y
@@ -229,7 +227,6 @@ CONFIG_MTD_UBI=m
 CONFIG_MTD_UBI_GLUEBI=m
 CONFIG_BLK_DEV_FD=m
 CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_CDROM_PKTCDVD=m
@@ -237,7 +234,6 @@ CONFIG_ATA_OVER_ETH=m
 CONFIG_RAID_ATTRS=m
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_ST=m
-CONFIG_CHR_DEV_OSST=m
 CONFIG_BLK_DEV_SR=y
 CONFIG_CHR_DEV_SG=m
 CONFIG_SCSI_CONSTANTS=y
@@ -408,7 +404,6 @@ CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig
index b5ba08d7ab57..1d2b248c7cd3 100644
--- a/arch/mips/configs/malta_kvm_defconfig
+++ b/arch/mips/configs/malta_kvm_defconfig
@@ -46,8 +46,6 @@ CONFIG_SYN_COOKIES=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_TCP_MD5SIG=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_IPV6_ROUTE_INFO=y
@@ -233,7 +231,6 @@ CONFIG_MTD_UBI=m
 CONFIG_MTD_UBI_GLUEBI=m
 CONFIG_BLK_DEV_FD=m
 CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_CDROM_PKTCDVD=m
@@ -241,7 +238,6 @@ CONFIG_ATA_OVER_ETH=m
 CONFIG_RAID_ATTRS=m
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_ST=m
-CONFIG_CHR_DEV_OSST=m
 CONFIG_BLK_DEV_SR=y
 CONFIG_CHR_DEV_SG=m
 CONFIG_SCSI_CONSTANTS=y
@@ -415,7 +411,6 @@ CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
diff --git a/arch/mips/configs/malta_qemu_32r6_defconfig b/arch/mips/configs/malta_qemu_32r6_defconfig
index 6fb9bc29f4a0..fd63a2b152f6 100644
--- a/arch/mips/configs/malta_qemu_32r6_defconfig
+++ b/arch/mips/configs/malta_qemu_32r6_defconfig
@@ -76,7 +76,6 @@ CONFIG_NET_ACT_POLICE=y
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_SG=y
 # CONFIG_SCSI_LOWLEVEL is not set
@@ -98,7 +97,6 @@ CONFIG_PCNET32=y
 # CONFIG_NET_VENDOR_DEC is not set
 # CONFIG_NET_VENDOR_DLINK is not set
 # CONFIG_NET_VENDOR_EMULEX is not set
-# CONFIG_NET_VENDOR_HP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MELLANOX is not set
@@ -172,7 +170,6 @@ CONFIG_NLS_ISO8859_1=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
diff --git a/arch/mips/configs/maltaaprp_defconfig b/arch/mips/configs/maltaaprp_defconfig
index eb72df528243..1f07e354c954 100644
--- a/arch/mips/configs/maltaaprp_defconfig
+++ b/arch/mips/configs/maltaaprp_defconfig
@@ -78,7 +78,6 @@ CONFIG_NET_ACT_POLICE=y
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_SG=y
 # CONFIG_SCSI_LOWLEVEL is not set
@@ -100,7 +99,6 @@ CONFIG_PCNET32=y
 # CONFIG_NET_VENDOR_DEC is not set
 # CONFIG_NET_VENDOR_DLINK is not set
 # CONFIG_NET_VENDOR_EMULEX is not set
-# CONFIG_NET_VENDOR_HP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MELLANOX is not set
@@ -173,7 +171,6 @@ CONFIG_NLS_ISO8859_1=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
diff --git a/arch/mips/configs/maltasmvp_defconfig b/arch/mips/configs/maltasmvp_defconfig
index 1fb40d310f49..5cd3eca236de 100644
--- a/arch/mips/configs/maltasmvp_defconfig
+++ b/arch/mips/configs/maltasmvp_defconfig
@@ -79,7 +79,6 @@ CONFIG_NET_ACT_POLICE=y
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_SG=y
 # CONFIG_SCSI_LOWLEVEL is not set
@@ -99,7 +98,6 @@ CONFIG_PCNET32=y
 # CONFIG_NET_VENDOR_DEC is not set
 # CONFIG_NET_VENDOR_DLINK is not set
 # CONFIG_NET_VENDOR_EMULEX is not set
-# CONFIG_NET_VENDOR_HP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MELLANOX is not set
@@ -174,7 +172,6 @@ CONFIG_NLS_ISO8859_1=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
diff --git a/arch/mips/configs/maltasmvp_eva_defconfig b/arch/mips/configs/maltasmvp_eva_defconfig
index 75cb778c6149..45688e742a15 100644
--- a/arch/mips/configs/maltasmvp_eva_defconfig
+++ b/arch/mips/configs/maltasmvp_eva_defconfig
@@ -80,7 +80,6 @@ CONFIG_NET_ACT_POLICE=y
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_SG=y
 # CONFIG_SCSI_LOWLEVEL is not set
@@ -102,7 +101,6 @@ CONFIG_PCNET32=y
 # CONFIG_NET_VENDOR_DEC is not set
 # CONFIG_NET_VENDOR_DLINK is not set
 # CONFIG_NET_VENDOR_EMULEX is not set
-# CONFIG_NET_VENDOR_HP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MELLANOX is not set
@@ -176,7 +174,6 @@ CONFIG_NLS_ISO8859_1=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
diff --git a/arch/mips/configs/maltaup_defconfig b/arch/mips/configs/maltaup_defconfig
index 7b4f247dc60c..136f965784db 100644
--- a/arch/mips/configs/maltaup_defconfig
+++ b/arch/mips/configs/maltaup_defconfig
@@ -77,7 +77,6 @@ CONFIG_NET_ACT_POLICE=y
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_SG=y
 # CONFIG_SCSI_LOWLEVEL is not set
@@ -99,7 +98,6 @@ CONFIG_PCNET32=y
 # CONFIG_NET_VENDOR_DEC is not set
 # CONFIG_NET_VENDOR_DLINK is not set
 # CONFIG_NET_VENDOR_EMULEX is not set
-# CONFIG_NET_VENDOR_HP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MELLANOX is not set
@@ -172,7 +170,6 @@ CONFIG_NLS_ISO8859_1=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig
index 8d58653f1b4e..75b8da8d9927 100644
--- a/arch/mips/configs/maltaup_xpa_defconfig
+++ b/arch/mips/configs/maltaup_xpa_defconfig
@@ -45,8 +45,6 @@ CONFIG_SYN_COOKIES=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_TCP_MD5SIG=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_IPV6_ROUTE_INFO=y
@@ -231,7 +229,6 @@ CONFIG_MTD_UBI=m
 CONFIG_MTD_UBI_GLUEBI=m
 CONFIG_BLK_DEV_FD=m
 CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_CDROM_PKTCDVD=m
@@ -239,7 +236,6 @@ CONFIG_ATA_OVER_ETH=m
 CONFIG_RAID_ATTRS=m
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_ST=m
-CONFIG_CHR_DEV_OSST=m
 CONFIG_BLK_DEV_SR=y
 CONFIG_CHR_DEV_SG=m
 CONFIG_SCSI_CONSTANTS=y
@@ -414,7 +410,6 @@ CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig
index 4194e79b435c..efbfaa539938 100644
--- a/arch/mips/configs/mtx1_defconfig
+++ b/arch/mips/configs/mtx1_defconfig
@@ -58,13 +58,9 @@ CONFIG_SYN_COOKIES=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
 CONFIG_IPV6_TUNNEL=m
 CONFIG_NETWORK_SECMARK=y
 CONFIG_NETFILTER=y
@@ -284,7 +280,6 @@ CONFIG_PCMCIA_XIRCOM=m
 CONFIG_DL2K=m
 CONFIG_SUNDANCE=m
 CONFIG_PCMCIA_FMVJ18X=m
-CONFIG_HP100=m
 CONFIG_E100=m
 CONFIG_E1000=m
 CONFIG_IXGB=m
@@ -368,9 +363,6 @@ CONFIG_HDLC_X25=m
 CONFIG_PCI200SYN=m
 CONFIG_WANXL=m
 CONFIG_FARSYNC=m
-CONFIG_DSCC4=m
-CONFIG_DSCC4_PCISYNC=y
-CONFIG_DSCC4_PCI_RST=y
 CONFIG_LAPBETHER=m
 # CONFIG_KEYBOARD_ATKBD is not set
 CONFIG_KEYBOARD_GPIO=y
@@ -683,7 +675,6 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_MD5=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
@@ -692,5 +683,4 @@ CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/mips/configs/omega2p_defconfig b/arch/mips/configs/omega2p_defconfig
index fc39ddf610a9..9c34daf83563 100644
--- a/arch/mips/configs/omega2p_defconfig
+++ b/arch/mips/configs/omega2p_defconfig
@@ -35,9 +35,6 @@ CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
diff --git a/arch/mips/configs/pic32mzda_defconfig b/arch/mips/configs/pic32mzda_defconfig
index fd567247adc7..48dd02d01ac1 100644
--- a/arch/mips/configs/pic32mzda_defconfig
+++ b/arch/mips/configs/pic32mzda_defconfig
@@ -45,7 +45,6 @@ CONFIG_KEYBOARD_GPIO_POLLED=m
 CONFIG_SERIAL_PIC32=y
 CONFIG_SERIAL_PIC32_CONSOLE=y
 CONFIG_HW_RANDOM=y
-CONFIG_RAW_DRIVER=m
 CONFIG_GPIO_SYSFS=y
 # CONFIG_HWMON is not set
 CONFIG_HIDRAW=y
diff --git a/arch/mips/configs/rb532_defconfig b/arch/mips/configs/rb532_defconfig
index 252d472387aa..93306f5e045b 100644
--- a/arch/mips/configs/rb532_defconfig
+++ b/arch/mips/configs/rb532_defconfig
@@ -33,9 +33,6 @@ CONFIG_IP_MULTIPLE_TABLES=y
 CONFIG_IP_ROUTE_MULTIPATH=y
 CONFIG_IP_ROUTE_VERBOSE=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 CONFIG_INET_DIAG=m
 CONFIG_TCP_CONG_ADVANCED=y
 CONFIG_TCP_CONG_CUBIC=m
@@ -162,5 +159,4 @@ CONFIG_SQUASHFS=y
 CONFIG_CRYPTO_TEST=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC16=m
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
diff --git a/arch/mips/configs/rbtx49xx_defconfig b/arch/mips/configs/rbtx49xx_defconfig
index f8212a813be7..30c195f28278 100644
--- a/arch/mips/configs/rbtx49xx_defconfig
+++ b/arch/mips/configs/rbtx49xx_defconfig
@@ -21,9 +21,6 @@ CONFIG_UNIX=y
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_PNP=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
 CONFIG_MTD=y
@@ -51,7 +48,6 @@ CONFIG_TC35815=y
 CONFIG_SERIAL_TXX9_CONSOLE=y
 CONFIG_SERIAL_TXX9_STDSERIAL=y
 CONFIG_SPI=y
-CONFIG_SPI_TXX9=y
 # CONFIG_HWMON is not set
 CONFIG_WATCHDOG=y
 CONFIG_TXX9_WDT=m
@@ -65,8 +61,6 @@ CONFIG_SND=m
 # CONFIG_SND_SPI is not set
 # CONFIG_SND_MIPS is not set
 CONFIG_SND_SOC=m
-CONFIG_SND_SOC_TXX9ACLC=m
-CONFIG_SND_SOC_TXX9ACLC_GENERIC=m
 # CONFIG_USB_SUPPORT is not set
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
@@ -78,7 +72,6 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_INTF_DEV_UIE_EMUL=y
 CONFIG_RTC_DRV_RS5C348=y
 CONFIG_RTC_DRV_DS1742=y
-CONFIG_RTC_DRV_TX4939=y
 CONFIG_DMADEVICES=y
 CONFIG_TXX9_DMAC=m
 # CONFIG_DNOTIFY is not set
diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig
index 7d6f235e8ccb..d6981855221b 100644
--- a/arch/mips/configs/rm200_defconfig
+++ b/arch/mips/configs/rm200_defconfig
@@ -29,9 +29,6 @@ CONFIG_NET_IPIP=m
 CONFIG_IP_MROUTE=y
 CONFIG_IP_PIMSM_V1=y
 CONFIG_IP_PIMSM_V2=y
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_TCP_MD5SIG=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_IPV6_ROUTE_INFO=y
@@ -39,7 +36,6 @@ CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_MIP6=m
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
 CONFIG_IPV6_TUNNEL=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_IPV6_SUBTREES=y
@@ -192,9 +188,7 @@ CONFIG_PARIDE_KTTI=m
 CONFIG_PARIDE_ON20=m
 CONFIG_PARIDE_ON26=m
 CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_SX8=m
 CONFIG_BLK_DEV_RAM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
@@ -400,7 +394,6 @@ CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_BLOWFISH=m
diff --git a/arch/mips/configs/rt305x_defconfig b/arch/mips/configs/rt305x_defconfig
index eb359db15dba..bf017d493002 100644
--- a/arch/mips/configs/rt305x_defconfig
+++ b/arch/mips/configs/rt305x_defconfig
@@ -35,9 +35,6 @@ CONFIG_IP_ROUTE_VERBOSE=y
 CONFIG_IP_MROUTE=y
 CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_INET_DIAG is not set
 CONFIG_TCP_CONG_ADVANCED=y
 # CONFIG_TCP_CONG_BIC is not set
@@ -140,7 +137,6 @@ CONFIG_CRC32_SARWATE=y
 # CONFIG_XZ_DEC_ARMTHUMB is not set
 # CONFIG_XZ_DEC_SPARC is not set
 CONFIG_PRINTK_TIME=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_FS=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/mips/configs/sb1250_swarm_defconfig b/arch/mips/configs/sb1250_swarm_defconfig
index de94bf756a93..030186f89501 100644
--- a/arch/mips/configs/sb1250_swarm_defconfig
+++ b/arch/mips/configs/sb1250_swarm_defconfig
@@ -88,7 +88,6 @@ CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAMELLIA=m
@@ -96,7 +95,6 @@ CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
-CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_SERPENT=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_DEFLATE=m
diff --git a/arch/mips/configs/vocore2_defconfig b/arch/mips/configs/vocore2_defconfig
index a14f8ea5c386..0722a3bf03c0 100644
--- a/arch/mips/configs/vocore2_defconfig
+++ b/arch/mips/configs/vocore2_defconfig
@@ -35,9 +35,6 @@ CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
diff --git a/arch/mips/configs/xway_defconfig b/arch/mips/configs/xway_defconfig
index eeb689f715cb..eb5acf1f24ae 100644
--- a/arch/mips/configs/xway_defconfig
+++ b/arch/mips/configs/xway_defconfig
@@ -37,9 +37,6 @@ CONFIG_IP_ROUTE_VERBOSE=y
 CONFIG_IP_MROUTE=y
 CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
 CONFIG_SYN_COOKIES=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_INET_DIAG is not set
 CONFIG_TCP_CONG_ADVANCED=y
 # CONFIG_TCP_CONG_BIC is not set
@@ -146,7 +143,6 @@ CONFIG_CRYPTO_ARC4=m
 CONFIG_CRC_ITU_T=m
 CONFIG_CRC32_SARWATE=y
 CONFIG_PRINTK_TIME=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_FS=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h
index 57561e0e6e8d..44f9824c1d8c 100644
--- a/arch/mips/include/asm/irq.h
+++ b/arch/mips/include/asm/irq.h
@@ -63,10 +63,6 @@ extern void do_domain_IRQ(struct irq_domain *domain, unsigned int irq);
 extern void arch_init_irq(void);
 extern void spurious_interrupt(void);
 
-extern int allocate_irqno(void);
-extern void alloc_legacy_irqno(void);
-extern void free_irqno(unsigned int irq);
-
 /*
  * Before R2 the timer and performance counter interrupts were both fixed to
  * IE7.	 Since R2 their number has to be read from the c0_intctl register.
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 717716cc51c5..5cedb28e8a40 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -84,8 +84,6 @@
 
 
 #define KVM_MAX_VCPUS		16
-/* memory slots that does not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS	0
 
 #define KVM_HALT_POLL_NS_DEFAULT 500000
 
diff --git a/arch/mips/include/asm/mach-ar7/ar7.h b/arch/mips/include/asm/mach-ar7/ar7.h
index cbe75ade3277..1e8621a6afa3 100644
--- a/arch/mips/include/asm/mach-ar7/ar7.h
+++ b/arch/mips/include/asm/mach-ar7/ar7.h
@@ -104,8 +104,6 @@ struct plat_dsl_data {
 	int reset_bit_sar;
 };
 
-extern int ar7_cpu_clock, ar7_bus_clock, ar7_dsp_clock;
-
 static inline int ar7_is_titan(void)
 {
 	return (readl((void *)KSEG1ADDR(AR7_REGS_GPIO + 0x24)) & 0xffff) ==
diff --git a/arch/mips/include/asm/octeon/cvmx-fpa.h b/arch/mips/include/asm/octeon/cvmx-fpa.h
index 29ae63606ab4..f6dfcca97f19 100644
--- a/arch/mips/include/asm/octeon/cvmx-fpa.h
+++ b/arch/mips/include/asm/octeon/cvmx-fpa.h
@@ -264,26 +264,6 @@ static inline void cvmx_fpa_free(void *ptr, uint64_t pool,
 }
 
 /**
- * Setup a FPA pool to control a new block of memory.
- * This can only be called once per pool. Make sure proper
- * locking enforces this.
- *
- * @pool:	Pool to initialize
- *		     0 <= pool < 8
- * @name:	Constant character string to name this pool.
- *		     String is not copied.
- * @buffer:	Pointer to the block of memory to use. This must be
- *		     accessible by all processors and external hardware.
- * @block_size: Size for each block controlled by the FPA
- * @num_blocks: Number of blocks
- *
- * Returns 0 on Success,
- *	   -1 on failure
- */
-extern int cvmx_fpa_setup_pool(uint64_t pool, const char *name, void *buffer,
-			       uint64_t block_size, uint64_t num_blocks);
-
-/**
  * Shutdown a Memory pool and validate that it had all of
  * the buffers originally placed in it. This should only be
  * called by one processor after all hardware has finished
diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h
index 7e714aefc76d..5c1d726c702f 100644
--- a/arch/mips/include/asm/octeon/octeon.h
+++ b/arch/mips/include/asm/octeon/octeon.h
@@ -43,7 +43,6 @@ extern int octeon_get_southbridge_interrupt(void);
 extern int octeon_get_boot_coremask(void);
 extern int octeon_get_boot_num_arguments(void);
 extern const char *octeon_get_boot_argument(int arg);
-extern void octeon_hal_setup_reserved32(void);
 extern void octeon_user_io_init(void);
 
 extern void octeon_init_cvmcount(void);
diff --git a/arch/mips/include/asm/octeon/pci-octeon.h b/arch/mips/include/asm/octeon/pci-octeon.h
index b12d9a3fbfb6..2f46f6c6e3d0 100644
--- a/arch/mips/include/asm/octeon/pci-octeon.h
+++ b/arch/mips/include/asm/octeon/pci-octeon.h
@@ -64,6 +64,4 @@ enum octeon_dma_bar_type {
 extern enum octeon_dma_bar_type octeon_dma_bar_type;
 
 void octeon_pci_dma_init(void);
-extern char *octeon_swiotlb;
-
 #endif
diff --git a/arch/mips/include/asm/sibyte/sb1250.h b/arch/mips/include/asm/sibyte/sb1250.h
index dbde5f93f0dd..495b31925ed7 100644
--- a/arch/mips/include/asm/sibyte/sb1250.h
+++ b/arch/mips/include/asm/sibyte/sb1250.h
@@ -32,7 +32,6 @@ extern unsigned int soc_type;
 extern unsigned int periph_rev;
 extern unsigned int zbbus_mhz;
 
-extern void sb1250_time_init(void);
 extern void sb1250_mask_irq(int cpu, int irq);
 extern void sb1250_unmask_irq(int cpu, int irq);
 
diff --git a/arch/mips/include/asm/sni.h b/arch/mips/include/asm/sni.h
index 7dfa297ce597..7fb6656a6bfd 100644
--- a/arch/mips/include/asm/sni.h
+++ b/arch/mips/include/asm/sni.h
@@ -226,9 +226,6 @@ extern void sni_pcit_cplus_irq_init(void);
 extern void sni_rm200_irq_init(void);
 extern void sni_pcimt_irq_init(void);
 
-/* timer inits */
-extern void sni_cpu_time_init(void);
-
 /* eisa init for RM200/400 */
 #ifdef CONFIG_EISA
 extern int sni_eisa_root_init(void);
diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c
index 7db6ff9aed7d..f88ce78e13e3 100644
--- a/arch/mips/kernel/prom.c
+++ b/arch/mips/kernel/prom.c
@@ -26,7 +26,7 @@ __init void mips_set_machine_name(const char *name)
 	if (name == NULL)
 		return;
 
-	strlcpy(mips_machine_name, name, sizeof(mips_machine_name));
+	strscpy(mips_machine_name, name, sizeof(mips_machine_name));
 	pr_info("MIPS: machine is %s\n", mips_get_machine_name());
 }
 
@@ -52,9 +52,9 @@ int __init __dt_register_buses(const char *bus0, const char *bus1)
 	if (!of_have_populated_dt())
 		panic("device tree not present");
 
-	strlcpy(of_ids[0].compatible, bus0, sizeof(of_ids[0].compatible));
+	strscpy(of_ids[0].compatible, bus0, sizeof(of_ids[0].compatible));
 	if (bus1) {
-		strlcpy(of_ids[1].compatible, bus1,
+		strscpy(of_ids[1].compatible, bus1,
 			sizeof(of_ids[1].compatible));
 	}
 
diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c
index 56b51de2dc51..58fc8d089402 100644
--- a/arch/mips/kernel/relocate.c
+++ b/arch/mips/kernel/relocate.c
@@ -340,7 +340,7 @@ void *__init relocate_kernel(void)
 	early_init_dt_scan(fdt);
 	if (boot_command_line[0]) {
 		/* Boot command line was passed in device tree */
-		strlcpy(arcs_cmdline, boot_command_line, COMMAND_LINE_SIZE);
+		strscpy(arcs_cmdline, boot_command_line, COMMAND_LINE_SIZE);
 	}
 #endif /* CONFIG_USE_OF */
 
diff --git a/arch/mips/kernel/segment.c b/arch/mips/kernel/segment.c
index 0a9bd7b0983b..24560501c70d 100644
--- a/arch/mips/kernel/segment.c
+++ b/arch/mips/kernel/segment.c
@@ -46,7 +46,7 @@ static void build_segment_config(char *str, unsigned int cfg)
 		((cfg & MIPS_SEGCFG_EU) >> MIPS_SEGCFG_EU_SHIFT));
 }
 
-static int show_segments(struct seq_file *m, void *v)
+static int segments_show(struct seq_file *m, void *v)
 {
 	unsigned int segcfg;
 	char str[42];
@@ -80,18 +80,7 @@ static int show_segments(struct seq_file *m, void *v)
 
 	return 0;
 }
-
-static int segments_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, show_segments, NULL);
-}
-
-static const struct file_operations segments_fops = {
-	.open		= segments_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(segments);
 
 static int __init segments_info(void)
 {
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 2ca156a5b231..39c79f67c7a3 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -42,6 +42,7 @@
 #include <asm/setup.h>
 #include <asm/smp-ops.h>
 #include <asm/prom.h>
+#include <asm/fw/fw.h>
 
 #ifdef CONFIG_MIPS_ELF_APPENDED_DTB
 char __section(".appended_dtb") __appended_dtb[0x100000];
@@ -756,6 +757,24 @@ static void __init prefill_possible_map(void)
 static inline void prefill_possible_map(void) {}
 #endif
 
+static void __init setup_rng_seed(void)
+{
+	char *rng_seed_hex = fw_getenv("rngseed");
+	u8 rng_seed[512];
+	size_t len;
+
+	if (!rng_seed_hex)
+		return;
+
+	len = min(sizeof(rng_seed), strlen(rng_seed_hex) / 2);
+	if (hex2bin(rng_seed, rng_seed_hex, len))
+		return;
+
+	add_bootloader_randomness(rng_seed, len);
+	memzero_explicit(rng_seed, len);
+	memzero_explicit(rng_seed_hex, len * 2);
+}
+
 void __init setup_arch(char **cmdline_p)
 {
 	cpu_probe();
@@ -786,6 +805,8 @@ void __init setup_arch(char **cmdline_p)
 	paging_init();
 
 	memblock_dump_all();
+
+	setup_rng_seed();
 }
 
 unsigned long kernelsp[NR_CPUS];
diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c
index db17e870bdff..74cd64a24d05 100644
--- a/arch/mips/kvm/mmu.c
+++ b/arch/mips/kvm/mmu.c
@@ -615,17 +615,17 @@ retry:
 	 * Used to check for invalidations in progress, of the pfn that is
 	 * returned by pfn_to_pfn_prot below.
 	 */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	/*
-	 * Ensure the read of mmu_notifier_seq isn't reordered with PTE reads in
-	 * gfn_to_pfn_prot() (which calls get_user_pages()), so that we don't
+	 * Ensure the read of mmu_invalidate_seq isn't reordered with PTE reads
+	 * in gfn_to_pfn_prot() (which calls get_user_pages()), so that we don't
 	 * risk the page we get a reference to getting unmapped before we have a
-	 * chance to grab the mmu_lock without mmu_notifier_retry() noticing.
+	 * chance to grab the mmu_lock without mmu_invalidate_retry() noticing.
 	 *
 	 * This smp_rmb() pairs with the effective smp_wmb() of the combination
 	 * of the pte_unmap_unlock() after the PTE is zapped, and the
 	 * spin_lock() in kvm_mmu_notifier_invalidate_<page|range_end>() before
-	 * mmu_notifier_seq is incremented.
+	 * mmu_invalidate_seq is incremented.
 	 */
 	smp_rmb();
 
@@ -638,7 +638,7 @@ retry:
 
 	spin_lock(&kvm->mmu_lock);
 	/* Check if an invalidation has taken place since we got pfn */
-	if (mmu_notifier_retry(kvm, mmu_seq)) {
+	if (mmu_invalidate_retry(kvm, mmu_seq)) {
 		/*
 		 * This can happen when mappings are changed asynchronously, but
 		 * also synchronously if a COW is triggered by
diff --git a/arch/mips/lantiq/clk.c b/arch/mips/lantiq/clk.c
index 7a623684d9b5..2d5a0bcb0cec 100644
--- a/arch/mips/lantiq/clk.c
+++ b/arch/mips/lantiq/clk.c
@@ -50,6 +50,7 @@ struct clk *clk_get_io(void)
 {
 	return &cpu_clk_generic[2];
 }
+EXPORT_SYMBOL_GPL(clk_get_io);
 
 struct clk *clk_get_ppe(void)
 {
diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c
index c731082a0c42..be4829cc7a3a 100644
--- a/arch/mips/lantiq/prom.c
+++ b/arch/mips/lantiq/prom.c
@@ -34,6 +34,14 @@ unsigned long physical_memsize = 0L;
  */
 static struct ltq_soc_info soc_info;
 
+/*
+ * These structs are used to override vsmp_init_secondary()
+ */
+#if defined(CONFIG_MIPS_MT_SMP)
+extern const struct plat_smp_ops vsmp_smp_ops;
+static struct plat_smp_ops lantiq_smp_ops;
+#endif
+
 const char *get_system_type(void)
 {
 	return soc_info.sys_type;
@@ -84,6 +92,17 @@ void __init plat_mem_setup(void)
 	__dt_setup_arch(dtb);
 }
 
+#if defined(CONFIG_MIPS_MT_SMP)
+static void lantiq_init_secondary(void)
+{
+	/*
+	 * MIPS CPU startup function vsmp_init_secondary() will only
+	 * enable some of the interrupts for the second CPU/VPE.
+	 */
+	set_c0_status(ST0_IM);
+}
+#endif
+
 void __init prom_init(void)
 {
 	/* call the soc specific detetcion code and get it to fill soc_info */
@@ -95,7 +114,10 @@ void __init prom_init(void)
 	prom_init_cmdline();
 
 #if defined(CONFIG_MIPS_MT_SMP)
-	if (register_vsmp_smp_ops())
-		panic("failed to register_vsmp_smp_ops()");
+	if (cpu_has_mipsmt) {
+		lantiq_smp_ops = vsmp_smp_ops;
+		lantiq_smp_ops.init_secondary = lantiq_init_secondary;
+		register_smp_ops(&lantiq_smp_ops);
+	}
 #endif
 }
diff --git a/arch/mips/lantiq/xway/vmmc.c b/arch/mips/lantiq/xway/vmmc.c
index 7a14da8d9d15..2796e87dfcae 100644
--- a/arch/mips/lantiq/xway/vmmc.c
+++ b/arch/mips/lantiq/xway/vmmc.c
@@ -4,9 +4,10 @@
  *  Copyright (C) 2012 John Crispin <john@phrozen.org>
  */
 
+#include <linux/err.h>
 #include <linux/export.h>
+#include <linux/gpio/consumer.h>
 #include <linux/of_platform.h>
-#include <linux/of_gpio.h>
 #include <linux/dma-mapping.h>
 
 #include <lantiq_soc.h>
@@ -25,23 +26,28 @@ EXPORT_SYMBOL(ltq_get_cp1_base);
 static int vmmc_probe(struct platform_device *pdev)
 {
 #define CP1_SIZE       (1 << 20)
+	struct gpio_desc *gpio;
 	int gpio_count;
 	dma_addr_t dma;
+	int error;
 
 	cp1_base =
 		(void *) CPHYSADDR(dma_alloc_coherent(&pdev->dev, CP1_SIZE,
 						    &dma, GFP_KERNEL));
 
-	gpio_count = of_gpio_count(pdev->dev.of_node);
+	gpio_count = gpiod_count(&pdev->dev, NULL);
 	while (gpio_count > 0) {
-		enum of_gpio_flags flags;
-		int gpio = of_get_gpio_flags(pdev->dev.of_node,
-					     --gpio_count, &flags);
-		if (gpio_request(gpio, "vmmc-relay"))
+		gpio = devm_gpiod_get_index(&pdev->dev,
+					    NULL, --gpio_count, GPIOD_OUT_HIGH);
+		error = PTR_ERR_OR_ZERO(gpio);
+		if (error) {
+			dev_err(&pdev->dev,
+				"failed to request GPIO idx %d: %d\n",
+				gpio_count, error);
 			continue;
-		dev_info(&pdev->dev, "requested GPIO %d\n", gpio);
-		gpio_direction_output(gpio,
-				      (flags & OF_GPIO_ACTIVE_LOW) ? (0) : (1));
+		}
+
+		gpiod_set_consumer_name(gpio, "vmmc-relay");
 	}
 
 	dev_info(&pdev->dev, "reserved %dMB at 0x%p", CP1_SIZE >> 20, cp1_base);
diff --git a/arch/mips/lib/bswapdi.c b/arch/mips/lib/bswapdi.c
index fcef74084492..88242dc7de17 100644
--- a/arch/mips/lib/bswapdi.c
+++ b/arch/mips/lib/bswapdi.c
@@ -1,17 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/export.h>
 #include <linux/compiler.h>
+#include <uapi/linux/swab.h>
+
+/* To silence -Wmissing-prototypes. */
+unsigned long long __bswapdi2(unsigned long long u);
 
 unsigned long long notrace __bswapdi2(unsigned long long u)
 {
-	return (((u) & 0xff00000000000000ull) >> 56) |
-	       (((u) & 0x00ff000000000000ull) >> 40) |
-	       (((u) & 0x0000ff0000000000ull) >> 24) |
-	       (((u) & 0x000000ff00000000ull) >>  8) |
-	       (((u) & 0x00000000ff000000ull) <<  8) |
-	       (((u) & 0x0000000000ff0000ull) << 24) |
-	       (((u) & 0x000000000000ff00ull) << 40) |
-	       (((u) & 0x00000000000000ffull) << 56);
+	return ___constant_swab64(u);
 }
-
 EXPORT_SYMBOL(__bswapdi2);
diff --git a/arch/mips/lib/bswapsi.c b/arch/mips/lib/bswapsi.c
index 22d8e4f6d66e..2ed655497de5 100644
--- a/arch/mips/lib/bswapsi.c
+++ b/arch/mips/lib/bswapsi.c
@@ -1,13 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/export.h>
 #include <linux/compiler.h>
+#include <uapi/linux/swab.h>
+
+/* To silence -Wmissing-prototypes. */
+unsigned int __bswapsi2(unsigned int u);
 
 unsigned int notrace __bswapsi2(unsigned int u)
 {
-	return (((u) & 0xff000000) >> 24) |
-	       (((u) & 0x00ff0000) >>  8) |
-	       (((u) & 0x0000ff00) <<  8) |
-	       (((u) & 0x000000ff) << 24);
+	return ___constant_swab32(u);
 }
-
 EXPORT_SYMBOL(__bswapsi2);
diff --git a/arch/mips/loongson2ef/common/pci.c b/arch/mips/loongson2ef/common/pci.c
index 200916925e95..7d9ea51e8c01 100644
--- a/arch/mips/loongson2ef/common/pci.c
+++ b/arch/mips/loongson2ef/common/pci.c
@@ -73,8 +73,6 @@ static void __init setup_pcimap(void)
 #endif
 }
 
-extern int sbx00_acpi_init(void);
-
 static int __init pcibios_init(void)
 {
 	setup_pcimap();
diff --git a/arch/mips/loongson32/common/platform.c b/arch/mips/loongson32/common/platform.c
index 794c96c2a4cd..311dc1580bbd 100644
--- a/arch/mips/loongson32/common/platform.c
+++ b/arch/mips/loongson32/common/platform.c
@@ -98,7 +98,7 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv)
 	if (plat_dat->bus_id) {
 		__raw_writel(__raw_readl(LS1X_MUX_CTRL0) | GMAC1_USE_UART1 |
 			     GMAC1_USE_UART0, LS1X_MUX_CTRL0);
-		switch (plat_dat->interface) {
+		switch (plat_dat->phy_interface) {
 		case PHY_INTERFACE_MODE_RGMII:
 			val &= ~(GMAC1_USE_TXCLK | GMAC1_USE_PWM23);
 			break;
@@ -107,12 +107,12 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv)
 			break;
 		default:
 			pr_err("unsupported mii mode %d\n",
-			       plat_dat->interface);
+			       plat_dat->phy_interface);
 			return -ENOTSUPP;
 		}
 		val &= ~GMAC1_SHUT;
 	} else {
-		switch (plat_dat->interface) {
+		switch (plat_dat->phy_interface) {
 		case PHY_INTERFACE_MODE_RGMII:
 			val &= ~(GMAC0_USE_TXCLK | GMAC0_USE_PWM01);
 			break;
@@ -121,7 +121,7 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv)
 			break;
 		default:
 			pr_err("unsupported mii mode %d\n",
-			       plat_dat->interface);
+			       plat_dat->phy_interface);
 			return -ENOTSUPP;
 		}
 		val &= ~GMAC0_SHUT;
@@ -131,7 +131,7 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv)
 	plat_dat = dev_get_platdata(&pdev->dev);
 
 	val &= ~PHY_INTF_SELI;
-	if (plat_dat->interface == PHY_INTERFACE_MODE_RMII)
+	if (plat_dat->phy_interface == PHY_INTERFACE_MODE_RMII)
 		val |= 0x4 << PHY_INTF_SELI_SHIFT;
 	__raw_writel(val, LS1X_MUX_CTRL1);
 
@@ -146,9 +146,9 @@ static struct plat_stmmacenet_data ls1x_eth0_pdata = {
 	.bus_id			= 0,
 	.phy_addr		= -1,
 #if defined(CONFIG_LOONGSON1_LS1B)
-	.interface		= PHY_INTERFACE_MODE_MII,
+	.phy_interface		= PHY_INTERFACE_MODE_MII,
 #elif defined(CONFIG_LOONGSON1_LS1C)
-	.interface		= PHY_INTERFACE_MODE_RMII,
+	.phy_interface		= PHY_INTERFACE_MODE_RMII,
 #endif
 	.mdio_bus_data		= &ls1x_mdio_bus_data,
 	.dma_cfg		= &ls1x_eth_dma_cfg,
@@ -186,7 +186,7 @@ struct platform_device ls1x_eth0_pdev = {
 static struct plat_stmmacenet_data ls1x_eth1_pdata = {
 	.bus_id			= 1,
 	.phy_addr		= -1,
-	.interface		= PHY_INTERFACE_MODE_MII,
+	.phy_interface		= PHY_INTERFACE_MODE_MII,
 	.mdio_bus_data		= &ls1x_mdio_bus_data,
 	.dma_cfg		= &ls1x_eth_dma_cfg,
 	.has_gmac		= 1,
diff --git a/arch/mips/loongson32/ls1c/board.c b/arch/mips/loongson32/ls1c/board.c
index e9de6da0ce51..9dcfe9de55b0 100644
--- a/arch/mips/loongson32/ls1c/board.c
+++ b/arch/mips/loongson32/ls1c/board.c
@@ -15,7 +15,6 @@ static struct platform_device *ls1c_platform_devices[] __initdata = {
 static int __init ls1c_platform_init(void)
 {
 	ls1x_serial_set_uartclk(&ls1x_uart_pdev);
-	ls1x_rtc_set_extclk(&ls1x_rtc_pdev);
 
 	return platform_add_devices(ls1c_platform_devices,
 				   ARRAY_SIZE(ls1c_platform_devices));
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 587cf1d115e8..265bc57819df 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -1032,7 +1032,7 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 	 */
 	if (dec_insn.micro_mips_mode) {
 		/*
-		 * If next instruction is a 16-bit instruction, then it
+		 * If next instruction is a 16-bit instruction, then
 		 * it cannot be a FPU instruction. This could happen
 		 * since we can be called for non-FPU instructions.
 		 */
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index 30e0922f4cea..e17d862cfa4c 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -2,7 +2,7 @@
 /*
  */
 
-/**
+/*
  * Both AR2315 and AR2316 chips have PCI interface unit, which supports DMA
  * and interrupt. PCI interface supports MMIO access method, but does not
  * seem to support I/O ports.
diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c
index 1ca42f482130..8d16cd021f60 100644
--- a/arch/mips/pci/pci-lantiq.c
+++ b/arch/mips/pci/pci-lantiq.c
@@ -9,11 +9,11 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/delay.h>
+#include <linux/gpio/consumer.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/clk.h>
 #include <linux/of_platform.h>
-#include <linux/of_gpio.h>
 #include <linux/of_irq.h>
 #include <linux/of_pci.h>
 
@@ -62,7 +62,7 @@
 __iomem void *ltq_pci_mapped_cfg;
 static __iomem void *ltq_pci_membase;
 
-static int reset_gpio;
+static struct gpio_desc *reset_gpio;
 static struct clk *clk_pci, *clk_external;
 static struct resource pci_io_resource;
 static struct resource pci_mem_resource;
@@ -95,6 +95,7 @@ static int ltq_pci_startup(struct platform_device *pdev)
 	struct device_node *node = pdev->dev.of_node;
 	const __be32 *req_mask, *bus_clk;
 	u32 temp_buffer;
+	int error;
 
 	/* get our clocks */
 	clk_pci = clk_get(&pdev->dev, NULL);
@@ -123,17 +124,14 @@ static int ltq_pci_startup(struct platform_device *pdev)
 		clk_disable(clk_external);
 
 	/* setup reset gpio used by pci */
-	reset_gpio = of_get_named_gpio(node, "gpio-reset", 0);
-	if (gpio_is_valid(reset_gpio)) {
-		int ret = devm_gpio_request(&pdev->dev,
-						reset_gpio, "pci-reset");
-		if (ret) {
-			dev_err(&pdev->dev,
-				"failed to request gpio %d\n", reset_gpio);
-			return ret;
-		}
-		gpio_direction_output(reset_gpio, 1);
+	reset_gpio = devm_gpiod_get_optional(&pdev->dev, "reset",
+					     GPIOD_OUT_LOW);
+	error = PTR_ERR_OR_ZERO(reset_gpio);
+	if (error) {
+		dev_err(&pdev->dev, "failed to request gpio: %d\n", error);
+		return error;
 	}
+	gpiod_set_consumer_name(reset_gpio, "pci_reset");
 
 	/* enable auto-switching between PCI and EBU */
 	ltq_pci_w32(0xa, PCI_CR_CLK_CTRL);
@@ -195,11 +193,11 @@ static int ltq_pci_startup(struct platform_device *pdev)
 	ltq_ebu_w32(ltq_ebu_r32(LTQ_EBU_PCC_IEN) | 0x10, LTQ_EBU_PCC_IEN);
 
 	/* toggle reset pin */
-	if (gpio_is_valid(reset_gpio)) {
-		__gpio_set_value(reset_gpio, 0);
+	if (reset_gpio) {
+		gpiod_set_value_cansleep(reset_gpio, 1);
 		wmb();
 		mdelay(1);
-		__gpio_set_value(reset_gpio, 1);
+		gpiod_set_value_cansleep(reset_gpio, 0);
 	}
 	return 0;
 }
diff --git a/arch/mips/pic32/pic32mzda/init.c b/arch/mips/pic32/pic32mzda/init.c
index d9c8c4e46aff..08c46cf122d7 100644
--- a/arch/mips/pic32/pic32mzda/init.c
+++ b/arch/mips/pic32/pic32mzda/init.c
@@ -44,7 +44,7 @@ void __init plat_mem_setup(void)
 	pr_info(" builtin_cmdline  : %s\n", CONFIG_CMDLINE);
 #endif
 	if (dtb != __dtb_start)
-		strlcpy(arcs_cmdline, boot_command_line, COMMAND_LINE_SIZE);
+		strscpy(arcs_cmdline, boot_command_line, COMMAND_LINE_SIZE);
 
 #ifdef CONFIG_EARLY_PRINTK
 	fw_init_early_console(-1);
diff --git a/arch/mips/ralink/bootrom.c b/arch/mips/ralink/bootrom.c
index 94ca8379b83c..8c8cc0a81ed8 100644
--- a/arch/mips/ralink/bootrom.c
+++ b/arch/mips/ralink/bootrom.c
@@ -18,22 +18,11 @@ static int bootrom_show(struct seq_file *s, void *unused)
 
 	return 0;
 }
-
-static int bootrom_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, bootrom_show, NULL);
-}
-
-static const struct file_operations bootrom_file_ops = {
-	.open		= bootrom_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(bootrom);
 
 static int __init bootrom_setup(void)
 {
-	debugfs_create_file("bootrom", 0444, NULL, NULL, &bootrom_file_ops);
+	debugfs_create_file("bootrom", 0444, NULL, NULL, &bootrom_fops);
 	return 0;
 }
 
diff --git a/arch/mips/sgi-ip27/ip27-xtalk.c b/arch/mips/sgi-ip27/ip27-xtalk.c
index e762886d1dda..5143d1cf8984 100644
--- a/arch/mips/sgi-ip27/ip27-xtalk.c
+++ b/arch/mips/sgi-ip27/ip27-xtalk.c
@@ -27,15 +27,18 @@ static void bridge_platform_create(nasid_t nasid, int widget, int masterwid)
 {
 	struct xtalk_bridge_platform_data *bd;
 	struct sgi_w1_platform_data *wd;
-	struct platform_device *pdev;
+	struct platform_device *pdev_wd;
+	struct platform_device *pdev_bd;
 	struct resource w1_res;
 	unsigned long offset;
 
 	offset = NODE_OFFSET(nasid);
 
 	wd = kzalloc(sizeof(*wd), GFP_KERNEL);
-	if (!wd)
-		goto no_mem;
+	if (!wd) {
+		pr_warn("xtalk:n%d/%x bridge create out of memory\n", nasid, widget);
+		return;
+	}
 
 	snprintf(wd->dev_id, sizeof(wd->dev_id), "bridge-%012lx",
 		 offset + (widget << SWIN_SIZE_BITS));
@@ -46,24 +49,35 @@ static void bridge_platform_create(nasid_t nasid, int widget, int masterwid)
 	w1_res.end = w1_res.start + 3;
 	w1_res.flags = IORESOURCE_MEM;
 
-	pdev = platform_device_alloc("sgi_w1", PLATFORM_DEVID_AUTO);
-	if (!pdev) {
-		kfree(wd);
-		goto no_mem;
+	pdev_wd = platform_device_alloc("sgi_w1", PLATFORM_DEVID_AUTO);
+	if (!pdev_wd) {
+		pr_warn("xtalk:n%d/%x bridge create out of memory\n", nasid, widget);
+		goto err_kfree_wd;
+	}
+	if (platform_device_add_resources(pdev_wd, &w1_res, 1)) {
+		pr_warn("xtalk:n%d/%x bridge failed to add platform resources.\n", nasid, widget);
+		goto err_put_pdev_wd;
+	}
+	if (platform_device_add_data(pdev_wd, wd, sizeof(*wd))) {
+		pr_warn("xtalk:n%d/%x bridge failed to add platform data.\n", nasid, widget);
+		goto err_put_pdev_wd;
+	}
+	if (platform_device_add(pdev_wd)) {
+		pr_warn("xtalk:n%d/%x bridge failed to add platform device.\n", nasid, widget);
+		goto err_put_pdev_wd;
 	}
-	platform_device_add_resources(pdev, &w1_res, 1);
-	platform_device_add_data(pdev, wd, sizeof(*wd));
 	/* platform_device_add_data() duplicates the data */
 	kfree(wd);
-	platform_device_add(pdev);
 
 	bd = kzalloc(sizeof(*bd), GFP_KERNEL);
-	if (!bd)
-		goto no_mem;
-	pdev = platform_device_alloc("xtalk-bridge", PLATFORM_DEVID_AUTO);
-	if (!pdev) {
-		kfree(bd);
-		goto no_mem;
+	if (!bd) {
+		pr_warn("xtalk:n%d/%x bridge create out of memory\n", nasid, widget);
+		goto err_unregister_pdev_wd;
+	}
+	pdev_bd = platform_device_alloc("xtalk-bridge", PLATFORM_DEVID_AUTO);
+	if (!pdev_bd) {
+		pr_warn("xtalk:n%d/%x bridge create out of memory\n", nasid, widget);
+		goto err_kfree_bd;
 	}
 
 
@@ -84,15 +98,31 @@ static void bridge_platform_create(nasid_t nasid, int widget, int masterwid)
 	bd->io.flags	= IORESOURCE_IO;
 	bd->io_offset	= offset;
 
-	platform_device_add_data(pdev, bd, sizeof(*bd));
+	if (platform_device_add_data(pdev_bd, bd, sizeof(*bd))) {
+		pr_warn("xtalk:n%d/%x bridge failed to add platform data.\n", nasid, widget);
+		goto err_put_pdev_bd;
+	}
+	if (platform_device_add(pdev_bd)) {
+		pr_warn("xtalk:n%d/%x bridge failed to add platform device.\n", nasid, widget);
+		goto err_put_pdev_bd;
+	}
 	/* platform_device_add_data() duplicates the data */
 	kfree(bd);
-	platform_device_add(pdev);
 	pr_info("xtalk:n%d/%x bridge widget\n", nasid, widget);
 	return;
 
-no_mem:
-	pr_warn("xtalk:n%d/%x bridge create out of memory\n", nasid, widget);
+err_put_pdev_bd:
+	platform_device_put(pdev_bd);
+err_kfree_bd:
+	kfree(bd);
+err_unregister_pdev_wd:
+	platform_device_unregister(pdev_wd);
+	return;
+err_put_pdev_wd:
+	platform_device_put(pdev_wd);
+err_kfree_wd:
+	kfree(wd);
+	return;
 }
 
 static int probe_one_port(nasid_t nasid, int widget, int masterwid)
diff --git a/arch/mips/sgi-ip30/ip30-xtalk.c b/arch/mips/sgi-ip30/ip30-xtalk.c
index 8129524421cb..7ceb2b23ea1c 100644
--- a/arch/mips/sgi-ip30/ip30-xtalk.c
+++ b/arch/mips/sgi-ip30/ip30-xtalk.c
@@ -40,12 +40,15 @@ static void bridge_platform_create(int widget, int masterwid)
 {
 	struct xtalk_bridge_platform_data *bd;
 	struct sgi_w1_platform_data *wd;
-	struct platform_device *pdev;
+	struct platform_device *pdev_wd;
+	struct platform_device *pdev_bd;
 	struct resource w1_res;
 
 	wd = kzalloc(sizeof(*wd), GFP_KERNEL);
-	if (!wd)
-		goto no_mem;
+	if (!wd) {
+		pr_warn("xtalk:%x bridge create out of memory\n", widget);
+		return;
+	}
 
 	snprintf(wd->dev_id, sizeof(wd->dev_id), "bridge-%012lx",
 		 IP30_SWIN_BASE(widget));
@@ -56,24 +59,35 @@ static void bridge_platform_create(int widget, int masterwid)
 	w1_res.end = w1_res.start + 3;
 	w1_res.flags = IORESOURCE_MEM;
 
-	pdev = platform_device_alloc("sgi_w1", PLATFORM_DEVID_AUTO);
-	if (!pdev) {
-		kfree(wd);
-		goto no_mem;
+	pdev_wd = platform_device_alloc("sgi_w1", PLATFORM_DEVID_AUTO);
+	if (!pdev_wd) {
+		pr_warn("xtalk:%x bridge create out of memory\n", widget);
+		goto err_kfree_wd;
+	}
+	if (platform_device_add_resources(pdev_wd, &w1_res, 1)) {
+		pr_warn("xtalk:%x bridge failed to add platform resources.\n", widget);
+		goto err_put_pdev_wd;
+	}
+	if (platform_device_add_data(pdev_wd, wd, sizeof(*wd))) {
+		pr_warn("xtalk:%x bridge failed to add platform data.\n", widget);
+		goto err_put_pdev_wd;
+	}
+	if (platform_device_add(pdev_wd)) {
+		pr_warn("xtalk:%x bridge failed to add platform device.\n", widget);
+		goto err_put_pdev_wd;
 	}
-	platform_device_add_resources(pdev, &w1_res, 1);
-	platform_device_add_data(pdev, wd, sizeof(*wd));
 	/* platform_device_add_data() duplicates the data */
 	kfree(wd);
-	platform_device_add(pdev);
 
 	bd = kzalloc(sizeof(*bd), GFP_KERNEL);
-	if (!bd)
-		goto no_mem;
-	pdev = platform_device_alloc("xtalk-bridge", PLATFORM_DEVID_AUTO);
-	if (!pdev) {
-		kfree(bd);
-		goto no_mem;
+	if (!bd) {
+		pr_warn("xtalk:%x bridge create out of memory\n", widget);
+		goto err_unregister_pdev_wd;
+	}
+	pdev_bd = platform_device_alloc("xtalk-bridge", PLATFORM_DEVID_AUTO);
+	if (!pdev_bd) {
+		pr_warn("xtalk:%x bridge create out of memory\n", widget);
+		goto err_kfree_bd;
 	}
 
 	bd->bridge_addr	= IP30_RAW_SWIN_BASE(widget);
@@ -93,15 +107,31 @@ static void bridge_platform_create(int widget, int masterwid)
 	bd->io.flags	= IORESOURCE_IO;
 	bd->io_offset	= IP30_SWIN_BASE(widget);
 
-	platform_device_add_data(pdev, bd, sizeof(*bd));
+	if (platform_device_add_data(pdev_bd, bd, sizeof(*bd))) {
+		pr_warn("xtalk:%x bridge failed to add platform data.\n", widget);
+		goto err_put_pdev_bd;
+	}
+	if (platform_device_add(pdev_bd)) {
+		pr_warn("xtalk:%x bridge failed to add platform device.\n", widget);
+		goto err_put_pdev_bd;
+	}
 	/* platform_device_add_data() duplicates the data */
 	kfree(bd);
-	platform_device_add(pdev);
 	pr_info("xtalk:%x bridge widget\n", widget);
 	return;
 
-no_mem:
-	pr_warn("xtalk:%x bridge create out of memory\n", widget);
+err_put_pdev_bd:
+	platform_device_put(pdev_bd);
+err_kfree_bd:
+	kfree(bd);
+err_unregister_pdev_wd:
+	platform_device_unregister(pdev_wd);
+	return;
+err_put_pdev_wd:
+	platform_device_put(pdev_wd);
+err_kfree_wd:
+	kfree(wd);
+	return;
 }
 
 static unsigned int __init xbow_widget_active(s8 wid)
diff --git a/arch/mips/sibyte/sb1250/irq.c b/arch/mips/sibyte/sb1250/irq.c
index 86f49c48fc34..2f08ad267a11 100644
--- a/arch/mips/sibyte/sb1250/irq.c
+++ b/arch/mips/sibyte/sb1250/irq.c
@@ -262,12 +262,6 @@ void __init arch_init_irq(void)
 	__raw_writeq(tmp, IOADDR(A_IMR_REGISTER(0, R_IMR_INTERRUPT_MASK)));
 	__raw_writeq(tmp, IOADDR(A_IMR_REGISTER(1, R_IMR_INTERRUPT_MASK)));
 
-	/*
-	 * Note that the timer interrupts are also mapped, but this is
-	 * done in sb1250_time_init().	Also, the profiling driver
-	 * does its own management of IP7.
-	 */
-
 	/* Enable necessary IPs, disable the rest */
 	change_c0_status(ST0_IM, imask);
 }
diff --git a/arch/nios2/include/asm/entry.h b/arch/nios2/include/asm/entry.h
index cf37f55efbc2..bafb7b2ca59f 100644
--- a/arch/nios2/include/asm/entry.h
+++ b/arch/nios2/include/asm/entry.h
@@ -50,7 +50,8 @@
 	stw	r13, PT_R13(sp)
 	stw	r14, PT_R14(sp)
 	stw	r15, PT_R15(sp)
-	stw	r2, PT_ORIG_R2(sp)
+	movi	r24, -1
+	stw	r24, PT_ORIG_R2(sp)
 	stw	r7, PT_ORIG_R7(sp)
 
 	stw	ra, PT_RA(sp)
diff --git a/arch/nios2/include/asm/ptrace.h b/arch/nios2/include/asm/ptrace.h
index 642462144872..9da34c3022a2 100644
--- a/arch/nios2/include/asm/ptrace.h
+++ b/arch/nios2/include/asm/ptrace.h
@@ -74,6 +74,8 @@ extern void show_regs(struct pt_regs *);
 	((struct pt_regs *)((unsigned long)current_thread_info() + THREAD_SIZE)\
 		- 1)
 
+#define force_successful_syscall_return() (current_pt_regs()->orig_r2 = -1)
+
 int do_syscall_trace_enter(void);
 void do_syscall_trace_exit(void);
 #endif /* __ASSEMBLY__ */
diff --git a/arch/nios2/kernel/entry.S b/arch/nios2/kernel/entry.S
index 0794cd7803df..99f0a65e6234 100644
--- a/arch/nios2/kernel/entry.S
+++ b/arch/nios2/kernel/entry.S
@@ -185,6 +185,7 @@ ENTRY(handle_system_call)
 	ldw	r5, PT_R5(sp)
 
 local_restart:
+	stw	r2, PT_ORIG_R2(sp)
 	/* Check that the requested system call is within limits */
 	movui	r1, __NR_syscalls
 	bgeu	r2, r1, ret_invsyscall
@@ -192,7 +193,6 @@ local_restart:
 	movhi	r11, %hiadj(sys_call_table)
 	add	r1, r1, r11
 	ldw	r1, %lo(sys_call_table)(r1)
-	beq	r1, r0, ret_invsyscall
 
 	/* Check if we are being traced */
 	GET_THREAD_INFO r11
@@ -213,6 +213,9 @@ local_restart:
 translate_rc_and_ret:
 	movi	r1, 0
 	bge	r2, zero, 3f
+	ldw	r1, PT_ORIG_R2(sp)
+	addi	r1, r1, 1
+	beq	r1, zero, 3f
 	sub	r2, zero, r2
 	movi	r1, 1
 3:
@@ -255,9 +258,9 @@ traced_system_call:
 	ldw	r6, PT_R6(sp)
 	ldw	r7, PT_R7(sp)
 
-	/* Fetch the syscall function, we don't need to check the boundaries
-	 * since this is already done.
-	 */
+	/* Fetch the syscall function. */
+	movui	r1, __NR_syscalls
+	bgeu	r2, r1, traced_invsyscall
 	slli	r1, r2, 2
 	movhi	r11,%hiadj(sys_call_table)
 	add	r1, r1, r11
@@ -276,6 +279,9 @@ traced_system_call:
 translate_rc_and_ret2:
 	movi	r1, 0
 	bge	r2, zero, 4f
+	ldw	r1, PT_ORIG_R2(sp)
+	addi	r1, r1, 1
+	beq	r1, zero, 4f
 	sub	r2, zero, r2
 	movi	r1, 1
 4:
@@ -287,6 +293,11 @@ end_translate_rc_and_ret2:
 	RESTORE_SWITCH_STACK
 	br	ret_from_exception
 
+	/* If the syscall number was invalid return ENOSYS */
+traced_invsyscall:
+	movi	r2, -ENOSYS
+	br	translate_rc_and_ret2
+
 Luser_return:
 	GET_THREAD_INFO	r11			/* get thread_info pointer */
 	ldw	r10, TI_FLAGS(r11)		/* get thread_info->flags */
@@ -336,9 +347,6 @@ external_interrupt:
 	/* skip if no interrupt is pending */
 	beq	r12, r0, ret_from_interrupt
 
-	movi	r24, -1
-	stw	r24, PT_ORIG_R2(sp)
-
 	/*
 	 * Process an external hardware interrupt.
 	 */
diff --git a/arch/nios2/kernel/signal.c b/arch/nios2/kernel/signal.c
index cb0b91589cf2..a5b93a30c6eb 100644
--- a/arch/nios2/kernel/signal.c
+++ b/arch/nios2/kernel/signal.c
@@ -242,7 +242,7 @@ static int do_signal(struct pt_regs *regs)
 	/*
 	 * If we were from a system call, check for system call restarting...
 	 */
-	if (regs->orig_r2 >= 0) {
+	if (regs->orig_r2 >= 0 && regs->r1) {
 		continue_addr = regs->ea;
 		restart_addr = continue_addr - 4;
 		retval = regs->r2;
@@ -264,6 +264,7 @@ static int do_signal(struct pt_regs *regs)
 			regs->ea = restart_addr;
 			break;
 		}
+		regs->orig_r2 = -1;
 	}
 
 	if (get_signal(&ksig)) {
diff --git a/arch/nios2/kernel/syscall_table.c b/arch/nios2/kernel/syscall_table.c
index 6176d63023c1..c2875a6dd5a4 100644
--- a/arch/nios2/kernel/syscall_table.c
+++ b/arch/nios2/kernel/syscall_table.c
@@ -13,5 +13,6 @@
 #define __SYSCALL(nr, call) [nr] = (call),
 
 void *sys_call_table[__NR_syscalls] = {
+	[0 ... __NR_syscalls-1] = sys_ni_syscall,
 #include <asm/unistd.h>
 };
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 7f059cd1196a..a98940e64243 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -146,10 +146,10 @@ menu "Processor type and features"
 
 choice
 	prompt "Processor type"
-	default PA7000
+	default PA7000 if "$(ARCH)" = "parisc"
 
 config PA7000
-	bool "PA7000/PA7100"
+	bool "PA7000/PA7100" if "$(ARCH)" = "parisc"
 	help
 	  This is the processor type of your CPU.  This information is
 	  used for optimizing purposes.  In order to compile a kernel
@@ -160,21 +160,21 @@ config PA7000
 	  which is required on some machines.
 
 config PA7100LC
-	bool "PA7100LC"
+	bool "PA7100LC" if "$(ARCH)" = "parisc"
 	help
 	  Select this option for the PCX-L processor, as used in the
 	  712, 715/64, 715/80, 715/100, 715/100XC, 725/100, 743, 748,
 	  D200, D210, D300, D310 and E-class
 
 config PA7200
-	bool "PA7200"
+	bool "PA7200" if "$(ARCH)" = "parisc"
 	help
 	  Select this option for the PCX-T' processor, as used in the
 	  C100, C110, J100, J110, J210XC, D250, D260, D350, D360,
 	  K100, K200, K210, K220, K400, K410 and K420
 
 config PA7300LC
-	bool "PA7300LC"
+	bool "PA7300LC" if "$(ARCH)" = "parisc"
 	help
 	  Select this option for the PCX-L2 processor, as used in the
 	  744, A180, B132L, B160L, B180L, C132L, C160L, C180L,
@@ -224,7 +224,8 @@ config MLONGCALLS
 	  Enabling this option will probably slow down your kernel.
 
 config 64BIT
-	bool "64-bit kernel"
+	def_bool y if "$(ARCH)" = "parisc64"
+	bool "64-bit kernel" if "$(ARCH)" = "parisc"
 	depends on PA8X00
 	help
 	  Enable this if you want to support 64bit kernel on PA-RISC platform.
diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h
index 56ffd260c669..0ec9cfc5131f 100644
--- a/arch/parisc/include/asm/bitops.h
+++ b/arch/parisc/include/asm/bitops.h
@@ -12,14 +12,6 @@
 #include <asm/barrier.h>
 #include <linux/atomic.h>
 
-/* compiler build environment sanity checks: */
-#if !defined(CONFIG_64BIT) && defined(__LP64__)
-#error "Please use 'ARCH=parisc' to build the 32-bit kernel."
-#endif
-#if defined(CONFIG_64BIT) && !defined(__LP64__)
-#error "Please use 'ARCH=parisc64' to build the 64-bit kernel."
-#endif
-
 /* See http://marc.theaimsgroup.com/?t=108826637900003 for discussion
  * on use of volatile and __*_bit() (set/clear/change):
  *	*_bit() want use of volatile.
diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S
index e0a9e9657622..fd15fd4bbb61 100644
--- a/arch/parisc/kernel/head.S
+++ b/arch/parisc/kernel/head.S
@@ -22,7 +22,7 @@
 #include <linux/init.h>
 #include <linux/pgtable.h>
 
-	.level	PA_ASM_LEVEL
+	.level	1.1
 
 	__INITDATA
 ENTRY(boot_args)
@@ -70,6 +70,47 @@ $bss_loop:
 	stw,ma          %arg2,4(%r1)
 	stw,ma          %arg3,4(%r1)
 
+#if !defined(CONFIG_64BIT) && defined(CONFIG_PA20)
+	/* This 32-bit kernel was compiled for PA2.0 CPUs. Check current CPU
+	 * and halt kernel if we detect a PA1.x CPU. */
+	ldi		32,%r10
+	mtctl		%r10,%cr11
+	.level 2.0
+	mfctl,w		%cr11,%r10
+	.level 1.1
+	comib,<>,n	0,%r10,$cpu_ok
+
+	load32		PA(msg1),%arg0
+	ldi		msg1_end-msg1,%arg1
+$iodc_panic:
+	copy		%arg0, %r10
+	copy		%arg1, %r11
+	load32		PA(init_stack),%sp
+#define MEM_CONS 0x3A0
+	ldw		MEM_CONS+32(%r0),%arg0	// HPA
+	ldi		ENTRY_IO_COUT,%arg1
+	ldw		MEM_CONS+36(%r0),%arg2	// SPA
+	ldw		MEM_CONS+8(%r0),%arg3	// layers
+	load32		PA(__bss_start),%r1
+	stw		%r1,-52(%sp)		// arg4
+	stw		%r0,-56(%sp)		// arg5
+	stw		%r10,-60(%sp)		// arg6 = ptr to text
+	stw		%r11,-64(%sp)		// arg7 = len
+	stw		%r0,-68(%sp)		// arg8
+	load32		PA(.iodc_panic_ret), %rp
+	ldw		MEM_CONS+40(%r0),%r1	// ENTRY_IODC
+	bv,n		(%r1)
+.iodc_panic_ret:
+	b .				/* wait endless with ... */
+	or		%r10,%r10,%r10	/* qemu idle sleep */
+msg1:	.ascii "Can't boot kernel which was built for PA8x00 CPUs on this machine.\r\n"
+msg1_end:
+
+$cpu_ok:
+#endif
+
+	.level	PA_ASM_LEVEL
+
 	/* Initialize startup VM. Just map first 16/32 MB of memory */
 	load32		PA(swapper_pg_dir),%r4
 	mtctl		%r4,%cr24	/* Initialize kernel root pointer */
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index fbb882cb8dbb..b05055f3ba4b 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -480,7 +480,7 @@ static void execute_on_irq_stack(void *func, unsigned long param1)
 	*irq_stack_in_use = 1;
 }
 
-#ifndef CONFIG_PREEMPT_RT
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
 void do_softirq_own_stack(void)
 {
 	execute_on_irq_stack(__do_softirq, 0);
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index bac581b5ecfc..e8a4d77cff53 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -93,7 +93,7 @@
 #define R1(i) (((i)>>21)&0x1f)
 #define R2(i) (((i)>>16)&0x1f)
 #define R3(i) ((i)&0x1f)
-#define FR3(i) ((((i)<<1)&0x1f)|(((i)>>6)&1))
+#define FR3(i) ((((i)&0x1f)<<1)|(((i)>>6)&1))
 #define IM(i,n) (((i)>>1&((1<<(n-1))-1))|((i)&1?((0-1L)<<(n-1)):0))
 #define IM5_2(i) IM((i)>>16,5)
 #define IM5_3(i) IM((i),5)
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 398e0b5e485f..ed6db13a1d7c 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -83,6 +83,8 @@ enum {
 	FW_FEATURE_POWERNV_ALWAYS = 0,
 	FW_FEATURE_PS3_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
 	FW_FEATURE_PS3_ALWAYS = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
+	FW_FEATURE_NATIVE_POSSIBLE = 0,
+	FW_FEATURE_NATIVE_ALWAYS = 0,
 	FW_FEATURE_POSSIBLE =
 #ifdef CONFIG_PPC_PSERIES
 		FW_FEATURE_PSERIES_POSSIBLE |
@@ -93,6 +95,9 @@ enum {
 #ifdef CONFIG_PPC_PS3
 		FW_FEATURE_PS3_POSSIBLE |
 #endif
+#ifdef CONFIG_PPC_HASH_MMU_NATIVE
+		FW_FEATURE_NATIVE_ALWAYS |
+#endif
 		0,
 	FW_FEATURE_ALWAYS =
 #ifdef CONFIG_PPC_PSERIES
@@ -104,6 +109,9 @@ enum {
 #ifdef CONFIG_PPC_PS3
 		FW_FEATURE_PS3_ALWAYS &
 #endif
+#ifdef CONFIG_PPC_HASH_MMU_NATIVE
+		FW_FEATURE_NATIVE_ALWAYS &
+#endif
 		FW_FEATURE_POSSIBLE,
 
 #else /* CONFIG_PPC64 */
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 26ede09c521d..983551859891 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -113,7 +113,14 @@ static inline void __hard_RI_enable(void)
 
 static inline notrace unsigned long irq_soft_mask_return(void)
 {
-	return READ_ONCE(local_paca->irq_soft_mask);
+	unsigned long flags;
+
+	asm volatile(
+		"lbz %0,%1(13)"
+		: "=r" (flags)
+		: "i" (offsetof(struct paca_struct, irq_soft_mask)));
+
+	return flags;
 }
 
 /*
@@ -140,24 +147,46 @@ static inline notrace void irq_soft_mask_set(unsigned long mask)
 	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
 		WARN_ON(mask && !(mask & IRQS_DISABLED));
 
-	WRITE_ONCE(local_paca->irq_soft_mask, mask);
-	barrier();
+	asm volatile(
+		"stb %0,%1(13)"
+		:
+		: "r" (mask),
+		  "i" (offsetof(struct paca_struct, irq_soft_mask))
+		: "memory");
 }
 
 static inline notrace unsigned long irq_soft_mask_set_return(unsigned long mask)
 {
-	unsigned long flags = irq_soft_mask_return();
+	unsigned long flags;
 
-	irq_soft_mask_set(mask);
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+	WARN_ON(mask && !(mask & IRQS_DISABLED));
+#endif
+
+	asm volatile(
+		"lbz %0,%1(13); stb %2,%1(13)"
+		: "=&r" (flags)
+		: "i" (offsetof(struct paca_struct, irq_soft_mask)),
+		  "r" (mask)
+		: "memory");
 
 	return flags;
 }
 
 static inline notrace unsigned long irq_soft_mask_or_return(unsigned long mask)
 {
-	unsigned long flags = irq_soft_mask_return();
+	unsigned long flags, tmp;
+
+	asm volatile(
+		"lbz %0,%2(13); or %1,%0,%3; stb %1,%2(13)"
+		: "=&r" (flags), "=r" (tmp)
+		: "i" (offsetof(struct paca_struct, irq_soft_mask)),
+		  "r" (mask)
+		: "memory");
 
-	irq_soft_mask_set(flags | mask);
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+	WARN_ON((mask | flags) && !((mask | flags) & IRQS_DISABLED));
+#endif
 
 	return flags;
 }
@@ -282,7 +311,8 @@ static inline bool pmi_irq_pending(void)
 	flags = irq_soft_mask_set_return(IRQS_ALL_DISABLED);		\
 	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;			\
 	if (!arch_irqs_disabled_flags(flags)) {				\
-		WRITE_ONCE(local_paca->saved_r1, current_stack_pointer);\
+		asm volatile("std%X0 %1,%0" : "=m" (local_paca->saved_r1) \
+					    : "r" (current_stack_pointer)); \
 		trace_hardirqs_off();					\
 	}								\
 } while(0)
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 4def2bd17b9b..d49065af08e9 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -666,7 +666,7 @@ static inline pte_t *find_kvm_host_pte(struct kvm *kvm, unsigned long mmu_seq,
 	VM_WARN(!spin_is_locked(&kvm->mmu_lock),
 		"%s called with kvm mmu_lock not held \n", __func__);
 
-	if (mmu_notifier_retry(kvm, mmu_seq))
+	if (mmu_invalidate_retry(kvm, mmu_seq))
 		return NULL;
 
 	pte = __find_linux_pte(kvm->mm->pgd, ea, NULL, hshift);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 0f17268c1f0b..9ede61a5a469 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -199,7 +199,7 @@ static inline void check_stack_overflow(unsigned long sp)
 	}
 }
 
-#ifndef CONFIG_PREEMPT_RT
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
 static __always_inline void call_do_softirq(const void *sp)
 {
 	/* Temporarily switch r1 to sp, call __do_softirq() then restore r1. */
@@ -335,7 +335,7 @@ void *mcheckirq_ctx[NR_CPUS] __read_mostly;
 void *softirq_ctx[NR_CPUS] __read_mostly;
 void *hardirq_ctx[NR_CPUS] __read_mostly;
 
-#ifndef CONFIG_PREEMPT_RT
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
 void do_softirq_own_stack(void)
 {
 	call_do_softirq(softirq_ctx[smp_processor_id()]);
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index bdd3332200c5..31de91c8359c 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -68,10 +68,6 @@ void __init set_pci_dma_ops(const struct dma_map_ops *dma_ops)
 	pci_dma_ops = dma_ops;
 }
 
-/*
- * This function should run under locking protection, specifically
- * hose_spinlock.
- */
 static int get_phb_number(struct device_node *dn)
 {
 	int ret, phb_id = -1;
@@ -108,15 +104,20 @@ static int get_phb_number(struct device_node *dn)
 	if (!ret)
 		phb_id = (int)(prop & (MAX_PHBS - 1));
 
+	spin_lock(&hose_spinlock);
+
 	/* We need to be sure to not use the same PHB number twice. */
 	if ((phb_id >= 0) && !test_and_set_bit(phb_id, phb_bitmap))
-		return phb_id;
+		goto out_unlock;
 
 	/* If everything fails then fallback to dynamic PHB numbering. */
 	phb_id = find_first_zero_bit(phb_bitmap, MAX_PHBS);
 	BUG_ON(phb_id >= MAX_PHBS);
 	set_bit(phb_id, phb_bitmap);
 
+out_unlock:
+	spin_unlock(&hose_spinlock);
+
 	return phb_id;
 }
 
@@ -127,10 +128,13 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
 	phb = zalloc_maybe_bootmem(sizeof(struct pci_controller), GFP_KERNEL);
 	if (phb == NULL)
 		return NULL;
-	spin_lock(&hose_spinlock);
+
 	phb->global_number = get_phb_number(dev);
+
+	spin_lock(&hose_spinlock);
 	list_add_tail(&phb->list_node, &hose_list);
 	spin_unlock(&hose_spinlock);
+
 	phb->dn = dev;
 	phb->is_dynamic = slab_is_available();
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 433965bf37b4..855b59892c5c 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -245,6 +245,15 @@ static int __init pcibios_init(void)
 
 	printk(KERN_INFO "PCI: Probing PCI hardware\n");
 
+#ifdef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT
+	/*
+	 * Enable PCI domains in /proc when PCI bus numbers are not unique
+	 * across all PCI domains to prevent conflicts. And keep PCI domain 0
+	 * backward compatible in /proc for video cards.
+	 */
+	pci_add_flags(PCI_ENABLE_PROC_DOMAINS | PCI_COMPAT_DOMAIN_0);
+#endif
+
 	if (pci_has_flag(PCI_REASSIGN_ALL_BUS))
 		pci_assign_all_buses = 1;
 
diff --git a/arch/powerpc/kernel/rtas_entry.S b/arch/powerpc/kernel/rtas_entry.S
index 9a434d42e660..6ce95ddadbcd 100644
--- a/arch/powerpc/kernel/rtas_entry.S
+++ b/arch/powerpc/kernel/rtas_entry.S
@@ -109,8 +109,12 @@ __enter_rtas:
 	 * its critical regions (as specified in PAPR+ section 7.2.1). MSR[S]
 	 * is not impacted by RFI_TO_KERNEL (only urfid can unset it). So if
 	 * MSR[S] is set, it will remain when entering RTAS.
+	 * If we're in HV mode, RTAS must also run in HV mode, so extract MSR_HV
+	 * from the saved MSR value and insert into the value RTAS will use.
 	 */
+	extrdi	r0, r6, 1, 63 - MSR_HV_LG
 	LOAD_REG_IMMEDIATE(r6, MSR_ME | MSR_RI)
+	insrdi	r6, r0, 1, 63 - MSR_HV_LG
 
 	li      r0,0
 	mtmsrd  r0,1                    /* disable RI before using SRR0/1 */
diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S
index cb3358886203..6c1db3b6de2d 100644
--- a/arch/powerpc/kernel/systbl.S
+++ b/arch/powerpc/kernel/systbl.S
@@ -18,6 +18,7 @@
 	.p2align	3
 #define __SYSCALL(nr, entry)	.8byte entry
 #else
+	.p2align	2
 #define __SYSCALL(nr, entry)	.long entry
 #endif
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 1ae09992c9ea..bc6a381b5346 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -90,7 +90,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 	unsigned long pfn;
 
 	/* used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/* Get host physical address for gpa */
@@ -151,7 +151,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 	cpte = kvmppc_mmu_hpte_cache_next(vcpu);
 
 	spin_lock(&kvm->mmu_lock);
-	if (!cpte || mmu_notifier_retry(kvm, mmu_seq)) {
+	if (!cpte || mmu_invalidate_retry(kvm, mmu_seq)) {
 		r = -EAGAIN;
 		goto out_unlock;
 	}
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 514fd45c1994..e9744b41a226 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -578,7 +578,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu,
 		return -EFAULT;
 
 	/* used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	ret = -EFAULT;
@@ -693,7 +693,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu,
 
 	/* Check if we might have been invalidated; let the guest retry if so */
 	ret = RESUME_GUEST;
-	if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) {
+	if (mmu_invalidate_retry(vcpu->kvm, mmu_seq)) {
 		unlock_rmap(rmap);
 		goto out_unlock;
 	}
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 9d4b3feda3b6..5d5e12f3bf86 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -640,7 +640,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 	/* Check if we might have been invalidated; let the guest retry if so */
 	spin_lock(&kvm->mmu_lock);
 	ret = -EAGAIN;
-	if (mmu_notifier_retry(kvm, mmu_seq))
+	if (mmu_invalidate_retry(kvm, mmu_seq))
 		goto out_unlock;
 
 	/* Now traverse again under the lock and change the tree */
@@ -830,7 +830,7 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
 	bool large_enable;
 
 	/* used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/*
@@ -1191,7 +1191,7 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm,
 	 * Increase the mmu notifier sequence number to prevent any page
 	 * fault that read the memslot earlier from writing a PTE.
 	 */
-	kvm->mmu_notifier_seq++;
+	kvm->mmu_invalidate_seq++;
 	spin_unlock(&kvm->mmu_lock);
 }
 
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index be8249cc6107..5a64a1341e6f 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -1580,7 +1580,7 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
 	/* 2. Find the host pte for this L1 guest real address */
 
 	/* Used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/* See if can find translation in our partition scoped tables for L1 */
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 2257fb18cb72..5a05953ae13f 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -219,7 +219,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	g_ptel = ptel;
 
 	/* used later to detect if we might have been invalidated */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/* Find the memslot (if any) for this address */
@@ -366,7 +366,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 			rmap = real_vmalloc_addr(rmap);
 		lock_rmap(rmap);
 		/* Check for pending invalidations under the rmap chain lock */
-		if (mmu_notifier_retry(kvm, mmu_seq)) {
+		if (mmu_invalidate_retry(kvm, mmu_seq)) {
 			/* inval in progress, write a non-present HPTE */
 			pteh |= HPTE_V_ABSENT;
 			pteh &= ~HPTE_V_VALID;
@@ -932,7 +932,7 @@ static long kvmppc_do_h_page_init_zero(struct kvm_vcpu *vcpu,
 	int i;
 
 	/* Used later to detect if we might have been invalidated */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	arch_spin_lock(&kvm->mmu_lock.rlock.raw_lock);
@@ -960,7 +960,7 @@ static long kvmppc_do_h_page_init_copy(struct kvm_vcpu *vcpu,
 	long ret = H_SUCCESS;
 
 	/* Used later to detect if we might have been invalidated */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	arch_spin_lock(&kvm->mmu_lock.rlock.raw_lock);
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 7f16afc331ef..05668e964140 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -339,7 +339,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	unsigned long flags;
 
 	/* used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/*
@@ -460,7 +460,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	}
 
 	spin_lock(&kvm->mmu_lock);
-	if (mmu_notifier_retry(kvm, mmu_seq)) {
+	if (mmu_invalidate_retry(kvm, mmu_seq)) {
 		ret = -EAGAIN;
 		goto out;
 	}
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 698274109c91..e712f80fe189 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -937,15 +937,6 @@ pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addre
 	pmd = *pmdp;
 	pmd_clear(pmdp);
 
-	/*
-	 * pmdp collapse_flush need to ensure that there are no parallel gup
-	 * walk after this call. This is needed so that we can have stable
-	 * page ref count when collapsing a page. We don't allow a collapse page
-	 * if we have gup taken on the page. We can ensure that by sending IPI
-	 * because gup walk happens with IRQ disabled.
-	 */
-	serialize_against_pte_lookup(vma->vm_mm);
-
 	radix__flush_tlb_collapsed_pmd(vma->vm_mm, address);
 
 	return pmd;
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index 20f6ed813bff..2f8385523a13 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -124,9 +124,6 @@ struct papr_scm_priv {
 
 	/* The bits which needs to be overridden */
 	u64 health_bitmap_inject_mask;
-
-	/* array to have event_code and stat_id mappings */
-	u8 *nvdimm_events_map;
 };
 
 static int papr_scm_pmem_flush(struct nd_region *nd_region,
@@ -350,6 +347,25 @@ static ssize_t drc_pmem_query_stats(struct papr_scm_priv *p,
 #ifdef CONFIG_PERF_EVENTS
 #define to_nvdimm_pmu(_pmu)	container_of(_pmu, struct nvdimm_pmu, pmu)
 
+static const char * const nvdimm_events_map[] = {
+	[1] = "CtlResCt",
+	[2] = "CtlResTm",
+	[3] = "PonSecs ",
+	[4] = "MemLife ",
+	[5] = "CritRscU",
+	[6] = "HostLCnt",
+	[7] = "HostSCnt",
+	[8] = "HostSDur",
+	[9] = "HostLDur",
+	[10] = "MedRCnt ",
+	[11] = "MedWCnt ",
+	[12] = "MedRDur ",
+	[13] = "MedWDur ",
+	[14] = "CchRHCnt",
+	[15] = "CchWHCnt",
+	[16] = "FastWCnt",
+};
+
 static int papr_scm_pmu_get_value(struct perf_event *event, struct device *dev, u64 *count)
 {
 	struct papr_scm_perf_stat *stat;
@@ -357,11 +373,15 @@ static int papr_scm_pmu_get_value(struct perf_event *event, struct device *dev,
 	struct papr_scm_priv *p = dev_get_drvdata(dev);
 	int rc, size;
 
+	/* Invalid eventcode */
+	if (event->attr.config == 0 || event->attr.config >= ARRAY_SIZE(nvdimm_events_map))
+		return -EINVAL;
+
 	/* Allocate request buffer enough to hold single performance stat */
 	size = sizeof(struct papr_scm_perf_stats) +
 		sizeof(struct papr_scm_perf_stat);
 
-	if (!p || !p->nvdimm_events_map)
+	if (!p)
 		return -EINVAL;
 
 	stats = kzalloc(size, GFP_KERNEL);
@@ -370,7 +390,7 @@ static int papr_scm_pmu_get_value(struct perf_event *event, struct device *dev,
 
 	stat = &stats->scm_statistic[0];
 	memcpy(&stat->stat_id,
-	       &p->nvdimm_events_map[event->attr.config * sizeof(stat->stat_id)],
+	       nvdimm_events_map[event->attr.config],
 		sizeof(stat->stat_id));
 	stat->stat_val = 0;
 
@@ -458,56 +478,6 @@ static void papr_scm_pmu_del(struct perf_event *event, int flags)
 	papr_scm_pmu_read(event);
 }
 
-static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu *nd_pmu)
-{
-	struct papr_scm_perf_stat *stat;
-	struct papr_scm_perf_stats *stats;
-	u32 available_events;
-	int index, rc = 0;
-
-	if (!p->stat_buffer_len)
-		return -ENOENT;
-
-	available_events = (p->stat_buffer_len  - sizeof(struct papr_scm_perf_stats))
-			/ sizeof(struct papr_scm_perf_stat);
-	if (available_events == 0)
-		return -EOPNOTSUPP;
-
-	/* Allocate the buffer for phyp where stats are written */
-	stats = kzalloc(p->stat_buffer_len, GFP_KERNEL);
-	if (!stats) {
-		rc = -ENOMEM;
-		return rc;
-	}
-
-	/* Called to get list of events supported */
-	rc = drc_pmem_query_stats(p, stats, 0);
-	if (rc)
-		goto out;
-
-	/*
-	 * Allocate memory and populate nvdimm_event_map.
-	 * Allocate an extra element for NULL entry
-	 */
-	p->nvdimm_events_map = kcalloc(available_events + 1,
-				       sizeof(stat->stat_id),
-				       GFP_KERNEL);
-	if (!p->nvdimm_events_map) {
-		rc = -ENOMEM;
-		goto out;
-	}
-
-	/* Copy all stat_ids to event map */
-	for (index = 0, stat = stats->scm_statistic;
-	     index < available_events; index++, ++stat) {
-		memcpy(&p->nvdimm_events_map[index * sizeof(stat->stat_id)],
-		       &stat->stat_id, sizeof(stat->stat_id));
-	}
-out:
-	kfree(stats);
-	return rc;
-}
-
 static void papr_scm_pmu_register(struct papr_scm_priv *p)
 {
 	struct nvdimm_pmu *nd_pmu;
@@ -519,9 +489,10 @@ static void papr_scm_pmu_register(struct papr_scm_priv *p)
 		goto pmu_err_print;
 	}
 
-	rc = papr_scm_pmu_check_events(p, nd_pmu);
-	if (rc)
+	if (!p->stat_buffer_len) {
+		rc = -ENOENT;
 		goto pmu_check_events_err;
+	}
 
 	nd_pmu->pmu.task_ctx_nr = perf_invalid_context;
 	nd_pmu->pmu.name = nvdimm_name(p->nvdimm);
@@ -539,7 +510,7 @@ static void papr_scm_pmu_register(struct papr_scm_priv *p)
 
 	rc = register_nvdimm_pmu(nd_pmu, p->pdev);
 	if (rc)
-		goto pmu_register_err;
+		goto pmu_check_events_err;
 
 	/*
 	 * Set archdata.priv value to nvdimm_pmu structure, to handle the
@@ -548,8 +519,6 @@ static void papr_scm_pmu_register(struct papr_scm_priv *p)
 	p->pdev->archdata.priv = nd_pmu;
 	return;
 
-pmu_register_err:
-	kfree(p->nvdimm_events_map);
 pmu_check_events_err:
 	kfree(nd_pmu);
 pmu_err_print:
@@ -1560,7 +1529,6 @@ static int papr_scm_remove(struct platform_device *pdev)
 		unregister_nvdimm_pmu(pdev->archdata.priv);
 
 	pdev->archdata.priv = NULL;
-	kfree(p->nvdimm_events_map);
 	kfree(p->bus_desc.provider_name);
 	kfree(p);
 
diff --git a/arch/powerpc/platforms/pseries/plpks.c b/arch/powerpc/platforms/pseries/plpks.c
index 52aaa2894606..f4b5b5a64db3 100644
--- a/arch/powerpc/platforms/pseries/plpks.c
+++ b/arch/powerpc/platforms/pseries/plpks.c
@@ -17,6 +17,7 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <asm/hvcall.h>
+#include <asm/machdep.h>
 
 #include "plpks.h"
 
@@ -457,4 +458,4 @@ static __init int pseries_plpks_init(void)
 
 	return rc;
 }
-arch_initcall(pseries_plpks_init);
+machine_arch_initcall(pseries, pseries_plpks_init);
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index ed66c31e4655..59d18881f35b 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -386,6 +386,7 @@ config RISCV_ISA_C
 config RISCV_ISA_SVPBMT
 	bool "SVPBMT extension support"
 	depends on 64BIT && MMU
+	depends on !XIP_KERNEL
 	select RISCV_ALTERNATIVE
 	default y
 	help
diff --git a/arch/riscv/Kconfig.erratas b/arch/riscv/Kconfig.erratas
index 6850e9389930..f3623df23b5f 100644
--- a/arch/riscv/Kconfig.erratas
+++ b/arch/riscv/Kconfig.erratas
@@ -46,7 +46,7 @@ config ERRATA_THEAD
 
 config ERRATA_THEAD_PBMT
 	bool "Apply T-Head memory type errata"
-	depends on ERRATA_THEAD && 64BIT
+	depends on ERRATA_THEAD && 64BIT && MMU
 	select RISCV_ALTERNATIVE_EARLY
 	default y
 	help
@@ -57,7 +57,7 @@ config ERRATA_THEAD_PBMT
 
 config ERRATA_THEAD_CMO
 	bool "Apply T-Head cache management errata"
-	depends on ERRATA_THEAD
+	depends on ERRATA_THEAD && MMU
 	select RISCV_DMA_NONCOHERENT
 	default y
 	help
diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts
index 044982a11df5..f3f87ed2007f 100644
--- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts
+++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts
@@ -84,12 +84,10 @@
 
 	phy1: ethernet-phy@9 {
 		reg = <9>;
-		ti,fifo-depth = <0x1>;
 	};
 
 	phy0: ethernet-phy@8 {
 		reg = <8>;
-		ti,fifo-depth = <0x1>;
 	};
 };
 
@@ -102,7 +100,6 @@
 	disable-wp;
 	cap-sd-highspeed;
 	cap-mmc-highspeed;
-	card-detect-delay = <200>;
 	mmc-ddr-1_8v;
 	mmc-hs200-1_8v;
 	sd-uhs-sdr12;
diff --git a/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts b/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts
index 82c93c8f5c17..c87cc2d8fe29 100644
--- a/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts
+++ b/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts
@@ -54,12 +54,10 @@
 
 	phy1: ethernet-phy@5 {
 		reg = <5>;
-		ti,fifo-depth = <0x01>;
 	};
 
 	phy0: ethernet-phy@4 {
 		reg = <4>;
-		ti,fifo-depth = <0x01>;
 	};
 };
 
@@ -72,7 +70,6 @@
 	disable-wp;
 	cap-sd-highspeed;
 	cap-mmc-highspeed;
-	card-detect-delay = <200>;
 	mmc-ddr-1_8v;
 	mmc-hs200-1_8v;
 	sd-uhs-sdr12;
diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi
index 499c2e63ad35..6d9d455fa160 100644
--- a/arch/riscv/boot/dts/microchip/mpfs.dtsi
+++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi
@@ -185,7 +185,7 @@
 		ranges;
 
 		cctrllr: cache-controller@2010000 {
-			compatible = "sifive,fu540-c000-ccache", "cache";
+			compatible = "microchip,mpfs-ccache", "sifive,fu540-c000-ccache", "cache";
 			reg = <0x0 0x2010000 0x0 0x1000>;
 			cache-block-size = <64>;
 			cache-level = <2>;
@@ -193,7 +193,7 @@
 			cache-size = <2097152>;
 			cache-unified;
 			interrupt-parent = <&plic>;
-			interrupts = <1>, <2>, <3>;
+			interrupts = <1>, <3>, <4>, <2>;
 		};
 
 		clint: clint@2000000 {
@@ -485,9 +485,8 @@
 			ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>;
 			msi-parent = <&pcie>;
 			msi-controller;
-			microchip,axi-m-atr0 = <0x10 0x0>;
 			status = "disabled";
-			pcie_intc: legacy-interrupt-controller {
+			pcie_intc: interrupt-controller {
 				#address-cells = <0>;
 				#interrupt-cells = <1>;
 				interrupt-controller;
diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c
index 202c83f677b2..96648c176f37 100644
--- a/arch/riscv/errata/thead/errata.c
+++ b/arch/riscv/errata/thead/errata.c
@@ -37,6 +37,7 @@ static bool errata_probe_cmo(unsigned int stage,
 	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
 		return false;
 
+	riscv_cbom_block_size = L1_CACHE_BYTES;
 	riscv_noncoherent_supported();
 	return true;
 #else
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index a60acaecfeda..273ece6b622f 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -42,6 +42,11 @@ void flush_icache_mm(struct mm_struct *mm, bool local);
 
 #endif /* CONFIG_SMP */
 
+/*
+ * The T-Head CMO errata internally probe the CBOM block size, but otherwise
+ * don't depend on Zicbom.
+ */
+extern unsigned int riscv_cbom_block_size;
 #ifdef CONFIG_RISCV_ISA_ZICBOM
 void riscv_init_cbom_blocksize(void);
 #else
diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h
index 83d6d4d2b1df..26a446a34057 100644
--- a/arch/riscv/include/asm/kvm_vcpu_sbi.h
+++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h
@@ -33,4 +33,16 @@ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu,
 				     u32 type, u64 flags);
 const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(unsigned long extid);
 
+#ifdef CONFIG_RISCV_SBI_V01
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01;
+#endif
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_ipi;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor;
+
 #endif /* __RISCV_KVM_VCPU_SBI_H__ */
diff --git a/arch/riscv/include/asm/signal.h b/arch/riscv/include/asm/signal.h
new file mode 100644
index 000000000000..532c29ef0376
--- /dev/null
+++ b/arch/riscv/include/asm/signal.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_SIGNAL_H
+#define __ASM_SIGNAL_H
+
+#include <uapi/asm/signal.h>
+#include <uapi/asm/ptrace.h>
+
+asmlinkage __visible
+void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags);
+
+#endif
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 78933ac04995..67322f878e0d 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -42,6 +42,8 @@
 
 #ifndef __ASSEMBLY__
 
+extern long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE / sizeof(long)];
+
 #include <asm/processor.h>
 #include <asm/csr.h>
 
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 553d755483ed..3b5583db9d80 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -28,7 +28,7 @@ unsigned long elf_hwcap __read_mostly;
 /* Host ISA bitmap */
 static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly;
 
-__ro_after_init DEFINE_STATIC_KEY_ARRAY_FALSE(riscv_isa_ext_keys, RISCV_ISA_EXT_KEY_MAX);
+DEFINE_STATIC_KEY_ARRAY_FALSE(riscv_isa_ext_keys, RISCV_ISA_EXT_KEY_MAX);
 EXPORT_SYMBOL(riscv_isa_ext_keys);
 
 /**
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 95ef6e2bf45c..2dfc463b86bb 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -296,8 +296,8 @@ void __init setup_arch(char **cmdline_p)
 	setup_smp();
 #endif
 
-	riscv_fill_hwcap();
 	riscv_init_cbom_blocksize();
+	riscv_fill_hwcap();
 	apply_boot_alternatives();
 }
 
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 38b05ca6fe66..5c591123c440 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -15,6 +15,7 @@
 
 #include <asm/ucontext.h>
 #include <asm/vdso.h>
+#include <asm/signal.h>
 #include <asm/signal32.h>
 #include <asm/switch_to.h>
 #include <asm/csr.h>
@@ -123,6 +124,8 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	if (restore_altstack(&frame->uc.uc_stack))
 		goto badframe;
 
+	regs->cause = -1UL;
+
 	return regs->a0;
 
 badframe:
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 39d0f8bba4b4..635e6ec26938 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -20,9 +20,10 @@
 
 #include <asm/asm-prototypes.h>
 #include <asm/bug.h>
+#include <asm/csr.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
-#include <asm/csr.h>
+#include <asm/thread_info.h>
 
 int show_unhandled_signals = 1;
 
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 3a35b2d95697..3620ecac2fa1 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -666,7 +666,7 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
 		return ret;
 	}
 
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 
 	hfn = gfn_to_pfn_prot(kvm, gfn, is_write, &writable);
 	if (hfn == KVM_PFN_ERR_HWPOISON) {
@@ -686,7 +686,7 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
 
 	spin_lock(&kvm->mmu_lock);
 
-	if (mmu_notifier_retry(kvm, mmu_seq))
+	if (mmu_invalidate_retry(kvm, mmu_seq))
 		goto out_unlock;
 
 	if (writable) {
diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
index d45e7da3f0d3..f96991d230bf 100644
--- a/arch/riscv/kvm/vcpu_sbi.c
+++ b/arch/riscv/kvm/vcpu_sbi.c
@@ -32,23 +32,13 @@ static int kvm_linux_err_map_sbi(int err)
 	};
 }
 
-#ifdef CONFIG_RISCV_SBI_V01
-extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01;
-#else
+#ifndef CONFIG_RISCV_SBI_V01
 static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = {
 	.extid_start = -1UL,
 	.extid_end = -1UL,
 	.handler = NULL,
 };
 #endif
-extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base;
-extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time;
-extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_ipi;
-extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence;
-extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst;
-extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm;
-extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental;
-extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor;
 
 static const struct kvm_vcpu_sbi_extension *sbi_ext[] = {
 	&vcpu_sbi_ext_v01,
diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c
index 16f50c46ba39..185f2386a747 100644
--- a/arch/riscv/kvm/vcpu_timer.c
+++ b/arch/riscv/kvm/vcpu_timer.c
@@ -299,7 +299,6 @@ static void kvm_riscv_vcpu_update_timedelta(struct kvm_vcpu *vcpu)
 
 void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu_csr *csr;
 	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
 
 	kvm_riscv_vcpu_update_timedelta(vcpu);
@@ -307,7 +306,6 @@ void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu)
 	if (!t->sstc_enabled)
 		return;
 
-	csr = &vcpu->arch.guest_csr;
 #if defined(CONFIG_32BIT)
 	csr_write(CSR_VSTIMECMP, (u32)t->next_cycles);
 	csr_write(CSR_VSTIMECMPH, (u32)(t->next_cycles >> 32));
@@ -324,13 +322,11 @@ void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu)
 
 void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu_csr *csr;
 	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
 
 	if (!t->sstc_enabled)
 		return;
 
-	csr = &vcpu->arch.guest_csr;
 	t = &vcpu->arch.timer;
 #if defined(CONFIG_32BIT)
 	t->next_cycles = csr_read(CSR_VSTIMECMP);
diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
index cd2225304c82..e3f9bdf47c5f 100644
--- a/arch/riscv/mm/dma-noncoherent.c
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -12,7 +12,7 @@
 #include <linux/of_device.h>
 #include <asm/cacheflush.h>
 
-static unsigned int riscv_cbom_block_size = L1_CACHE_BYTES;
+unsigned int riscv_cbom_block_size;
 static bool noncoherent_supported;
 
 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
@@ -79,38 +79,41 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 void riscv_init_cbom_blocksize(void)
 {
 	struct device_node *node;
+	unsigned long cbom_hartid;
+	u32 val, probed_block_size;
 	int ret;
-	u32 val;
 
+	probed_block_size = 0;
 	for_each_of_cpu_node(node) {
 		unsigned long hartid;
-		int cbom_hartid;
 
 		ret = riscv_of_processor_hartid(node, &hartid);
 		if (ret)
 			continue;
 
-		if (hartid < 0)
-			continue;
-
 		/* set block-size for cbom extension if available */
 		ret = of_property_read_u32(node, "riscv,cbom-block-size", &val);
 		if (ret)
 			continue;
 
-		if (!riscv_cbom_block_size) {
-			riscv_cbom_block_size = val;
+		if (!probed_block_size) {
+			probed_block_size = val;
 			cbom_hartid = hartid;
 		} else {
-			if (riscv_cbom_block_size != val)
-				pr_warn("cbom-block-size mismatched between harts %d and %lu\n",
+			if (probed_block_size != val)
+				pr_warn("cbom-block-size mismatched between harts %lu and %lu\n",
 					cbom_hartid, hartid);
 		}
 	}
+
+	if (probed_block_size)
+		riscv_cbom_block_size = probed_block_size;
 }
 #endif
 
 void riscv_noncoherent_supported(void)
 {
+	WARN(!riscv_cbom_block_size,
+	     "Non-coherent DMA support enabled without a block size\n");
 	noncoherent_supported = true;
 }
diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index 5e49e4b4a4cc..86c56616e5de 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -118,10 +118,10 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
 	if (!numpages)
 		return 0;
 
-	mmap_read_lock(&init_mm);
+	mmap_write_lock(&init_mm);
 	ret =  walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL,
 				     &masks);
-	mmap_read_unlock(&init_mm);
+	mmap_write_unlock(&init_mm);
 
 	flush_tlb_kernel_range(start, end);
 
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index f6dfde577ce8..2a827002934b 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -40,8 +40,6 @@ CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_SCHED_AUTOGROUP=y
 CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
-CONFIG_USERFAULTFD=y
-# CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
 CONFIG_LIVEPATCH=y
 CONFIG_MARCH_ZEC12=y
@@ -74,6 +72,7 @@ CONFIG_MODULES=y
 CONFIG_MODULE_FORCE_LOAD=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
 CONFIG_MODULE_SIG_SHA256=y
@@ -93,6 +92,10 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_IOSCHED_BFQ=y
 CONFIG_BFQ_GROUP_IOSCHED=y
 CONFIG_BINFMT_MISC=m
+CONFIG_ZSWAP=y
+CONFIG_ZSMALLOC_STAT=y
+CONFIG_SLUB_STATS=y
+# CONFIG_COMPAT_BRK is not set
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
@@ -102,14 +105,12 @@ CONFIG_CMA_DEBUGFS=y
 CONFIG_CMA_SYSFS=y
 CONFIG_CMA_AREAS=7
 CONFIG_MEM_SOFT_DIRTY=y
-CONFIG_ZSWAP=y
-CONFIG_ZSMALLOC=y
-CONFIG_ZSMALLOC_STAT=y
 CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
 CONFIG_IDLE_PAGE_TRACKING=y
 CONFIG_PERCPU_STATS=y
 CONFIG_GUP_TEST=y
 CONFIG_ANON_VMA_NAME=y
+CONFIG_USERFAULTFD=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_PACKET_DIAG=m
@@ -167,6 +168,7 @@ CONFIG_BRIDGE_NETFILTER=m
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_PROCFS=y
 CONFIG_NF_CONNTRACK_EVENTS=y
 CONFIG_NF_CONNTRACK_TIMEOUT=y
 CONFIG_NF_CONNTRACK_TIMESTAMP=y
@@ -493,7 +495,6 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_ASIX is not set
 # CONFIG_NET_VENDOR_ATHEROS is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
-# CONFIG_NET_VENDOR_BROCADE is not set
 # CONFIG_NET_VENDOR_CADENCE is not set
 # CONFIG_NET_VENDOR_CAVIUM is not set
 # CONFIG_NET_VENDOR_CHELSIO is not set
@@ -509,7 +510,7 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_GOOGLE is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
-# CONFIG_NET_VENDOR_MICROSOFT is not set
+# CONFIG_NET_VENDOR_WANGXUN is not set
 # CONFIG_NET_VENDOR_LITEX is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 CONFIG_MLX4_EN=m
@@ -518,16 +519,18 @@ CONFIG_MLX5_CORE_EN=y
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_MICROCHIP is not set
 # CONFIG_NET_VENDOR_MICROSEMI is not set
+# CONFIG_NET_VENDOR_MICROSOFT is not set
 # CONFIG_NET_VENDOR_MYRI is not set
+# CONFIG_NET_VENDOR_NI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETERION is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
-# CONFIG_NET_VENDOR_NI is not set
 # CONFIG_NET_VENDOR_NVIDIA is not set
 # CONFIG_NET_VENDOR_OKI is not set
 # CONFIG_NET_VENDOR_PACKET_ENGINES is not set
 # CONFIG_NET_VENDOR_PENSANDO is not set
 # CONFIG_NET_VENDOR_QLOGIC is not set
+# CONFIG_NET_VENDOR_BROCADE is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RDC is not set
 # CONFIG_NET_VENDOR_REALTEK is not set
@@ -535,9 +538,9 @@ CONFIG_MLX5_CORE_EN=y
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
-# CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SILAN is not set
 # CONFIG_NET_VENDOR_SIS is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
@@ -570,6 +573,8 @@ CONFIG_VIRTIO_CONSOLE=m
 CONFIG_HW_RANDOM_VIRTIO=m
 CONFIG_HANGCHECK_TIMER=m
 CONFIG_TN3270_FS=y
+# CONFIG_RANDOM_TRUST_CPU is not set
+# CONFIG_RANDOM_TRUST_BOOTLOADER is not set
 CONFIG_PPS=m
 # CONFIG_PTP_1588_CLOCK is not set
 # CONFIG_HWMON is not set
@@ -727,18 +732,26 @@ CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_CRC32=m
-CONFIG_CRYPTO_BLAKE2S=m
+CONFIG_CRYPTO_CRC32_S390=y
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MD5=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
+CONFIG_CRYPTO_SHA512_S390=m
+CONFIG_CRYPTO_SHA1_S390=m
+CONFIG_CRYPTO_SHA256_S390=m
 CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_SM3=m
+CONFIG_CRYPTO_SHA3_256_S390=m
+CONFIG_CRYPTO_SHA3_512_S390=m
+CONFIG_CRYPTO_SM3_GENERIC=m
 CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_AES_TI=m
+CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_ARC4=m
 CONFIG_CRYPTO_BLOWFISH=m
@@ -746,11 +759,14 @@ CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_DES=m
+CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
+CONFIG_CRYPTO_CHACHA_S390=m
 CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SM4_GENERIC=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_842=m
@@ -766,16 +782,6 @@ CONFIG_CRYPTO_STATS=y
 CONFIG_ZCRYPT=m
 CONFIG_PKEY=m
 CONFIG_CRYPTO_PAES_S390=m
-CONFIG_CRYPTO_SHA1_S390=m
-CONFIG_CRYPTO_SHA256_S390=m
-CONFIG_CRYPTO_SHA512_S390=m
-CONFIG_CRYPTO_SHA3_256_S390=m
-CONFIG_CRYPTO_SHA3_512_S390=m
-CONFIG_CRYPTO_DES_S390=m
-CONFIG_CRYPTO_AES_S390=m
-CONFIG_CRYPTO_CHACHA_S390=m
-CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_CRYPTO_CRC32_S390=y
 CONFIG_CRYPTO_DEV_VIRTIO=m
 CONFIG_CORDIC=m
 CONFIG_CRYPTO_LIB_CURVE25519=m
@@ -797,6 +803,7 @@ CONFIG_HEADERS_INSTALL=y
 CONFIG_DEBUG_SECTION_MISMATCH=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_PAGEALLOC=y
+CONFIG_SLUB_DEBUG_ON=y
 CONFIG_PAGE_OWNER=y
 CONFIG_DEBUG_RODATA_TEST=y
 CONFIG_DEBUG_WX=y
@@ -808,8 +815,6 @@ CONFIG_DEBUG_OBJECTS_TIMERS=y
 CONFIG_DEBUG_OBJECTS_WORK=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
 CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
-CONFIG_SLUB_DEBUG_ON=y
-CONFIG_SLUB_STATS=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_VM=y
 CONFIG_DEBUG_VM_PGFLAGS=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 706df3a4a867..fb780e80e4c8 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -38,8 +38,6 @@ CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_SCHED_AUTOGROUP=y
 CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
-CONFIG_USERFAULTFD=y
-# CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
 CONFIG_LIVEPATCH=y
 CONFIG_MARCH_ZEC12=y
@@ -69,6 +67,7 @@ CONFIG_MODULES=y
 CONFIG_MODULE_FORCE_LOAD=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
 CONFIG_MODULE_SIG_SHA256=y
@@ -88,6 +87,9 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_IOSCHED_BFQ=y
 CONFIG_BFQ_GROUP_IOSCHED=y
 CONFIG_BINFMT_MISC=m
+CONFIG_ZSWAP=y
+CONFIG_ZSMALLOC_STAT=y
+# CONFIG_COMPAT_BRK is not set
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
@@ -95,13 +97,11 @@ CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CMA_SYSFS=y
 CONFIG_CMA_AREAS=7
 CONFIG_MEM_SOFT_DIRTY=y
-CONFIG_ZSWAP=y
-CONFIG_ZSMALLOC=y
-CONFIG_ZSMALLOC_STAT=y
 CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
 CONFIG_IDLE_PAGE_TRACKING=y
 CONFIG_PERCPU_STATS=y
 CONFIG_ANON_VMA_NAME=y
+CONFIG_USERFAULTFD=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_PACKET_DIAG=m
@@ -159,6 +159,7 @@ CONFIG_BRIDGE_NETFILTER=m
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_PROCFS=y
 CONFIG_NF_CONNTRACK_EVENTS=y
 CONFIG_NF_CONNTRACK_TIMEOUT=y
 CONFIG_NF_CONNTRACK_TIMESTAMP=y
@@ -484,7 +485,6 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_ASIX is not set
 # CONFIG_NET_VENDOR_ATHEROS is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
-# CONFIG_NET_VENDOR_BROCADE is not set
 # CONFIG_NET_VENDOR_CADENCE is not set
 # CONFIG_NET_VENDOR_CAVIUM is not set
 # CONFIG_NET_VENDOR_CHELSIO is not set
@@ -500,7 +500,7 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_GOOGLE is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
-# CONFIG_NET_VENDOR_MICROSOFT is not set
+# CONFIG_NET_VENDOR_WANGXUN is not set
 # CONFIG_NET_VENDOR_LITEX is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 CONFIG_MLX4_EN=m
@@ -509,16 +509,18 @@ CONFIG_MLX5_CORE_EN=y
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_MICROCHIP is not set
 # CONFIG_NET_VENDOR_MICROSEMI is not set
+# CONFIG_NET_VENDOR_MICROSOFT is not set
 # CONFIG_NET_VENDOR_MYRI is not set
+# CONFIG_NET_VENDOR_NI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETERION is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
-# CONFIG_NET_VENDOR_NI is not set
 # CONFIG_NET_VENDOR_NVIDIA is not set
 # CONFIG_NET_VENDOR_OKI is not set
 # CONFIG_NET_VENDOR_PACKET_ENGINES is not set
 # CONFIG_NET_VENDOR_PENSANDO is not set
 # CONFIG_NET_VENDOR_QLOGIC is not set
+# CONFIG_NET_VENDOR_BROCADE is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RDC is not set
 # CONFIG_NET_VENDOR_REALTEK is not set
@@ -526,9 +528,9 @@ CONFIG_MLX5_CORE_EN=y
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
-# CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SILAN is not set
 # CONFIG_NET_VENDOR_SIS is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
@@ -561,6 +563,8 @@ CONFIG_VIRTIO_CONSOLE=m
 CONFIG_HW_RANDOM_VIRTIO=m
 CONFIG_HANGCHECK_TIMER=m
 CONFIG_TN3270_FS=y
+# CONFIG_RANDOM_TRUST_CPU is not set
+# CONFIG_RANDOM_TRUST_BOOTLOADER is not set
 # CONFIG_PTP_1588_CLOCK is not set
 # CONFIG_HWMON is not set
 CONFIG_WATCHDOG=y
@@ -713,18 +717,26 @@ CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_CRC32=m
-CONFIG_CRYPTO_BLAKE2S=m
+CONFIG_CRYPTO_CRC32_S390=y
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MD5=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
+CONFIG_CRYPTO_SHA512_S390=m
+CONFIG_CRYPTO_SHA1_S390=m
+CONFIG_CRYPTO_SHA256_S390=m
 CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_SM3=m
+CONFIG_CRYPTO_SHA3_256_S390=m
+CONFIG_CRYPTO_SHA3_512_S390=m
+CONFIG_CRYPTO_SM3_GENERIC=m
 CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_AES_TI=m
+CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_ANUBIS=m
 CONFIG_CRYPTO_ARC4=m
 CONFIG_CRYPTO_BLOWFISH=m
@@ -732,11 +744,14 @@ CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_DES=m
+CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
+CONFIG_CRYPTO_CHACHA_S390=m
 CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_ARIA=m
 CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_SM4_GENERIC=m
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_842=m
@@ -752,16 +767,6 @@ CONFIG_CRYPTO_STATS=y
 CONFIG_ZCRYPT=m
 CONFIG_PKEY=m
 CONFIG_CRYPTO_PAES_S390=m
-CONFIG_CRYPTO_SHA1_S390=m
-CONFIG_CRYPTO_SHA256_S390=m
-CONFIG_CRYPTO_SHA512_S390=m
-CONFIG_CRYPTO_SHA3_256_S390=m
-CONFIG_CRYPTO_SHA3_512_S390=m
-CONFIG_CRYPTO_DES_S390=m
-CONFIG_CRYPTO_AES_S390=m
-CONFIG_CRYPTO_CHACHA_S390=m
-CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_CRYPTO_CRC32_S390=y
 CONFIG_CRYPTO_DEV_VIRTIO=m
 CONFIG_CORDIC=m
 CONFIG_PRIME_NUMBERS=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index f4976f611b94..a5576b8d4081 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -1,4 +1,3 @@
-# CONFIG_SWAP is not set
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BPF_SYSCALL=y
@@ -9,7 +8,6 @@ CONFIG_BPF_SYSCALL=y
 # CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_COMPAT_BRK is not set
 CONFIG_MARCH_ZEC12=y
 CONFIG_TUNE_ZEC12=y
 # CONFIG_COMPAT is not set
@@ -28,6 +26,8 @@ CONFIG_CRASH_DUMP=y
 # CONFIG_BLOCK_LEGACY_AUTOLOAD is not set
 CONFIG_PARTITION_ADVANCED=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_SWAP is not set
+# CONFIG_COMPAT_BRK is not set
 # CONFIG_COMPACTION is not set
 # CONFIG_MIGRATION is not set
 CONFIG_NET=y
@@ -53,10 +53,12 @@ CONFIG_ZFCP=y
 # CONFIG_HVC_IUCV is not set
 # CONFIG_HW_RANDOM_S390 is not set
 # CONFIG_HMC_DRV is not set
+# CONFIG_S390_UV_UAPI is not set
 # CONFIG_S390_TAPE is not set
 # CONFIG_VMCP is not set
 # CONFIG_MONWRITER is not set
 # CONFIG_S390_VMUR is not set
+# CONFIG_RANDOM_TRUST_BOOTLOADER is not set
 # CONFIG_HID is not set
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_VHOST_MENU is not set
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index f0bc4dc3e9bf..6511d15ace45 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -437,7 +437,7 @@ __init int hypfs_diag_init(void)
 	int rc;
 
 	if (diag204_probe()) {
-		pr_err("The hardware system does not support hypfs\n");
+		pr_info("The hardware system does not support hypfs\n");
 		return -ENODATA;
 	}
 
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 5c97f48cea91..ee919bfc8186 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -496,9 +496,9 @@ fail_hypfs_sprp_exit:
 	hypfs_vm_exit();
 fail_hypfs_diag_exit:
 	hypfs_diag_exit();
+	pr_err("Initialization of hypfs failed with rc=%i\n", rc);
 fail_dbfs_exit:
 	hypfs_dbfs_exit();
-	pr_err("Initialization of hypfs failed with rc=%i\n", rc);
 	return rc;
 }
 device_initcall(hypfs_init)
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 9a7d15da966e..2de74fcd0578 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -176,14 +176,8 @@ arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 	return old & mask;
 }
 
-static __always_inline bool
-arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
-{
-	const volatile unsigned long *p = __bitops_word(nr, addr);
-	unsigned long mask = __bitops_mask(nr);
-
-	return *p & mask;
-}
+#define arch_test_bit generic_test_bit
+#define arch_test_bit_acquire generic_test_bit_acquire
 
 static inline bool arch_test_and_set_bit_lock(unsigned long nr,
 					      volatile unsigned long *ptr)
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index f22beda9e6d5..ccdbccfde148 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -28,9 +28,11 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 static inline int prepare_hugepage_range(struct file *file,
 			unsigned long addr, unsigned long len)
 {
-	if (len & ~HPAGE_MASK)
+	struct hstate *h = hstate_file(file);
+
+	if (len & ~huge_page_mask(h))
 		return -EINVAL;
-	if (addr & ~HPAGE_MASK)
+	if (addr & ~huge_page_mask(h))
 		return -EINVAL;
 	return 0;
 }
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index f39092e0ceaa..b1e98a9ed152 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -1038,16 +1038,11 @@ static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
 #define __KVM_HAVE_ARCH_VM_FREE
 void kvm_arch_free_vm(struct kvm *kvm);
 
-#ifdef CONFIG_VFIO_PCI_ZDEV_KVM
-int kvm_s390_pci_register_kvm(struct zpci_dev *zdev, struct kvm *kvm);
-void kvm_s390_pci_unregister_kvm(struct zpci_dev *zdev);
-#else
-static inline int kvm_s390_pci_register_kvm(struct zpci_dev *dev,
-					    struct kvm *kvm)
-{
-	return -EPERM;
-}
-static inline void kvm_s390_pci_unregister_kvm(struct zpci_dev *dev) {}
-#endif
+struct zpci_kvm_hook {
+	int (*kvm_register)(void *opaque, struct kvm *kvm);
+	void (*kvm_unregister)(void *opaque);
+};
+
+extern struct zpci_kvm_hook zpci_kvm_hook;
 
 #endif
diff --git a/arch/s390/include/asm/softirq_stack.h b/arch/s390/include/asm/softirq_stack.h
index af68d6c1d584..1ac5115d3115 100644
--- a/arch/s390/include/asm/softirq_stack.h
+++ b/arch/s390/include/asm/softirq_stack.h
@@ -5,7 +5,7 @@
 #include <asm/lowcore.h>
 #include <asm/stacktrace.h>
 
-#ifndef CONFIG_PREEMPT_RT
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
 static inline void do_softirq_own_stack(void)
 {
 	call_on_stack(0, S390_lowcore.async_stack, void, __do_softirq);
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 60ac66aab163..31cb9b00a36b 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -64,7 +64,7 @@ static inline unsigned long nmi_get_mcesa_size(void)
  * structure. The structure is required for machine check happening
  * early in the boot process.
  */
-static struct mcesa boot_mcesa __initdata __aligned(MCESA_MAX_SIZE);
+static struct mcesa boot_mcesa __aligned(MCESA_MAX_SIZE);
 
 void __init nmi_alloc_mcesa_early(u64 *mcesad)
 {
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 89949b9f3cf8..d5119e039d85 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -91,6 +91,18 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 	memcpy(dst, src, arch_task_struct_size);
 	dst->thread.fpu.regs = dst->thread.fpu.fprs;
+
+	/*
+	 * Don't transfer over the runtime instrumentation or the guarded
+	 * storage control block pointers. These fields are cleared here instead
+	 * of in copy_thread() to avoid premature freeing of associated memory
+	 * on fork() failure. Wait to clear the RI flag because ->stack still
+	 * refers to the source thread.
+	 */
+	dst->thread.ri_cb = NULL;
+	dst->thread.gs_cb = NULL;
+	dst->thread.gs_bc_cb = NULL;
+
 	return 0;
 }
 
@@ -150,13 +162,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	frame->childregs.flags = 0;
 	if (new_stackp)
 		frame->childregs.gprs[15] = new_stackp;
-
-	/* Don't copy runtime instrumentation info */
-	p->thread.ri_cb = NULL;
+	/*
+	 * Clear the runtime instrumentation flag after the above childregs
+	 * copy. The CB pointer was already cleared in arch_dup_task_struct().
+	 */
 	frame->childregs.psw.mask &= ~PSW_MASK_RI;
-	/* Don't copy guarded storage control block */
-	p->thread.gs_cb = NULL;
-	p->thread.gs_bc_cb = NULL;
 
 	/* Set a new TLS ?  */
 	if (clone_flags & CLONE_SETTLS) {
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index ed4fbbbdd1b0..bbd4bde4f65d 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -479,6 +479,7 @@ static void __init setup_lowcore_dat_off(void)
 	put_abs_lowcore(restart_data, lc->restart_data);
 	put_abs_lowcore(restart_source, lc->restart_source);
 	put_abs_lowcore(restart_psw, lc->restart_psw);
+	put_abs_lowcore(mcesad, lc->mcesad);
 
 	mcck_stack = (unsigned long)memblock_alloc(THREAD_SIZE, THREAD_SIZE);
 	if (!mcck_stack)
@@ -507,8 +508,8 @@ static void __init setup_lowcore_dat_on(void)
 	S390_lowcore.svc_new_psw.mask |= PSW_MASK_DAT;
 	S390_lowcore.program_new_psw.mask |= PSW_MASK_DAT;
 	S390_lowcore.io_new_psw.mask |= PSW_MASK_DAT;
-	__ctl_store(S390_lowcore.cregs_save_area, 0, 15);
 	__ctl_set_bit(0, 28);
+	__ctl_store(S390_lowcore.cregs_save_area, 0, 15);
 	put_abs_lowcore(restart_flags, RESTART_FLAG_CTLREGS);
 	put_abs_lowcore(program_new_psw, lc->program_new_psw);
 	for (cr = 0; cr < ARRAY_SIZE(lc->cregs_save_area); cr++)
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 2e526f11b91e..5ea3830af0cc 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -131,6 +131,7 @@ SECTIONS
 	/*
 	 * Table with the patch locations to undo expolines
 	*/
+	. = ALIGN(4);
 	.nospec_call_table : {
 		__nospec_call_start = . ;
 		*(.s390_indirect*)
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 082ec5f2c3a5..0243b6e38d36 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -489,6 +489,8 @@ enum prot_type {
 	PROT_TYPE_ALC  = 2,
 	PROT_TYPE_DAT  = 3,
 	PROT_TYPE_IEP  = 4,
+	/* Dummy value for passing an initialized value when code != PGM_PROTECTION */
+	PROT_NONE,
 };
 
 static int trans_exc_ending(struct kvm_vcpu *vcpu, int code, unsigned long gva, u8 ar,
@@ -504,6 +506,10 @@ static int trans_exc_ending(struct kvm_vcpu *vcpu, int code, unsigned long gva,
 	switch (code) {
 	case PGM_PROTECTION:
 		switch (prot) {
+		case PROT_NONE:
+			/* We should never get here, acts like termination */
+			WARN_ON_ONCE(1);
+			break;
 		case PROT_TYPE_IEP:
 			tec->b61 = 1;
 			fallthrough;
@@ -968,8 +974,10 @@ static int guest_range_to_gpas(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
 				return rc;
 		} else {
 			gpa = kvm_s390_real_to_abs(vcpu, ga);
-			if (kvm_is_error_gpa(vcpu->kvm, gpa))
+			if (kvm_is_error_gpa(vcpu->kvm, gpa)) {
 				rc = PGM_ADDRESSING;
+				prot = PROT_NONE;
+			}
 		}
 		if (rc)
 			return trans_exc(vcpu, rc, ga, ar, mode, prot);
@@ -1112,8 +1120,6 @@ int access_guest_with_key(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
 		if (rc == PGM_PROTECTION && try_storage_prot_override)
 			rc = access_guest_page_with_key(vcpu->kvm, mode, gpas[idx],
 							data, fragment_len, PAGE_SPO_ACC);
-		if (rc == PGM_PROTECTION)
-			prot = PROT_TYPE_KEYC;
 		if (rc)
 			break;
 		len -= fragment_len;
@@ -1123,6 +1129,10 @@ int access_guest_with_key(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar,
 	if (rc > 0) {
 		bool terminate = (mode == GACC_STORE) && (idx > 0);
 
+		if (rc == PGM_PROTECTION)
+			prot = PROT_TYPE_KEYC;
+		else
+			prot = PROT_NONE;
 		rc = trans_exc_ending(vcpu, rc, ga, ar, mode, prot, terminate);
 	}
 out_unlock:
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index b9c944b262c7..ab569faf0df2 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -3324,7 +3324,7 @@ static void aen_host_forward(unsigned long si)
 	if (gaite->count == 0)
 		return;
 	if (gaite->aisb != 0)
-		set_bit_inv(gaite->aisbo, (unsigned long *)gaite->aisb);
+		set_bit_inv(gaite->aisbo, phys_to_virt(gaite->aisb));
 
 	kvm = kvm_s390_pci_si_to_kvm(aift, si);
 	if (!kvm)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index edfd4bbd0cba..b7ef0b71014d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -505,7 +505,7 @@ int kvm_arch_init(void *opaque)
 		goto out;
 	}
 
-	if (kvm_s390_pci_interp_allowed()) {
+	if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) {
 		rc = kvm_s390_pci_init();
 		if (rc) {
 			pr_err("Unable to allocate AIFT for PCI\n");
@@ -527,7 +527,7 @@ out:
 void kvm_arch_exit(void)
 {
 	kvm_s390_gib_destroy();
-	if (kvm_s390_pci_interp_allowed())
+	if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM))
 		kvm_s390_pci_exit();
 	debug_unregister(kvm_s390_dbf);
 	debug_unregister(kvm_s390_dbf_uv);
diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c
index 4946fb7757d6..c50c1645c0ae 100644
--- a/arch/s390/kvm/pci.c
+++ b/arch/s390/kvm/pci.c
@@ -58,7 +58,7 @@ static int zpci_setup_aipb(u8 nisc)
 	if (!zpci_aipb)
 		return -ENOMEM;
 
-	aift->sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC, 0);
+	aift->sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC, NULL);
 	if (!aift->sbv) {
 		rc = -ENOMEM;
 		goto free_aipb;
@@ -71,7 +71,7 @@ static int zpci_setup_aipb(u8 nisc)
 		rc = -ENOMEM;
 		goto free_sbv;
 	}
-	aift->gait = (struct zpci_gaite *)page_to_phys(page);
+	aift->gait = (struct zpci_gaite *)page_to_virt(page);
 
 	zpci_aipb->aipb.faisb = virt_to_phys(aift->sbv->vector);
 	zpci_aipb->aipb.gait = virt_to_phys(aift->gait);
@@ -373,7 +373,7 @@ static int kvm_s390_pci_aif_disable(struct zpci_dev *zdev, bool force)
 		gaite->gisc = 0;
 		gaite->aisbo = 0;
 		gaite->gisa = 0;
-		aift->kzdev[zdev->aisb] = 0;
+		aift->kzdev[zdev->aisb] = NULL;
 		/* Clear zdev info */
 		airq_iv_free_bit(aift->sbv, zdev->aisb);
 		airq_iv_release(zdev->aibv);
@@ -431,8 +431,9 @@ static void kvm_s390_pci_dev_release(struct zpci_dev *zdev)
  * available, enable them and let userspace indicate whether or not they will
  * be used (specify SHM bit to disable).
  */
-int kvm_s390_pci_register_kvm(struct zpci_dev *zdev, struct kvm *kvm)
+static int kvm_s390_pci_register_kvm(void *opaque, struct kvm *kvm)
 {
+	struct zpci_dev *zdev = opaque;
 	int rc;
 
 	if (!zdev)
@@ -510,10 +511,10 @@ err:
 	kvm_put_kvm(kvm);
 	return rc;
 }
-EXPORT_SYMBOL_GPL(kvm_s390_pci_register_kvm);
 
-void kvm_s390_pci_unregister_kvm(struct zpci_dev *zdev)
+static void kvm_s390_pci_unregister_kvm(void *opaque)
 {
+	struct zpci_dev *zdev = opaque;
 	struct kvm *kvm;
 
 	if (!zdev)
@@ -566,7 +567,6 @@ out:
 
 	kvm_put_kvm(kvm);
 }
-EXPORT_SYMBOL_GPL(kvm_s390_pci_unregister_kvm);
 
 void kvm_s390_pci_init_list(struct kvm *kvm)
 {
@@ -672,6 +672,12 @@ out:
 
 int kvm_s390_pci_init(void)
 {
+	zpci_kvm_hook.kvm_register = kvm_s390_pci_register_kvm;
+	zpci_kvm_hook.kvm_unregister = kvm_s390_pci_unregister_kvm;
+
+	if (!kvm_s390_pci_interp_allowed())
+		return 0;
+
 	aift = kzalloc(sizeof(struct zpci_aift), GFP_KERNEL);
 	if (!aift)
 		return -ENOMEM;
@@ -684,6 +690,12 @@ int kvm_s390_pci_init(void)
 
 void kvm_s390_pci_exit(void)
 {
+	zpci_kvm_hook.kvm_register = NULL;
+	zpci_kvm_hook.kvm_unregister = NULL;
+
+	if (!kvm_s390_pci_interp_allowed())
+		return;
+
 	mutex_destroy(&aift->aift_lock);
 
 	kfree(aift);
diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h
index 3a3606c3a0fe..486d06ef563f 100644
--- a/arch/s390/kvm/pci.h
+++ b/arch/s390/kvm/pci.h
@@ -46,9 +46,9 @@ extern struct zpci_aift *aift;
 static inline struct kvm *kvm_s390_pci_si_to_kvm(struct zpci_aift *aift,
 						 unsigned long si)
 {
-	if (!IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM) || aift->kzdev == 0 ||
-	    aift->kzdev[si] == 0)
-		return 0;
+	if (!IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM) || !aift->kzdev ||
+	    !aift->kzdev[si])
+		return NULL;
 	return aift->kzdev[si]->kvm;
 };
 
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 13449941516c..9ab6ca6f7f59 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -379,7 +379,9 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
 	flags = FAULT_FLAG_DEFAULT;
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
-	if (access == VM_WRITE || is_write)
+	if (is_write)
+		access = VM_WRITE;
+	if (access == VM_WRITE)
 		flags |= FAULT_FLAG_WRITE;
 	mmap_read_lock(mm);
 
@@ -419,8 +421,6 @@ retry:
 	if (unlikely(!(vma->vm_flags & access)))
 		goto out_up;
 
-	if (is_vm_hugetlb_page(vma))
-		address &= HPAGE_MASK;
 	/*
 	 * If for any reason at all we couldn't handle the fault,
 	 * make sure we exit gracefully rather than endlessly redo
diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile
index bf557a1b789c..5ae31ca9dd44 100644
--- a/arch/s390/pci/Makefile
+++ b/arch/s390/pci/Makefile
@@ -5,5 +5,5 @@
 
 obj-$(CONFIG_PCI)	+= pci.o pci_irq.o pci_dma.o pci_clp.o pci_sysfs.o \
 			   pci_event.o pci_debug.o pci_insn.o pci_mmio.o \
-			   pci_bus.o
+			   pci_bus.o pci_kvm_hook.o
 obj-$(CONFIG_PCI_IOV)	+= pci_iov.o
diff --git a/arch/s390/pci/pci_kvm_hook.c b/arch/s390/pci/pci_kvm_hook.c
new file mode 100644
index 000000000000..ff34baf50a3e
--- /dev/null
+++ b/arch/s390/pci/pci_kvm_hook.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VFIO ZPCI devices support
+ *
+ * Copyright (C) IBM Corp. 2022.  All rights reserved.
+ *	Author(s): Pierre Morel <pmorel@linux.ibm.com>
+ */
+#include <linux/kvm_host.h>
+
+struct zpci_kvm_hook zpci_kvm_hook;
+EXPORT_SYMBOL_GPL(zpci_kvm_hook);
diff --git a/arch/sh/include/asm/bitops-op32.h b/arch/sh/include/asm/bitops-op32.h
index 565a85d8b7fb..5ace89b46507 100644
--- a/arch/sh/include/asm/bitops-op32.h
+++ b/arch/sh/include/asm/bitops-op32.h
@@ -135,16 +135,8 @@ arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 	return (old & mask) != 0;
 }
 
-/**
- * arch_test_bit - Determine whether a bit is set
- * @nr: bit number to test
- * @addr: Address to start counting from
- */
-static __always_inline bool
-arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
-{
-	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
-}
+#define arch_test_bit generic_test_bit
+#define arch_test_bit_acquire generic_test_bit_acquire
 
 #include <asm-generic/bitops/non-instrumented-non-atomic.h>
 
diff --git a/arch/sh/include/asm/sections.h b/arch/sh/include/asm/sections.h
index 8edb824049b9..0cb0ca149ac3 100644
--- a/arch/sh/include/asm/sections.h
+++ b/arch/sh/include/asm/sections.h
@@ -4,7 +4,7 @@
 
 #include <asm-generic/sections.h>
 
-extern long __machvec_start, __machvec_end;
+extern char __machvec_start[], __machvec_end[];
 extern char __uncached_start, __uncached_end;
 extern char __start_eh_frame[], __stop_eh_frame[];
 
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 909276738078..4e6835de54cf 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -149,7 +149,7 @@ void irq_ctx_exit(int cpu)
 	hardirq_ctx[cpu] = NULL;
 }
 
-#ifndef CONFIG_PREEMPT_RT
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
 void do_softirq_own_stack(void)
 {
 	struct thread_info *curctx;
diff --git a/arch/sh/kernel/machvec.c b/arch/sh/kernel/machvec.c
index d606679a211e..57efaf5b82ae 100644
--- a/arch/sh/kernel/machvec.c
+++ b/arch/sh/kernel/machvec.c
@@ -20,8 +20,8 @@
 #define MV_NAME_SIZE 32
 
 #define for_each_mv(mv) \
-	for ((mv) = (struct sh_machine_vector *)&__machvec_start; \
-	     (mv) && (unsigned long)(mv) < (unsigned long)&__machvec_end; \
+	for ((mv) = (struct sh_machine_vector *)__machvec_start; \
+	     (mv) && (unsigned long)(mv) < (unsigned long)__machvec_end; \
 	     (mv)++)
 
 static struct sh_machine_vector * __init get_mv_byname(const char *name)
@@ -87,8 +87,8 @@ void __init sh_mv_setup(void)
 	if (!machvec_selected) {
 		unsigned long machvec_size;
 
-		machvec_size = ((unsigned long)&__machvec_end -
-				(unsigned long)&__machvec_start);
+		machvec_size = ((unsigned long)__machvec_end -
+				(unsigned long)__machvec_start);
 
 		/*
 		 * Sanity check for machvec section alignment. Ensure
@@ -102,7 +102,7 @@ void __init sh_mv_setup(void)
 		 * vector (usually the only one) from .machvec.init.
 		 */
 		if (machvec_size >= sizeof(struct sh_machine_vector))
-			sh_mv = *(struct sh_machine_vector *)&__machvec_start;
+			sh_mv = *(struct sh_machine_vector *)__machvec_start;
 	}
 
 	pr_notice("Booting machvec: %s\n", get_system_type());
diff --git a/arch/sparc/include/asm/smp_32.h b/arch/sparc/include/asm/smp_32.h
index 856081761b0f..2cf7971d7f6c 100644
--- a/arch/sparc/include/asm/smp_32.h
+++ b/arch/sparc/include/asm/smp_32.h
@@ -33,9 +33,6 @@ extern volatile unsigned long cpu_callin_map[NR_CPUS];
 extern cpumask_t smp_commenced_mask;
 extern struct linux_prom_registers smp_penguin_ctable;
 
-typedef void (*smpfunc_t)(unsigned long, unsigned long, unsigned long,
-		       unsigned long, unsigned long);
-
 void cpu_panic(void);
 
 /*
@@ -57,7 +54,7 @@ void smp_bogo(struct seq_file *);
 void smp_info(struct seq_file *);
 
 struct sparc32_ipi_ops {
-	void (*cross_call)(smpfunc_t func, cpumask_t mask, unsigned long arg1,
+	void (*cross_call)(void *func, cpumask_t mask, unsigned long arg1,
 			   unsigned long arg2, unsigned long arg3,
 			   unsigned long arg4);
 	void (*resched)(int cpu);
@@ -66,28 +63,28 @@ struct sparc32_ipi_ops {
 };
 extern const struct sparc32_ipi_ops *sparc32_ipi_ops;
 
-static inline void xc0(smpfunc_t func)
+static inline void xc0(void *func)
 {
 	sparc32_ipi_ops->cross_call(func, *cpu_online_mask, 0, 0, 0, 0);
 }
 
-static inline void xc1(smpfunc_t func, unsigned long arg1)
+static inline void xc1(void *func, unsigned long arg1)
 {
 	sparc32_ipi_ops->cross_call(func, *cpu_online_mask, arg1, 0, 0, 0);
 }
-static inline void xc2(smpfunc_t func, unsigned long arg1, unsigned long arg2)
+static inline void xc2(void *func, unsigned long arg1, unsigned long arg2)
 {
 	sparc32_ipi_ops->cross_call(func, *cpu_online_mask, arg1, arg2, 0, 0);
 }
 
-static inline void xc3(smpfunc_t func, unsigned long arg1, unsigned long arg2,
+static inline void xc3(void *func, unsigned long arg1, unsigned long arg2,
 		       unsigned long arg3)
 {
 	sparc32_ipi_ops->cross_call(func, *cpu_online_mask,
 				    arg1, arg2, arg3, 0);
 }
 
-static inline void xc4(smpfunc_t func, unsigned long arg1, unsigned long arg2,
+static inline void xc4(void *func, unsigned long arg1, unsigned long arg2,
 		       unsigned long arg3, unsigned long arg4)
 {
 	sparc32_ipi_ops->cross_call(func, *cpu_online_mask,
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 41fa1be980a3..72da2e10e255 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -855,7 +855,7 @@ void __irq_entry handler_irq(int pil, struct pt_regs *regs)
 	set_irq_regs(old_regs);
 }
 
-#ifndef CONFIG_PREEMPT_RT
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
 void do_softirq_own_stack(void)
 {
 	void *orig_sp, *sp = softirq_stack[smp_processor_id()];
diff --git a/arch/sparc/kernel/leon_smp.c b/arch/sparc/kernel/leon_smp.c
index 1eed26d423fb..991e9ad3d3e8 100644
--- a/arch/sparc/kernel/leon_smp.c
+++ b/arch/sparc/kernel/leon_smp.c
@@ -359,7 +359,7 @@ void leonsmp_ipi_interrupt(void)
 }
 
 static struct smp_funcall {
-	smpfunc_t func;
+	void *func;
 	unsigned long arg1;
 	unsigned long arg2;
 	unsigned long arg3;
@@ -372,7 +372,7 @@ static struct smp_funcall {
 static DEFINE_SPINLOCK(cross_call_lock);
 
 /* Cross calls must be serialized, at least currently. */
-static void leon_cross_call(smpfunc_t func, cpumask_t mask, unsigned long arg1,
+static void leon_cross_call(void *func, cpumask_t mask, unsigned long arg1,
 			    unsigned long arg2, unsigned long arg3,
 			    unsigned long arg4)
 {
@@ -384,7 +384,7 @@ static void leon_cross_call(smpfunc_t func, cpumask_t mask, unsigned long arg1,
 
 		{
 			/* If you make changes here, make sure gcc generates proper code... */
-			register smpfunc_t f asm("i0") = func;
+			register void *f asm("i0") = func;
 			register unsigned long a1 asm("i1") = arg1;
 			register unsigned long a2 asm("i2") = arg2;
 			register unsigned long a3 asm("i3") = arg3;
@@ -444,11 +444,13 @@ static void leon_cross_call(smpfunc_t func, cpumask_t mask, unsigned long arg1,
 /* Running cross calls. */
 void leon_cross_call_irq(void)
 {
+	void (*func)(unsigned long, unsigned long, unsigned long, unsigned long,
+		     unsigned long) = ccall_info.func;
 	int i = smp_processor_id();
 
 	ccall_info.processors_in[i] = 1;
-	ccall_info.func(ccall_info.arg1, ccall_info.arg2, ccall_info.arg3,
-			ccall_info.arg4, ccall_info.arg5);
+	func(ccall_info.arg1, ccall_info.arg2, ccall_info.arg3, ccall_info.arg4,
+	     ccall_info.arg5);
 	ccall_info.processors_out[i] = 1;
 }
 
diff --git a/arch/sparc/kernel/sun4d_smp.c b/arch/sparc/kernel/sun4d_smp.c
index ff30f03beb7c..9a62a5cf3337 100644
--- a/arch/sparc/kernel/sun4d_smp.c
+++ b/arch/sparc/kernel/sun4d_smp.c
@@ -268,7 +268,7 @@ static void sun4d_ipi_resched(int cpu)
 }
 
 static struct smp_funcall {
-	smpfunc_t func;
+	void *func;
 	unsigned long arg1;
 	unsigned long arg2;
 	unsigned long arg3;
@@ -281,7 +281,7 @@ static struct smp_funcall {
 static DEFINE_SPINLOCK(cross_call_lock);
 
 /* Cross calls must be serialized, at least currently. */
-static void sun4d_cross_call(smpfunc_t func, cpumask_t mask, unsigned long arg1,
+static void sun4d_cross_call(void *func, cpumask_t mask, unsigned long arg1,
 			     unsigned long arg2, unsigned long arg3,
 			     unsigned long arg4)
 {
@@ -296,7 +296,7 @@ static void sun4d_cross_call(smpfunc_t func, cpumask_t mask, unsigned long arg1,
 			 * If you make changes here, make sure
 			 * gcc generates proper code...
 			 */
-			register smpfunc_t f asm("i0") = func;
+			register void *f asm("i0") = func;
 			register unsigned long a1 asm("i1") = arg1;
 			register unsigned long a2 asm("i2") = arg2;
 			register unsigned long a3 asm("i3") = arg3;
@@ -353,11 +353,13 @@ static void sun4d_cross_call(smpfunc_t func, cpumask_t mask, unsigned long arg1,
 /* Running cross calls. */
 void smp4d_cross_call_irq(void)
 {
+	void (*func)(unsigned long, unsigned long, unsigned long, unsigned long,
+		     unsigned long) = ccall_info.func;
 	int i = hard_smp_processor_id();
 
 	ccall_info.processors_in[i] = 1;
-	ccall_info.func(ccall_info.arg1, ccall_info.arg2, ccall_info.arg3,
-			ccall_info.arg4, ccall_info.arg5);
+	func(ccall_info.arg1, ccall_info.arg2, ccall_info.arg3, ccall_info.arg4,
+	     ccall_info.arg5);
 	ccall_info.processors_out[i] = 1;
 }
 
diff --git a/arch/sparc/kernel/sun4m_smp.c b/arch/sparc/kernel/sun4m_smp.c
index 228a6527082d..056df034e79e 100644
--- a/arch/sparc/kernel/sun4m_smp.c
+++ b/arch/sparc/kernel/sun4m_smp.c
@@ -157,7 +157,7 @@ static void sun4m_ipi_mask_one(int cpu)
 }
 
 static struct smp_funcall {
-	smpfunc_t func;
+	void *func;
 	unsigned long arg1;
 	unsigned long arg2;
 	unsigned long arg3;
@@ -170,7 +170,7 @@ static struct smp_funcall {
 static DEFINE_SPINLOCK(cross_call_lock);
 
 /* Cross calls must be serialized, at least currently. */
-static void sun4m_cross_call(smpfunc_t func, cpumask_t mask, unsigned long arg1,
+static void sun4m_cross_call(void *func, cpumask_t mask, unsigned long arg1,
 			     unsigned long arg2, unsigned long arg3,
 			     unsigned long arg4)
 {
@@ -230,11 +230,13 @@ static void sun4m_cross_call(smpfunc_t func, cpumask_t mask, unsigned long arg1,
 /* Running cross calls. */
 void smp4m_cross_call_irq(void)
 {
+	void (*func)(unsigned long, unsigned long, unsigned long, unsigned long,
+		     unsigned long) = ccall_info.func;
 	int i = smp_processor_id();
 
 	ccall_info.processors_in[i] = 1;
-	ccall_info.func(ccall_info.arg1, ccall_info.arg2, ccall_info.arg3,
-			ccall_info.arg4, ccall_info.arg5);
+	func(ccall_info.arg1, ccall_info.arg2, ccall_info.arg3, ccall_info.arg4,
+	     ccall_info.arg5);
 	ccall_info.processors_out[i] = 1;
 }
 
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index a9aa6a92c7fe..13f027afc875 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -1636,19 +1636,19 @@ static void __init get_srmmu_type(void)
 /* Local cross-calls. */
 static void smp_flush_page_for_dma(unsigned long page)
 {
-	xc1((smpfunc_t) local_ops->page_for_dma, page);
+	xc1(local_ops->page_for_dma, page);
 	local_ops->page_for_dma(page);
 }
 
 static void smp_flush_cache_all(void)
 {
-	xc0((smpfunc_t) local_ops->cache_all);
+	xc0(local_ops->cache_all);
 	local_ops->cache_all();
 }
 
 static void smp_flush_tlb_all(void)
 {
-	xc0((smpfunc_t) local_ops->tlb_all);
+	xc0(local_ops->tlb_all);
 	local_ops->tlb_all();
 }
 
@@ -1659,7 +1659,7 @@ static void smp_flush_cache_mm(struct mm_struct *mm)
 		cpumask_copy(&cpu_mask, mm_cpumask(mm));
 		cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
 		if (!cpumask_empty(&cpu_mask))
-			xc1((smpfunc_t) local_ops->cache_mm, (unsigned long) mm);
+			xc1(local_ops->cache_mm, (unsigned long)mm);
 		local_ops->cache_mm(mm);
 	}
 }
@@ -1671,7 +1671,7 @@ static void smp_flush_tlb_mm(struct mm_struct *mm)
 		cpumask_copy(&cpu_mask, mm_cpumask(mm));
 		cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
 		if (!cpumask_empty(&cpu_mask)) {
-			xc1((smpfunc_t) local_ops->tlb_mm, (unsigned long) mm);
+			xc1(local_ops->tlb_mm, (unsigned long)mm);
 			if (atomic_read(&mm->mm_users) == 1 && current->active_mm == mm)
 				cpumask_copy(mm_cpumask(mm),
 					     cpumask_of(smp_processor_id()));
@@ -1691,8 +1691,8 @@ static void smp_flush_cache_range(struct vm_area_struct *vma,
 		cpumask_copy(&cpu_mask, mm_cpumask(mm));
 		cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
 		if (!cpumask_empty(&cpu_mask))
-			xc3((smpfunc_t) local_ops->cache_range,
-			    (unsigned long) vma, start, end);
+			xc3(local_ops->cache_range, (unsigned long)vma, start,
+			    end);
 		local_ops->cache_range(vma, start, end);
 	}
 }
@@ -1708,8 +1708,8 @@ static void smp_flush_tlb_range(struct vm_area_struct *vma,
 		cpumask_copy(&cpu_mask, mm_cpumask(mm));
 		cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
 		if (!cpumask_empty(&cpu_mask))
-			xc3((smpfunc_t) local_ops->tlb_range,
-			    (unsigned long) vma, start, end);
+			xc3(local_ops->tlb_range, (unsigned long)vma, start,
+			    end);
 		local_ops->tlb_range(vma, start, end);
 	}
 }
@@ -1723,8 +1723,7 @@ static void smp_flush_cache_page(struct vm_area_struct *vma, unsigned long page)
 		cpumask_copy(&cpu_mask, mm_cpumask(mm));
 		cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
 		if (!cpumask_empty(&cpu_mask))
-			xc2((smpfunc_t) local_ops->cache_page,
-			    (unsigned long) vma, page);
+			xc2(local_ops->cache_page, (unsigned long)vma, page);
 		local_ops->cache_page(vma, page);
 	}
 }
@@ -1738,8 +1737,7 @@ static void smp_flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
 		cpumask_copy(&cpu_mask, mm_cpumask(mm));
 		cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
 		if (!cpumask_empty(&cpu_mask))
-			xc2((smpfunc_t) local_ops->tlb_page,
-			    (unsigned long) vma, page);
+			xc2(local_ops->tlb_page, (unsigned long)vma, page);
 		local_ops->tlb_page(vma, page);
 	}
 }
@@ -1753,7 +1751,7 @@ static void smp_flush_page_to_ram(unsigned long page)
 	 * XXX This experiment failed, research further... -DaveM
 	 */
 #if 1
-	xc1((smpfunc_t) local_ops->page_to_ram, page);
+	xc1(local_ops->page_to_ram, page);
 #endif
 	local_ops->page_to_ram(page);
 }
@@ -1764,8 +1762,7 @@ static void smp_flush_sig_insns(struct mm_struct *mm, unsigned long insn_addr)
 	cpumask_copy(&cpu_mask, mm_cpumask(mm));
 	cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
 	if (!cpumask_empty(&cpu_mask))
-		xc2((smpfunc_t) local_ops->sig_insns,
-		    (unsigned long) mm, insn_addr);
+		xc2(local_ops->sig_insns, (unsigned long)mm, insn_addr);
 	local_ops->sig_insns(mm, insn_addr);
 }
 
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index 78de31ac1da7..ad4ff3b0e91e 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -6,6 +6,7 @@ config UML
 	bool
 	default y
 	select ARCH_EPHEMERAL_INODES
+	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_STRNCPY_FROM_USER
diff --git a/arch/um/Makefile b/arch/um/Makefile
index f2fe63bfd819..f1d4d67157be 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -132,10 +132,18 @@ export LDS_ELF_FORMAT := $(ELF_FORMAT)
 # The wrappers will select whether using "malloc" or the kernel allocator.
 LINK_WRAPS = -Wl,--wrap,malloc -Wl,--wrap,free -Wl,--wrap,calloc
 
+# Avoid binutils 2.39+ warnings by marking the stack non-executable and
+# ignorning warnings for the kallsyms sections.
+LDFLAGS_EXECSTACK = -z noexecstack
+ifeq ($(CONFIG_LD_IS_BFD),y)
+LDFLAGS_EXECSTACK += $(call ld-option,--no-warn-rwx-segments)
+endif
+
 LD_FLAGS_CMDLINE = $(foreach opt,$(KBUILD_LDFLAGS),-Wl,$(opt))
 
 # Used by link-vmlinux.sh which has special support for um link
 export CFLAGS_vmlinux := $(LINK-y) $(LINK_WRAPS) $(LD_FLAGS_CMDLINE)
+export LDFLAGS_vmlinux := $(LDFLAGS_EXECSTACK)
 
 # When cleaning we don't include .config, so we don't include
 # TT or skas makefiles and don't clean skas_ptregs.h.
diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c
index 79e38afd4b91..e719af8bdf56 100644
--- a/arch/um/drivers/virtio_uml.c
+++ b/arch/um/drivers/virtio_uml.c
@@ -1011,7 +1011,7 @@ error_kzalloc:
 
 static int vu_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		       struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		       const char * const names[], u32 sizes[], const bool *ctx,
+		       const char * const names[], const bool *ctx,
 		       struct irq_affinity *desc)
 {
 	struct virtio_uml_device *vu_dev = to_virtio_uml_device(vdev);
diff --git a/arch/um/include/asm/cpufeature.h b/arch/um/include/asm/cpufeature.h
index 19cd7ed6ec3c..4b6d1b526bc1 100644
--- a/arch/um/include/asm/cpufeature.h
+++ b/arch/um/include/asm/cpufeature.h
@@ -65,20 +65,6 @@ extern void setup_clear_cpu_cap(unsigned int bit);
 
 #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
 
-#if defined(__clang__) && !defined(CONFIG_CC_HAS_ASM_GOTO)
-
-/*
- * Workaround for the sake of BPF compilation which utilizes kernel
- * headers, but clang does not support ASM GOTO and fails the build.
- */
-#ifndef __BPF_TRACING__
-#warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments"
-#endif
-
-#define static_cpu_has(bit)            boot_cpu_has(bit)
-
-#else
-
 /*
  * Static testing of CPU features. Used the same as boot_cpu_has(). It
  * statically patches the target code for additional performance. Use
@@ -137,7 +123,6 @@ t_no:
 		boot_cpu_has(bit) :				\
 		_static_cpu_has(bit)				\
 )
-#endif
 
 #define cpu_has_bug(c, bit)		cpu_has(c, (bit))
 #define set_cpu_bug(c, bit)		set_cpu_cap(c, (bit))
diff --git a/arch/um/kernel/sysrq.c b/arch/um/kernel/sysrq.c
index 7452f70d50d0..746715379f12 100644
--- a/arch/um/kernel/sysrq.c
+++ b/arch/um/kernel/sysrq.c
@@ -48,7 +48,8 @@ void show_stack(struct task_struct *task, unsigned long *stack,
 			break;
 		if (i && ((i % STACKSLOTS_PER_LINE) == 0))
 			pr_cont("\n");
-		pr_cont(" %08lx", *stack++);
+		pr_cont(" %08lx", READ_ONCE_NOCHECK(*stack));
+		stack++;
 	}
 
 	printk("%sCall Trace:\n", loglvl);
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index e0de60e503b9..d9e023c78f56 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -33,7 +33,7 @@
 #include "um_arch.h"
 
 #define DEFAULT_COMMAND_LINE_ROOT "root=98:0"
-#define DEFAULT_COMMAND_LINE_CONSOLE "console=tty"
+#define DEFAULT_COMMAND_LINE_CONSOLE "console=tty0"
 
 /* Changed in add_arg and setup_arch, which run before SMP is started */
 static char __initdata command_line[COMMAND_LINE_SIZE] = { 0 };
diff --git a/arch/um/os-Linux/user_syms.c b/arch/um/os-Linux/user_syms.c
index cb667c9225ab..fd575ecbcaec 100644
--- a/arch/um/os-Linux/user_syms.c
+++ b/arch/um/os-Linux/user_syms.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define __NO_FORTIFY
 #include <linux/types.h>
 #include <linux/module.h>
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f9920f1341c8..5b53ecca1e15 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -107,6 +107,8 @@ config X86
 	select ARCH_SUPPORTS_PAGE_TABLE_CHECK	if X86_64
 	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
 	select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP	if NR_CPUS <= 4096
+	select ARCH_SUPPORTS_CFI_CLANG		if X86_64
+	select ARCH_USES_CFI_TRAPS		if X86_64 && CFI_CLANG
 	select ARCH_SUPPORTS_LTO_CLANG
 	select ARCH_SUPPORTS_LTO_CLANG_THIN
 	select ARCH_USE_BUILTIN_BSWAP
@@ -257,6 +259,7 @@ config X86
 	select HAVE_STATIC_CALL_INLINE		if HAVE_OBJTOOL
 	select HAVE_PREEMPT_DYNAMIC_CALL
 	select HAVE_RSEQ
+	select HAVE_RUST			if X86_64
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UACCESS_VALIDATION		if HAVE_OBJTOOL
 	select HAVE_UNSTABLE_SCHED_CLOCK
@@ -448,6 +451,11 @@ config X86_X2APIC
 	  This allows 32-bit apic IDs (so it can support very large systems),
 	  and accesses the local apic via MSRs not via mmio.
 
+	  Some Intel systems circa 2022 and later are locked into x2APIC mode
+	  and can not fall back to the legacy APIC modes if SGX or TDX are
+	  enabled in the BIOS.  They will be unable to boot without enabling
+	  this option.
+
 	  If you don't know what to do here, say N.
 
 config X86_MPPARSE
@@ -1919,7 +1927,7 @@ endchoice
 
 config X86_SGX
 	bool "Software Guard eXtensions (SGX)"
-	depends on X86_64 && CPU_SUP_INTEL
+	depends on X86_64 && CPU_SUP_INTEL && X86_X2APIC
 	depends on CRYPTO=y
 	depends on CRYPTO_SHA256=y
 	select SRCU
@@ -2569,7 +2577,7 @@ menuconfig APM
 
 	  1) make sure that you have enough swap space and that it is
 	  enabled.
-	  2) pass the "no-hlt" option to the kernel
+	  2) pass the "idle=poll" option to the kernel
 	  3) switch on floating point emulation in the kernel and pass
 	  the "no387" option to the kernel
 	  4) pass the "floppy=nodma" option to the kernel
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 7854685c5f25..2d7e640674c6 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -68,6 +68,7 @@ export BITS
 #    https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383
 #
 KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx
+KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2
 
 ifeq ($(CONFIG_X86_KERNEL_IBT),y)
 #
@@ -155,8 +156,17 @@ else
         cflags-$(CONFIG_GENERIC_CPU)	+= -mtune=generic
         KBUILD_CFLAGS += $(cflags-y)
 
+        rustflags-$(CONFIG_MK8)		+= -Ctarget-cpu=k8
+        rustflags-$(CONFIG_MPSC)	+= -Ctarget-cpu=nocona
+        rustflags-$(CONFIG_MCORE2)	+= -Ctarget-cpu=core2
+        rustflags-$(CONFIG_MATOM)	+= -Ctarget-cpu=atom
+        rustflags-$(CONFIG_GENERIC_CPU)	+= -Ztune-cpu=generic
+        KBUILD_RUSTFLAGS += $(rustflags-y)
+
         KBUILD_CFLAGS += -mno-red-zone
         KBUILD_CFLAGS += -mcmodel=kernel
+        KBUILD_RUSTFLAGS += -Cno-redzone=y
+        KBUILD_RUSTFLAGS += -Ccode-model=kernel
 endif
 
 #
@@ -286,10 +296,6 @@ vdso_install:
 
 archprepare: checkbin
 checkbin:
-ifndef CONFIG_CC_HAS_ASM_GOTO
-	@echo Compiler lacks asm-goto support.
-	@exit 1
-endif
 ifdef CONFIG_RETPOLINE
 ifeq ($(RETPOLINE_CFLAGS),)
 	@echo "You are building kernel with non-retpoline compiler." >&2
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 4910bf230d7b..62208ec04ca4 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -132,7 +132,17 @@ void snp_set_page_private(unsigned long paddr);
 void snp_set_page_shared(unsigned long paddr);
 void sev_prep_identity_maps(unsigned long top_level_pgt);
 #else
-static inline void sev_enable(struct boot_params *bp) { }
+static inline void sev_enable(struct boot_params *bp)
+{
+	/*
+	 * bp->cc_blob_address should only be set by boot/compressed kernel.
+	 * Initialize it to 0 unconditionally (thus here in this stub too) to
+	 * ensure that uninitialized values from buggy bootloaders aren't
+	 * propagated.
+	 */
+	if (bp)
+		bp->cc_blob_address = 0;
+}
 static inline void sev_es_shutdown_ghcb(void) { }
 static inline bool sev_es_check_ghcb_fault(unsigned long address)
 {
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index 52f989f6acc2..c93930d5ccbd 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -277,6 +277,14 @@ void sev_enable(struct boot_params *bp)
 	bool snp;
 
 	/*
+	 * bp->cc_blob_address should only be set by boot/compressed kernel.
+	 * Initialize it to 0 to ensure that uninitialized values from
+	 * buggy bootloaders aren't propagated.
+	 */
+	if (bp)
+		bp->cc_blob_address = 0;
+
+	/*
 	 * Setup/preliminary detection of SNP. This will be sanity-checked
 	 * against CPUID/MSR values later.
 	 */
diff --git a/arch/x86/configs/xen.config b/arch/x86/configs/xen.config
index d9fc7139fd46..581296255b39 100644
--- a/arch/x86/configs/xen.config
+++ b/arch/x86/configs/xen.config
@@ -14,7 +14,6 @@ CONFIG_CPU_FREQ=y
 
 # x86 xen specific config options
 CONFIG_XEN_PVH=y
-CONFIG_XEN_MAX_DOMAIN_MEMORY=500
 CONFIG_XEN_SAVE_RESTORE=y
 # CONFIG_XEN_DEBUG_FS is not set
 CONFIG_XEN_MCE_LOG=y
diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S
index 802d71582689..4a43e072d2d1 100644
--- a/arch/x86/crypto/blowfish-x86_64-asm_64.S
+++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S
@@ -6,6 +6,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 
 .file "blowfish-x86_64-asm.S"
 .text
@@ -141,7 +142,7 @@ SYM_FUNC_START(__blowfish_enc_blk)
 	RET;
 SYM_FUNC_END(__blowfish_enc_blk)
 
-SYM_FUNC_START(blowfish_dec_blk)
+SYM_TYPED_FUNC_START(blowfish_dec_blk)
 	/* input:
 	 *	%rdi: ctx
 	 *	%rsi: dst
@@ -332,7 +333,7 @@ SYM_FUNC_START(__blowfish_enc_blk_4way)
 	RET;
 SYM_FUNC_END(__blowfish_enc_blk_4way)
 
-SYM_FUNC_START(blowfish_dec_blk_4way)
+SYM_TYPED_FUNC_START(blowfish_dec_blk_4way)
 	/* input:
 	 *	%rdi: ctx
 	 *	%rsi: dst
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 682338e7e2a3..4dd19819053a 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -311,7 +311,7 @@ SYM_CODE_START(entry_INT80_compat)
 	 * Interrupts are off on entry.
 	 */
 	ASM_CLAC			/* Do this early to minimize exposure */
-	SWAPGS
+	ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV
 
 	/*
 	 * User tracing code (ptrace or signal handlers) might assume that
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 12f6c4d714cd..381d3333b996 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -91,7 +91,7 @@ ifneq ($(RETPOLINE_VDSO_CFLAGS),)
 endif
 endif
 
-$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
+$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(CC_FLAGS_CFI) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
 $(vobjs): KBUILD_AFLAGS += -DBUILD_VDSO
 
 #
@@ -153,6 +153,7 @@ KBUILD_CFLAGS_32 := $(filter-out $(RANDSTRUCT_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_CFI),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
 KBUILD_CFLAGS_32 += -fno-stack-protector
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2db93498ff71..c20d8cd47c48 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2102,6 +2102,15 @@ static struct extra_reg intel_tnt_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+EVENT_ATTR_STR(mem-loads,	mem_ld_grt,	"event=0xd0,umask=0x5,ldlat=3");
+EVENT_ATTR_STR(mem-stores,	mem_st_grt,	"event=0xd0,umask=0x6");
+
+static struct attribute *grt_mem_attrs[] = {
+	EVENT_PTR(mem_ld_grt),
+	EVENT_PTR(mem_st_grt),
+	NULL
+};
+
 static struct extra_reg intel_grt_extra_regs[] __read_mostly = {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
 	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
@@ -4052,8 +4061,9 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 		/* Disable guest PEBS if host PEBS is enabled. */
 		arr[pebs_enable].guest = 0;
 	} else {
-		/* Disable guest PEBS for cross-mapped PEBS counters. */
+		/* Disable guest PEBS thoroughly for cross-mapped PEBS counters. */
 		arr[pebs_enable].guest &= ~kvm_pmu->host_cross_mapped_mask;
+		arr[global_ctrl].guest &= ~kvm_pmu->host_cross_mapped_mask;
 		/* Set hw GLOBAL_CTRL bits for PEBS counter when it runs for guest */
 		arr[global_ctrl].guest |= arr[pebs_enable].guest;
 	}
@@ -5974,6 +5984,36 @@ __init int intel_pmu_init(void)
 		name = "Tremont";
 		break;
 
+	case INTEL_FAM6_ALDERLAKE_N:
+		x86_pmu.mid_ack = true;
+		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
+		hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+
+		x86_pmu.event_constraints = intel_slm_event_constraints;
+		x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_grt_extra_regs;
+
+		x86_pmu.pebs_aliases = NULL;
+		x86_pmu.pebs_prec_dist = true;
+		x86_pmu.pebs_block = true;
+		x86_pmu.lbr_pt_coexist = true;
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
+
+		intel_pmu_pebs_data_source_grt();
+		x86_pmu.pebs_latency_data = adl_latency_data_small;
+		x86_pmu.get_event_constraints = tnt_get_event_constraints;
+		x86_pmu.limit_period = spr_limit_period;
+		td_attr = tnt_events_attrs;
+		mem_attr = grt_mem_attrs;
+		extra_attr = nhm_format_attr;
+		pr_cont("Gracemont events, ");
+		name = "gracemont";
+		break;
+
 	case INTEL_FAM6_WESTMERE:
 	case INTEL_FAM6_WESTMERE_EP:
 	case INTEL_FAM6_WESTMERE_EX:
@@ -6291,10 +6331,8 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_aliases = NULL;
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.pebs_block = true;
-		x86_pmu.pebs_capable = ~0ULL;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
-		x86_pmu.flags |= PMU_FL_PEBS_ALL;
 		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
 		x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
 
@@ -6318,7 +6356,6 @@ __init int intel_pmu_init(void)
 
 	case INTEL_FAM6_ALDERLAKE:
 	case INTEL_FAM6_ALDERLAKE_L:
-	case INTEL_FAM6_ALDERLAKE_N:
 	case INTEL_FAM6_RAPTORLAKE:
 	case INTEL_FAM6_RAPTORLAKE_P:
 		/*
@@ -6337,10 +6374,8 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_aliases = NULL;
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.pebs_block = true;
-		x86_pmu.pebs_capable = ~0ULL;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
-		x86_pmu.flags |= PMU_FL_PEBS_ALL;
 		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
 		x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
 		x86_pmu.lbr_pt_coexist = true;
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index ba60427caa6d..ac973c6f82ad 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -110,13 +110,18 @@ void __init intel_pmu_pebs_data_source_skl(bool pmem)
 	__intel_pmu_pebs_data_source_skl(pmem, pebs_data_source);
 }
 
-static void __init intel_pmu_pebs_data_source_grt(u64 *data_source)
+static void __init __intel_pmu_pebs_data_source_grt(u64 *data_source)
 {
 	data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT);
 	data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
 	data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD);
 }
 
+void __init intel_pmu_pebs_data_source_grt(void)
+{
+	__intel_pmu_pebs_data_source_grt(pebs_data_source);
+}
+
 void __init intel_pmu_pebs_data_source_adl(void)
 {
 	u64 *data_source;
@@ -127,7 +132,7 @@ void __init intel_pmu_pebs_data_source_adl(void)
 
 	data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source;
 	memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
-	intel_pmu_pebs_data_source_grt(data_source);
+	__intel_pmu_pebs_data_source_grt(data_source);
 }
 
 static u64 precise_store_data(u64 status)
@@ -291,6 +296,7 @@ static u64 load_latency_data(struct perf_event *event, u64 status)
 static u64 store_latency_data(struct perf_event *event, u64 status)
 {
 	union intel_x86_pebs_dse dse;
+	union perf_mem_data_src src;
 	u64 val;
 
 	dse.val = status;
@@ -304,7 +310,14 @@ static u64 store_latency_data(struct perf_event *event, u64 status)
 
 	val |= P(BLK, NA);
 
-	return val;
+	/*
+	 * the pebs_data_source table is only for loads
+	 * so override the mem_op to say STORE instead
+	 */
+	src.val = val;
+	src.mem_op = P(OP,STORE);
+
+	return src.val;
 }
 
 struct pebs_record_core {
@@ -822,7 +835,7 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
 
 struct event_constraint intel_grt_pebs_event_constraints[] = {
 	/* Allow all events as PEBS with no flags */
-	INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0xf),
+	INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0x3),
 	INTEL_HYBRID_LAT_CONSTRAINT(0x6d0, 0xf),
 	EVENT_CONSTRAINT_END
 };
@@ -2262,6 +2275,7 @@ void __init intel_ds_init(void)
 					PERF_SAMPLE_BRANCH_STACK |
 					PERF_SAMPLE_TIME;
 				x86_pmu.flags |= PMU_FL_PEBS_ALL;
+				x86_pmu.pebs_capable = ~0ULL;
 				pebs_qual = "-baseline";
 				x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_EXTENDED_REGS;
 			} else {
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 4f70fb6c2c1e..47fca6a7a8bc 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1097,6 +1097,14 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 
 	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
 		reg->config = mask;
+
+		/*
+		 * The Arch LBR HW can retrieve the common branch types
+		 * from the LBR_INFO. It doesn't require the high overhead
+		 * SW disassemble.
+		 * Enable the branch type by default for the Arch LBR.
+		 */
+		reg->reg |= X86_BR_TYPE_SAVE;
 		return 0;
 	}
 
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index ce440011cc4e..1ef4f7861e2e 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -841,6 +841,22 @@ int snb_pci2phy_map_init(int devid)
 	return 0;
 }
 
+static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/*
+	 * SNB IMC counters are 32-bit and are laid out back to back
+	 * in MMIO space. Therefore we must use a 32-bit accessor function
+	 * using readq() from uncore_mmio_read_counter() causes problems
+	 * because it is reading 64-bit at a time. This is okay for the
+	 * uncore_perf_event_update() function because it drops the upper
+	 * 32-bits but not okay for plain uncore_read_counter() as invoked
+	 * in uncore_pmu_event_start().
+	 */
+	return (u64)readl(box->io_addr + hwc->event_base);
+}
+
 static struct pmu snb_uncore_imc_pmu = {
 	.task_ctx_nr	= perf_invalid_context,
 	.event_init	= snb_uncore_imc_event_init,
@@ -860,7 +876,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = {
 	.disable_event	= snb_uncore_imc_disable_event,
 	.enable_event	= snb_uncore_imc_enable_event,
 	.hw_config	= snb_uncore_imc_hw_config,
-	.read_counter	= uncore_mmio_read_counter,
+	.read_counter	= snb_uncore_imc_read_counter,
 };
 
 static struct intel_uncore_type snb_uncore_imc = {
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ba3d24a6a4ec..266143abcbd8 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1516,6 +1516,8 @@ void intel_pmu_pebs_data_source_skl(bool pmem);
 
 void intel_pmu_pebs_data_source_adl(void);
 
+void intel_pmu_pebs_data_source_grt(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);
diff --git a/arch/x86/include/asm/acrn.h b/arch/x86/include/asm/acrn.h
index e003a01b7c67..1dd14381bcb6 100644
--- a/arch/x86/include/asm/acrn.h
+++ b/arch/x86/include/asm/acrn.h
@@ -10,6 +10,15 @@
 /* Bit 0 indicates whether guest VM is privileged */
 #define	ACRN_FEATURE_PRIVILEGED_VM	BIT(0)
 
+/*
+ * Timing Information.
+ * This leaf returns the current TSC frequency in kHz.
+ *
+ * EAX: (Virtual) TSC frequency in kHz.
+ * EBX, ECX, EDX: RESERVED (reserved fields are set to zero).
+ */
+#define ACRN_CPUID_TIMING_INFO		0x40000010
+
 void acrn_setup_intr_handler(void (*handler)(void));
 void acrn_remove_intr_handler(void);
 
@@ -21,6 +30,11 @@ static inline u32 acrn_cpuid_base(void)
 	return 0;
 }
 
+static inline unsigned long acrn_get_tsc_khz(void)
+{
+	return cpuid_eax(ACRN_CPUID_TIMING_INFO);
+}
+
 /*
  * Hypercalls for ACRN
  *
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 973c6bd17f98..2edf68475fec 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -207,6 +207,20 @@ static __always_inline bool constant_test_bit(long nr, const volatile unsigned l
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -226,17 +240,37 @@ arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
 					  variable_test_bit(nr, addr);
 }
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
+static __always_inline unsigned long variable__ffs(unsigned long word)
+{
+	asm("rep; bsf %1,%0"
+		: "=r" (word)
+		: "rm" (word));
+	return word;
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
  *
  * Undefined if no bit exists, so code should check against 0 first.
  */
-static __always_inline unsigned long __ffs(unsigned long word)
+#define __ffs(word)				\
+	(__builtin_constant_p(word) ?		\
+	 (unsigned long)__builtin_ctzl(word) :	\
+	 variable__ffs(word))
+
+static __always_inline unsigned long variable_ffz(unsigned long word)
 {
 	asm("rep; bsf %1,%0"
 		: "=r" (word)
-		: "rm" (word));
+		: "r" (~word));
 	return word;
 }
 
@@ -246,13 +280,10 @@ static __always_inline unsigned long __ffs(unsigned long word)
  *
  * Undefined if no zero exists, so code should check against ~0UL first.
  */
-static __always_inline unsigned long ffz(unsigned long word)
-{
-	asm("rep; bsf %1,%0"
-		: "=r" (word)
-		: "r" (~word));
-	return word;
-}
+#define ffz(word)				\
+	(__builtin_constant_p(word) ?		\
+	 (unsigned long)__builtin_ctzl(~word) :	\
+	 variable_ffz(word))
 
 /*
  * __fls: find last set bit in word
@@ -271,18 +302,7 @@ static __always_inline unsigned long __fls(unsigned long word)
 #undef ADDR
 
 #ifdef __KERNEL__
-/**
- * ffs - find first set bit in word
- * @x: the word to search
- *
- * This is defined the same way as the libc and compiler builtin ffs
- * routines, therefore differs in spirit from the other bitops.
- *
- * ffs(value) returns 0 if value is 0 or the position of the first
- * set bit if value is nonzero. The first (least significant) bit
- * is at position 1.
- */
-static __always_inline int ffs(int x)
+static __always_inline int variable_ffs(int x)
 {
 	int r;
 
@@ -313,6 +333,19 @@ static __always_inline int ffs(int x)
 }
 
 /**
+ * ffs - find first set bit in word
+ * @x: the word to search
+ *
+ * This is defined the same way as the libc and compiler builtin ffs
+ * routines, therefore differs in spirit from the other bitops.
+ *
+ * ffs(value) returns 0 if value is 0 or the position of the first
+ * set bit if value is nonzero. The first (least significant) bit
+ * is at position 1.
+ */
+#define ffs(x) (__builtin_constant_p(x) ? __builtin_ffs(x) : variable_ffs(x))
+
+/**
  * fls - find last set bit in word
  * @x: the word to search
  *
diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
new file mode 100644
index 000000000000..58dacd90daef
--- /dev/null
+++ b/arch/x86/include/asm/cfi.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_CFI_H
+#define _ASM_X86_CFI_H
+
+/*
+ * Clang Control Flow Integrity (CFI) support.
+ *
+ * Copyright (C) 2022 Google LLC
+ */
+
+#include <linux/cfi.h>
+
+#ifdef CONFIG_CFI_CLANG
+enum bug_trap_type handle_cfi_failure(struct pt_regs *regs);
+#else
+static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
+{
+	return BUG_TRAP_TYPE_NONE;
+}
+#endif /* CONFIG_CFI_CLANG */
+
+#endif /* _ASM_X86_CFI_H */
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 8cbf623f0ecf..b472ef76826a 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -94,4 +94,6 @@ static inline bool intel_cpu_signatures_match(unsigned int s1, unsigned int p1,
 	return p1 & p2;
 }
 
+extern u64 x86_read_arch_cap_msr(void);
+
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index ea34cc31b047..1a85e1fb0922 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -155,20 +155,6 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
 
 #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
 
-#if defined(__clang__) && !defined(CONFIG_CC_HAS_ASM_GOTO)
-
-/*
- * Workaround for the sake of BPF compilation which utilizes kernel
- * headers, but clang does not support ASM GOTO and fails the build.
- */
-#ifndef __BPF_TRACING__
-#warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments"
-#endif
-
-#define static_cpu_has(bit)            boot_cpu_has(bit)
-
-#else
-
 /*
  * Static testing of CPU features. Used the same as boot_cpu_has(). It
  * statically patches the target code for additional performance. Use
@@ -208,7 +194,6 @@ t_no:
 		boot_cpu_has(bit) :				\
 		_static_cpu_has(bit)				\
 )
-#endif
 
 #define cpu_has_bug(c, bit)		cpu_has(c, (bit))
 #define set_cpu_bug(c, bit)		set_cpu_cap(c, (bit))
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 235dc85c91c3..ef4775c6db01 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -457,7 +457,8 @@
 #define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
 #define X86_BUG_SRBDS			X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
 #define X86_BUG_MMIO_STALE_DATA		X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */
-#define X86_BUG_RETBLEED		X86_BUG(26) /* CPU is affected by RETBleed */
-#define X86_BUG_EIBRS_PBRSB		X86_BUG(27) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
+#define X86_BUG_MMIO_UNKNOWN		X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */
+#define X86_BUG_RETBLEED		X86_BUG(27) /* CPU is affected by RETBleed */
+#define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h
index 503622627400..991e31cfde94 100644
--- a/arch/x86/include/asm/extable_fixup_types.h
+++ b/arch/x86/include/asm/extable_fixup_types.h
@@ -64,4 +64,6 @@
 #define	EX_TYPE_UCOPY_LEN4		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(4))
 #define	EX_TYPE_UCOPY_LEN8		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(8))
 
+#define EX_TYPE_ZEROPAD			20 /* longword load with zeropad on fault */
+
 #endif
diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h
index 689880eca9ba..9b08082a5d9f 100644
--- a/arch/x86/include/asm/ibt.h
+++ b/arch/x86/include/asm/ibt.h
@@ -31,6 +31,16 @@
 
 #define __noendbr	__attribute__((nocf_check))
 
+/*
+ * Create a dummy function pointer reference to prevent objtool from marking
+ * the function as needing to be "sealed" (i.e. ENDBR converted to NOP by
+ * apply_ibt_endbr()).
+ */
+#define IBT_NOSEAL(fname)				\
+	".pushsection .discard.ibt_endbr_noseal\n\t"	\
+	_ASM_PTR fname "\n\t"				\
+	".popsection\n\t"
+
 static inline __attribute_const__ u32 gen_endbr(void)
 {
 	u32 endbr;
@@ -84,6 +94,7 @@ extern __noendbr void ibt_restore(u64 save);
 #ifndef __ASSEMBLY__
 
 #define ASM_ENDBR
+#define IBT_NOSEAL(name)
 
 #define __noendbr
 
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index def6ca121111..5d75fe229342 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -27,6 +27,7 @@
  *		_X	- regular server parts
  *		_D	- micro server parts
  *		_N,_P	- other mobile parts
+ *		_S	- other client parts
  *
  *		Historical OPTDIFFs:
  *
@@ -112,6 +113,10 @@
 
 #define INTEL_FAM6_RAPTORLAKE		0xB7
 #define INTEL_FAM6_RAPTORLAKE_P		0xBA
+#define INTEL_FAM6_RAPTORLAKE_S		0xBF
+
+#define INTEL_FAM6_METEORLAKE		0xAC
+#define INTEL_FAM6_METEORLAKE_L		0xAA
 
 /* "Small Core" Processors (Atom) */
 
diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h
index 63f818aedf77..147cb8fdda92 100644
--- a/arch/x86/include/asm/irq_stack.h
+++ b/arch/x86/include/asm/irq_stack.h
@@ -203,7 +203,7 @@
 			      IRQ_CONSTRAINTS, regs, vector);		\
 }
 
-#ifndef CONFIG_PREEMPT_RT
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
 /*
  * Macro to invoke __do_softirq on the irq stack. This is only called from
  * task context when bottom halves are about to be reenabled and soft
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5ffa578cafe1..aa381ab69a19 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -53,7 +53,7 @@
 #define KVM_MAX_VCPU_IDS (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO)
 
 /* memory slots that are not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS 3
+#define KVM_INTERNAL_MEM_SLOTS 3
 
 #define KVM_HALT_POLL_NS_DEFAULT 200000
 
@@ -729,6 +729,7 @@ struct kvm_vcpu_arch {
 	struct fpu_guest guest_fpu;
 
 	u64 xcr0;
+	u64 guest_supported_xcr0;
 
 	struct kvm_pio_request pio;
 	void *pio_data;
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 73ca20049835..f484d656d34e 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -43,6 +43,18 @@
 
 #endif /* __ASSEMBLY__ */
 
+#define __CFI_TYPE(name)					\
+	SYM_START(__cfi_##name, SYM_L_LOCAL, SYM_A_NONE)	\
+	.fill 11, 1, 0x90 ASM_NL				\
+	.byte 0xb8 ASM_NL					\
+	.long __kcfi_typeid_##name ASM_NL			\
+	SYM_FUNC_END(__cfi_##name)
+
+/* SYM_TYPED_FUNC_START -- use for indirectly called globals, w/ CFI type */
+#define SYM_TYPED_FUNC_START(name)				\
+	SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)	\
+	ENDBR
+
 /* SYM_FUNC_START -- use for global functions */
 #define SYM_FUNC_START(name)				\
 	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)	\
diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h
index 97198001e567..6115bb3d5795 100644
--- a/arch/x86/include/asm/mc146818rtc.h
+++ b/arch/x86/include/asm/mc146818rtc.h
@@ -95,7 +95,7 @@ static inline unsigned char current_lock_cmos_reg(void)
 unsigned char rtc_cmos_read(unsigned char addr);
 void rtc_cmos_write(unsigned char val, unsigned char addr);
 
-extern int mach_set_rtc_mmss(const struct timespec64 *now);
+extern int mach_set_cmos_time(const struct timespec64 *now);
 extern void mach_get_cmos_time(struct timespec64 *now);
 
 #define RTC_IRQ 8
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index cc73061e7255..6e986088817d 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -42,6 +42,7 @@
 #define MCI_STATUS_CEC_SHIFT	38           /* Corrected Error Count */
 #define MCI_STATUS_CEC_MASK	GENMASK_ULL(52,38)
 #define MCI_STATUS_CEC(c)	(((c) & MCI_STATUS_CEC_MASK) >> MCI_STATUS_CEC_SHIFT)
+#define MCI_STATUS_MSCOD(m)	(((m) >> 16) & 0xffff)
 
 /* AMD-specific bits */
 #define MCI_STATUS_TCC		BIT_ULL(55)  /* Task context corrupt */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 0c3d3440fe27..74ecc2bd6cd0 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -9,6 +9,7 @@
 struct ucode_patch {
 	struct list_head plist;
 	void *data;		/* Intel uses only this one */
+	unsigned int size;
 	u32 patch_id;
 	u16 equiv_cpu;
 };
@@ -32,9 +33,6 @@ enum ucode_state {
 };
 
 struct microcode_ops {
-	enum ucode_state (*request_microcode_user) (int cpu,
-				const void __user *buf, size_t size);
-
 	enum ucode_state (*request_microcode_fw) (int cpu, struct device *,
 						  bool refresh_fw);
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 6674bdb096f3..1e086b37a307 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -155,6 +155,11 @@
 						 * Return Stack Buffer Predictions.
 						 */
 
+#define ARCH_CAP_XAPIC_DISABLE		BIT(21)	/*
+						 * IA32_XAPIC_DISABLE_STATUS MSR
+						 * supported
+						 */
+
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
 						 * Writeback and invalidate the
@@ -1054,4 +1059,12 @@
 #define MSR_IA32_HW_FEEDBACK_PTR        0x17d0
 #define MSR_IA32_HW_FEEDBACK_CONFIG     0x17d1
 
+/* x2APIC locked status */
+#define MSR_IA32_XAPIC_DISABLE_STATUS	0xBD
+#define LEGACY_XAPIC_DISABLED		BIT(0) /*
+						* x2APIC mode is locked and
+						* disabling x2APIC will cause
+						* a #GP
+						*/
+
 #endif /* _ASM_X86_MSR_INDEX_H */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index e64fd20778b6..c936ce9f0c47 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -35,33 +35,56 @@
 #define RSB_CLEAR_LOOPS		32	/* To forcibly overwrite all entries */
 
 /*
+ * Common helper for __FILL_RETURN_BUFFER and __FILL_ONE_RETURN.
+ */
+#define __FILL_RETURN_SLOT			\
+	ANNOTATE_INTRA_FUNCTION_CALL;		\
+	call	772f;				\
+	int3;					\
+772:
+
+/*
+ * Stuff the entire RSB.
+ *
  * Google experimented with loop-unrolling and this turned out to be
  * the optimal version - two calls, each with their own speculation
  * trap should their return address end up getting used, in a loop.
  */
-#define __FILL_RETURN_BUFFER(reg, nr, sp)	\
-	mov	$(nr/2), reg;			\
-771:						\
-	ANNOTATE_INTRA_FUNCTION_CALL;		\
-	call	772f;				\
-773:	/* speculation trap */			\
-	UNWIND_HINT_EMPTY;			\
-	pause;					\
-	lfence;					\
-	jmp	773b;				\
-772:						\
-	ANNOTATE_INTRA_FUNCTION_CALL;		\
-	call	774f;				\
-775:	/* speculation trap */			\
-	UNWIND_HINT_EMPTY;			\
-	pause;					\
-	lfence;					\
-	jmp	775b;				\
-774:						\
-	add	$(BITS_PER_LONG/8) * 2, sp;	\
-	dec	reg;				\
-	jnz	771b;				\
-	/* barrier for jnz misprediction */	\
+#ifdef CONFIG_X86_64
+#define __FILL_RETURN_BUFFER(reg, nr)			\
+	mov	$(nr/2), reg;				\
+771:							\
+	__FILL_RETURN_SLOT				\
+	__FILL_RETURN_SLOT				\
+	add	$(BITS_PER_LONG/8) * 2, %_ASM_SP;	\
+	dec	reg;					\
+	jnz	771b;					\
+	/* barrier for jnz misprediction */		\
+	lfence;
+#else
+/*
+ * i386 doesn't unconditionally have LFENCE, as such it can't
+ * do a loop.
+ */
+#define __FILL_RETURN_BUFFER(reg, nr)			\
+	.rept nr;					\
+	__FILL_RETURN_SLOT;				\
+	.endr;						\
+	add	$(BITS_PER_LONG/8) * nr, %_ASM_SP;
+#endif
+
+/*
+ * Stuff a single RSB slot.
+ *
+ * To mitigate Post-Barrier RSB speculation, one CALL instruction must be
+ * forced to retire before letting a RET instruction execute.
+ *
+ * On PBRSB-vulnerable CPUs, it is not safe for a RET to be executed
+ * before this point.
+ */
+#define __FILL_ONE_RETURN				\
+	__FILL_RETURN_SLOT				\
+	add	$(BITS_PER_LONG/8), %_ASM_SP;		\
 	lfence;
 
 #ifdef __ASSEMBLY__
@@ -132,28 +155,15 @@
 #endif
 .endm
 
-.macro ISSUE_UNBALANCED_RET_GUARD
-	ANNOTATE_INTRA_FUNCTION_CALL
-	call .Lunbalanced_ret_guard_\@
-	int3
-.Lunbalanced_ret_guard_\@:
-	add $(BITS_PER_LONG/8), %_ASM_SP
-	lfence
-.endm
-
  /*
   * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP
   * monstrosity above, manually.
   */
-.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2
-.ifb \ftr2
-	ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr
-.else
-	ALTERNATIVE_2 "jmp .Lskip_rsb_\@", "", \ftr, "jmp .Lunbalanced_\@", \ftr2
-.endif
-	__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)
-.Lunbalanced_\@:
-	ISSUE_UNBALANCED_RET_GUARD
+.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS)
+	ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \
+		__stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \
+		__stringify(__FILL_ONE_RETURN), \ftr2
+
 .Lskip_rsb_\@:
 .endm
 
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 964442b99245..2a0b8dd4ec33 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -743,6 +743,7 @@ extern void default_banner(void);
 	 word 771b;				\
 	 .byte ptype;				\
 	 .byte 772b-771b;			\
+	 _ASM_ALIGN;				\
 	.popsection
 
 
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 89df6c6617f5..f3d601574730 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -294,6 +294,7 @@ extern struct paravirt_patch_template pv_ops;
 	"  .byte " type "\n"				\
 	"  .byte 772b-771b\n"				\
 	"  .short " clobber "\n"			\
+	_ASM_ALIGN "\n"					\
 	".popsection\n"
 
 /* Generate patchable code, with the default asm parameters. */
@@ -328,7 +329,7 @@ int paravirt_disable_iospace(void);
  * Unfortunately, this is a relatively slow operation for modern CPUs,
  * because it cannot necessarily determine what the destination
  * address is.  In this case, the address is a runtime constant, so at
- * the very least we can patch the call to e a simple direct call, or
+ * the very least we can patch the call to a simple direct call, or,
  * ideally, patch an inline implementation into the callsite.  (Direct
  * calls are essentially free, because the call and return addresses
  * are completely predictable.)
@@ -339,10 +340,10 @@ int paravirt_disable_iospace(void);
  * on the stack.  All caller-save registers (eax,edx,ecx) are expected
  * to be modified (either clobbered or used for return values).
  * X86_64, on the other hand, already specifies a register-based calling
- * conventions, returning at %rax, with parameters going on %rdi, %rsi,
+ * conventions, returning at %rax, with parameters going in %rdi, %rsi,
  * %rdx, and %rcx. Note that for this reason, x86_64 does not need any
  * special handling for dealing with 4 arguments, unlike i386.
- * However, x86_64 also have to clobber all caller saved registers, which
+ * However, x86_64 also has to clobber all caller saved registers, which
  * unfortunately, are quite a bit (r8 - r11)
  *
  * The call instruction itself is marked by placing its start address
@@ -360,22 +361,22 @@ int paravirt_disable_iospace(void);
  * There are 5 sets of PVOP_* macros for dealing with 0-4 arguments.
  * It could be extended to more arguments, but there would be little
  * to be gained from that.  For each number of arguments, there are
- * the two VCALL and CALL variants for void and non-void functions.
+ * two VCALL and CALL variants for void and non-void functions.
  *
  * When there is a return value, the invoker of the macro must specify
  * the return type.  The macro then uses sizeof() on that type to
- * determine whether its a 32 or 64 bit value, and places the return
+ * determine whether it's a 32 or 64 bit value and places the return
  * in the right register(s) (just %eax for 32-bit, and %edx:%eax for
- * 64-bit). For x86_64 machines, it just returns at %rax regardless of
+ * 64-bit). For x86_64 machines, it just returns in %rax regardless of
  * the return value size.
  *
- * 64-bit arguments are passed as a pair of adjacent 32-bit arguments
+ * 64-bit arguments are passed as a pair of adjacent 32-bit arguments;
  * i386 also passes 64-bit arguments as a pair of adjacent 32-bit arguments
  * in low,high order
  *
  * Small structures are passed and returned in registers.  The macro
  * calling convention can't directly deal with this, so the wrapper
- * functions must do this.
+ * functions must do it.
  *
  * These PVOP_* macros are only defined within this header.  This
  * means that all uses must be wrapped in inline functions.  This also
@@ -414,8 +415,17 @@ int paravirt_disable_iospace(void);
 				"=c" (__ecx)
 #define PVOP_CALL_CLOBBERS	PVOP_VCALL_CLOBBERS, "=a" (__eax)
 
-/* void functions are still allowed [re]ax for scratch */
+/*
+ * void functions are still allowed [re]ax for scratch.
+ *
+ * The ZERO_CALL_USED REGS feature may end up zeroing out callee-saved
+ * registers. Make sure we model this with the appropriate clobbers.
+ */
+#ifdef CONFIG_ZERO_CALL_USED_REGS
+#define PVOP_VCALLEE_CLOBBERS	"=a" (__eax), PVOP_VCALL_CLOBBERS
+#else
 #define PVOP_VCALLEE_CLOBBERS	"=a" (__eax)
+#endif
 #define PVOP_CALLEE_CLOBBERS	PVOP_VCALLEE_CLOBBERS
 
 #define EXTRA_CLOBBERS	 , "r8", "r9", "r10", "r11"
diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index d60ed0668a59..d24b04ebf950 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -81,6 +81,15 @@ static void __resctrl_sched_in(void)
 	}
 }
 
+static inline unsigned int resctrl_arch_round_mon_val(unsigned int val)
+{
+	unsigned int scale = boot_cpu_data.x86_cache_occ_scale;
+
+	/* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */
+	val /= scale;
+	return val * scale;
+}
+
 static inline void resctrl_sched_in(void)
 {
 	if (static_branch_likely(&rdt_enable_key))
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 8a9eba191516..7fa611216417 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -11,7 +11,7 @@
 
 #define __CLOBBERS_MEM(clb...)	"memory", ## clb
 
-#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CONFIG_CC_HAS_ASM_GOTO)
+#ifndef __GCC_ASM_FLAG_OUTPUTS__
 
 /* Use asm goto */
 
@@ -27,7 +27,7 @@ cc_label:	c = true;						\
 	c;								\
 })
 
-#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */
+#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) */
 
 /* Use flags output or a set instruction */
 
@@ -40,7 +40,7 @@ cc_label:	c = true;						\
 	c;								\
 })
 
-#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */
+#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) */
 
 #define GEN_UNARY_RMWcc_4(op, var, cc, arg0)				\
 	__GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM())
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 4a23e52fe0ee..ebc271bb6d8e 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -195,7 +195,7 @@ void snp_set_memory_shared(unsigned long vaddr, unsigned int npages);
 void snp_set_memory_private(unsigned long vaddr, unsigned int npages);
 void snp_set_wakeup_secondary_cpu(void);
 bool snp_init(struct boot_params *bp);
-void snp_abort(void);
+void __init __noreturn snp_abort(void);
 int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err);
 #else
 static inline void sev_es_ist_enter(struct pt_regs *regs) { }
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 81a0211a372d..a73bced40e24 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -21,16 +21,6 @@ DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
 DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id);
 DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
 
-static inline struct cpumask *cpu_llc_shared_mask(int cpu)
-{
-	return per_cpu(cpu_llc_shared_map, cpu);
-}
-
-static inline struct cpumask *cpu_l2c_shared_mask(int cpu)
-{
-	return per_cpu(cpu_l2c_shared_map, cpu);
-}
-
 DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid);
 DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid);
 DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid);
@@ -172,6 +162,16 @@ extern int safe_smp_processor_id(void);
 # define safe_smp_processor_id()	smp_processor_id()
 #endif
 
+static inline struct cpumask *cpu_llc_shared_mask(int cpu)
+{
+	return per_cpu(cpu_llc_shared_map, cpu);
+}
+
+static inline struct cpumask *cpu_l2c_shared_mask(int cpu)
+{
+	return per_cpu(cpu_l2c_shared_map, cpu);
+}
+
 #else /* !CONFIG_SMP */
 #define wbinvd_on_cpu(cpu)     wbinvd()
 static inline int wbinvd_on_all_cpus(void)
@@ -179,6 +179,11 @@ static inline int wbinvd_on_all_cpus(void)
 	wbinvd();
 	return 0;
 }
+
+static inline struct cpumask *cpu_llc_shared_mask(int cpu)
+{
+	return (struct cpumask *)cpumask_of(0);
+}
 #endif /* CONFIG_SMP */
 
 extern unsigned disabled_cpus;
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index b0583c1da14f..1ec6a9ea2328 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -503,9 +503,6 @@ strncpy_from_user(char *dst, const char __user *src, long count);
 
 extern __must_check long strnlen_user(const char __user *str, long n);
 
-unsigned long __must_check clear_user(void __user *mem, unsigned long len);
-unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
-
 #ifdef CONFIG_ARCH_HAS_COPY_MC
 unsigned long __must_check
 copy_mc_to_kernel(void *to, const void *from, unsigned len);
@@ -527,6 +524,8 @@ extern struct movsl_mask {
 #define ARCH_HAS_NOCACHE_UACCESS 1
 
 #ifdef CONFIG_X86_32
+unsigned long __must_check clear_user(void __user *mem, unsigned long len);
+unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
 # include <asm/uaccess_32.h>
 #else
 # include <asm/uaccess_64.h>
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 45697e04d771..d13d71af5cf6 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -79,4 +79,49 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
 	kasan_check_write(dst, size);
 	return __copy_user_flushcache(dst, src, size);
 }
+
+/*
+ * Zero Userspace.
+ */
+
+__must_check unsigned long
+clear_user_original(void __user *addr, unsigned long len);
+__must_check unsigned long
+clear_user_rep_good(void __user *addr, unsigned long len);
+__must_check unsigned long
+clear_user_erms(void __user *addr, unsigned long len);
+
+static __always_inline __must_check unsigned long __clear_user(void __user *addr, unsigned long size)
+{
+	might_fault();
+	stac();
+
+	/*
+	 * No memory constraint because it doesn't change any memory gcc
+	 * knows about.
+	 */
+	asm volatile(
+		"1:\n\t"
+		ALTERNATIVE_3("rep stosb",
+			      "call clear_user_erms",	  ALT_NOT(X86_FEATURE_FSRM),
+			      "call clear_user_rep_good", ALT_NOT(X86_FEATURE_ERMS),
+			      "call clear_user_original", ALT_NOT(X86_FEATURE_REP_GOOD))
+		"2:\n"
+	       _ASM_EXTABLE_UA(1b, 2b)
+	       : "+c" (size), "+D" (addr), ASM_CALL_CONSTRAINT
+	       : "a" (0)
+		/* rep_good clobbers %rdx */
+	       : "rdx");
+
+	clac();
+
+	return size;
+}
+
+static __always_inline unsigned long clear_user(void __user *to, unsigned long n)
+{
+	if (access_ok(to, n))
+		return __clear_user(to, n);
+	return n;
+}
 #endif /* _ASM_X86_UACCESS_64_H */
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
index 8338b0432b50..46b4f1f7f354 100644
--- a/arch/x86/include/asm/word-at-a-time.h
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -77,58 +77,18 @@ static inline unsigned long find_zero(unsigned long mask)
  * and the next page not being mapped, take the exception and
  * return zeroes in the non-existing part.
  */
-#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
-
 static inline unsigned long load_unaligned_zeropad(const void *addr)
 {
-	unsigned long offset, data;
 	unsigned long ret;
 
-	asm_volatile_goto(
+	asm volatile(
 		"1:	mov %[mem], %[ret]\n"
-
-		_ASM_EXTABLE(1b, %l[do_exception])
-
-		: [ret] "=r" (ret)
-		: [mem] "m" (*(unsigned long *)addr)
-		: : do_exception);
-
-	return ret;
-
-do_exception:
-	offset = (unsigned long)addr & (sizeof(long) - 1);
-	addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
-	data = *(unsigned long *)addr;
-	ret = data >> offset * 8;
-
-	return ret;
-}
-
-#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
-
-static inline unsigned long load_unaligned_zeropad(const void *addr)
-{
-	unsigned long offset, data;
-	unsigned long ret, err = 0;
-
-	asm(	"1:	mov %[mem], %[ret]\n"
 		"2:\n"
-
-		_ASM_EXTABLE_FAULT(1b, 2b)
-
-		: [ret] "=&r" (ret), "+a" (err)
+		_ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_ZEROPAD)
+		: [ret] "=r" (ret)
 		: [mem] "m" (*(unsigned long *)addr));
 
-	if (unlikely(err)) {
-		offset = (unsigned long)addr & (sizeof(long) - 1);
-		addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
-		data = *(unsigned long *)addr;
-		ret = data >> offset * 8;
-	}
-
 	return ret;
 }
 
-#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
-
 #endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index a20a5ebfacd7..1286a73ebdbc 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -139,6 +139,8 @@ obj-$(CONFIG_UNWINDER_GUESS)		+= unwind_guess.o
 
 obj-$(CONFIG_AMD_MEM_ENCRYPT)		+= sev.o
 
+obj-$(CONFIG_CFI_CLANG)			+= cfi.o
+
 ###
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 62f6b8b7c4a5..5cadcea035e0 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -453,6 +453,15 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 		return ret;
 	i += ret;
 
+	/*
+	 * The compiler is supposed to EMIT an INT3 after every unconditional
+	 * JMP instruction due to AMD BTC. However, if the compiler is too old
+	 * or SLS isn't enabled, we still need an INT3 after indirect JMPs
+	 * even on Intel.
+	 */
+	if (op == JMP32_INSN_OPCODE && i < insn->length)
+		bytes[i++] = INT3_INSN_OPCODE;
+
 	for (; i < insn->length;)
 		bytes[i++] = BYTES_NOP1;
 
@@ -1319,22 +1328,23 @@ struct bp_patching_desc {
 	atomic_t refs;
 };
 
-static struct bp_patching_desc *bp_desc;
+static struct bp_patching_desc bp_desc;
 
 static __always_inline
-struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp)
+struct bp_patching_desc *try_get_desc(void)
 {
-	/* rcu_dereference */
-	struct bp_patching_desc *desc = __READ_ONCE(*descp);
+	struct bp_patching_desc *desc = &bp_desc;
 
-	if (!desc || !arch_atomic_inc_not_zero(&desc->refs))
+	if (!arch_atomic_inc_not_zero(&desc->refs))
 		return NULL;
 
 	return desc;
 }
 
-static __always_inline void put_desc(struct bp_patching_desc *desc)
+static __always_inline void put_desc(void)
 {
+	struct bp_patching_desc *desc = &bp_desc;
+
 	smp_mb__before_atomic();
 	arch_atomic_dec(&desc->refs);
 }
@@ -1367,15 +1377,15 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 
 	/*
 	 * Having observed our INT3 instruction, we now must observe
-	 * bp_desc:
+	 * bp_desc with non-zero refcount:
 	 *
-	 *	bp_desc = desc			INT3
+	 *	bp_desc.refs = 1		INT3
 	 *	WMB				RMB
-	 *	write INT3			if (desc)
+	 *	write INT3			if (bp_desc.refs != 0)
 	 */
 	smp_rmb();
 
-	desc = try_get_desc(&bp_desc);
+	desc = try_get_desc();
 	if (!desc)
 		return 0;
 
@@ -1429,7 +1439,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 	ret = 1;
 
 out_put:
-	put_desc(desc);
+	put_desc();
 	return ret;
 }
 
@@ -1460,18 +1470,20 @@ static int tp_vec_nr;
  */
 static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 {
-	struct bp_patching_desc desc = {
-		.vec = tp,
-		.nr_entries = nr_entries,
-		.refs = ATOMIC_INIT(1),
-	};
 	unsigned char int3 = INT3_INSN_OPCODE;
 	unsigned int i;
 	int do_sync;
 
 	lockdep_assert_held(&text_mutex);
 
-	smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */
+	bp_desc.vec = tp;
+	bp_desc.nr_entries = nr_entries;
+
+	/*
+	 * Corresponds to the implicit memory barrier in try_get_desc() to
+	 * ensure reading a non-zero refcount provides up to date bp_desc data.
+	 */
+	atomic_set_release(&bp_desc.refs, 1);
 
 	/*
 	 * Corresponding read barrier in int3 notifier for making sure the
@@ -1559,12 +1571,10 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 		text_poke_sync();
 
 	/*
-	 * Remove and synchronize_rcu(), except we have a very primitive
-	 * refcount based completion.
+	 * Remove and wait for refs to be zero.
 	 */
-	WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */
-	if (!atomic_dec_and_test(&desc.refs))
-		atomic_cond_read_acquire(&desc.refs, !VAL);
+	if (!atomic_dec_and_test(&bp_desc.refs))
+		atomic_cond_read_acquire(&bp_desc.refs, !VAL);
 }
 
 static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 6d303d1d276c..c6876d3ea4b1 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -61,6 +61,7 @@
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
 #include <asm/irq_regs.h>
+#include <asm/cpu.h>
 
 unsigned int num_processors;
 
@@ -1751,11 +1752,26 @@ EXPORT_SYMBOL_GPL(x2apic_mode);
 
 enum {
 	X2APIC_OFF,
-	X2APIC_ON,
 	X2APIC_DISABLED,
+	/* All states below here have X2APIC enabled */
+	X2APIC_ON,
+	X2APIC_ON_LOCKED
 };
 static int x2apic_state;
 
+static bool x2apic_hw_locked(void)
+{
+	u64 ia32_cap;
+	u64 msr;
+
+	ia32_cap = x86_read_arch_cap_msr();
+	if (ia32_cap & ARCH_CAP_XAPIC_DISABLE) {
+		rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr);
+		return (msr & LEGACY_XAPIC_DISABLED);
+	}
+	return false;
+}
+
 static void __x2apic_disable(void)
 {
 	u64 msr;
@@ -1793,6 +1809,10 @@ static int __init setup_nox2apic(char *str)
 				apicid);
 			return 0;
 		}
+		if (x2apic_hw_locked()) {
+			pr_warn("APIC locked in x2apic mode, can't disable\n");
+			return 0;
+		}
 		pr_warn("x2apic already enabled.\n");
 		__x2apic_disable();
 	}
@@ -1807,10 +1827,18 @@ early_param("nox2apic", setup_nox2apic);
 void x2apic_setup(void)
 {
 	/*
-	 * If x2apic is not in ON state, disable it if already enabled
+	 * Try to make the AP's APIC state match that of the BSP,  but if the
+	 * BSP is unlocked and the AP is locked then there is a state mismatch.
+	 * Warn about the mismatch in case a GP fault occurs due to a locked AP
+	 * trying to be turned off.
+	 */
+	if (x2apic_state != X2APIC_ON_LOCKED && x2apic_hw_locked())
+		pr_warn("x2apic lock mismatch between BSP and AP.\n");
+	/*
+	 * If x2apic is not in ON or LOCKED state, disable it if already enabled
 	 * from BIOS.
 	 */
-	if (x2apic_state != X2APIC_ON) {
+	if (x2apic_state < X2APIC_ON) {
 		__x2apic_disable();
 		return;
 	}
@@ -1831,6 +1859,11 @@ static __init void x2apic_disable(void)
 	if (x2apic_id >= 255)
 		panic("Cannot disable x2apic, id: %08x\n", x2apic_id);
 
+	if (x2apic_hw_locked()) {
+		pr_warn("Cannot disable locked x2apic, id: %08x\n", x2apic_id);
+		return;
+	}
+
 	__x2apic_disable();
 	register_lapic_address(mp_lapic_addr);
 }
@@ -1889,7 +1922,10 @@ void __init check_x2apic(void)
 	if (x2apic_enabled()) {
 		pr_info("x2apic: enabled by BIOS, switching to x2apic ops\n");
 		x2apic_mode = 1;
-		x2apic_state = X2APIC_ON;
+		if (x2apic_hw_locked())
+			x2apic_state = X2APIC_ON_LOCKED;
+		else
+			x2apic_state = X2APIC_ON;
 	} else if (!boot_cpu_has(X86_FEATURE_X2APIC)) {
 		x2apic_state = X2APIC_DISABLED;
 	}
diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c
new file mode 100644
index 000000000000..8674a5c0c031
--- /dev/null
+++ b/arch/x86/kernel/cfi.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Clang Control Flow Integrity (CFI) support.
+ *
+ * Copyright (C) 2022 Google LLC
+ */
+#include <asm/cfi.h>
+#include <asm/insn.h>
+#include <asm/insn-eval.h>
+#include <linux/string.h>
+
+/*
+ * Returns the target address and the expected type when regs->ip points
+ * to a compiler-generated CFI trap.
+ */
+static bool decode_cfi_insn(struct pt_regs *regs, unsigned long *target,
+			    u32 *type)
+{
+	char buffer[MAX_INSN_SIZE];
+	struct insn insn;
+	int offset = 0;
+
+	*target = *type = 0;
+
+	/*
+	 * The compiler generates the following instruction sequence
+	 * for indirect call checks:
+	 *
+	 *   movl    -<id>, %r10d       ; 6 bytes
+	 *   addl    -4(%reg), %r10d    ; 4 bytes
+	 *   je      .Ltmp1             ; 2 bytes
+	 *   ud2                        ; <- regs->ip
+	 *   .Ltmp1:
+	 *
+	 * We can decode the expected type and the target address from the
+	 * movl/addl instructions.
+	 */
+	if (copy_from_kernel_nofault(buffer, (void *)regs->ip - 12, MAX_INSN_SIZE))
+		return false;
+	if (insn_decode_kernel(&insn, &buffer[offset]))
+		return false;
+	if (insn.opcode.value != 0xBA)
+		return false;
+
+	*type = -(u32)insn.immediate.value;
+
+	if (copy_from_kernel_nofault(buffer, (void *)regs->ip - 6, MAX_INSN_SIZE))
+		return false;
+	if (insn_decode_kernel(&insn, &buffer[offset]))
+		return false;
+	if (insn.opcode.value != 0x3)
+		return false;
+
+	/* Read the target address from the register. */
+	offset = insn_get_modrm_rm_off(&insn, regs);
+	if (offset < 0)
+		return false;
+
+	*target = *(unsigned long *)((void *)regs + offset);
+
+	return true;
+}
+
+/*
+ * Checks if a ud2 trap is because of a CFI failure, and handles the trap
+ * if needed. Returns a bug_trap_type value similarly to report_bug.
+ */
+enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
+{
+	unsigned long target;
+	u32 type;
+
+	if (!is_cfi_trap(regs->ip))
+		return BUG_TRAP_TYPE_NONE;
+
+	if (!decode_cfi_insn(regs, &target, &type))
+		return report_cfi_failure_noaddr(regs, regs->ip);
+
+	return report_cfi_failure(regs, regs->ip, &target, type);
+}
+
+/*
+ * Ensure that __kcfi_typeid_ symbols are emitted for functions that may
+ * not be indirectly called with all configurations.
+ */
+__ADDRESSABLE(__memcpy)
diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c
index 23f5f27b5a02..485441b7f030 100644
--- a/arch/x86/kernel/cpu/acrn.c
+++ b/arch/x86/kernel/cpu/acrn.c
@@ -28,6 +28,9 @@ static void __init acrn_init_platform(void)
 {
 	/* Setup the IDT for ACRN hypervisor callback */
 	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_acrn_hv_callback);
+
+	x86_platform.calibrate_tsc = acrn_get_tsc_khz;
+	x86_platform.calibrate_cpu = acrn_get_tsc_khz;
 }
 
 static bool acrn_x2apic_available(void)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 510d85261132..da7c361f47e0 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -433,7 +433,8 @@ static void __init mmio_select_mitigation(void)
 	u64 ia32_cap;
 
 	if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) ||
-	    cpu_mitigations_off()) {
+	     boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) ||
+	     cpu_mitigations_off()) {
 		mmio_mitigation = MMIO_MITIGATION_OFF;
 		return;
 	}
@@ -538,6 +539,8 @@ out:
 		pr_info("TAA: %s\n", taa_strings[taa_mitigation]);
 	if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
 		pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]);
+	else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
+		pr_info("MMIO Stale Data: Unknown: No mitigations\n");
 }
 
 static void __init md_clear_select_mitigation(void)
@@ -2275,6 +2278,9 @@ static ssize_t tsx_async_abort_show_state(char *buf)
 
 static ssize_t mmio_stale_data_show_state(char *buf)
 {
+	if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
+		return sysfs_emit(buf, "Unknown: No mitigations\n");
+
 	if (mmio_mitigation == MMIO_MITIGATION_OFF)
 		return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]);
 
@@ -2421,6 +2427,7 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 		return srbds_show_state(buf);
 
 	case X86_BUG_MMIO_STALE_DATA:
+	case X86_BUG_MMIO_UNKNOWN:
 		return mmio_stale_data_show_state(buf);
 
 	case X86_BUG_RETBLEED:
@@ -2480,7 +2487,10 @@ ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *
 
 ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
+	if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
+		return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_UNKNOWN);
+	else
+		return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
 }
 
 ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 64a73f415f03..3e508f239098 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1135,7 +1135,8 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #define NO_SWAPGS		BIT(6)
 #define NO_ITLB_MULTIHIT	BIT(7)
 #define NO_SPECTRE_V2		BIT(8)
-#define NO_EIBRS_PBRSB		BIT(9)
+#define NO_MMIO			BIT(9)
+#define NO_EIBRS_PBRSB		BIT(10)
 
 #define VULNWL(vendor, family, model, whitelist)	\
 	X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist)
@@ -1158,6 +1159,11 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	VULNWL(VORTEX,	6, X86_MODEL_ANY,	NO_SPECULATION),
 
 	/* Intel Family 6 */
+	VULNWL_INTEL(TIGERLAKE,			NO_MMIO),
+	VULNWL_INTEL(TIGERLAKE_L,		NO_MMIO),
+	VULNWL_INTEL(ALDERLAKE,			NO_MMIO),
+	VULNWL_INTEL(ALDERLAKE_L,		NO_MMIO),
+
 	VULNWL_INTEL(ATOM_SALTWELL,		NO_SPECULATION | NO_ITLB_MULTIHIT),
 	VULNWL_INTEL(ATOM_SALTWELL_TABLET,	NO_SPECULATION | NO_ITLB_MULTIHIT),
 	VULNWL_INTEL(ATOM_SALTWELL_MID,		NO_SPECULATION | NO_ITLB_MULTIHIT),
@@ -1176,9 +1182,9 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	VULNWL_INTEL(ATOM_AIRMONT_MID,		NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
 	VULNWL_INTEL(ATOM_AIRMONT_NP,		NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
 
-	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_GOLDMONT_D,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
+	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_INTEL(ATOM_GOLDMONT_D,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
 
 	/*
 	 * Technically, swapgs isn't serializing on AMD (despite it previously
@@ -1193,18 +1199,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	VULNWL_INTEL(ATOM_TREMONT_D,		NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
 
 	/* AMD Family 0xf - 0x12 */
-	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
 
 	/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
-	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
 
 	/* Zhaoxin Family 7 */
-	VULNWL(CENTAUR,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS),
-	VULNWL(ZHAOXIN,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS),
+	VULNWL(CENTAUR,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
+	VULNWL(ZHAOXIN,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
 	{}
 };
 
@@ -1358,10 +1364,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	 * Affected CPU list is generally enough to enumerate the vulnerability,
 	 * but for virtualization case check for ARCH_CAP MSR bits also, VMM may
 	 * not want the guest to enumerate the bug.
+	 *
+	 * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist,
+	 * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits.
 	 */
-	if (cpu_matches(cpu_vuln_blacklist, MMIO) &&
-	    !arch_cap_mmio_immune(ia32_cap))
-		setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
+	if (!arch_cap_mmio_immune(ia32_cap)) {
+		if (cpu_matches(cpu_vuln_blacklist, MMIO))
+			setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
+		else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO))
+			setup_force_cpu_bug(X86_BUG_MMIO_UNKNOWN);
+	}
 
 	if (!cpu_has(c, X86_FEATURE_BTC_NO)) {
 		if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA))
diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c
index 717192915f28..8ed341714686 100644
--- a/arch/x86/kernel/cpu/mce/apei.c
+++ b/arch/x86/kernel/cpu/mce/apei.c
@@ -29,15 +29,26 @@
 void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
 {
 	struct mce m;
+	int lsb;
 
 	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
 		return;
 
+	/*
+	 * Even if the ->validation_bits are set for address mask,
+	 * to be extra safe, check and reject an error radius '0',
+	 * and fall back to the default page size.
+	 */
+	if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK)
+		lsb = find_first_bit((void *)&mem_err->physical_addr_mask, PAGE_SHIFT);
+	else
+		lsb = PAGE_SHIFT;
+
 	mce_setup(&m);
 	m.bank = -1;
 	/* Fake a memory read error with unknown channel */
 	m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | MCI_STATUS_MISCV | 0x9f;
-	m.misc = (MCI_MISC_ADDR_PHYS << 6) | PAGE_SHIFT;
+	m.misc = (MCI_MISC_ADDR_PHYS << 6) | lsb;
 
 	if (severity >= GHES_SEV_RECOVERABLE)
 		m.status |= MCI_STATUS_UC;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 8b2fcdfa6d31..e7410e98fc1f 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -788,6 +788,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover,
 		kfree(patch);
 		return -EINVAL;
 	}
+	patch->size = *patch_size;
 
 	mc_hdr      = (struct microcode_header_amd *)(fw + SECTION_HDR_SIZE);
 	proc_id     = mc_hdr->processor_rev_id;
@@ -869,7 +870,7 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
 		return ret;
 
 	memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
-	memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), PATCH_MAX_SIZE));
+	memcpy(amd_ucode_patch, p->data, min_t(u32, p->size, PATCH_MAX_SIZE));
 
 	return ret;
 }
@@ -924,12 +925,6 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 	return ret;
 }
 
-static enum ucode_state
-request_microcode_user(int cpu, const void __user *buf, size_t size)
-{
-	return UCODE_ERROR;
-}
-
 static void microcode_fini_cpu_amd(int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
@@ -938,7 +933,6 @@ static void microcode_fini_cpu_amd(int cpu)
 }
 
 static struct microcode_ops microcode_amd_ops = {
-	.request_microcode_user           = request_microcode_user,
 	.request_microcode_fw             = request_microcode_amd,
 	.collect_cpu_info                 = collect_cpu_info_amd,
 	.apply_microcode                  = apply_microcode_amd,
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index ad57e0e4d674..6a41cee242f6 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -491,7 +491,7 @@ wait_for_siblings:
  */
 static int microcode_reload_late(void)
 {
-	int ret;
+	int old = boot_cpu_data.microcode, ret;
 
 	pr_err("Attempting late microcode loading - it is dangerous and taints the kernel.\n");
 	pr_err("You should switch to early loading, if possible.\n");
@@ -503,7 +503,8 @@ static int microcode_reload_late(void)
 	if (ret == 0)
 		microcode_check();
 
-	pr_info("Reload completed, microcode revision: 0x%x\n", boot_cpu_data.microcode);
+	pr_info("Reload completed, microcode revision: 0x%x -> 0x%x\n",
+		old, boot_cpu_data.microcode);
 
 	return ret;
 }
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 025c8f0cd948..1fcbd671f1df 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -916,24 +916,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device,
 	return ret;
 }
 
-static enum ucode_state
-request_microcode_user(int cpu, const void __user *buf, size_t size)
-{
-	struct iov_iter iter;
-	struct iovec iov;
-
-	if (is_blacklisted(cpu))
-		return UCODE_NFOUND;
-
-	iov.iov_base = (void __user *)buf;
-	iov.iov_len = size;
-	iov_iter_init(&iter, WRITE, &iov, 1, size);
-
-	return generic_load_microcode(cpu, &iter);
-}
-
 static struct microcode_ops microcode_intel_ops = {
-	.request_microcode_user		  = request_microcode_user,
 	.request_microcode_fw             = request_microcode_fw,
 	.collect_cpu_info                 = collect_cpu_info,
 	.apply_microcode                  = apply_microcode_intel,
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index bb1c3f5f60c8..de62b0b87ced 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -147,7 +147,6 @@ static inline void cache_alloc_hsw_probe(void)
 	r->cache.shareable_bits = 0xc0000;
 	r->cache.min_cbm_bits = 2;
 	r->alloc_capable = true;
-	r->alloc_enabled = true;
 
 	rdt_alloc_capable = true;
 }
@@ -211,7 +210,6 @@ static bool __get_mem_config_intel(struct rdt_resource *r)
 	thread_throttle_mode_init();
 
 	r->alloc_capable = true;
-	r->alloc_enabled = true;
 
 	return true;
 }
@@ -242,7 +240,6 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 	r->data_width = 4;
 
 	r->alloc_capable = true;
-	r->alloc_enabled = true;
 
 	return true;
 }
@@ -261,7 +258,6 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
 	r->cache.shareable_bits = ebx & r->default_ctrl;
 	r->data_width = (r->cache.cbm_len + 3) / 4;
 	r->alloc_capable = true;
-	r->alloc_enabled = true;
 }
 
 static void rdt_get_cdp_config(int level)
@@ -300,7 +296,7 @@ mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
  * that can be written to QOS_MSRs.
  * There are currently no SKUs which support non linear delay values.
  */
-u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
+static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
 {
 	if (r->membw.delay_linear)
 		return MAX_MBA_BW - bw;
@@ -401,7 +397,7 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 	return NULL;
 }
 
-void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm)
+static void setup_default_ctrlval(struct rdt_resource *r, u32 *dc)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	int i;
@@ -410,12 +406,17 @@ void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm)
 	 * Initialize the Control MSRs to having no control.
 	 * For Cache Allocation: Set all bits in cbm
 	 * For Memory Allocation: Set b/w requested to 100%
-	 * and the bandwidth in MBps to U32_MAX
 	 */
-	for (i = 0; i < hw_res->num_closid; i++, dc++, dm++) {
+	for (i = 0; i < hw_res->num_closid; i++, dc++)
 		*dc = r->default_ctrl;
-		*dm = MBA_MAX_MBPS;
-	}
+}
+
+static void domain_free(struct rdt_hw_domain *hw_dom)
+{
+	kfree(hw_dom->arch_mbm_total);
+	kfree(hw_dom->arch_mbm_local);
+	kfree(hw_dom->ctrl_val);
+	kfree(hw_dom);
 }
 
 static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
@@ -423,23 +424,15 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
 	struct msr_param m;
-	u32 *dc, *dm;
+	u32 *dc;
 
 	dc = kmalloc_array(hw_res->num_closid, sizeof(*hw_dom->ctrl_val),
 			   GFP_KERNEL);
 	if (!dc)
 		return -ENOMEM;
 
-	dm = kmalloc_array(hw_res->num_closid, sizeof(*hw_dom->mbps_val),
-			   GFP_KERNEL);
-	if (!dm) {
-		kfree(dc);
-		return -ENOMEM;
-	}
-
 	hw_dom->ctrl_val = dc;
-	hw_dom->mbps_val = dm;
-	setup_default_ctrlval(r, dc, dm);
+	setup_default_ctrlval(r, dc);
 
 	m.low = 0;
 	m.high = hw_res->num_closid;
@@ -447,39 +440,31 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
 	return 0;
 }
 
-static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
+/**
+ * arch_domain_mbm_alloc() - Allocate arch private storage for the MBM counters
+ * @num_rmid:	The size of the MBM counter array
+ * @hw_dom:	The domain that owns the allocated arrays
+ */
+static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom)
 {
 	size_t tsize;
 
-	if (is_llc_occupancy_enabled()) {
-		d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL);
-		if (!d->rmid_busy_llc)
-			return -ENOMEM;
-		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
-	}
 	if (is_mbm_total_enabled()) {
-		tsize = sizeof(*d->mbm_total);
-		d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
-		if (!d->mbm_total) {
-			bitmap_free(d->rmid_busy_llc);
+		tsize = sizeof(*hw_dom->arch_mbm_total);
+		hw_dom->arch_mbm_total = kcalloc(num_rmid, tsize, GFP_KERNEL);
+		if (!hw_dom->arch_mbm_total)
 			return -ENOMEM;
-		}
 	}
 	if (is_mbm_local_enabled()) {
-		tsize = sizeof(*d->mbm_local);
-		d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
-		if (!d->mbm_local) {
-			bitmap_free(d->rmid_busy_llc);
-			kfree(d->mbm_total);
+		tsize = sizeof(*hw_dom->arch_mbm_local);
+		hw_dom->arch_mbm_local = kcalloc(num_rmid, tsize, GFP_KERNEL);
+		if (!hw_dom->arch_mbm_local) {
+			kfree(hw_dom->arch_mbm_total);
+			hw_dom->arch_mbm_total = NULL;
 			return -ENOMEM;
 		}
 	}
 
-	if (is_mbm_enabled()) {
-		INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
-		mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL);
-	}
-
 	return 0;
 }
 
@@ -502,6 +487,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 	struct list_head *add_pos = NULL;
 	struct rdt_hw_domain *hw_dom;
 	struct rdt_domain *d;
+	int err;
 
 	d = rdt_find_domain(r, id, &add_pos);
 	if (IS_ERR(d)) {
@@ -527,25 +513,22 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 	rdt_domain_reconfigure_cdp(r);
 
 	if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
-		kfree(hw_dom);
+		domain_free(hw_dom);
 		return;
 	}
 
-	if (r->mon_capable && domain_setup_mon_state(r, d)) {
-		kfree(hw_dom->ctrl_val);
-		kfree(hw_dom->mbps_val);
-		kfree(hw_dom);
+	if (r->mon_capable && arch_domain_mbm_alloc(r->num_rmid, hw_dom)) {
+		domain_free(hw_dom);
 		return;
 	}
 
 	list_add_tail(&d->list, add_pos);
 
-	/*
-	 * If resctrl is mounted, add
-	 * per domain monitor data directories.
-	 */
-	if (static_branch_unlikely(&rdt_mon_enable_key))
-		mkdir_mondata_subdir_allrdtgrp(r, d);
+	err = resctrl_online_domain(r, d);
+	if (err) {
+		list_del(&d->list);
+		domain_free(hw_dom);
+	}
 }
 
 static void domain_remove_cpu(int cpu, struct rdt_resource *r)
@@ -563,27 +546,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 
 	cpumask_clear_cpu(cpu, &d->cpu_mask);
 	if (cpumask_empty(&d->cpu_mask)) {
-		/*
-		 * If resctrl is mounted, remove all the
-		 * per domain monitor data directories.
-		 */
-		if (static_branch_unlikely(&rdt_mon_enable_key))
-			rmdir_mondata_subdir_allrdtgrp(r, d->id);
+		resctrl_offline_domain(r, d);
 		list_del(&d->list);
-		if (r->mon_capable && is_mbm_enabled())
-			cancel_delayed_work(&d->mbm_over);
-		if (is_llc_occupancy_enabled() &&  has_busy_rmid(r, d)) {
-			/*
-			 * When a package is going down, forcefully
-			 * decrement rmid->ebusy. There is no way to know
-			 * that the L3 was flushed and hence may lead to
-			 * incorrect counts in rare scenarios, but leaving
-			 * the RMID as busy creates RMID leaks if the
-			 * package never comes back.
-			 */
-			__check_limbo(d, true);
-			cancel_delayed_work(&d->cqm_limbo);
-		}
 
 		/*
 		 * rdt_domain "d" is going to be freed below, so clear
@@ -591,13 +555,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 		 */
 		if (d->plr)
 			d->plr->d = NULL;
+		domain_free(hw_dom);
 
-		kfree(hw_dom->ctrl_val);
-		kfree(hw_dom->mbps_val);
-		bitmap_free(d->rmid_busy_llc);
-		kfree(d->mbm_total);
-		kfree(d->mbm_local);
-		kfree(hw_dom);
 		return;
 	}
 
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 87666275eed9..1dafbdc5ac31 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -61,6 +61,7 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
 	     struct rdt_domain *d)
 {
 	struct resctrl_staged_config *cfg;
+	u32 closid = data->rdtgrp->closid;
 	struct rdt_resource *r = s->res;
 	unsigned long bw_val;
 
@@ -72,6 +73,12 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
 
 	if (!bw_validate(data->buf, &bw_val, r))
 		return -EINVAL;
+
+	if (is_mba_sc(r)) {
+		d->mbps_val[closid] = bw_val;
+		return 0;
+	}
+
 	cfg->new_ctrl = bw_val;
 	cfg->have_new_ctrl = true;
 
@@ -261,14 +268,13 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
 
 static bool apply_config(struct rdt_hw_domain *hw_dom,
 			 struct resctrl_staged_config *cfg, u32 idx,
-			 cpumask_var_t cpu_mask, bool mba_sc)
+			 cpumask_var_t cpu_mask)
 {
 	struct rdt_domain *dom = &hw_dom->d_resctrl;
-	u32 *dc = !mba_sc ? hw_dom->ctrl_val : hw_dom->mbps_val;
 
-	if (cfg->new_ctrl != dc[idx]) {
+	if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) {
 		cpumask_set_cpu(cpumask_any(&dom->cpu_mask), cpu_mask);
-		dc[idx] = cfg->new_ctrl;
+		hw_dom->ctrl_val[idx] = cfg->new_ctrl;
 
 		return true;
 	}
@@ -276,6 +282,27 @@ static bool apply_config(struct rdt_hw_domain *hw_dom,
 	return false;
 }
 
+int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
+			    u32 closid, enum resctrl_conf_type t, u32 cfg_val)
+{
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	u32 idx = get_config_index(closid, t);
+	struct msr_param msr_param;
+
+	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
+		return -EINVAL;
+
+	hw_dom->ctrl_val[idx] = cfg_val;
+
+	msr_param.res = r;
+	msr_param.low = idx;
+	msr_param.high = idx + 1;
+	hw_res->msr_update(d, &msr_param, r);
+
+	return 0;
+}
+
 int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 {
 	struct resctrl_staged_config *cfg;
@@ -284,14 +311,12 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 	enum resctrl_conf_type t;
 	cpumask_var_t cpu_mask;
 	struct rdt_domain *d;
-	bool mba_sc;
 	int cpu;
 	u32 idx;
 
 	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
 		return -ENOMEM;
 
-	mba_sc = is_mba_sc(r);
 	msr_param.res = NULL;
 	list_for_each_entry(d, &r->domains, list) {
 		hw_dom = resctrl_to_arch_dom(d);
@@ -301,7 +326,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 				continue;
 
 			idx = get_config_index(closid, t);
-			if (!apply_config(hw_dom, cfg, idx, cpu_mask, mba_sc))
+			if (!apply_config(hw_dom, cfg, idx, cpu_mask))
 				continue;
 
 			if (!msr_param.res) {
@@ -315,11 +340,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 		}
 	}
 
-	/*
-	 * Avoid writing the control msr with control values when
-	 * MBA software controller is enabled
-	 */
-	if (cpumask_empty(cpu_mask) || mba_sc)
+	if (cpumask_empty(cpu_mask))
 		goto done;
 	cpu = get_cpu();
 	/* Update resource control msr on this CPU if it's in cpu_mask. */
@@ -406,6 +427,14 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 
 	list_for_each_entry(s, &resctrl_schema_all, list) {
 		r = s->res;
+
+		/*
+		 * Writes to mba_sc resources update the software controller,
+		 * not the control MSR.
+		 */
+		if (is_mba_sc(r))
+			continue;
+
 		ret = resctrl_arch_update_domains(r, rdtgrp->closid);
 		if (ret)
 			goto out;
@@ -433,9 +462,7 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
 	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
 	u32 idx = get_config_index(closid, type);
 
-	if (!is_mba_sc(r))
-		return hw_dom->ctrl_val[idx];
-	return hw_dom->mbps_val[idx];
+	return hw_dom->ctrl_val[idx];
 }
 
 static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid)
@@ -450,8 +477,12 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 		if (sep)
 			seq_puts(s, ";");
 
-		ctrl_val = resctrl_arch_get_config(r, dom, closid,
-						   schema->conf_type);
+		if (is_mba_sc(r))
+			ctrl_val = dom->mbps_val[closid];
+		else
+			ctrl_val = resctrl_arch_get_config(r, dom, closid,
+							   schema->conf_type);
+
 		seq_printf(s, r->format_str, dom->id, max_data_width,
 			   ctrl_val);
 		sep = true;
@@ -518,7 +549,6 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 {
 	struct kernfs_open_file *of = m->private;
-	struct rdt_hw_resource *hw_res;
 	u32 resid, evtid, domid;
 	struct rdtgroup *rdtgrp;
 	struct rdt_resource *r;
@@ -538,8 +568,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	domid = md.u.domid;
 	evtid = md.u.evtid;
 
-	hw_res = &rdt_resources_all[resid];
-	r = &hw_res->r_resctrl;
+	r = &rdt_resources_all[resid].r_resctrl;
 	d = rdt_find_domain(r, domid, NULL);
 	if (IS_ERR_OR_NULL(d)) {
 		ret = -ENOENT;
@@ -548,12 +577,12 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 
 	mon_event_read(&rr, r, d, rdtgrp, evtid, false);
 
-	if (rr.val & RMID_VAL_ERROR)
+	if (rr.err == -EIO)
 		seq_puts(m, "Error\n");
-	else if (rr.val & RMID_VAL_UNAVAIL)
+	else if (rr.err == -EINVAL)
 		seq_puts(m, "Unavailable\n");
 	else
-		seq_printf(m, "%llu\n", rr.val * hw_res->mon_scale);
+		seq_printf(m, "%llu\n", rr.val);
 
 out:
 	rdtgroup_kn_unlock(of->kn);
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 1d647188a43b..5f7128686cfd 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -22,21 +22,12 @@
 
 #define L2_QOS_CDP_ENABLE		0x01ULL
 
-/*
- * Event IDs are used to program IA32_QM_EVTSEL before reading event
- * counter from IA32_QM_CTR
- */
-#define QOS_L3_OCCUP_EVENT_ID		0x01
-#define QOS_L3_MBM_TOTAL_EVENT_ID	0x02
-#define QOS_L3_MBM_LOCAL_EVENT_ID	0x03
-
 #define CQM_LIMBOCHECK_INTERVAL	1000
 
 #define MBM_CNTR_WIDTH_BASE		24
 #define MBM_OVERFLOW_INTERVAL		1000
 #define MAX_MBA_BW			100u
 #define MBA_IS_LINEAR			0x4
-#define MBA_MAX_MBPS			U32_MAX
 #define MAX_MBA_BW_AMD			0x800
 #define MBM_CNTR_WIDTH_OFFSET_AMD	20
 
@@ -74,7 +65,7 @@ DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key);
  * @list:		entry in &rdt_resource->evt_list
  */
 struct mon_evt {
-	u32			evtid;
+	enum resctrl_event_id	evtid;
 	char			*name;
 	struct list_head	list;
 };
@@ -91,9 +82,9 @@ struct mon_evt {
 union mon_data_bits {
 	void *priv;
 	struct {
-		unsigned int rid	: 10;
-		unsigned int evtid	: 8;
-		unsigned int domid	: 14;
+		unsigned int rid		: 10;
+		enum resctrl_event_id evtid	: 8;
+		unsigned int domid		: 14;
 	} u;
 };
 
@@ -101,12 +92,12 @@ struct rmid_read {
 	struct rdtgroup		*rgrp;
 	struct rdt_resource	*r;
 	struct rdt_domain	*d;
-	int			evtid;
+	enum resctrl_event_id	evtid;
 	bool			first;
+	int			err;
 	u64			val;
 };
 
-extern unsigned int resctrl_cqm_threshold;
 extern bool rdt_alloc_capable;
 extern bool rdt_mon_capable;
 extern unsigned int rdt_mon_features;
@@ -288,35 +279,45 @@ struct rftype {
 
 /**
  * struct mbm_state - status for each MBM counter in each domain
- * @chunks:	Total data moved (multiply by rdt_group.mon_scale to get bytes)
- * @prev_msr:	Value of IA32_QM_CTR for this RMID last time we read it
- * @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting
+ * @prev_bw_bytes: Previous bytes value read for bandwidth calculation
  * @prev_bw:	The most recent bandwidth in MBps
  * @delta_bw:	Difference between the current and previous bandwidth
  * @delta_comp:	Indicates whether to compute the delta_bw
  */
 struct mbm_state {
-	u64	chunks;
-	u64	prev_msr;
-	u64	prev_bw_msr;
+	u64	prev_bw_bytes;
 	u32	prev_bw;
 	u32	delta_bw;
 	bool	delta_comp;
 };
 
 /**
+ * struct arch_mbm_state - values used to compute resctrl_arch_rmid_read()s
+ *			   return value.
+ * @chunks:	Total data moved (multiply by rdt_group.mon_scale to get bytes)
+ * @prev_msr:	Value of IA32_QM_CTR last time it was read for the RMID used to
+ *		find this struct.
+ */
+struct arch_mbm_state {
+	u64	chunks;
+	u64	prev_msr;
+};
+
+/**
  * struct rdt_hw_domain - Arch private attributes of a set of CPUs that share
  *			  a resource
  * @d_resctrl:	Properties exposed to the resctrl file system
  * @ctrl_val:	array of cache or mem ctrl values (indexed by CLOSID)
- * @mbps_val:	When mba_sc is enabled, this holds the bandwidth in MBps
+ * @arch_mbm_total:	arch private state for MBM total bandwidth
+ * @arch_mbm_local:	arch private state for MBM local bandwidth
  *
  * Members of this structure are accessed via helpers that provide abstraction.
  */
 struct rdt_hw_domain {
 	struct rdt_domain		d_resctrl;
 	u32				*ctrl_val;
-	u32				*mbps_val;
+	struct arch_mbm_state		*arch_mbm_total;
+	struct arch_mbm_state		*arch_mbm_local;
 };
 
 static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r)
@@ -459,14 +460,6 @@ int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable);
 	for_each_rdt_resource(r)					      \
 		if (r->mon_capable)
 
-#define for_each_alloc_enabled_rdt_resource(r)				      \
-	for_each_rdt_resource(r)					      \
-		if (r->alloc_enabled)
-
-#define for_each_mon_enabled_rdt_resource(r)				      \
-	for_each_rdt_resource(r)					      \
-		if (r->mon_enabled)
-
 /* CPUID.(EAX=10H, ECX=ResID=1).EAX */
 union cpuid_0x10_1_eax {
 	struct {
@@ -530,10 +523,6 @@ void free_rmid(u32 rmid);
 int rdt_get_mon_l3_config(struct rdt_resource *r);
 void mon_event_count(void *info);
 int rdtgroup_mondata_show(struct seq_file *m, void *arg);
-void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
-				    unsigned int dom_id);
-void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
-				    struct rdt_domain *d);
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
 		    int evtid, int first);
@@ -542,8 +531,6 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom,
 void mbm_handle_overflow(struct work_struct *work);
 void __init intel_rdt_mbm_apply_quirk(void);
 bool is_mba_sc(struct rdt_resource *r);
-void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm);
-u32 delay_bw_map(unsigned long bw, struct rdt_resource *r);
 void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
 void cqm_handle_limbo(struct work_struct *work);
 bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index eaf25a234ff5..efe0c30d3a12 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -16,8 +16,12 @@
  */
 
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <linux/slab.h>
+
 #include <asm/cpu_device_id.h>
+#include <asm/resctrl.h>
+
 #include "internal.h"
 
 struct rmid_entry {
@@ -37,8 +41,8 @@ static LIST_HEAD(rmid_free_lru);
  * @rmid_limbo_count     count of currently unused but (potentially)
  *     dirty RMIDs.
  *     This counts RMIDs that no one is currently using but that
- *     may have a occupancy value > intel_cqm_threshold. User can change
- *     the threshold occupancy value.
+ *     may have a occupancy value > resctrl_rmid_realloc_threshold. User can
+ *     change the threshold occupancy value.
  */
 static unsigned int rmid_limbo_count;
 
@@ -59,10 +63,15 @@ bool rdt_mon_capable;
 unsigned int rdt_mon_features;
 
 /*
- * This is the threshold cache occupancy at which we will consider an
+ * This is the threshold cache occupancy in bytes at which we will consider an
  * RMID available for re-allocation.
  */
-unsigned int resctrl_cqm_threshold;
+unsigned int resctrl_rmid_realloc_threshold;
+
+/*
+ * This is the maximum value for the reallocation threshold, in bytes.
+ */
+unsigned int resctrl_rmid_realloc_limit;
 
 #define CF(cf)	((unsigned long)(1048576 * (cf) + 0.5))
 
@@ -137,9 +146,54 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid)
 	return entry;
 }
 
-static u64 __rmid_read(u32 rmid, u32 eventid)
+static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
+						 u32 rmid,
+						 enum resctrl_event_id eventid)
 {
-	u64 val;
+	switch (eventid) {
+	case QOS_L3_OCCUP_EVENT_ID:
+		return NULL;
+	case QOS_L3_MBM_TOTAL_EVENT_ID:
+		return &hw_dom->arch_mbm_total[rmid];
+	case QOS_L3_MBM_LOCAL_EVENT_ID:
+		return &hw_dom->arch_mbm_local[rmid];
+	}
+
+	/* Never expect to get here */
+	WARN_ON_ONCE(1);
+
+	return NULL;
+}
+
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
+			     u32 rmid, enum resctrl_event_id eventid)
+{
+	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct arch_mbm_state *am;
+
+	am = get_arch_mbm_state(hw_dom, rmid, eventid);
+	if (am)
+		memset(am, 0, sizeof(*am));
+}
+
+static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
+{
+	u64 shift = 64 - width, chunks;
+
+	chunks = (cur_msr << shift) - (prev_msr << shift);
+	return chunks >> shift;
+}
+
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+			   u32 rmid, enum resctrl_event_id eventid, u64 *val)
+{
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+	struct arch_mbm_state *am;
+	u64 msr_val, chunks;
+
+	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
+		return -EINVAL;
 
 	/*
 	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
@@ -150,16 +204,26 @@ static u64 __rmid_read(u32 rmid, u32 eventid)
 	 * are error bits.
 	 */
 	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
-	rdmsrl(MSR_IA32_QM_CTR, val);
-
-	return val;
-}
+	rdmsrl(MSR_IA32_QM_CTR, msr_val);
+
+	if (msr_val & RMID_VAL_ERROR)
+		return -EIO;
+	if (msr_val & RMID_VAL_UNAVAIL)
+		return -EINVAL;
+
+	am = get_arch_mbm_state(hw_dom, rmid, eventid);
+	if (am) {
+		am->chunks += mbm_overflow_count(am->prev_msr, msr_val,
+						 hw_res->mbm_width);
+		chunks = get_corrected_mbm_count(rmid, am->chunks);
+		am->prev_msr = msr_val;
+	} else {
+		chunks = msr_val;
+	}
 
-static bool rmid_dirty(struct rmid_entry *entry)
-{
-	u64 val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
+	*val = chunks * hw_res->mon_scale;
 
-	return val >= resctrl_cqm_threshold;
+	return 0;
 }
 
 /*
@@ -170,11 +234,11 @@ static bool rmid_dirty(struct rmid_entry *entry)
  */
 void __check_limbo(struct rdt_domain *d, bool force_free)
 {
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 	struct rmid_entry *entry;
-	struct rdt_resource *r;
 	u32 crmid = 1, nrmid;
-
-	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	bool rmid_dirty;
+	u64 val = 0;
 
 	/*
 	 * Skip RMID 0 and start from RMID 1 and check all the RMIDs that
@@ -188,7 +252,15 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 			break;
 
 		entry = __rmid_entry(nrmid);
-		if (force_free || !rmid_dirty(entry)) {
+
+		if (resctrl_arch_rmid_read(r, d, entry->rmid,
+					   QOS_L3_OCCUP_EVENT_ID, &val)) {
+			rmid_dirty = true;
+		} else {
+			rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
+		}
+
+		if (force_free || !rmid_dirty) {
 			clear_bit(entry->rmid, d->rmid_busy_llc);
 			if (!--entry->busy) {
 				rmid_limbo_count--;
@@ -227,19 +299,19 @@ int alloc_rmid(void)
 
 static void add_rmid_to_limbo(struct rmid_entry *entry)
 {
-	struct rdt_resource *r;
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 	struct rdt_domain *d;
-	int cpu;
-	u64 val;
-
-	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	int cpu, err;
+	u64 val = 0;
 
 	entry->busy = 0;
 	cpu = get_cpu();
 	list_for_each_entry(d, &r->domains, list) {
 		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
-			val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
-			if (val <= resctrl_cqm_threshold)
+			err = resctrl_arch_rmid_read(r, d, entry->rmid,
+						     QOS_L3_OCCUP_EVENT_ID,
+						     &val);
+			if (err || val <= resctrl_rmid_realloc_threshold)
 				continue;
 		}
 
@@ -277,24 +349,18 @@ void free_rmid(u32 rmid)
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
-static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
+static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 {
-	u64 shift = 64 - width, chunks;
+	struct mbm_state *m;
+	u64 tval = 0;
 
-	chunks = (cur_msr << shift) - (prev_msr << shift);
-	return chunks >> shift;
-}
+	if (rr->first)
+		resctrl_arch_reset_rmid(rr->r, rr->d, rmid, rr->evtid);
 
-static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
-{
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r);
-	struct mbm_state *m;
-	u64 chunks, tval;
+	rr->err = resctrl_arch_rmid_read(rr->r, rr->d, rmid, rr->evtid, &tval);
+	if (rr->err)
+		return rr->err;
 
-	tval = __rmid_read(rmid, rr->evtid);
-	if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) {
-		return tval;
-	}
 	switch (rr->evtid) {
 	case QOS_L3_OCCUP_EVENT_ID:
 		rr->val += tval;
@@ -308,48 +374,47 @@ static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
 	default:
 		/*
 		 * Code would never reach here because an invalid
-		 * event id would fail the __rmid_read.
+		 * event id would fail in resctrl_arch_rmid_read().
 		 */
-		return RMID_VAL_ERROR;
+		return -EINVAL;
 	}
 
 	if (rr->first) {
 		memset(m, 0, sizeof(struct mbm_state));
-		m->prev_bw_msr = m->prev_msr = tval;
 		return 0;
 	}
 
-	chunks = mbm_overflow_count(m->prev_msr, tval, hw_res->mbm_width);
-	m->chunks += chunks;
-	m->prev_msr = tval;
-
-	rr->val += get_corrected_mbm_count(rmid, m->chunks);
+	rr->val += tval;
 
 	return 0;
 }
 
 /*
+ * mbm_bw_count() - Update bw count from values previously read by
+ *		    __mon_event_count().
+ * @rmid:	The rmid used to identify the cached mbm_state.
+ * @rr:		The struct rmid_read populated by __mon_event_count().
+ *
  * Supporting function to calculate the memory bandwidth
- * and delta bandwidth in MBps.
+ * and delta bandwidth in MBps. The chunks value previously read by
+ * __mon_event_count() is compared with the chunks value from the previous
+ * invocation. This must be called once per second to maintain values in MBps.
  */
 static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
 {
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r);
 	struct mbm_state *m = &rr->d->mbm_local[rmid];
-	u64 tval, cur_bw, chunks;
+	u64 cur_bw, bytes, cur_bytes;
 
-	tval = __rmid_read(rmid, rr->evtid);
-	if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
-		return;
+	cur_bytes = rr->val;
+	bytes = cur_bytes - m->prev_bw_bytes;
+	m->prev_bw_bytes = cur_bytes;
 
-	chunks = mbm_overflow_count(m->prev_bw_msr, tval, hw_res->mbm_width);
-	cur_bw = (get_corrected_mbm_count(rmid, chunks) * hw_res->mon_scale) >> 20;
+	cur_bw = bytes / SZ_1M;
 
 	if (m->delta_comp)
 		m->delta_bw = abs(cur_bw - m->prev_bw);
 	m->delta_comp = false;
 	m->prev_bw = cur_bw;
-	m->prev_bw_msr = tval;
 }
 
 /*
@@ -361,11 +426,11 @@ void mon_event_count(void *info)
 	struct rdtgroup *rdtgrp, *entry;
 	struct rmid_read *rr = info;
 	struct list_head *head;
-	u64 ret_val;
+	int ret;
 
 	rdtgrp = rr->rgrp;
 
-	ret_val = __mon_event_count(rdtgrp->mon.rmid, rr);
+	ret = __mon_event_count(rdtgrp->mon.rmid, rr);
 
 	/*
 	 * For Ctrl groups read data from child monitor groups and
@@ -377,13 +442,17 @@ void mon_event_count(void *info)
 	if (rdtgrp->type == RDTCTRL_GROUP) {
 		list_for_each_entry(entry, head, mon.crdtgrp_list) {
 			if (__mon_event_count(entry->mon.rmid, rr) == 0)
-				ret_val = 0;
+				ret = 0;
 		}
 	}
 
-	/* Report error if none of rmid_reads are successful */
-	if (ret_val)
-		rr->val = ret_val;
+	/*
+	 * __mon_event_count() calls for newly created monitor groups may
+	 * report -EINVAL/Unavailable if the monitor hasn't seen any traffic.
+	 * Discard error if any of the monitor event reads succeeded.
+	 */
+	if (ret == 0)
+		rr->err = 0;
 }
 
 /*
@@ -420,10 +489,8 @@ void mon_event_count(void *info)
  */
 static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 {
-	u32 closid, rmid, cur_msr, cur_msr_val, new_msr_val;
+	u32 closid, rmid, cur_msr_val, new_msr_val;
 	struct mbm_state *pmbm_data, *cmbm_data;
-	struct rdt_hw_resource *hw_r_mba;
-	struct rdt_hw_domain *hw_dom_mba;
 	u32 cur_bw, delta_bw, user_bw;
 	struct rdt_resource *r_mba;
 	struct rdt_domain *dom_mba;
@@ -433,8 +500,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	if (!is_mbm_local_enabled())
 		return;
 
-	hw_r_mba = &rdt_resources_all[RDT_RESOURCE_MBA];
-	r_mba = &hw_r_mba->r_resctrl;
+	r_mba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
+
 	closid = rgrp->closid;
 	rmid = rgrp->mon.rmid;
 	pmbm_data = &dom_mbm->mbm_local[rmid];
@@ -444,16 +511,13 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 		pr_warn_once("Failure to get domain for MBA update\n");
 		return;
 	}
-	hw_dom_mba = resctrl_to_arch_dom(dom_mba);
 
 	cur_bw = pmbm_data->prev_bw;
-	user_bw = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE);
+	user_bw = dom_mba->mbps_val[closid];
 	delta_bw = pmbm_data->delta_bw;
-	/*
-	 * resctrl_arch_get_config() chooses the mbps/ctrl value to return
-	 * based on is_mba_sc(). For now, reach into the hw_dom.
-	 */
-	cur_msr_val = hw_dom_mba->ctrl_val[closid];
+
+	/* MBA resource doesn't support CDP */
+	cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE);
 
 	/*
 	 * For Ctrl groups read data from child monitor groups.
@@ -488,9 +552,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 		return;
 	}
 
-	cur_msr = hw_r_mba->msr_base + closid;
-	wrmsrl(cur_msr, delay_bw_map(new_msr_val, r_mba));
-	hw_dom_mba->ctrl_val[closid] = new_msr_val;
+	resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
 
 	/*
 	 * Delta values are updated dynamically package wise for each
@@ -523,10 +585,12 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
 	 */
 	if (is_mbm_total_enabled()) {
 		rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
+		rr.val = 0;
 		__mon_event_count(rmid, &rr);
 	}
 	if (is_mbm_local_enabled()) {
 		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
+		rr.val = 0;
 		__mon_event_count(rmid, &rr);
 
 		/*
@@ -686,9 +750,10 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)
 {
 	unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	unsigned int cl_size = boot_cpu_data.x86_cache_size;
+	unsigned int threshold;
 	int ret;
 
+	resctrl_rmid_realloc_limit = boot_cpu_data.x86_cache_size * 1024;
 	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale;
 	r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
 	hw_res->mbm_width = MBM_CNTR_WIDTH_BASE;
@@ -705,10 +770,14 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)
 	 *
 	 * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC.
 	 */
-	resctrl_cqm_threshold = cl_size * 1024 / r->num_rmid;
+	threshold = resctrl_rmid_realloc_limit / r->num_rmid;
 
-	/* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */
-	resctrl_cqm_threshold /= hw_res->mon_scale;
+	/*
+	 * Because num_rmid may not be a power of two, round the value
+	 * to the nearest multiple of hw_res->mon_scale so it matches a
+	 * value the hardware will measure. mon_scale may not be a power of 2.
+	 */
+	resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(threshold);
 
 	ret = dom_data_init(r);
 	if (ret)
@@ -717,7 +786,6 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)
 	l3_mon_evt_init(r);
 
 	r->mon_capable = true;
-	r->mon_enabled = true;
 
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index db813f819ad6..d961ae3ed96e 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -420,6 +420,7 @@ static int pseudo_lock_fn(void *_rdtgrp)
 	struct pseudo_lock_region *plr = rdtgrp->plr;
 	u32 rmid_p, closid_p;
 	unsigned long i;
+	u64 saved_msr;
 #ifdef CONFIG_KASAN
 	/*
 	 * The registers used for local register variables are also used
@@ -463,6 +464,7 @@ static int pseudo_lock_fn(void *_rdtgrp)
 	 * the buffer and evict pseudo-locked memory read earlier from the
 	 * cache.
 	 */
+	saved_msr = __rdmsr(MSR_MISC_FEATURE_CONTROL);
 	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
 	closid_p = this_cpu_read(pqr_state.cur_closid);
 	rmid_p = this_cpu_read(pqr_state.cur_rmid);
@@ -514,7 +516,7 @@ static int pseudo_lock_fn(void *_rdtgrp)
 	__wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p);
 
 	/* Re-enable the hardware prefetcher(s) */
-	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+	wrmsrl(MSR_MISC_FEATURE_CONTROL, saved_msr);
 	local_irq_enable();
 
 	plr->thread_done = 1;
@@ -835,7 +837,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
 	 * First determine which cpus have pseudo-locked regions
 	 * associated with them.
 	 */
-	for_each_alloc_enabled_rdt_resource(r) {
+	for_each_alloc_capable_rdt_resource(r) {
 		list_for_each_entry(d_i, &r->domains, list) {
 			if (d_i->plr)
 				cpumask_or(cpu_with_psl, cpu_with_psl,
@@ -871,6 +873,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
 static int measure_cycles_lat_fn(void *_plr)
 {
 	struct pseudo_lock_region *plr = _plr;
+	u32 saved_low, saved_high;
 	unsigned long i;
 	u64 start, end;
 	void *mem_r;
@@ -879,6 +882,7 @@ static int measure_cycles_lat_fn(void *_plr)
 	/*
 	 * Disable hardware prefetchers.
 	 */
+	rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
 	wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
 	mem_r = READ_ONCE(plr->kmem);
 	/*
@@ -895,7 +899,7 @@ static int measure_cycles_lat_fn(void *_plr)
 		end = rdtsc_ordered();
 		trace_pseudo_lock_mem_latency((u32)(end - start));
 	}
-	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+	wrmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
 	local_irq_enable();
 	plr->thread_done = 1;
 	wake_up_interruptible(&plr->lock_thread_wq);
@@ -940,6 +944,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
 	u64 hits_before = 0, hits_after = 0, miss_before = 0, miss_after = 0;
 	struct perf_event *miss_event, *hit_event;
 	int hit_pmcnum, miss_pmcnum;
+	u32 saved_low, saved_high;
 	unsigned int line_size;
 	unsigned int size;
 	unsigned long i;
@@ -973,6 +978,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
 	/*
 	 * Disable hardware prefetchers.
 	 */
+	rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
 	wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
 
 	/* Initialize rest of local variables */
@@ -1031,7 +1037,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
 	 */
 	rmb();
 	/* Re-enable hardware prefetchers */
-	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+	wrmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
 	local_irq_enable();
 out_hit:
 	perf_event_release_kernel(hit_event);
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index f276aff521e8..e5a48f05e787 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1030,10 +1030,7 @@ static int rdt_delay_linear_show(struct kernfs_open_file *of,
 static int max_threshold_occ_show(struct kernfs_open_file *of,
 				  struct seq_file *seq, void *v)
 {
-	struct rdt_resource *r = of->kn->parent->priv;
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-
-	seq_printf(seq, "%u\n", resctrl_cqm_threshold * hw_res->mon_scale);
+	seq_printf(seq, "%u\n", resctrl_rmid_realloc_threshold);
 
 	return 0;
 }
@@ -1055,7 +1052,6 @@ static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of,
 static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
 				       char *buf, size_t nbytes, loff_t off)
 {
-	struct rdt_hw_resource *hw_res;
 	unsigned int bytes;
 	int ret;
 
@@ -1063,11 +1059,10 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
 	if (ret)
 		return ret;
 
-	if (bytes > (boot_cpu_data.x86_cache_size * 1024))
+	if (bytes > resctrl_rmid_realloc_limit)
 		return -EINVAL;
 
-	hw_res = resctrl_to_arch_res(of->kn->parent->priv);
-	resctrl_cqm_threshold = bytes / hw_res->mon_scale;
+	resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(bytes);
 
 	return nbytes;
 }
@@ -1356,11 +1351,13 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 			      struct seq_file *s, void *v)
 {
 	struct resctrl_schema *schema;
+	enum resctrl_conf_type type;
 	struct rdtgroup *rdtgrp;
 	struct rdt_resource *r;
 	struct rdt_domain *d;
 	unsigned int size;
 	int ret = 0;
+	u32 closid;
 	bool sep;
 	u32 ctrl;
 
@@ -1386,8 +1383,11 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 		goto out;
 	}
 
+	closid = rdtgrp->closid;
+
 	list_for_each_entry(schema, &resctrl_schema_all, list) {
 		r = schema->res;
+		type = schema->conf_type;
 		sep = false;
 		seq_printf(s, "%*s:", max_name_width, schema->name);
 		list_for_each_entry(d, &r->domains, list) {
@@ -1396,9 +1396,12 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 			if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
 				size = 0;
 			} else {
-				ctrl = resctrl_arch_get_config(r, d,
-							       rdtgrp->closid,
-							       schema->conf_type);
+				if (is_mba_sc(r))
+					ctrl = d->mbps_val[closid];
+				else
+					ctrl = resctrl_arch_get_config(r, d,
+								       closid,
+								       type);
 				if (r->rid == RDT_RESOURCE_MBA)
 					size = ctrl;
 				else
@@ -1756,7 +1759,7 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 	if (ret)
 		goto out_destroy;
 
-	/* loop over enabled controls, these are all alloc_enabled */
+	/* loop over enabled controls, these are all alloc_capable */
 	list_for_each_entry(s, &resctrl_schema_all, list) {
 		r = s->res;
 		fflags =  r->fflags | RF_CTRL_INFO;
@@ -1765,7 +1768,7 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 			goto out_destroy;
 	}
 
-	for_each_mon_enabled_rdt_resource(r) {
+	for_each_mon_capable_rdt_resource(r) {
 		fflags =  r->fflags | RF_MON_INFO;
 		sprintf(name, "%s_MON", r->name);
 		ret = rdtgroup_mkdir_info_resdir(r, name, fflags);
@@ -1889,26 +1892,61 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
 		l3_qos_cfg_update(&hw_res->cdp_enabled);
 }
 
+static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_domain *d)
+{
+	u32 num_closid = resctrl_arch_get_num_closid(r);
+	int cpu = cpumask_any(&d->cpu_mask);
+	int i;
+
+	d->mbps_val = kcalloc_node(num_closid, sizeof(*d->mbps_val),
+				   GFP_KERNEL, cpu_to_node(cpu));
+	if (!d->mbps_val)
+		return -ENOMEM;
+
+	for (i = 0; i < num_closid; i++)
+		d->mbps_val[i] = MBA_MAX_MBPS;
+
+	return 0;
+}
+
+static void mba_sc_domain_destroy(struct rdt_resource *r,
+				  struct rdt_domain *d)
+{
+	kfree(d->mbps_val);
+	d->mbps_val = NULL;
+}
+
 /*
- * Enable or disable the MBA software controller
- * which helps user specify bandwidth in MBps.
  * MBA software controller is supported only if
  * MBM is supported and MBA is in linear scale.
  */
+static bool supports_mba_mbps(void)
+{
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
+
+	return (is_mbm_local_enabled() &&
+		r->alloc_capable && is_mba_linear());
+}
+
+/*
+ * Enable or disable the MBA software controller
+ * which helps user specify bandwidth in MBps.
+ */
 static int set_mba_sc(bool mba_sc)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
-	struct rdt_hw_domain *hw_dom;
+	u32 num_closid = resctrl_arch_get_num_closid(r);
 	struct rdt_domain *d;
+	int i;
 
-	if (!is_mbm_enabled() || !is_mba_linear() ||
-	    mba_sc == is_mba_sc(r))
+	if (!supports_mba_mbps() || mba_sc == is_mba_sc(r))
 		return -EINVAL;
 
 	r->membw.mba_sc = mba_sc;
+
 	list_for_each_entry(d, &r->domains, list) {
-		hw_dom = resctrl_to_arch_dom(d);
-		setup_default_ctrlval(r, hw_dom->ctrl_val, hw_dom->mbps_val);
+		for (i = 0; i < num_closid; i++)
+			d->mbps_val[i] = MBA_MAX_MBPS;
 	}
 
 	return 0;
@@ -2106,7 +2144,7 @@ static int schemata_list_create(void)
 	struct rdt_resource *r;
 	int ret = 0;
 
-	for_each_alloc_enabled_rdt_resource(r) {
+	for_each_alloc_capable_rdt_resource(r) {
 		if (resctrl_arch_get_cdp_enabled(r->rid)) {
 			ret = schemata_list_add(r, CDP_CODE);
 			if (ret)
@@ -2261,7 +2299,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		ctx->enable_cdpl2 = true;
 		return 0;
 	case Opt_mba_mbps:
-		if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		if (!supports_mba_mbps())
 			return -EINVAL;
 		ctx->enable_mba_mbps = true;
 		return 0;
@@ -2452,7 +2490,7 @@ static void rdt_kill_sb(struct super_block *sb)
 	set_mba_sc(false);
 
 	/*Put everything back to default values. */
-	for_each_alloc_enabled_rdt_resource(r)
+	for_each_alloc_capable_rdt_resource(r)
 		reset_all_ctrls(r);
 	cdp_disable_all();
 	rmdir_all_sub();
@@ -2499,14 +2537,12 @@ static int mon_addfile(struct kernfs_node *parent_kn, const char *name,
  * Remove all subdirectories of mon_data of ctrl_mon groups
  * and monitor groups with given domain id.
  */
-void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, unsigned int dom_id)
+static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
+					   unsigned int dom_id)
 {
 	struct rdtgroup *prgrp, *crgrp;
 	char name[32];
 
-	if (!r->mon_enabled)
-		return;
-
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
 		sprintf(name, "mon_%s_%02d", r->name, dom_id);
 		kernfs_remove_by_name(prgrp->mon.mon_data_kn, name);
@@ -2565,16 +2601,13 @@ out_destroy:
  * Add all subdirectories of mon_data for "ctrl_mon" groups
  * and "monitor" groups with given domain id.
  */
-void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
-				    struct rdt_domain *d)
+static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
+					   struct rdt_domain *d)
 {
 	struct kernfs_node *parent_kn;
 	struct rdtgroup *prgrp, *crgrp;
 	struct list_head *head;
 
-	if (!r->mon_enabled)
-		return;
-
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
 		parent_kn = prgrp->mon.mon_data_kn;
 		mkdir_mondata_subdir(parent_kn, d, r, prgrp);
@@ -2642,7 +2675,7 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn,
 	 * Create the subdirectories for each domain. Note that all events
 	 * in a domain like L3 are grouped into a resource whose domain is L3
 	 */
-	for_each_mon_enabled_rdt_resource(r) {
+	for_each_mon_capable_rdt_resource(r) {
 		ret = mkdir_mondata_subdir_alldom(kn, r, prgrp);
 		if (ret)
 			goto out_destroy;
@@ -2786,14 +2819,19 @@ static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
 }
 
 /* Initialize MBA resource with default values. */
-static void rdtgroup_init_mba(struct rdt_resource *r)
+static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid)
 {
 	struct resctrl_staged_config *cfg;
 	struct rdt_domain *d;
 
 	list_for_each_entry(d, &r->domains, list) {
+		if (is_mba_sc(r)) {
+			d->mbps_val[closid] = MBA_MAX_MBPS;
+			continue;
+		}
+
 		cfg = &d->staged_config[CDP_NONE];
-		cfg->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl;
+		cfg->new_ctrl = r->default_ctrl;
 		cfg->have_new_ctrl = true;
 	}
 }
@@ -2808,7 +2846,9 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 	list_for_each_entry(s, &resctrl_schema_all, list) {
 		r = s->res;
 		if (r->rid == RDT_RESOURCE_MBA) {
-			rdtgroup_init_mba(r);
+			rdtgroup_init_mba(r, rdtgrp->closid);
+			if (is_mba_sc(r))
+				continue;
 		} else {
 			ret = rdtgroup_init_cat(s, rdtgrp->closid);
 			if (ret < 0)
@@ -3236,6 +3276,110 @@ out:
 	return ret;
 }
 
+static void domain_destroy_mon_state(struct rdt_domain *d)
+{
+	bitmap_free(d->rmid_busy_llc);
+	kfree(d->mbm_total);
+	kfree(d->mbm_local);
+}
+
+void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d)
+{
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
+		mba_sc_domain_destroy(r, d);
+
+	if (!r->mon_capable)
+		return;
+
+	/*
+	 * If resctrl is mounted, remove all the
+	 * per domain monitor data directories.
+	 */
+	if (static_branch_unlikely(&rdt_mon_enable_key))
+		rmdir_mondata_subdir_allrdtgrp(r, d->id);
+
+	if (is_mbm_enabled())
+		cancel_delayed_work(&d->mbm_over);
+	if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) {
+		/*
+		 * When a package is going down, forcefully
+		 * decrement rmid->ebusy. There is no way to know
+		 * that the L3 was flushed and hence may lead to
+		 * incorrect counts in rare scenarios, but leaving
+		 * the RMID as busy creates RMID leaks if the
+		 * package never comes back.
+		 */
+		__check_limbo(d, true);
+		cancel_delayed_work(&d->cqm_limbo);
+	}
+
+	domain_destroy_mon_state(d);
+}
+
+static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
+{
+	size_t tsize;
+
+	if (is_llc_occupancy_enabled()) {
+		d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL);
+		if (!d->rmid_busy_llc)
+			return -ENOMEM;
+	}
+	if (is_mbm_total_enabled()) {
+		tsize = sizeof(*d->mbm_total);
+		d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
+		if (!d->mbm_total) {
+			bitmap_free(d->rmid_busy_llc);
+			return -ENOMEM;
+		}
+	}
+	if (is_mbm_local_enabled()) {
+		tsize = sizeof(*d->mbm_local);
+		d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
+		if (!d->mbm_local) {
+			bitmap_free(d->rmid_busy_llc);
+			kfree(d->mbm_total);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d)
+{
+	int err;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
+		/* RDT_RESOURCE_MBA is never mon_capable */
+		return mba_sc_domain_allocate(r, d);
+
+	if (!r->mon_capable)
+		return 0;
+
+	err = domain_setup_mon_state(r, d);
+	if (err)
+		return err;
+
+	if (is_mbm_enabled()) {
+		INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
+		mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL);
+	}
+
+	if (is_llc_occupancy_enabled())
+		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
+
+	/* If resctrl is mounted, add per domain monitor data directories. */
+	if (static_branch_unlikely(&rdt_mon_enable_key))
+		mkdir_mondata_subdir_allrdtgrp(r, d);
+
+	return 0;
+}
+
 /*
  * rdtgroup_init - rdtgroup initialization
  *
diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index 24c1bb8eb196..9f13d724172e 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -12,6 +12,9 @@
 #include "encls.h"
 #include "sgx.h"
 
+static int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
+			    struct sgx_backing *backing);
+
 #define PCMDS_PER_PAGE (PAGE_SIZE / sizeof(struct sgx_pcmd))
 /*
  * 32 PCMD entries share a PCMD page. PCMD_FIRST_MASK is used to
@@ -344,8 +347,11 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma,
 	}
 
 	va_page = sgx_encl_grow(encl, false);
-	if (IS_ERR(va_page))
+	if (IS_ERR(va_page)) {
+		if (PTR_ERR(va_page) == -EBUSY)
+			vmret = VM_FAULT_NOPAGE;
 		goto err_out_epc;
+	}
 
 	if (va_page)
 		list_add(&va_page->list, &encl->va_pages);
@@ -914,7 +920,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl,
 }
 
 /**
- * sgx_encl_get_backing() - Pin the backing storage
+ * __sgx_encl_get_backing() - Pin the backing storage
  * @encl:	an enclave pointer
  * @page_index:	enclave page index
  * @backing:	data for accessing backing storage for the page
@@ -926,7 +932,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl,
  *   0 on success,
  *   -errno otherwise.
  */
-static int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
+static int __sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
 			 struct sgx_backing *backing)
 {
 	pgoff_t page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index);
@@ -1001,7 +1007,7 @@ static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl)
 }
 
 /**
- * sgx_encl_alloc_backing() - allocate a new backing storage page
+ * sgx_encl_alloc_backing() - create a new backing storage page
  * @encl:	an enclave pointer
  * @page_index:	enclave page index
  * @backing:	data for accessing backing storage for the page
@@ -1009,7 +1015,9 @@ static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl)
  * When called from ksgxd, sets the active memcg from one of the
  * mms in the enclave's mm_list prior to any backing page allocation,
  * in order to ensure that shmem page allocations are charged to the
- * enclave.
+ * enclave.  Create a backing page for loading data back into an EPC page with
+ * ELDU.  This function takes a reference on a new backing page which
+ * must be dropped with a corresponding call to sgx_encl_put_backing().
  *
  * Return:
  *   0 on success,
@@ -1022,7 +1030,7 @@ int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
 	struct mem_cgroup *memcg = set_active_memcg(encl_memcg);
 	int ret;
 
-	ret = sgx_encl_get_backing(encl, page_index, backing);
+	ret = __sgx_encl_get_backing(encl, page_index, backing);
 
 	set_active_memcg(memcg);
 	mem_cgroup_put(encl_memcg);
@@ -1040,15 +1048,17 @@ int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
  * It is the caller's responsibility to ensure that it is appropriate to use
  * sgx_encl_lookup_backing() rather than sgx_encl_alloc_backing(). If lookup is
  * not used correctly, this will cause an allocation which is not accounted for.
+ * This function takes a reference on an existing backing page which must be
+ * dropped with a corresponding call to sgx_encl_put_backing().
  *
  * Return:
  *   0 on success,
  *   -errno otherwise.
  */
-int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
+static int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
 			   struct sgx_backing *backing)
 {
-	return sgx_encl_get_backing(encl, page_index, backing);
+	return __sgx_encl_get_backing(encl, page_index, backing);
 }
 
 /**
diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h
index a65a952116fd..f94ff14c9486 100644
--- a/arch/x86/kernel/cpu/sgx/encl.h
+++ b/arch/x86/kernel/cpu/sgx/encl.h
@@ -107,8 +107,6 @@ bool current_is_ksgxd(void);
 void sgx_encl_release(struct kref *ref);
 int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm);
 const cpumask_t *sgx_encl_cpumask(struct sgx_encl *encl);
-int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
-			    struct sgx_backing *backing);
 int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
 			   struct sgx_backing *backing);
 void sgx_encl_put_backing(struct sgx_backing *backing);
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 515e2a5f25bb..0aad028f04d4 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -49,9 +49,13 @@ static LIST_HEAD(sgx_dirty_page_list);
  * Reset post-kexec EPC pages to the uninitialized state. The pages are removed
  * from the input list, and made available for the page allocator. SECS pages
  * prepending their children in the input list are left intact.
+ *
+ * Return 0 when sanitization was successful or kthread was stopped, and the
+ * number of unsanitized pages otherwise.
  */
-static void __sgx_sanitize_pages(struct list_head *dirty_page_list)
+static unsigned long __sgx_sanitize_pages(struct list_head *dirty_page_list)
 {
+	unsigned long left_dirty = 0;
 	struct sgx_epc_page *page;
 	LIST_HEAD(dirty);
 	int ret;
@@ -59,7 +63,7 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list)
 	/* dirty_page_list is thread-local, no need for a lock: */
 	while (!list_empty(dirty_page_list)) {
 		if (kthread_should_stop())
-			return;
+			return 0;
 
 		page = list_first_entry(dirty_page_list, struct sgx_epc_page, list);
 
@@ -92,12 +96,14 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list)
 		} else {
 			/* The page is not yet clean - move to the dirty list. */
 			list_move_tail(&page->list, &dirty);
+			left_dirty++;
 		}
 
 		cond_resched();
 	}
 
 	list_splice(&dirty, dirty_page_list);
+	return left_dirty;
 }
 
 static bool sgx_reclaimer_age(struct sgx_epc_page *epc_page)
@@ -395,10 +401,7 @@ static int ksgxd(void *p)
 	 * required for SECS pages, whose child pages blocked EREMOVE.
 	 */
 	__sgx_sanitize_pages(&sgx_dirty_page_list);
-	__sgx_sanitize_pages(&sgx_dirty_page_list);
-
-	/* sanity check: */
-	WARN_ON(!list_empty(&sgx_dirty_page_list));
+	WARN_ON(__sgx_sanitize_pages(&sgx_dirty_page_list));
 
 	while (!kthread_should_stop()) {
 		if (try_to_freeze())
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index afae4dd77495..b3dba35f466e 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -128,7 +128,7 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl)
 		/* No access to the user space stack of other tasks. Ignore. */
 		break;
 	default:
-		printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n",
+		printk("%sCode: Unable to access opcode bytes at 0x%lx.\n",
 		       loglvl, prologue);
 		break;
 	}
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 68b38925a74f..44f937015e1e 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -264,11 +264,11 @@ static __init void early_pci_serial_init(char *s)
 	bar0 = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0);
 
 	/*
-	 * Verify it is a UART type device
+	 * Verify it is a 16550-UART type device
 	 */
 	if (((classcode >> 16 != PCI_CLASS_COMMUNICATION_MODEM) &&
 	     (classcode >> 16 != PCI_CLASS_COMMUNICATION_SERIAL)) ||
-	   (((classcode >> 8) & 0xff) != 0x02)) /* 16550 I/F at BAR0 */ {
+	    (((classcode >> 8) & 0xff) != PCI_SERIAL_16550_COMPATIBLE)) {
 		if (!force)
 			return;
 	}
@@ -276,22 +276,22 @@ static __init void early_pci_serial_init(char *s)
 	/*
 	 * Determine if it is IO or memory mapped
 	 */
-	if (bar0 & 0x01) {
+	if ((bar0 & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) {
 		/* it is IO mapped */
 		serial_in = io_serial_in;
 		serial_out = io_serial_out;
-		early_serial_base = bar0&0xfffffffc;
+		early_serial_base = bar0 & PCI_BASE_ADDRESS_IO_MASK;
 		write_pci_config(bus, slot, func, PCI_COMMAND,
-						cmdreg|PCI_COMMAND_IO);
+				 cmdreg|PCI_COMMAND_IO);
 	} else {
 		/* It is memory mapped - assume 32-bit alignment */
 		serial_in = mem32_serial_in;
 		serial_out = mem32_serial_out;
 		/* WARNING! assuming the address is always in the first 4G */
 		early_serial_base =
-			(unsigned long)early_ioremap(bar0 & 0xfffffff0, 0x10);
+			(unsigned long)early_ioremap(bar0 & PCI_BASE_ADDRESS_MEM_MASK, 0x10);
 		write_pci_config(bus, slot, func, PCI_COMMAND,
-						cmdreg|PCI_COMMAND_MEMORY);
+				 cmdreg|PCI_COMMAND_MEMORY);
 	}
 
 	/*
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index e5dd6da78713..01833ebf5e8e 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -132,7 +132,7 @@ int irq_init_percpu_irqstack(unsigned int cpu)
 	return 0;
 }
 
-#ifndef CONFIG_PREEMPT_RT
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
 void do_softirq_own_stack(void)
 {
 	struct irq_stack *irqstk;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 74167dc5f55e..4c3c27b6aea3 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -505,7 +505,7 @@ static void kprobe_emulate_jcc(struct kprobe *p, struct pt_regs *regs)
 		match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^
 			((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT);
 		if (p->ainsn.jcc.type >= 0xe)
-			match = match && (regs->flags & X86_EFLAGS_ZF);
+			match = match || (regs->flags & X86_EFLAGS_ZF);
 	}
 	__kprobe_emulate_jmp(p, regs, (match && !invert) || (!match && invert));
 }
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 586f718b8e95..349046434513 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -4,11 +4,8 @@
  */
 #include <linux/platform_device.h>
 #include <linux/mc146818rtc.h>
-#include <linux/acpi.h>
-#include <linux/bcd.h>
 #include <linux/export.h>
 #include <linux/pnp.h>
-#include <linux/of.h>
 
 #include <asm/vsyscall.h>
 #include <asm/x86_init.h>
@@ -20,26 +17,23 @@
 /*
  * This is a special lock that is owned by the CPU and holds the index
  * register we are working with.  It is required for NMI access to the
- * CMOS/RTC registers.  See include/asm-i386/mc146818rtc.h for details.
+ * CMOS/RTC registers.  See arch/x86/include/asm/mc146818rtc.h for details.
  */
 volatile unsigned long cmos_lock;
 EXPORT_SYMBOL(cmos_lock);
 #endif /* CONFIG_X86_32 */
 
-/* For two digit years assume time is always after that */
-#define CMOS_YEARS_OFFS 2000
-
 DEFINE_SPINLOCK(rtc_lock);
 EXPORT_SYMBOL(rtc_lock);
 
 /*
- * In order to set the CMOS clock precisely, set_rtc_mmss has to be
+ * In order to set the CMOS clock precisely, mach_set_cmos_time has to be
  * called 500 ms after the second nowtime has started, because when
  * nowtime is written into the registers of the CMOS clock, it will
  * jump to the next second precisely 500 ms later. Check the Motorola
  * MC146818A or Dallas DS12887 data sheet for details.
  */
-int mach_set_rtc_mmss(const struct timespec64 *now)
+int mach_set_cmos_time(const struct timespec64 *now)
 {
 	unsigned long long nowtime = now->tv_sec;
 	struct rtc_time tm;
@@ -62,8 +56,7 @@ int mach_set_rtc_mmss(const struct timespec64 *now)
 
 void mach_get_cmos_time(struct timespec64 *now)
 {
-	unsigned int status, year, mon, day, hour, min, sec, century = 0;
-	unsigned long flags;
+	struct rtc_time tm;
 
 	/*
 	 * If pm_trace abused the RTC as storage, set the timespec to 0,
@@ -74,51 +67,13 @@ void mach_get_cmos_time(struct timespec64 *now)
 		return;
 	}
 
-	spin_lock_irqsave(&rtc_lock, flags);
-
-	/*
-	 * If UIP is clear, then we have >= 244 microseconds before
-	 * RTC registers will be updated.  Spec sheet says that this
-	 * is the reliable way to read RTC - registers. If UIP is set
-	 * then the register access might be invalid.
-	 */
-	while ((CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP))
-		cpu_relax();
-
-	sec = CMOS_READ(RTC_SECONDS);
-	min = CMOS_READ(RTC_MINUTES);
-	hour = CMOS_READ(RTC_HOURS);
-	day = CMOS_READ(RTC_DAY_OF_MONTH);
-	mon = CMOS_READ(RTC_MONTH);
-	year = CMOS_READ(RTC_YEAR);
-
-#ifdef CONFIG_ACPI
-	if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
-	    acpi_gbl_FADT.century)
-		century = CMOS_READ(acpi_gbl_FADT.century);
-#endif
-
-	status = CMOS_READ(RTC_CONTROL);
-	WARN_ON_ONCE(RTC_ALWAYS_BCD && (status & RTC_DM_BINARY));
-
-	spin_unlock_irqrestore(&rtc_lock, flags);
-
-	if (RTC_ALWAYS_BCD || !(status & RTC_DM_BINARY)) {
-		sec = bcd2bin(sec);
-		min = bcd2bin(min);
-		hour = bcd2bin(hour);
-		day = bcd2bin(day);
-		mon = bcd2bin(mon);
-		year = bcd2bin(year);
+	if (mc146818_get_time(&tm)) {
+		pr_err("Unable to read current time from RTC\n");
+		now->tv_sec = now->tv_nsec = 0;
+		return;
 	}
 
-	if (century) {
-		century = bcd2bin(century);
-		year += century * 100;
-	} else
-		year += CMOS_YEARS_OFFS;
-
-	now->tv_sec = mktime64(year, mon, day, hour, min, sec);
+	now->tv_sec = rtc_tm_to_time64(&tm);
 	now->tv_nsec = 0;
 }
 
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 63dc626627a0..a428c62330d3 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -701,7 +701,13 @@ e_term:
 void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
 					 unsigned int npages)
 {
-	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+	/*
+	 * This can be invoked in early boot while running identity mapped, so
+	 * use an open coded check for SNP instead of using cc_platform_has().
+	 * This eliminates worries about jump tables or checking boot_cpu_data
+	 * in the cc_platform_has() function.
+	 */
+	if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
 		return;
 
 	 /*
@@ -717,7 +723,13 @@ void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long padd
 void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
 					unsigned int npages)
 {
-	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+	/*
+	 * This can be invoked in early boot while running identity mapped, so
+	 * use an open coded check for SNP instead of using cc_platform_has().
+	 * This eliminates worries about jump tables or checking boot_cpu_data
+	 * in the cc_platform_has() function.
+	 */
+	if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
 		return;
 
 	/* Invalidate the memory pages before they are marked shared in the RMP table. */
@@ -2100,7 +2112,7 @@ bool __init snp_init(struct boot_params *bp)
 	return true;
 }
 
-void __init snp_abort(void)
+void __init __noreturn snp_abort(void)
 {
 	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
 }
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d62b2cb85cea..178015a820f0 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -63,6 +63,7 @@
 #include <asm/insn-eval.h>
 #include <asm/vdso.h>
 #include <asm/tdx.h>
+#include <asm/cfi.h>
 
 #ifdef CONFIG_X86_64
 #include <asm/x86_init.h>
@@ -313,7 +314,8 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 	 */
 	if (regs->flags & X86_EFLAGS_IF)
 		raw_local_irq_enable();
-	if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
+	if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN ||
+	    handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
 		regs->ip += LEN_UD2;
 		handled = true;
 	}
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 38185aedf7d1..0ea57da92940 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -93,22 +93,27 @@ static struct orc_entry *orc_find(unsigned long ip);
 static struct orc_entry *orc_ftrace_find(unsigned long ip)
 {
 	struct ftrace_ops *ops;
-	unsigned long caller;
+	unsigned long tramp_addr, offset;
 
 	ops = ftrace_ops_trampoline(ip);
 	if (!ops)
 		return NULL;
 
+	/* Set tramp_addr to the start of the code copied by the trampoline */
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
-		caller = (unsigned long)ftrace_regs_call;
+		tramp_addr = (unsigned long)ftrace_regs_caller;
 	else
-		caller = (unsigned long)ftrace_call;
+		tramp_addr = (unsigned long)ftrace_caller;
+
+	/* Now place tramp_addr to the location within the trampoline ip is at */
+	offset = ip - ops->trampoline;
+	tramp_addr += offset;
 
 	/* Prevent unlikely recursion */
-	if (ip == caller)
+	if (ip == tramp_addr)
 		return NULL;
 
-	return orc_find(caller);
+	return orc_find(tramp_addr);
 }
 #else
 static struct orc_entry *orc_ftrace_find(unsigned long ip)
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index e84ee5cdbd8c..57353519bc11 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -138,7 +138,7 @@ struct x86_platform_ops x86_platform __ro_after_init = {
 	.calibrate_cpu			= native_calibrate_cpu_early,
 	.calibrate_tsc			= native_calibrate_tsc,
 	.get_wallclock			= mach_get_cmos_time,
-	.set_wallclock			= mach_set_rtc_mmss,
+	.set_wallclock			= mach_set_cmos_time,
 	.iommu_shutdown			= iommu_shutdown_noop,
 	.is_untracked_pat_range		= is_ISA_range,
 	.nmi_init			= default_nmi_init,
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 75dcf7a72605..2796dde06302 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -315,7 +315,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	struct kvm_cpuid_entry2 *best;
-	u64 guest_supported_xcr0;
 
 	best = kvm_find_cpuid_entry(vcpu, 1);
 	if (best && apic) {
@@ -327,10 +326,16 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		kvm_apic_set_version(vcpu);
 	}
 
-	guest_supported_xcr0 =
+	vcpu->arch.guest_supported_xcr0 =
 		cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent);
 
-	vcpu->arch.guest_fpu.fpstate->user_xfeatures = guest_supported_xcr0;
+	/*
+	 * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if
+	 * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't
+	 * supported by the host.
+	 */
+	vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0 |
+						       XFEATURE_MASK_FPSSE;
 
 	kvm_update_pv_runtime(vcpu);
 
@@ -897,8 +902,6 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 			entry->edx = 0;
 		}
 		break;
-	case 9:
-		break;
 	case 0xa: { /* Architectural Performance Monitoring */
 		union cpuid10_eax eax;
 		union cpuid10_edx edx;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index b4eeb7c75dfa..aacb28c83e43 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -326,7 +326,8 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 	".align " __stringify(FASTOP_SIZE) " \n\t" \
 	".type " name ", @function \n\t" \
 	name ":\n\t" \
-	ASM_ENDBR
+	ASM_ENDBR \
+	IBT_NOSEAL(name)
 
 #define FOP_FUNC(name) \
 	__FOP_FUNC(#name)
@@ -446,27 +447,12 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 	FOP_END
 
 /* Special case for SETcc - 1 instruction per cc */
-
-/*
- * Depending on .config the SETcc functions look like:
- *
- * ENDBR			[4 bytes; CONFIG_X86_KERNEL_IBT]
- * SETcc %al			[3 bytes]
- * RET | JMP __x86_return_thunk	[1,5 bytes; CONFIG_RETHUNK]
- * INT3				[1 byte; CONFIG_SLS]
- */
-#define SETCC_ALIGN	16
-
 #define FOP_SETCC(op) \
-	".align " __stringify(SETCC_ALIGN) " \n\t" \
-	".type " #op ", @function \n\t" \
-	#op ": \n\t" \
-	ASM_ENDBR \
+	FOP_FUNC(op) \
 	#op " %al \n\t" \
-	__FOP_RET(#op) \
-	".skip " __stringify(SETCC_ALIGN) " - (.-" #op "), 0xcc \n\t"
+	FOP_RET(op)
 
-__FOP_START(setcc, SETCC_ALIGN)
+FOP_START(setcc)
 FOP_SETCC(seto)
 FOP_SETCC(setno)
 FOP_SETCC(setc)
@@ -493,7 +479,7 @@ FOP_END;
 
 /*
  * XXX: inoutclob user must know where the argument is being expanded.
- *      Relying on CONFIG_CC_HAS_ASM_GOTO would allow us to remove _fault.
+ *      Using asm goto would allow us to remove _fault.
  */
 #define asm_safe(insn, inoutclob...) \
 ({ \
@@ -1079,7 +1065,7 @@ static int em_bsr_c(struct x86_emulate_ctxt *ctxt)
 static __always_inline u8 test_cc(unsigned int condition, unsigned long flags)
 {
 	u8 rc;
-	void (*fop)(void) = (void *)em_setcc + SETCC_ALIGN * (condition & 0xf);
+	void (*fop)(void) = (void *)em_setcc + FASTOP_SIZE * (condition & 0xf);
 
 	flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF;
 	asm("push %[flags]; popf; " CALL_NOSPEC
@@ -4146,6 +4132,9 @@ static int em_xsetbv(struct x86_emulate_ctxt *ctxt)
 {
 	u32 eax, ecx, edx;
 
+	if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSXSAVE))
+		return emulate_ud(ctxt);
+
 	eax = reg_read(ctxt, VCPU_REGS_RAX);
 	edx = reg_read(ctxt, VCPU_REGS_RDX);
 	ecx = reg_read(ctxt, VCPU_REGS_RCX);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index eccddb136954..3552e6af3684 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1596,6 +1596,8 @@ static void __rmap_add(struct kvm *kvm,
 	rmap_head = gfn_to_rmap(gfn, sp->role.level, slot);
 	rmap_count = pte_list_add(cache, spte, rmap_head);
 
+	if (rmap_count > kvm->stat.max_mmu_rmap_size)
+		kvm->stat.max_mmu_rmap_size = rmap_count;
 	if (rmap_count > RMAP_RECYCLE_THRESHOLD) {
 		kvm_zap_all_rmap_sptes(kvm, rmap_head);
 		kvm_flush_remote_tlbs_with_address(
@@ -2914,7 +2916,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
 	 * If addresses are being invalidated, skip prefetching to avoid
 	 * accidentally prefetching those addresses.
 	 */
-	if (unlikely(vcpu->kvm->mmu_notifier_count))
+	if (unlikely(vcpu->kvm->mmu_invalidate_in_progress))
 		return;
 
 	__direct_pte_prefetch(vcpu, sp, sptep);
@@ -2928,7 +2930,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
  *
  * There are several ways to safely use this helper:
  *
- * - Check mmu_notifier_retry_hva() after grabbing the mapping level, before
+ * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before
  *   consuming it.  In this case, mmu_lock doesn't need to be held during the
  *   lookup, but it does need to be held while checking the MMU notifier.
  *
@@ -3056,7 +3058,7 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 		return;
 
 	/*
-	 * mmu_notifier_retry() was successful and mmu_lock is held, so
+	 * mmu_invalidate_retry() was successful and mmu_lock is held, so
 	 * the pmd can't be split from under us.
 	 */
 	fault->goal_level = fault->req_level;
@@ -4203,7 +4205,7 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
 		return true;
 
 	return fault->slot &&
-	       mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
+	       mmu_invalidate_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
 }
 
 static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
@@ -4227,7 +4229,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	if (r)
 		return r;
 
-	mmu_seq = vcpu->kvm->mmu_notifier_seq;
+	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	r = kvm_faultin_pfn(vcpu, fault);
@@ -5361,19 +5363,6 @@ void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu)
 	__kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu);
 }
 
-static bool need_remote_flush(u64 old, u64 new)
-{
-	if (!is_shadow_present_pte(old))
-		return false;
-	if (!is_shadow_present_pte(new))
-		return true;
-	if ((old ^ new) & SPTE_BASE_ADDR_MASK)
-		return true;
-	old ^= shadow_nx_mask;
-	new ^= shadow_nx_mask;
-	return (old & ~new & SPTE_PERM_MASK) != 0;
-}
-
 static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
 				    int *bytes)
 {
@@ -5519,7 +5508,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 			mmu_page_zap_pte(vcpu->kvm, sp, spte, NULL);
 			if (gentry && sp->role.level != PG_LEVEL_4K)
 				++vcpu->kvm->stat.mmu_pde_zapped;
-			if (need_remote_flush(entry, *spte))
+			if (is_shadow_present_pte(entry))
 				flush = true;
 			++spte;
 		}
@@ -6055,7 +6044,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 
 	write_lock(&kvm->mmu_lock);
 
-	kvm_inc_notifier_count(kvm, gfn_start, gfn_end);
+	kvm_mmu_invalidate_begin(kvm, gfn_start, gfn_end);
 
 	flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
 
@@ -6069,7 +6058,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 		kvm_flush_remote_tlbs_with_address(kvm, gfn_start,
 						   gfn_end - gfn_start);
 
-	kvm_dec_notifier_count(kvm, gfn_start, gfn_end);
+	kvm_mmu_invalidate_end(kvm, gfn_start, gfn_end);
 
 	write_unlock(&kvm->mmu_lock);
 }
@@ -6085,47 +6074,18 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
 				      const struct kvm_memory_slot *memslot,
 				      int start_level)
 {
-	bool flush = false;
-
 	if (kvm_memslots_have_rmaps(kvm)) {
 		write_lock(&kvm->mmu_lock);
-		flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect,
-					  start_level, KVM_MAX_HUGEPAGE_LEVEL,
-					  false);
+		slot_handle_level(kvm, memslot, slot_rmap_write_protect,
+				  start_level, KVM_MAX_HUGEPAGE_LEVEL, false);
 		write_unlock(&kvm->mmu_lock);
 	}
 
 	if (is_tdp_mmu_enabled(kvm)) {
 		read_lock(&kvm->mmu_lock);
-		flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, start_level);
+		kvm_tdp_mmu_wrprot_slot(kvm, memslot, start_level);
 		read_unlock(&kvm->mmu_lock);
 	}
-
-	/*
-	 * Flush TLBs if any SPTEs had to be write-protected to ensure that
-	 * guest writes are reflected in the dirty bitmap before the memslot
-	 * update completes, i.e. before enabling dirty logging is visible to
-	 * userspace.
-	 *
-	 * Perform the TLB flush outside the mmu_lock to reduce the amount of
-	 * time the lock is held. However, this does mean that another CPU can
-	 * now grab mmu_lock and encounter a write-protected SPTE while CPUs
-	 * still have a writable mapping for the associated GFN in their TLB.
-	 *
-	 * This is safe but requires KVM to be careful when making decisions
-	 * based on the write-protection status of an SPTE. Specifically, KVM
-	 * also write-protects SPTEs to monitor changes to guest page tables
-	 * during shadow paging, and must guarantee no CPUs can write to those
-	 * page before the lock is dropped. As mentioned in the previous
-	 * paragraph, a write-protected SPTE is no guarantee that CPU cannot
-	 * perform writes. So to determine if a TLB flush is truly required, KVM
-	 * will clear a separate software-only bit (MMU-writable) and skip the
-	 * flush if-and-only-if this bit was already clear.
-	 *
-	 * See is_writable_pte() for more details.
-	 */
-	if (flush)
-		kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
 }
 
 static inline bool need_topup(struct kvm_mmu_memory_cache *cache, int min)
@@ -6493,32 +6453,30 @@ void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
 void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 				   const struct kvm_memory_slot *memslot)
 {
-	bool flush = false;
-
 	if (kvm_memslots_have_rmaps(kvm)) {
 		write_lock(&kvm->mmu_lock);
 		/*
 		 * Clear dirty bits only on 4k SPTEs since the legacy MMU only
 		 * support dirty logging at a 4k granularity.
 		 */
-		flush = slot_handle_level_4k(kvm, memslot, __rmap_clear_dirty, false);
+		slot_handle_level_4k(kvm, memslot, __rmap_clear_dirty, false);
 		write_unlock(&kvm->mmu_lock);
 	}
 
 	if (is_tdp_mmu_enabled(kvm)) {
 		read_lock(&kvm->mmu_lock);
-		flush |= kvm_tdp_mmu_clear_dirty_slot(kvm, memslot);
+		kvm_tdp_mmu_clear_dirty_slot(kvm, memslot);
 		read_unlock(&kvm->mmu_lock);
 	}
 
 	/*
+	 * The caller will flush the TLBs after this function returns.
+	 *
 	 * It's also safe to flush TLBs out of mmu lock here as currently this
 	 * function is only used for dirty logging, in which case flushing TLB
 	 * out of mmu lock also guarantees no dirty pages will be lost in
 	 * dirty_bitmap.
 	 */
-	if (flush)
-		kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
 }
 
 void kvm_mmu_zap_all(struct kvm *kvm)
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index f5958071220c..39e0205e7300 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -589,7 +589,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 	 * If addresses are being invalidated, skip prefetching to avoid
 	 * accidentally prefetching those addresses.
 	 */
-	if (unlikely(vcpu->kvm->mmu_notifier_count))
+	if (unlikely(vcpu->kvm->mmu_invalidate_in_progress))
 		return;
 
 	if (sp->role.direct)
@@ -838,7 +838,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	else
 		fault->max_level = walker.level;
 
-	mmu_seq = vcpu->kvm->mmu_notifier_seq;
+	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	r = kvm_faultin_pfn(vcpu, fault);
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index f3744eea45f5..7670c13ce251 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -343,7 +343,7 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check,
 }
 
 /*
- * An shadow-present leaf SPTE may be non-writable for 3 possible reasons:
+ * A shadow-present leaf SPTE may be non-writable for 4 possible reasons:
  *
  *  1. To intercept writes for dirty logging. KVM write-protects huge pages
  *     so that they can be split be split down into the dirty logging
@@ -361,8 +361,13 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check,
  *     read-only memslot or guest memory backed by a read-only VMA. Writes to
  *     such pages are disallowed entirely.
  *
- * To keep track of why a given SPTE is write-protected, KVM uses 2
- * software-only bits in the SPTE:
+ *  4. To emulate the Accessed bit for SPTEs without A/D bits.  Note, in this
+ *     case, the SPTE is access-protected, not just write-protected!
+ *
+ * For cases #1 and #4, KVM can safely make such SPTEs writable without taking
+ * mmu_lock as capturing the Accessed/Dirty state doesn't require taking it.
+ * To differentiate #1 and #4 from #2 and #3, KVM uses two software-only bits
+ * in the SPTE:
  *
  *  shadow_mmu_writable_mask, aka MMU-writable -
  *    Cleared on SPTEs that KVM is currently write-protecting for shadow paging
@@ -391,7 +396,8 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check,
  * shadow page tables between vCPUs. Write-protecting an SPTE for dirty logging
  * (which does not clear the MMU-writable bit), does not flush TLBs before
  * dropping the lock, as it only needs to synchronize guest writes with the
- * dirty bitmap.
+ * dirty bitmap. Similarly, making the SPTE inaccessible (and non-writable) for
+ * access-tracking via the clear_young() MMU notifier also does not flush TLBs.
  *
  * So, there is the problem: clearing the MMU-writable bit can encounter a
  * write-protected SPTE while CPUs still have writable mappings for that SPTE
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index d7f8331d6f7e..c9b49a09e6b5 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -843,8 +843,7 @@ static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr)
 	if (!(exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS))
 		return true;
 
-	return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap,
-					 MSR_IA32_SPEC_CTRL);
+	return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap, msr);
 }
 
 unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 205ebdc2b11b..b0c47b41c264 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1011,15 +1011,10 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state);
 
-static inline u64 kvm_guest_supported_xcr0(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.guest_fpu.fpstate->user_xfeatures;
-}
-
 #ifdef CONFIG_X86_64
 static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu)
 {
-	return kvm_guest_supported_xcr0(vcpu) & XFEATURE_MASK_USER_DYNAMIC;
+	return vcpu->arch.guest_supported_xcr0 & XFEATURE_MASK_USER_DYNAMIC;
 }
 #endif
 
@@ -1042,7 +1037,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 	 * saving.  However, xcr0 bit 0 is always set, even if the
 	 * emulated CPU does not support XSAVE (see kvm_vcpu_reset()).
 	 */
-	valid_bits = kvm_guest_supported_xcr0(vcpu) | XFEATURE_MASK_FP;
+	valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP;
 	if (xcr0 & ~valid_bits)
 		return 1;
 
@@ -1070,6 +1065,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 
 int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu)
 {
+	/* Note, #UD due to CR4.OSXSAVE=0 has priority over the intercept. */
 	if (static_call(kvm_x86_get_cpl)(vcpu) != 0 ||
 	    __kvm_set_xcr(vcpu, kvm_rcx_read(vcpu), kvm_read_edx_eax(vcpu))) {
 		kvm_inject_gp(vcpu, 0);
@@ -1557,12 +1553,32 @@ static const u32 msr_based_features_all[] = {
 static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)];
 static unsigned int num_msr_based_features;
 
+/*
+ * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM
+ * does not yet virtualize. These include:
+ *   10 - MISC_PACKAGE_CTRLS
+ *   11 - ENERGY_FILTERING_CTL
+ *   12 - DOITM
+ *   18 - FB_CLEAR_CTRL
+ *   21 - XAPIC_DISABLE_STATUS
+ *   23 - OVERCLOCKING_STATUS
+ */
+
+#define KVM_SUPPORTED_ARCH_CAP \
+	(ARCH_CAP_RDCL_NO | ARCH_CAP_IBRS_ALL | ARCH_CAP_RSBA | \
+	 ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \
+	 ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
+	 ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
+	 ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO)
+
 static u64 kvm_get_arch_capabilities(void)
 {
 	u64 data = 0;
 
-	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
 		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data);
+		data &= KVM_SUPPORTED_ARCH_CAP;
+	}
 
 	/*
 	 * If nx_huge_pages is enabled, KVM's shadow paging will ensure that
@@ -1610,9 +1626,6 @@ static u64 kvm_get_arch_capabilities(void)
 		 */
 	}
 
-	/* Guests don't need to know "Fill buffer clear control" exists */
-	data &= ~ARCH_CAP_FB_CLEAR_CTRL;
-
 	return data;
 }
 
@@ -10652,7 +10665,8 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu)
 	case KVM_MP_STATE_INIT_RECEIVED:
 		break;
 	default:
-		return -EINTR;
+		WARN_ON_ONCE(1);
+		break;
 	}
 	return 1;
 }
@@ -11093,9 +11107,22 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 
 	vcpu_load(vcpu);
 
-	if (!lapic_in_kernel(vcpu) &&
-	    mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
+	switch (mp_state->mp_state) {
+	case KVM_MP_STATE_UNINITIALIZED:
+	case KVM_MP_STATE_HALTED:
+	case KVM_MP_STATE_AP_RESET_HOLD:
+	case KVM_MP_STATE_INIT_RECEIVED:
+	case KVM_MP_STATE_SIPI_RECEIVED:
+		if (!lapic_in_kernel(vcpu))
+			goto out;
+		break;
+
+	case KVM_MP_STATE_RUNNABLE:
+		break;
+
+	default:
 		goto out;
+	}
 
 	/*
 	 * KVM_MP_STATE_INIT_RECEIVED means the processor is in
@@ -11563,7 +11590,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	vcpu->arch.mci_ctl2_banks = kcalloc(KVM_MAX_MCE_BANKS, sizeof(u64),
 					    GFP_KERNEL_ACCOUNT);
 	if (!vcpu->arch.mce_banks || !vcpu->arch.mci_ctl2_banks)
-		goto fail_free_pio_data;
+		goto fail_free_mce_banks;
 	vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS;
 
 	if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask,
@@ -11617,7 +11644,6 @@ free_wbinvd_dirty_mask:
 fail_free_mce_banks:
 	kfree(vcpu->arch.mce_banks);
 	kfree(vcpu->arch.mci_ctl2_banks);
-fail_free_pio_data:
 	free_page((unsigned long)vcpu->arch.pio_data);
 fail_free_lapic:
 	kvm_free_lapic(vcpu);
@@ -12473,6 +12499,50 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
 		} else {
 			kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_4K);
 		}
+
+		/*
+		 * Unconditionally flush the TLBs after enabling dirty logging.
+		 * A flush is almost always going to be necessary (see below),
+		 * and unconditionally flushing allows the helpers to omit
+		 * the subtly complex checks when removing write access.
+		 *
+		 * Do the flush outside of mmu_lock to reduce the amount of
+		 * time mmu_lock is held.  Flushing after dropping mmu_lock is
+		 * safe as KVM only needs to guarantee the slot is fully
+		 * write-protected before returning to userspace, i.e. before
+		 * userspace can consume the dirty status.
+		 *
+		 * Flushing outside of mmu_lock requires KVM to be careful when
+		 * making decisions based on writable status of an SPTE, e.g. a
+		 * !writable SPTE doesn't guarantee a CPU can't perform writes.
+		 *
+		 * Specifically, KVM also write-protects guest page tables to
+		 * monitor changes when using shadow paging, and must guarantee
+		 * no CPUs can write to those page before mmu_lock is dropped.
+		 * Because CPUs may have stale TLB entries at this point, a
+		 * !writable SPTE doesn't guarantee CPUs can't perform writes.
+		 *
+		 * KVM also allows making SPTES writable outside of mmu_lock,
+		 * e.g. to allow dirty logging without taking mmu_lock.
+		 *
+		 * To handle these scenarios, KVM uses a separate software-only
+		 * bit (MMU-writable) to track if a SPTE is !writable due to
+		 * a guest page table being write-protected (KVM clears the
+		 * MMU-writable flag when write-protecting for shadow paging).
+		 *
+		 * The use of MMU-writable is also the primary motivation for
+		 * the unconditional flush.  Because KVM must guarantee that a
+		 * CPU doesn't contain stale, writable TLB entries for a
+		 * !MMU-writable SPTE, KVM must flush if it encounters any
+		 * MMU-writable SPTE regardless of whether the actual hardware
+		 * writable bit was set.  I.e. KVM is almost guaranteed to need
+		 * to flush, while unconditionally flushing allows the "remove
+		 * write access" helpers to ignore MMU-writable entirely.
+		 *
+		 * See is_writable_pte() for more details (the case involving
+		 * access-tracked SPTEs is particularly relevant).
+		 */
+		kvm_arch_flush_remote_tlbs_memslot(kvm, new);
 	}
 }
 
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index fe59b8ac4fcc..ecbfb4dd3b01 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,5 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 #include <linux/linkage.h>
+#include <asm/asm.h>
 #include <asm/export.h>
 
 /*
@@ -50,3 +51,140 @@ SYM_FUNC_START(clear_page_erms)
 	RET
 SYM_FUNC_END(clear_page_erms)
 EXPORT_SYMBOL_GPL(clear_page_erms)
+
+/*
+ * Default clear user-space.
+ * Input:
+ * rdi destination
+ * rcx count
+ *
+ * Output:
+ * rcx: uncleared bytes or 0 if successful.
+ */
+SYM_FUNC_START(clear_user_original)
+	/*
+	 * Copy only the lower 32 bits of size as that is enough to handle the rest bytes,
+	 * i.e., no need for a 'q' suffix and thus a REX prefix.
+	 */
+	mov %ecx,%eax
+	shr $3,%rcx
+	jz .Lrest_bytes
+
+	# do the qwords first
+	.p2align 4
+.Lqwords:
+	movq $0,(%rdi)
+	lea 8(%rdi),%rdi
+	dec %rcx
+	jnz .Lqwords
+
+.Lrest_bytes:
+	and $7,  %eax
+	jz .Lexit
+
+	# now do the rest bytes
+.Lbytes:
+	movb $0,(%rdi)
+	inc %rdi
+	dec %eax
+	jnz .Lbytes
+
+.Lexit:
+	/*
+	 * %rax still needs to be cleared in the exception case because this function is called
+	 * from inline asm and the compiler expects %rax to be zero when exiting the inline asm,
+	 * in case it might reuse it somewhere.
+	 */
+        xor %eax,%eax
+        RET
+
+.Lqwords_exception:
+        # convert remaining qwords back into bytes to return to caller
+        shl $3, %rcx
+        and $7, %eax
+        add %rax,%rcx
+        jmp .Lexit
+
+.Lbytes_exception:
+        mov %eax,%ecx
+        jmp .Lexit
+
+        _ASM_EXTABLE_UA(.Lqwords, .Lqwords_exception)
+        _ASM_EXTABLE_UA(.Lbytes, .Lbytes_exception)
+SYM_FUNC_END(clear_user_original)
+EXPORT_SYMBOL(clear_user_original)
+
+/*
+ * Alternative clear user-space when CPU feature X86_FEATURE_REP_GOOD is
+ * present.
+ * Input:
+ * rdi destination
+ * rcx count
+ *
+ * Output:
+ * rcx: uncleared bytes or 0 if successful.
+ */
+SYM_FUNC_START(clear_user_rep_good)
+	# call the original thing for less than a cacheline
+	cmp $64, %rcx
+	jb clear_user_original
+
+.Lprep:
+	# copy lower 32-bits for rest bytes
+	mov %ecx, %edx
+	shr $3, %rcx
+	jz .Lrep_good_rest_bytes
+
+.Lrep_good_qwords:
+	rep stosq
+
+.Lrep_good_rest_bytes:
+	and $7, %edx
+	jz .Lrep_good_exit
+
+.Lrep_good_bytes:
+	mov %edx, %ecx
+	rep stosb
+
+.Lrep_good_exit:
+	# see .Lexit comment above
+	xor %eax, %eax
+	RET
+
+.Lrep_good_qwords_exception:
+	# convert remaining qwords back into bytes to return to caller
+	shl $3, %rcx
+	and $7, %edx
+	add %rdx, %rcx
+	jmp .Lrep_good_exit
+
+	_ASM_EXTABLE_UA(.Lrep_good_qwords, .Lrep_good_qwords_exception)
+	_ASM_EXTABLE_UA(.Lrep_good_bytes, .Lrep_good_exit)
+SYM_FUNC_END(clear_user_rep_good)
+EXPORT_SYMBOL(clear_user_rep_good)
+
+/*
+ * Alternative clear user-space when CPU feature X86_FEATURE_ERMS is present.
+ * Input:
+ * rdi destination
+ * rcx count
+ *
+ * Output:
+ * rcx: uncleared bytes or 0 if successful.
+ *
+ */
+SYM_FUNC_START(clear_user_erms)
+	# call the original thing for less than a cacheline
+	cmp $64, %rcx
+	jb clear_user_original
+
+.Lerms_bytes:
+	rep stosb
+
+.Lerms_exit:
+	xorl %eax,%eax
+	RET
+
+	_ASM_EXTABLE_UA(.Lerms_bytes, .Lerms_exit)
+SYM_FUNC_END(clear_user_erms)
+EXPORT_SYMBOL(clear_user_erms)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index d0d7b9bc6cad..dd8cd8831251 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -2,6 +2,7 @@
 /* Copyright 2002 Andi Kleen */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
@@ -27,7 +28,7 @@
  * Output:
  * rax original destination
  */
-SYM_FUNC_START(__memcpy)
+SYM_TYPED_FUNC_START(__memcpy)
 	ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
 		      "jmp memcpy_erms", X86_FEATURE_ERMS
 
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index ad0139d25401..f1bb18617156 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -44,7 +44,7 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	 * called from other contexts.
 	 */
 	pagefault_disable();
-	ret = __copy_from_user_inatomic(to, from, n);
+	ret = raw_copy_from_user(to, from, n);
 	pagefault_enable();
 
 	return ret;
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 0ae6cf804197..6c1f8ac5e721 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -14,46 +14,6 @@
  * Zero Userspace
  */
 
-unsigned long __clear_user(void __user *addr, unsigned long size)
-{
-	long __d0;
-	might_fault();
-	/* no memory constraint because it doesn't change any memory gcc knows
-	   about */
-	stac();
-	asm volatile(
-		"	testq  %[size8],%[size8]\n"
-		"	jz     4f\n"
-		"	.align 16\n"
-		"0:	movq $0,(%[dst])\n"
-		"	addq   $8,%[dst]\n"
-		"	decl %%ecx ; jnz   0b\n"
-		"4:	movq  %[size1],%%rcx\n"
-		"	testl %%ecx,%%ecx\n"
-		"	jz     2f\n"
-		"1:	movb   $0,(%[dst])\n"
-		"	incq   %[dst]\n"
-		"	decl %%ecx ; jnz  1b\n"
-		"2:\n"
-
-		_ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN8, %[size1])
-		_ASM_EXTABLE_UA(1b, 2b)
-
-		: [size8] "=&c"(size), [dst] "=&D" (__d0)
-		: [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr));
-	clac();
-	return size;
-}
-EXPORT_SYMBOL(__clear_user);
-
-unsigned long clear_user(void __user *to, unsigned long n)
-{
-	if (access_ok(to, n))
-		return __clear_user(to, n);
-	return n;
-}
-EXPORT_SYMBOL(clear_user);
-
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
 /**
  * clean_cache_range - write back a cache range with CLWB
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index f8220fd2c169..829c1409ffbd 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -4,10 +4,12 @@ KCOV_INSTRUMENT_tlb.o			:= n
 KCOV_INSTRUMENT_mem_encrypt.o		:= n
 KCOV_INSTRUMENT_mem_encrypt_amd.o	:= n
 KCOV_INSTRUMENT_mem_encrypt_identity.o	:= n
+KCOV_INSTRUMENT_pgprot.o		:= n
 
 KASAN_SANITIZE_mem_encrypt.o		:= n
 KASAN_SANITIZE_mem_encrypt_amd.o	:= n
 KASAN_SANITIZE_mem_encrypt_identity.o	:= n
+KASAN_SANITIZE_pgprot.o		:= n
 
 # Disable KCSAN entirely, because otherwise we get warnings that some functions
 # reference __initdata sections.
@@ -17,6 +19,7 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_mem_encrypt.o		= -pg
 CFLAGS_REMOVE_mem_encrypt_amd.o		= -pg
 CFLAGS_REMOVE_mem_encrypt_identity.o	= -pg
+CFLAGS_REMOVE_pgprot.o			= -pg
 endif
 
 obj-y				:=  init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 331310c29349..60814e110a54 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -41,6 +41,59 @@ static bool ex_handler_default(const struct exception_table_entry *e,
 	return true;
 }
 
+/*
+ * This is the *very* rare case where we do a "load_unaligned_zeropad()"
+ * and it's a page crosser into a non-existent page.
+ *
+ * This happens when we optimistically load a pathname a word-at-a-time
+ * and the name is less than the full word and the  next page is not
+ * mapped. Typically that only happens for CONFIG_DEBUG_PAGEALLOC.
+ *
+ * NOTE! The faulting address is always a 'mov mem,reg' type instruction
+ * of size 'long', and the exception fixup must always point to right
+ * after the instruction.
+ */
+static bool ex_handler_zeropad(const struct exception_table_entry *e,
+			       struct pt_regs *regs,
+			       unsigned long fault_addr)
+{
+	struct insn insn;
+	const unsigned long mask = sizeof(long) - 1;
+	unsigned long offset, addr, next_ip, len;
+	unsigned long *reg;
+
+	next_ip = ex_fixup_addr(e);
+	len = next_ip - regs->ip;
+	if (len > MAX_INSN_SIZE)
+		return false;
+
+	if (insn_decode(&insn, (void *) regs->ip, len, INSN_MODE_KERN))
+		return false;
+	if (insn.length != len)
+		return false;
+
+	if (insn.opcode.bytes[0] != 0x8b)
+		return false;
+	if (insn.opnd_bytes != sizeof(long))
+		return false;
+
+	addr = (unsigned long) insn_get_addr_ref(&insn, regs);
+	if (addr == ~0ul)
+		return false;
+
+	offset = addr & mask;
+	addr = addr & ~mask;
+	if (fault_addr != addr + sizeof(long))
+		return false;
+
+	reg = insn_get_modrm_reg_ptr(&insn, regs);
+	if (!reg)
+		return false;
+
+	*reg = *(unsigned long *)addr >> (offset * 8);
+	return ex_handler_default(e, regs);
+}
+
 static bool ex_handler_fault(const struct exception_table_entry *fixup,
 			     struct pt_regs *regs, int trapnr)
 {
@@ -217,6 +270,8 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
 		return ex_handler_sgx(e, regs, trapnr);
 	case EX_TYPE_UCOPY_LEN:
 		return ex_handler_ucopy_len(e, regs, trapnr, reg, imm);
+	case EX_TYPE_ZEROPAD:
+		return ex_handler_zeropad(e, regs, fault_addr);
 	}
 	BUG();
 }
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index fa71a5d12e87..a498ae1fbe66 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -769,6 +769,8 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
 		unsigned long address, struct task_struct *tsk)
 {
 	const char *loglvl = task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG;
+	/* This is a racy snapshot, but it's better than nothing. */
+	int cpu = raw_smp_processor_id();
 
 	if (!unhandled_signal(tsk, SIGSEGV))
 		return;
@@ -782,6 +784,14 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
 
 	print_vma_addr(KERN_CONT " in ", regs->ip);
 
+	/*
+	 * Dump the likely CPU where the fatal segfault happened.
+	 * This can help identify faulty hardware.
+	 */
+	printk(KERN_CONT " likely on CPU %d (core %d, socket %d)", cpu,
+	       topology_core_id(cpu), topology_physical_package_id(cpu));
+
+
 	printk(KERN_CONT "\n");
 
 	show_opcodes(regs, loglvl);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 39c5246964a9..0fe690ebc269 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -645,7 +645,7 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
 			pages++;
 			spin_lock(&init_mm.page_table_lock);
 
-			prot = __pgprot(pgprot_val(prot) | __PAGE_KERNEL_LARGE);
+			prot = __pgprot(pgprot_val(prot) | _PAGE_PSE);
 
 			set_pte_init((pte_t *)pud,
 				     pfn_pte((paddr & PUD_MASK) >> PAGE_SHIFT,
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index d5ef64ddd35e..66a209f7eb86 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -62,6 +62,7 @@
 
 static bool __read_mostly pat_bp_initialized;
 static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT);
+static bool __initdata pat_force_disabled = !IS_ENABLED(CONFIG_X86_PAT);
 static bool __read_mostly pat_bp_enabled;
 static bool __read_mostly pat_cm_initialized;
 
@@ -86,6 +87,7 @@ void pat_disable(const char *msg_reason)
 static int __init nopat(char *str)
 {
 	pat_disable("PAT support disabled via boot option.");
+	pat_force_disabled = true;
 	return 0;
 }
 early_param("nopat", nopat);
@@ -272,7 +274,7 @@ static void pat_ap_init(u64 pat)
 	wrmsrl(MSR_IA32_CR_PAT, pat);
 }
 
-void init_cache_modes(void)
+void __init init_cache_modes(void)
 {
 	u64 pat = 0;
 
@@ -313,6 +315,12 @@ void init_cache_modes(void)
 		 */
 		pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) |
 		      PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC);
+	} else if (!pat_force_disabled && cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) {
+		/*
+		 * Clearly PAT is enabled underneath. Allow pat_enabled() to
+		 * reflect this.
+		 */
+		pat_bp_enabled = true;
 	}
 
 	__init_cache_modes(pat);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index c1f6c1c51d99..4922517ddb0d 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -419,7 +419,9 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
 		OPTIMIZER_HIDE_VAR(reg);
 		emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip);
 	} else {
-		EMIT2(0xFF, 0xE0 + reg);
+		EMIT2(0xFF, 0xE0 + reg);	/* jmp *%\reg */
+		if (IS_ENABLED(CONFIG_RETPOLINE) || IS_ENABLED(CONFIG_SLS))
+			EMIT1(0xCC);		/* int3 */
 	}
 
 	*pprog = prog;
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 31c634a22818..58a200dc762d 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -55,6 +55,10 @@ ifdef CONFIG_RETPOLINE
 PURGATORY_CFLAGS_REMOVE		+= $(RETPOLINE_CFLAGS)
 endif
 
+ifdef CONFIG_CFI_CLANG
+PURGATORY_CFLAGS_REMOVE		+= $(CC_FLAGS_CFI)
+endif
+
 CFLAGS_REMOVE_purgatory.o	+= $(PURGATORY_CFLAGS_REMOVE)
 CFLAGS_purgatory.o		+= $(PURGATORY_CFLAGS)
 
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index e2c5b296120d..2925074b9a58 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -56,6 +56,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
 	"^(xen_irq_disable_direct_reloc$|"
 	"xen_save_fl_direct_reloc$|"
 	"VDSO|"
+	"__kcfi_typeid_|"
 	"__crc_)",
 
 /*
diff --git a/arch/x86/um/shared/sysdep/syscalls_32.h b/arch/x86/um/shared/sysdep/syscalls_32.h
index 68fd2cf526fd..f6e9f84397e7 100644
--- a/arch/x86/um/shared/sysdep/syscalls_32.h
+++ b/arch/x86/um/shared/sysdep/syscalls_32.h
@@ -6,10 +6,9 @@
 #include <asm/unistd.h>
 #include <sysdep/ptrace.h>
 
-typedef long syscall_handler_t(struct pt_regs);
+typedef long syscall_handler_t(struct syscall_args);
 
 extern syscall_handler_t *sys_call_table[];
 
 #define EXECUTE_SYSCALL(syscall, regs) \
-	((long (*)(struct syscall_args)) \
-	 (*sys_call_table[syscall]))(SYSCALL_ARGS(&regs->regs))
+	((*sys_call_table[syscall]))(SYSCALL_ARGS(&regs->regs))
diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c
index ac8eee093f9c..66162eafd8e8 100644
--- a/arch/x86/um/tls_32.c
+++ b/arch/x86/um/tls_32.c
@@ -65,9 +65,6 @@ static int get_free_idx(struct task_struct* task)
 	struct thread_struct *t = &task->thread;
 	int idx;
 
-	if (!t->arch.tls_array)
-		return GDT_ENTRY_TLS_MIN;
-
 	for (idx = 0; idx < GDT_ENTRY_TLS_ENTRIES; idx++)
 		if (!t->arch.tls_array[idx].present)
 			return idx + GDT_ENTRY_TLS_MIN;
@@ -240,9 +237,6 @@ static int get_tls_entry(struct task_struct *task, struct user_desc *info,
 {
 	struct thread_struct *t = &task->thread;
 
-	if (!t->arch.tls_array)
-		goto clear;
-
 	if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
 		return -EINVAL;
 
diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
index 8c0396fd0e6f..6fbe97c52c99 100644
--- a/arch/x86/um/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
@@ -65,7 +65,7 @@ quiet_cmd_vdso = VDSO    $@
 		       -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
 		 sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
 
-VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv
+VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv -z noexecstack
 GCOV_PROFILE := n
 
 #
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 0ed2e487a693..9b1a58dda935 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -765,6 +765,7 @@ static void xen_load_idt(const struct desc_ptr *desc)
 {
 	static DEFINE_SPINLOCK(lock);
 	static struct trap_info traps[257];
+	static const struct trap_info zero = { };
 	unsigned out;
 
 	trace_xen_cpu_load_idt(desc);
@@ -774,7 +775,7 @@ static void xen_load_idt(const struct desc_ptr *desc)
 	memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc));
 
 	out = xen_convert_trap_info(desc, traps, false);
-	memset(&traps[out], 0, sizeof(traps[0]));
+	traps[out] = zero;
 
 	xen_mc_flush();
 	if (HYPERVISOR_set_trap_table(traps))
diff --git a/block/bdev.c b/block/bdev.c
index ce05175e71ce..d699ecdb3260 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -26,6 +26,7 @@
 #include <linux/namei.h>
 #include <linux/part_stat.h>
 #include <linux/uaccess.h>
+#include <linux/stat.h>
 #include "../fs/internal.h"
 #include "blk.h"
 
@@ -1069,3 +1070,25 @@ void sync_bdevs(bool wait)
 	spin_unlock(&blockdev_superblock->s_inode_list_lock);
 	iput(old_inode);
 }
+
+/*
+ * Handle STATX_DIOALIGN for block devices.
+ *
+ * Note that the inode passed to this is the inode of a block device node file,
+ * not the block device's internal inode.  Therefore it is *not* valid to use
+ * I_BDEV() here; the block device has to be looked up by i_rdev instead.
+ */
+void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
+{
+	struct block_device *bdev;
+
+	bdev = blkdev_get_no_open(inode->i_rdev);
+	if (!bdev)
+		return;
+
+	stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
+	stat->dio_offset_align = bdev_logical_block_size(bdev);
+	stat->result_mask |= STATX_DIOALIGN;
+
+	blkdev_put_no_open(bdev);
+}
diff --git a/block/blk-core.c b/block/blk-core.c
index a0d1104c5590..651057c4146b 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -295,7 +295,7 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 
 	while (!blk_try_enter_queue(q, pm)) {
 		if (flags & BLK_MQ_REQ_NOWAIT)
-			return -EBUSY;
+			return -EAGAIN;
 
 		/*
 		 * read pair of barrier in blk_freeze_queue_start(), we need to
@@ -325,7 +325,7 @@ int __bio_queue_enter(struct request_queue *q, struct bio *bio)
 			if (test_bit(GD_DEAD, &disk->state))
 				goto dead;
 			bio_wouldblock_error(bio);
-			return -EBUSY;
+			return -EAGAIN;
 		}
 
 		/*
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 67e6dbc1ae81..e59c3069e835 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -309,6 +309,11 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
 	struct blk_plug plug;
 	int ret = 0;
 
+	/* make sure that "len << SECTOR_SHIFT" doesn't overflow */
+	if (max_sectors > UINT_MAX >> SECTOR_SHIFT)
+		max_sectors = UINT_MAX >> SECTOR_SHIFT;
+	max_sectors &= ~bs_mask;
+
 	if (max_sectors == 0)
 		return -EOPNOTSUPP;
 	if ((sector | nr_sects) & bs_mask)
@@ -322,10 +327,10 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
 
 		bio = blk_next_bio(bio, bdev, 0, REQ_OP_SECURE_ERASE, gfp);
 		bio->bi_iter.bi_sector = sector;
-		bio->bi_iter.bi_size = len;
+		bio->bi_iter.bi_size = len << SECTOR_SHIFT;
 
-		sector += len << SECTOR_SHIFT;
-		nr_sects -= len << SECTOR_SHIFT;
+		sector += len;
+		nr_sects -= len;
 		if (!nr_sects) {
 			ret = submit_bio_wait(bio);
 			bio_put(bio);
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 8559cea7f300..dee789f2f98f 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -283,7 +283,9 @@ static const char *const rqf_name[] = {
 	RQF_NAME(SPECIAL_PAYLOAD),
 	RQF_NAME(ZONE_WRITE_LOCKED),
 	RQF_NAME(MQ_POLL_SLEPT),
+	RQF_NAME(TIMED_OUT),
 	RQF_NAME(ELV),
+	RQF_NAME(RESV),
 };
 #undef RQF_NAME
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 5ee62b95f3e5..c96c8c4f751b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1931,7 +1931,8 @@ out:
 	/* If we didn't flush the entire list, we could have told the driver
 	 * there was more coming, but that turned out to be a lie.
 	 */
-	if ((!list_empty(list) || errors) && q->mq_ops->commit_rqs && queued)
+	if ((!list_empty(list) || errors || needs_resource ||
+	     ret == BLK_STS_DEV_RESOURCE) && q->mq_ops->commit_rqs && queued)
 		q->mq_ops->commit_rqs(hctx);
 	/*
 	 * Any items that need requeuing? Stuff them into hctx->dispatch,
@@ -2229,26 +2230,6 @@ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
 }
 EXPORT_SYMBOL(blk_mq_delay_run_hw_queues);
 
-/**
- * blk_mq_queue_stopped() - check whether one or more hctxs have been stopped
- * @q: request queue.
- *
- * The caller is responsible for serializing this function against
- * blk_mq_{start,stop}_hw_queue().
- */
-bool blk_mq_queue_stopped(struct request_queue *q)
-{
-	struct blk_mq_hw_ctx *hctx;
-	unsigned long i;
-
-	queue_for_each_hw_ctx(q, hctx, i)
-		if (blk_mq_hctx_stopped(hctx))
-			return true;
-
-	return false;
-}
-EXPORT_SYMBOL(blk_mq_queue_stopped);
-
 /*
  * This function is often used for pausing .queue_rq() by driver when
  * there isn't enough resource or some conditions aren't satisfied, and
@@ -2570,7 +2551,7 @@ static void blk_mq_plug_issue_direct(struct blk_plug *plug, bool from_schedule)
 			break;
 		case BLK_STS_RESOURCE:
 		case BLK_STS_DEV_RESOURCE:
-			blk_mq_request_bypass_insert(rq, false, last);
+			blk_mq_request_bypass_insert(rq, false, true);
 			blk_mq_commit_rqs(hctx, &queued, from_schedule);
 			return;
 		default:
@@ -2680,6 +2661,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		list_del_init(&rq->queuelist);
 		ret = blk_mq_request_issue_directly(rq, list_empty(list));
 		if (ret != BLK_STS_OK) {
+			errors++;
 			if (ret == BLK_STS_RESOURCE ||
 					ret == BLK_STS_DEV_RESOURCE) {
 				blk_mq_request_bypass_insert(rq, false,
@@ -2687,7 +2669,6 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 				break;
 			}
 			blk_mq_end_request(rq, ret);
-			errors++;
 		} else
 			queued++;
 	}
diff --git a/block/genhd.c b/block/genhd.c
index d36fabf0abc1..988ba52fd331 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -602,7 +602,6 @@ void del_gendisk(struct gendisk *disk)
 	 * Prevent new I/O from crossing bio_queue_enter().
 	 */
 	blk_queue_start_drain(q);
-	blk_mq_freeze_queue_wait(q);
 
 	if (!(disk->flags & GENHD_FL_HIDDEN)) {
 		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
@@ -626,6 +625,8 @@ void del_gendisk(struct gendisk *disk)
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
 	device_del(disk_to_dev(disk));
 
+	blk_mq_freeze_queue_wait(q);
+
 	blk_throtl_cancel_bios(disk->queue);
 
 	blk_sync_queue(q);
diff --git a/block/partitions/core.c b/block/partitions/core.c
index fc1d70384825..b8112f52d388 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -596,6 +596,9 @@ static int blk_add_partitions(struct gendisk *disk)
 	if (disk->flags & GENHD_FL_NO_PART)
 		return 0;
 
+	if (test_bit(GD_SUPPRESS_PART_SCAN, &disk->state))
+		return 0;
+
 	state = check_partition(disk);
 	if (!state)
 		return 0;
diff --git a/certs/Kconfig b/certs/Kconfig
index bf9b511573d7..1f109b070877 100644
--- a/certs/Kconfig
+++ b/certs/Kconfig
@@ -43,7 +43,7 @@ config SYSTEM_TRUSTED_KEYRING
 	bool "Provide system-wide ring of trusted keys"
 	depends on KEYS
 	depends on ASYMMETRIC_KEY_TYPE
-	depends on X509_CERTIFICATE_PARSER
+	depends on X509_CERTIFICATE_PARSER = y
 	help
 	  Provide a system keyring to which trusted keys can be added.  Keys in
 	  the keyring are considered to be trusted.  Keys may be added at will
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 7802d8846a8d..bc9ddd2e3b05 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -27,9 +27,6 @@ menuconfig ACPI
 	  Management (APM) specification.  If both ACPI and APM support 
 	  are configured, ACPI is used.
 
-	  The project home page for the Linux ACPI subsystem is here:
-	  <https://01.org/linux-acpi>
-
 	  Linux support for ACPI is based on Intel Corporation's ACPI
 	  Component Architecture (ACPI CA).  For more information on the
 	  ACPI CA, see:
@@ -347,7 +344,6 @@ config ACPI_CUSTOM_DSDT_FILE
 	depends on !STANDALONE
 	help
 	  This option supports a custom DSDT by linking it into the kernel.
-	  See Documentation/admin-guide/acpi/dsdt-override.rst
 
 	  Enter the full path name to the file which includes the AmlCode
 	  or dsdt_aml_code declaration.
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index c29e41bfcf35..bb9fe7984b1a 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -36,11 +36,6 @@ static int acpi_ac_add(struct acpi_device *device);
 static int acpi_ac_remove(struct acpi_device *device);
 static void acpi_ac_notify(struct acpi_device *device, u32 event);
 
-struct acpi_ac_bl {
-	const char *hid;
-	int hrv;
-};
-
 static const struct acpi_device_id ac_device_ids[] = {
 	{"ACPI0003", 0},
 	{"", 0},
diff --git a/drivers/acpi/acpi_amba.c b/drivers/acpi/acpi_amba.c
index ab8a4e0191b1..f5b443ab01c2 100644
--- a/drivers/acpi/acpi_amba.c
+++ b/drivers/acpi/acpi_amba.c
@@ -21,6 +21,7 @@
 
 static const struct acpi_device_id amba_id_list[] = {
 	{"ARMH0061", 0}, /* PL061 GPIO Device */
+	{"ARMH0330", 0}, /* ARM DMA Controller DMA-330 */
 	{"ARMHC500", 0}, /* ARM CoreSight ETM4x */
 	{"ARMHC501", 0}, /* ARM CoreSight ETR */
 	{"ARMHC502", 0}, /* ARM CoreSight STM */
@@ -48,6 +49,7 @@ static void amba_register_dummy_clk(void)
 static int amba_handler_attach(struct acpi_device *adev,
 				const struct acpi_device_id *id)
 {
+	struct acpi_device *parent = acpi_dev_parent(adev);
 	struct amba_device *dev;
 	struct resource_entry *rentry;
 	struct list_head resource_list;
@@ -97,8 +99,8 @@ static int amba_handler_attach(struct acpi_device *adev,
 	 * attached to it, that physical device should be the parent of
 	 * the amba device we are about to create.
 	 */
-	if (adev->parent)
-		dev->dev.parent = acpi_get_first_physical_node(adev->parent);
+	if (parent)
+		dev->dev.parent = acpi_get_first_physical_node(parent);
 
 	ACPI_COMPANION_SET(&dev->dev, adev);
 
diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c
index ad245bbd965e..3bbe2276cac7 100644
--- a/drivers/acpi/acpi_apd.c
+++ b/drivers/acpi/acpi_apd.c
@@ -60,12 +60,6 @@ static int acpi_apd_setup(struct apd_private_data *pdata)
 }
 
 #ifdef CONFIG_X86_AMD_PLATFORM_DEVICE
-static int misc_check_res(struct acpi_resource *ares, void *data)
-{
-	struct resource res;
-
-	return !acpi_dev_resource_memory(ares, &res);
-}
 
 static int fch_misc_setup(struct apd_private_data *pdata)
 {
@@ -82,8 +76,7 @@ static int fch_misc_setup(struct apd_private_data *pdata)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&resource_list);
-	ret = acpi_dev_get_resources(adev, &resource_list, misc_check_res,
-				     NULL);
+	ret = acpi_dev_get_memory_resources(adev, &resource_list);
 	if (ret < 0)
 		return -ENOENT;
 
diff --git a/drivers/acpi/acpi_fpdt.c b/drivers/acpi/acpi_fpdt.c
index 6922a44b3ce7..a2056c4c8cb7 100644
--- a/drivers/acpi/acpi_fpdt.c
+++ b/drivers/acpi/acpi_fpdt.c
@@ -143,6 +143,23 @@ static const struct attribute_group boot_attr_group = {
 
 static struct kobject *fpdt_kobj;
 
+#if defined CONFIG_X86 && defined CONFIG_PHYS_ADDR_T_64BIT
+#include <linux/processor.h>
+static bool fpdt_address_valid(u64 address)
+{
+	/*
+	 * On some systems the table contains invalid addresses
+	 * with unsuppored high address bits set, check for this.
+	 */
+	return !(address >> boot_cpu_data.x86_phys_bits);
+}
+#else
+static bool fpdt_address_valid(u64 address)
+{
+	return true;
+}
+#endif
+
 static int fpdt_process_subtable(u64 address, u32 subtable_type)
 {
 	struct fpdt_subtable_header *subtable_header;
@@ -151,6 +168,11 @@ static int fpdt_process_subtable(u64 address, u32 subtable_type)
 	u32 length, offset;
 	int result;
 
+	if (!fpdt_address_valid(address)) {
+		pr_info(FW_BUG "invalid physical address: 0x%llx!\n", address);
+		return -EINVAL;
+	}
+
 	subtable_header = acpi_os_map_memory(address, sizeof(*subtable_header));
 	if (!subtable_header)
 		return -ENOMEM;
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index c4d4d21391d7..f08ffa75f4a7 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -167,10 +167,10 @@ static struct pwm_lookup byt_pwm_lookup[] = {
 
 static void byt_pwm_setup(struct lpss_private_data *pdata)
 {
-	struct acpi_device *adev = pdata->adev;
+	u64 uid;
 
 	/* Only call pwm_add_table for the first PWM controller */
-	if (!adev->pnp.unique_id || strcmp(adev->pnp.unique_id, "1"))
+	if (acpi_dev_uid_to_integer(pdata->adev, &uid) || uid != 1)
 		return;
 
 	pwm_add_table(byt_pwm_lookup, ARRAY_SIZE(byt_pwm_lookup));
@@ -180,14 +180,13 @@ static void byt_pwm_setup(struct lpss_private_data *pdata)
 
 static void byt_i2c_setup(struct lpss_private_data *pdata)
 {
-	const char *uid_str = acpi_device_uid(pdata->adev);
 	acpi_handle handle = pdata->adev->handle;
 	unsigned long long shared_host = 0;
 	acpi_status status;
-	long uid = 0;
+	u64 uid;
 
-	/* Expected to always be true, but better safe then sorry */
-	if (uid_str && !kstrtol(uid_str, 10, &uid) && uid) {
+	/* Expected to always be successfull, but better safe then sorry */
+	if (!acpi_dev_uid_to_integer(pdata->adev, &uid) && uid) {
 		/* Detect I2C bus shared with PUNIT and ignore its d3 status */
 		status = acpi_evaluate_integer(handle, "_SEM", NULL, &shared_host);
 		if (ACPI_SUCCESS(status) && shared_host)
@@ -211,10 +210,10 @@ static struct pwm_lookup bsw_pwm_lookup[] = {
 
 static void bsw_pwm_setup(struct lpss_private_data *pdata)
 {
-	struct acpi_device *adev = pdata->adev;
+	u64 uid;
 
 	/* Only call pwm_add_table for the first PWM controller */
-	if (!adev->pnp.unique_id || strcmp(adev->pnp.unique_id, "1"))
+	if (acpi_dev_uid_to_integer(pdata->adev, &uid) || uid != 1)
 		return;
 
 	pwm_add_table(bsw_pwm_lookup, ARRAY_SIZE(bsw_pwm_lookup));
@@ -392,13 +391,6 @@ static const struct acpi_device_id acpi_lpss_device_ids[] = {
 
 #ifdef CONFIG_X86_INTEL_LPSS
 
-static int is_memory(struct acpi_resource *res, void *not_used)
-{
-	struct resource r;
-
-	return !acpi_dev_resource_memory(res, &r);
-}
-
 /* LPSS main clock device. */
 static struct platform_device *lpss_clk_dev;
 
@@ -659,29 +651,25 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&resource_list);
-	ret = acpi_dev_get_resources(adev, &resource_list, is_memory, NULL);
+	ret = acpi_dev_get_memory_resources(adev, &resource_list);
 	if (ret < 0)
 		goto err_out;
 
-	list_for_each_entry(rentry, &resource_list, node)
-		if (resource_type(rentry->res) == IORESOURCE_MEM) {
-			if (dev_desc->prv_size_override)
-				pdata->mmio_size = dev_desc->prv_size_override;
-			else
-				pdata->mmio_size = resource_size(rentry->res);
-			pdata->mmio_base = ioremap(rentry->res->start,
-						   pdata->mmio_size);
-			break;
-		}
+	rentry = list_first_entry_or_null(&resource_list, struct resource_entry, node);
+	if (rentry) {
+		if (dev_desc->prv_size_override)
+			pdata->mmio_size = dev_desc->prv_size_override;
+		else
+			pdata->mmio_size = resource_size(rentry->res);
+		pdata->mmio_base = ioremap(rentry->res->start, pdata->mmio_size);
+	}
 
 	acpi_dev_free_resource_list(&resource_list);
 
 	if (!pdata->mmio_base) {
 		/* Avoid acpi_bus_attach() instantiating a pdev for this dev. */
 		adev->pnp.type.platform_id = 0;
-		/* Skip the device, but continue the namespace scan. */
-		ret = 0;
-		goto err_out;
+		goto out_free;
 	}
 
 	pdata->adev = adev;
@@ -692,11 +680,8 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
 
 	if (dev_desc->flags & LPSS_CLK) {
 		ret = register_device_clock(adev, pdata);
-		if (ret) {
-			/* Skip the device, but continue the namespace scan. */
-			ret = 0;
-			goto err_out;
-		}
+		if (ret)
+			goto out_free;
 	}
 
 	/*
@@ -708,15 +693,19 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
 
 	adev->driver_data = pdata;
 	pdev = acpi_create_platform_device(adev, dev_desc->properties);
-	if (!IS_ERR_OR_NULL(pdev)) {
-		acpi_lpss_create_device_links(adev, pdev);
-		return 1;
+	if (IS_ERR_OR_NULL(pdev)) {
+		adev->driver_data = NULL;
+		ret = PTR_ERR(pdev);
+		goto err_out;
 	}
 
-	ret = PTR_ERR(pdev);
-	adev->driver_data = NULL;
+	acpi_lpss_create_device_links(adev, pdev);
+	return 1;
 
- err_out:
+out_free:
+	/* Skip the device, but continue the namespace scan */
+	ret = 0;
+err_out:
 	kfree(pdata);
 	return ret;
 }
diff --git a/drivers/acpi/acpi_pcc.c b/drivers/acpi/acpi_pcc.c
index a12b55d81209..ee4ce5ba1fb2 100644
--- a/drivers/acpi/acpi_pcc.c
+++ b/drivers/acpi/acpi_pcc.c
@@ -23,6 +23,12 @@
 
 #include <acpi/pcc.h>
 
+/*
+ * Arbitrary retries in case the remote processor is slow to respond
+ * to PCC commands
+ */
+#define PCC_CMD_WAIT_RETRIES_NUM	500
+
 struct pcc_data {
 	struct pcc_mbox_chan *pcc_chan;
 	void __iomem *pcc_comm_addr;
@@ -63,6 +69,7 @@ acpi_pcc_address_space_setup(acpi_handle region_handle, u32 function,
 	if (IS_ERR(data->pcc_chan)) {
 		pr_err("Failed to find PCC channel for subspace %d\n",
 		       ctx->subspace_id);
+		kfree(data);
 		return AE_NOT_FOUND;
 	}
 
@@ -72,6 +79,8 @@ acpi_pcc_address_space_setup(acpi_handle region_handle, u32 function,
 	if (!data->pcc_comm_addr) {
 		pr_err("Failed to ioremap PCC comm region mem for %d\n",
 		       ctx->subspace_id);
+		pcc_mbox_free_channel(data->pcc_chan);
+		kfree(data);
 		return AE_NO_MEMORY;
 	}
 
@@ -86,6 +95,7 @@ acpi_pcc_address_space_handler(u32 function, acpi_physical_address addr,
 {
 	int ret;
 	struct pcc_data *data = region_context;
+	u64 usecs_lat;
 
 	reinit_completion(&data->done);
 
@@ -96,10 +106,22 @@ acpi_pcc_address_space_handler(u32 function, acpi_physical_address addr,
 	if (ret < 0)
 		return AE_ERROR;
 
-	if (data->pcc_chan->mchan->mbox->txdone_irq)
-		wait_for_completion(&data->done);
+	if (data->pcc_chan->mchan->mbox->txdone_irq) {
+		/*
+		 * pcc_chan->latency is just a Nominal value. In reality the remote
+		 * processor could be much slower to reply. So add an arbitrary
+		 * amount of wait on top of Nominal.
+		 */
+		usecs_lat = PCC_CMD_WAIT_RETRIES_NUM * data->pcc_chan->latency;
+		ret = wait_for_completion_timeout(&data->done,
+						  usecs_to_jiffies(usecs_lat));
+		if (ret == 0) {
+			pr_err("PCC command executed timeout!\n");
+			return AE_TIME;
+		}
+	}
 
-	mbox_client_txdone(data->pcc_chan->mchan, ret);
+	mbox_chan_txdone(data->pcc_chan->mchan, ret);
 
 	memcpy_fromio(value, data->pcc_comm_addr, data->ctx.length);
 
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index de3cbf152dee..fe00a5783f53 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -20,13 +20,13 @@
 #include "internal.h"
 
 static const struct acpi_device_id forbidden_id_list[] = {
+	{"ACPI0009", 0},	/* IOxAPIC */
+	{"ACPI000A", 0},	/* IOAPIC */
 	{"PNP0000",  0},	/* PIC */
 	{"PNP0100",  0},	/* Timer */
 	{"PNP0200",  0},	/* AT DMA Controller */
-	{"ACPI0009", 0},	/* IOxAPIC */
-	{"ACPI000A", 0},	/* IOAPIC */
 	{"SMB0001",  0},	/* ACPI SMBUS virtual device */
-	{"", 0},
+	{ }
 };
 
 static struct platform_device *acpi_platform_device_find_by_companion(struct acpi_device *adev)
@@ -78,7 +78,7 @@ static void acpi_platform_fill_resource(struct acpi_device *adev,
 	 * If the device has parent we need to take its resources into
 	 * account as well because this device might consume part of those.
 	 */
-	parent = acpi_get_first_physical_node(adev->parent);
+	parent = acpi_get_first_physical_node(acpi_dev_parent(adev));
 	if (parent && dev_is_pci(parent))
 		dest->parent = pci_find_resource(to_pci_dev(parent), dest);
 }
@@ -97,6 +97,7 @@ static void acpi_platform_fill_resource(struct acpi_device *adev,
 struct platform_device *acpi_create_platform_device(struct acpi_device *adev,
 						    const struct property_entry *properties)
 {
+	struct acpi_device *parent = acpi_dev_parent(adev);
 	struct platform_device *pdev = NULL;
 	struct platform_device_info pdevinfo;
 	struct resource_entry *rentry;
@@ -113,13 +114,11 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev,
 
 	INIT_LIST_HEAD(&resource_list);
 	count = acpi_dev_get_resources(adev, &resource_list, NULL, NULL);
-	if (count < 0) {
+	if (count < 0)
 		return NULL;
-	} else if (count > 0) {
-		resources = kcalloc(count, sizeof(struct resource),
-				    GFP_KERNEL);
+	if (count > 0) {
+		resources = kcalloc(count, sizeof(*resources), GFP_KERNEL);
 		if (!resources) {
-			dev_err(&adev->dev, "No memory for resources\n");
 			acpi_dev_free_resource_list(&resource_list);
 			return ERR_PTR(-ENOMEM);
 		}
@@ -137,10 +136,9 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev,
 	 * attached to it, that physical device should be the parent of the
 	 * platform device we are about to create.
 	 */
-	pdevinfo.parent = adev->parent ?
-		acpi_get_first_physical_node(adev->parent) : NULL;
+	pdevinfo.parent = parent ? acpi_get_first_physical_node(parent) : NULL;
 	pdevinfo.name = dev_name(&adev->dev);
-	pdevinfo.id = -1;
+	pdevinfo.id = PLATFORM_DEVID_NONE;
 	pdevinfo.res = resources;
 	pdevinfo.num_res = count;
 	pdevinfo.fwnode = acpi_fwnode_handle(adev);
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 5cbe2196176d..6d209ea68bd8 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -496,6 +496,22 @@ static const struct dmi_system_id video_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "SATELLITE R830"),
 		},
 	},
+	{
+	 .callback = video_disable_backlight_sysfs_if,
+	 .ident = "Toshiba Satellite Z830",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "SATELLITE Z830"),
+		},
+	},
+	{
+	 .callback = video_disable_backlight_sysfs_if,
+	 .ident = "Toshiba Portege Z830",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "PORTEGE Z830"),
+		},
+	},
 	/*
 	 * Some machine's _DOD IDs don't have bit 31(Device ID Scheme) set
 	 * but the IDs actually follow the Device ID Scheme.
@@ -2030,7 +2046,7 @@ static int acpi_video_bus_add(struct acpi_device *device)
 	acpi_status status;
 
 	status = acpi_walk_namespace(ACPI_TYPE_DEVICE,
-				device->parent->handle, 1,
+				acpi_dev_parent(device)->handle, 1,
 				acpi_video_bus_match, NULL,
 				device, NULL);
 	if (status == AE_ALREADY_EXISTS) {
diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index 9f49272cad39..9b52482b4ed5 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -125,12 +125,9 @@ EXPORT_SYMBOL_GPL(apei_exec_write_register);
 int apei_exec_write_register_value(struct apei_exec_context *ctx,
 				   struct acpi_whea_header *entry)
 {
-	int rc;
-
 	ctx->value = entry->value;
-	rc = apei_exec_write_register(ctx, entry);
 
-	return rc;
+	return apei_exec_write_register(ctx, entry);
 }
 EXPORT_SYMBOL_GPL(apei_exec_write_register_value);
 
diff --git a/drivers/acpi/apei/bert.c b/drivers/acpi/apei/bert.c
index 45973aa6e06d..c23eb75866d0 100644
--- a/drivers/acpi/apei/bert.c
+++ b/drivers/acpi/apei/bert.c
@@ -90,6 +90,9 @@ static void __init bert_print_all(struct acpi_bert_region *region,
 
 	if (skipped)
 		pr_info(HW_ERR "Skipped %d error records\n", skipped);
+
+	if (printed + skipped)
+		pr_info("Total records found: %d\n", printed + skipped);
 }
 
 static int __init setup_bert_disable(char *str)
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index 31b077eedb58..247989060e29 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -1020,14 +1020,10 @@ static int reader_pos;
 
 static int erst_open_pstore(struct pstore_info *psi)
 {
-	int rc;
-
 	if (erst_disable)
 		return -ENODEV;
 
-	rc = erst_get_record_id_begin(&reader_pos);
-
-	return rc;
+	return erst_get_record_id_begin(&reader_pos);
 }
 
 static int erst_close_pstore(struct pstore_info *psi)
diff --git a/drivers/acpi/arm64/dma.c b/drivers/acpi/arm64/dma.c
index f16739ad3cc0..93d796531af3 100644
--- a/drivers/acpi/arm64/dma.c
+++ b/drivers/acpi/arm64/dma.c
@@ -4,11 +4,12 @@
 #include <linux/device.h>
 #include <linux/dma-direct.h>
 
-void acpi_arch_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
+void acpi_arch_dma_setup(struct device *dev)
 {
 	int ret;
 	u64 end, mask;
-	u64 dmaaddr = 0, size = 0, offset = 0;
+	u64 size = 0;
+	const struct bus_dma_region *map = NULL;
 
 	/*
 	 * If @dev is expected to be DMA-capable then the bus code that created
@@ -26,7 +27,19 @@ void acpi_arch_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 	else
 		size = 1ULL << 32;
 
-	ret = acpi_dma_get_range(dev, &dmaaddr, &offset, &size);
+	ret = acpi_dma_get_range(dev, &map);
+	if (!ret && map) {
+		const struct bus_dma_region *r = map;
+
+		for (end = 0; r->size; r++) {
+			if (r->dma_start + r->size - 1 > end)
+				end = r->dma_start + r->size - 1;
+		}
+
+		size = end + 1;
+		dev->dma_range_map = map;
+	}
+
 	if (ret == -ENODEV)
 		ret = iort_dma_get_ranges(dev, &size);
 	if (!ret) {
@@ -34,17 +47,10 @@ void acpi_arch_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 		 * Limit coherent and dma mask based on size retrieved from
 		 * firmware.
 		 */
-		end = dmaaddr + size - 1;
+		end = size - 1;
 		mask = DMA_BIT_MASK(ilog2(end) + 1);
 		dev->bus_dma_limit = end;
 		dev->coherent_dma_mask = min(dev->coherent_dma_mask, mask);
 		*dev->dma_mask = min(*dev->dma_mask, mask);
 	}
-
-	*dma_addr = dmaaddr;
-	*dma_size = size;
-
-	ret = dma_direct_set_offset(dev, dmaaddr + offset, dmaaddr, size);
-
-	dev_dbg(dev, "dma_offset(%#08llx)%s\n", offset, ret ? " failed!" : "");
 }
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index c0d20d997891..d466c8195314 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -456,7 +456,7 @@ out_free:
                              Notification Handling
    -------------------------------------------------------------------------- */
 
-/**
+/*
  * acpi_bus_notify
  * ---------------
  * Callback for all 'system-level' device notifications (values 0x00-0x7F).
@@ -511,7 +511,7 @@ static void acpi_bus_notify(acpi_handle handle, u32 type, void *data)
 		break;
 	}
 
-	adev = acpi_bus_get_acpi_device(handle);
+	adev = acpi_get_acpi_dev(handle);
 	if (!adev)
 		goto err;
 
@@ -524,14 +524,14 @@ static void acpi_bus_notify(acpi_handle handle, u32 type, void *data)
 	}
 
 	if (!hotplug_event) {
-		acpi_bus_put_acpi_device(adev);
+		acpi_put_acpi_dev(adev);
 		return;
 	}
 
 	if (ACPI_SUCCESS(acpi_hotplug_schedule(adev, type)))
 		return;
 
-	acpi_bus_put_acpi_device(adev);
+	acpi_put_acpi_dev(adev);
 
  err:
 	acpi_evaluate_ost(handle, type, ost_code, NULL);
@@ -802,7 +802,7 @@ static bool acpi_of_modalias(struct acpi_device *adev,
 
 	str = obj->string.pointer;
 	chr = strchr(str, ',');
-	strlcpy(modalias, chr ? chr + 1 : str, len);
+	strscpy(modalias, chr ? chr + 1 : str, len);
 
 	return true;
 }
@@ -822,7 +822,7 @@ void acpi_set_modalias(struct acpi_device *adev, const char *default_id,
 		       char *modalias, size_t len)
 {
 	if (!acpi_of_modalias(adev, modalias, len))
-		strlcpy(modalias, default_id, len);
+		strscpy(modalias, default_id, len);
 }
 EXPORT_SYMBOL_GPL(acpi_set_modalias);
 
@@ -925,12 +925,13 @@ static const void *acpi_of_device_get_match_data(const struct device *dev)
 
 const void *acpi_device_get_match_data(const struct device *dev)
 {
+	const struct acpi_device_id *acpi_ids = dev->driver->acpi_match_table;
 	const struct acpi_device_id *match;
 
-	if (!dev->driver->acpi_match_table)
+	if (!acpi_ids)
 		return acpi_of_device_get_match_data(dev);
 
-	match = acpi_match_device(dev->driver->acpi_match_table, dev);
+	match = acpi_match_device(acpi_ids, dev);
 	if (!match)
 		return NULL;
 
@@ -948,14 +949,13 @@ EXPORT_SYMBOL(acpi_match_device_ids);
 bool acpi_driver_match_device(struct device *dev,
 			      const struct device_driver *drv)
 {
-	if (!drv->acpi_match_table)
-		return acpi_of_match_device(ACPI_COMPANION(dev),
-					    drv->of_match_table,
-					    NULL);
-
-	return __acpi_match_device(acpi_companion_match(dev),
-				   drv->acpi_match_table, drv->of_match_table,
-				   NULL, NULL);
+	const struct acpi_device_id *acpi_ids = drv->acpi_match_table;
+	const struct of_device_id *of_ids = drv->of_match_table;
+
+	if (!acpi_ids)
+		return acpi_of_match_device(ACPI_COMPANION(dev), of_ids, NULL);
+
+	return __acpi_match_device(acpi_companion_match(dev), acpi_ids, of_ids, NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(acpi_driver_match_device);
 
@@ -973,16 +973,13 @@ EXPORT_SYMBOL_GPL(acpi_driver_match_device);
  */
 int acpi_bus_register_driver(struct acpi_driver *driver)
 {
-	int ret;
-
 	if (acpi_disabled)
 		return -ENODEV;
 	driver->drv.name = driver->name;
 	driver->drv.bus = &acpi_bus_type;
 	driver->drv.owner = driver->owner;
 
-	ret = driver_register(&driver->drv);
-	return ret;
+	return driver_register(&driver->drv);
 }
 
 EXPORT_SYMBOL(acpi_bus_register_driver);
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 1e15a9f25ae9..093675b1a1ff 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -424,6 +424,9 @@ bool acpi_cpc_valid(void)
 	struct cpc_desc *cpc_ptr;
 	int cpu;
 
+	if (acpi_disabled)
+		return false;
+
 	for_each_present_cpu(cpu) {
 		cpc_ptr = per_cpu(cpc_desc_ptr, cpu);
 		if (!cpc_ptr)
@@ -1241,6 +1244,48 @@ out_err:
 EXPORT_SYMBOL_GPL(cppc_get_perf_caps);
 
 /**
+ * cppc_perf_ctrs_in_pcc - Check if any perf counters are in a PCC region.
+ *
+ * CPPC has flexibility about how CPU performance counters are accessed.
+ * One of the choices is PCC regions, which can have a high access latency. This
+ * routine allows callers of cppc_get_perf_ctrs() to know this ahead of time.
+ *
+ * Return: true if any of the counters are in PCC regions, false otherwise
+ */
+bool cppc_perf_ctrs_in_pcc(void)
+{
+	int cpu;
+
+	for_each_present_cpu(cpu) {
+		struct cpc_register_resource *ref_perf_reg;
+		struct cpc_desc *cpc_desc;
+
+		cpc_desc = per_cpu(cpc_desc_ptr, cpu);
+
+		if (CPC_IN_PCC(&cpc_desc->cpc_regs[DELIVERED_CTR]) ||
+		    CPC_IN_PCC(&cpc_desc->cpc_regs[REFERENCE_CTR]) ||
+		    CPC_IN_PCC(&cpc_desc->cpc_regs[CTR_WRAP_TIME]))
+			return true;
+
+
+		ref_perf_reg = &cpc_desc->cpc_regs[REFERENCE_PERF];
+
+		/*
+		 * If reference perf register is not supported then we should
+		 * use the nominal perf value
+		 */
+		if (!CPC_SUPPORTED(ref_perf_reg))
+			ref_perf_reg = &cpc_desc->cpc_regs[NOMINAL_PERF];
+
+		if (CPC_IN_PCC(ref_perf_reg))
+			return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(cppc_perf_ctrs_in_pcc);
+
+/**
  * cppc_get_perf_ctrs - Read a CPU's performance feedback counters.
  * @cpunum: CPU from which to read counters.
  * @perf_fb_ctrs: ptr to cppc_perf_fb_ctrs. See cppc_acpi.h
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 9dce1245689c..d594effe905f 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -75,15 +75,17 @@ static int acpi_dev_pm_explicit_get(struct acpi_device *device, int *state)
 int acpi_device_get_power(struct acpi_device *device, int *state)
 {
 	int result = ACPI_STATE_UNKNOWN;
+	struct acpi_device *parent;
 	int error;
 
 	if (!device || !state)
 		return -EINVAL;
 
+	parent = acpi_dev_parent(device);
+
 	if (!device->flags.power_manageable) {
 		/* TBD: Non-recursive algorithm for walking up hierarchy. */
-		*state = device->parent ?
-			device->parent->power.state : ACPI_STATE_D0;
+		*state = parent ? parent->power.state : ACPI_STATE_D0;
 		goto out;
 	}
 
@@ -122,10 +124,10 @@ int acpi_device_get_power(struct acpi_device *device, int *state)
 	 * point, the fact that the device is in D0 implies that the parent has
 	 * to be in D0 too, except if ignore_parent is set.
 	 */
-	if (!device->power.flags.ignore_parent && device->parent
-	    && device->parent->power.state == ACPI_STATE_UNKNOWN
-	    && result == ACPI_STATE_D0)
-		device->parent->power.state = ACPI_STATE_D0;
+	if (!device->power.flags.ignore_parent && parent &&
+	    parent->power.state == ACPI_STATE_UNKNOWN &&
+	    result == ACPI_STATE_D0)
+		parent->power.state = ACPI_STATE_D0;
 
 	*state = result;
 
@@ -191,13 +193,17 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 		return -ENODEV;
 	}
 
-	if (!device->power.flags.ignore_parent && device->parent &&
-	    state < device->parent->power.state) {
-		acpi_handle_debug(device->handle,
-				  "Cannot transition to %s for parent in %s\n",
-				  acpi_power_state_string(state),
-				  acpi_power_state_string(device->parent->power.state));
-		return -ENODEV;
+	if (!device->power.flags.ignore_parent) {
+		struct acpi_device *parent;
+
+		parent = acpi_dev_parent(device);
+		if (parent && state < parent->power.state) {
+			acpi_handle_debug(device->handle,
+					  "Cannot transition to %s for parent in %s\n",
+					  acpi_power_state_string(state),
+					  acpi_power_state_string(parent->power.state));
+			return -ENODEV;
+		}
 	}
 
 	/*
@@ -497,7 +503,7 @@ static void acpi_pm_notify_handler(acpi_handle handle, u32 val, void *not_used)
 
 	acpi_handle_debug(handle, "Wake notify\n");
 
-	adev = acpi_bus_get_acpi_device(handle);
+	adev = acpi_get_acpi_dev(handle);
 	if (!adev)
 		return;
 
@@ -515,7 +521,7 @@ static void acpi_pm_notify_handler(acpi_handle handle, u32 val, void *not_used)
 
 	mutex_unlock(&acpi_pm_notifier_lock);
 
-	acpi_bus_put_acpi_device(adev);
+	acpi_put_acpi_dev(adev);
 }
 
 /**
@@ -1460,7 +1466,7 @@ EXPORT_SYMBOL_GPL(acpi_storage_d3);
  * not valid to ask for the ACPI power state of the device in that time frame.
  *
  * This function is intended to be used in a driver's probe or remove
- * function. See Documentation/firmware-guide/acpi/low-power-probe.rst for
+ * function. See Documentation/firmware-guide/acpi/non-d0-probe.rst for
  * more information.
  */
 bool acpi_dev_state_d0(struct device *dev)
diff --git a/drivers/acpi/dptf/Kconfig b/drivers/acpi/dptf/Kconfig
index 1e8c7ce89bf1..4b3fdc03e4ed 100644
--- a/drivers/acpi/dptf/Kconfig
+++ b/drivers/acpi/dptf/Kconfig
@@ -11,9 +11,6 @@ menuconfig ACPI_DPTF
 	  a coordinated approach for different policies to effect the hardware
 	  state of a system.
 
-	  For more information see:
-	  <https://01.org/intel%C2%AE-dynamic-platform-and-thermal-framework-dptf-chromium-os/overview>
-
 if ACPI_DPTF
 
 config DPTF_POWER
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index c95e535035a0..9b42628cf21b 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -917,14 +917,10 @@ EXPORT_SYMBOL(ec_read);
 
 int ec_write(u8 addr, u8 val)
 {
-	int err;
-
 	if (!first_ec)
 		return -ENODEV;
 
-	err = acpi_ec_write(first_ec, addr, val);
-
-	return err;
+	return acpi_ec_write(first_ec, addr, val);
 }
 EXPORT_SYMBOL(ec_write);
 
diff --git a/drivers/acpi/fan_core.c b/drivers/acpi/fan_core.c
index b9a9a59ddcc1..52a0b303b70a 100644
--- a/drivers/acpi/fan_core.c
+++ b/drivers/acpi/fan_core.c
@@ -19,43 +19,12 @@
 
 #include "fan.h"
 
-MODULE_AUTHOR("Paul Diefenbaugh");
-MODULE_DESCRIPTION("ACPI Fan Driver");
-MODULE_LICENSE("GPL");
-
-static int acpi_fan_probe(struct platform_device *pdev);
-static int acpi_fan_remove(struct platform_device *pdev);
-
 static const struct acpi_device_id fan_device_ids[] = {
 	ACPI_FAN_DEVICE_IDS,
 	{"", 0},
 };
 MODULE_DEVICE_TABLE(acpi, fan_device_ids);
 
-#ifdef CONFIG_PM_SLEEP
-static int acpi_fan_suspend(struct device *dev);
-static int acpi_fan_resume(struct device *dev);
-static const struct dev_pm_ops acpi_fan_pm = {
-	.resume = acpi_fan_resume,
-	.freeze = acpi_fan_suspend,
-	.thaw = acpi_fan_resume,
-	.restore = acpi_fan_resume,
-};
-#define FAN_PM_OPS_PTR (&acpi_fan_pm)
-#else
-#define FAN_PM_OPS_PTR NULL
-#endif
-
-static struct platform_driver acpi_fan_driver = {
-	.probe = acpi_fan_probe,
-	.remove = acpi_fan_remove,
-	.driver = {
-		.name = "acpi-fan",
-		.acpi_match_table = fan_device_ids,
-		.pm = FAN_PM_OPS_PTR,
-	},
-};
-
 /* thermal cooling device callbacks */
 static int fan_get_max_state(struct thermal_cooling_device *cdev, unsigned long
 			     *state)
@@ -459,6 +428,33 @@ static int acpi_fan_resume(struct device *dev)
 
 	return result;
 }
+
+static const struct dev_pm_ops acpi_fan_pm = {
+	.resume = acpi_fan_resume,
+	.freeze = acpi_fan_suspend,
+	.thaw = acpi_fan_resume,
+	.restore = acpi_fan_resume,
+};
+#define FAN_PM_OPS_PTR (&acpi_fan_pm)
+
+#else
+
+#define FAN_PM_OPS_PTR NULL
+
 #endif
 
+static struct platform_driver acpi_fan_driver = {
+	.probe = acpi_fan_probe,
+	.remove = acpi_fan_remove,
+	.driver = {
+		.name = "acpi-fan",
+		.acpi_match_table = fan_device_ids,
+		.pm = FAN_PM_OPS_PTR,
+	},
+};
+
 module_platform_driver(acpi_fan_driver);
+
+MODULE_AUTHOR("Paul Diefenbaugh");
+MODULE_DESCRIPTION("ACPI Fan Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 628bf8f18130..219c02df9a08 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -102,10 +102,10 @@ struct acpi_device_bus_id {
 	struct list_head node;
 };
 
-int acpi_device_add(struct acpi_device *device,
-		    void (*release)(struct device *));
 void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
-			     int type);
+			     int type, void (*release)(struct device *));
+int acpi_tie_acpi_dev(struct acpi_device *adev);
+int acpi_device_add(struct acpi_device *device);
 int acpi_device_setup_files(struct acpi_device *dev);
 void acpi_device_remove_files(struct acpi_device *dev);
 void acpi_device_add_finalize(struct acpi_device *device);
diff --git a/drivers/acpi/irq.c b/drivers/acpi/irq.c
index dabe45eba055..4db5bb587599 100644
--- a/drivers/acpi/irq.c
+++ b/drivers/acpi/irq.c
@@ -118,12 +118,12 @@ acpi_get_irq_source_fwhandle(const struct acpi_resource_source *source,
 	if (WARN_ON(ACPI_FAILURE(status)))
 		return NULL;
 
-	device = acpi_bus_get_acpi_device(handle);
+	device = acpi_get_acpi_dev(handle);
 	if (WARN_ON(!device))
 		return NULL;
 
 	result = &device->fwnode;
-	acpi_bus_put_acpi_device(device);
+	acpi_put_acpi_dev(device);
 	return result;
 }
 
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index c3d783aca196..23f49a2f4d14 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -9,7 +9,6 @@
  */
 
 #define pr_fmt(fmt) "acpi/hmat: " fmt
-#define dev_fmt(fmt) "acpi/hmat: " fmt
 
 #include <linux/acpi.h>
 #include <linux/bitops.h>
@@ -302,7 +301,7 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 	u8 type, mem_hier;
 
 	if (hmat_loc->header.length < sizeof(*hmat_loc)) {
-		pr_notice("HMAT: Unexpected locality header length: %u\n",
+		pr_notice("Unexpected locality header length: %u\n",
 			 hmat_loc->header.length);
 		return -EINVAL;
 	}
@@ -314,12 +313,12 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 	total_size = sizeof(*hmat_loc) + sizeof(*entries) * ipds * tpds +
 		     sizeof(*inits) * ipds + sizeof(*targs) * tpds;
 	if (hmat_loc->header.length < total_size) {
-		pr_notice("HMAT: Unexpected locality header length:%u, minimum required:%u\n",
+		pr_notice("Unexpected locality header length:%u, minimum required:%u\n",
 			 hmat_loc->header.length, total_size);
 		return -EINVAL;
 	}
 
-	pr_info("HMAT: Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n",
+	pr_info("Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n",
 		hmat_loc->flags, hmat_data_type(type), ipds, tpds,
 		hmat_loc->entry_base_unit);
 
@@ -363,13 +362,13 @@ static __init int hmat_parse_cache(union acpi_subtable_headers *header,
 	u32 attrs;
 
 	if (cache->header.length < sizeof(*cache)) {
-		pr_notice("HMAT: Unexpected cache header length: %u\n",
+		pr_notice("Unexpected cache header length: %u\n",
 			 cache->header.length);
 		return -EINVAL;
 	}
 
 	attrs = cache->cache_attributes;
-	pr_info("HMAT: Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n",
+	pr_info("Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n",
 		cache->memory_PD, cache->cache_size, attrs,
 		cache->number_of_SMBIOShandles);
 
@@ -424,24 +423,24 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade
 	struct memory_target *target = NULL;
 
 	if (p->header.length != sizeof(*p)) {
-		pr_notice("HMAT: Unexpected address range header length: %u\n",
+		pr_notice("Unexpected address range header length: %u\n",
 			 p->header.length);
 		return -EINVAL;
 	}
 
 	if (hmat_revision == 1)
-		pr_info("HMAT: Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n",
+		pr_info("Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n",
 			p->reserved3, p->reserved4, p->flags, p->processor_PD,
 			p->memory_PD);
 	else
-		pr_info("HMAT: Memory Flags:%04x Processor Domain:%u Memory Domain:%u\n",
+		pr_info("Memory Flags:%04x Processor Domain:%u Memory Domain:%u\n",
 			p->flags, p->processor_PD, p->memory_PD);
 
 	if ((hmat_revision == 1 && p->flags & ACPI_HMAT_MEMORY_PD_VALID) ||
 	    hmat_revision > 1) {
 		target = find_mem_target(p->memory_PD);
 		if (!target) {
-			pr_debug("HMAT: Memory Domain missing from SRAT\n");
+			pr_debug("Memory Domain missing from SRAT\n");
 			return -EINVAL;
 		}
 	}
@@ -449,7 +448,7 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade
 		int p_node = pxm_to_node(p->processor_PD);
 
 		if (p_node == NUMA_NO_NODE) {
-			pr_debug("HMAT: Invalid Processor Domain\n");
+			pr_debug("Invalid Processor Domain\n");
 			return -EINVAL;
 		}
 		target->processor_pxm = p->processor_PD;
@@ -840,7 +839,7 @@ static __init int hmat_init(void)
 	case 2:
 		break;
 	default:
-		pr_notice("Ignoring HMAT: Unknown revision:%d\n", hmat_revision);
+		pr_notice("Ignoring: Unknown revision:%d\n", hmat_revision);
 		goto out_put;
 	}
 
@@ -848,7 +847,7 @@ static __init int hmat_init(void)
 		if (acpi_table_parse_entries(ACPI_SIG_HMAT,
 					     sizeof(struct acpi_table_hmat), i,
 					     hmat_parse_subtable, 0) < 0) {
-			pr_notice("Ignoring HMAT: Invalid table");
+			pr_notice("Ignoring: Invalid table");
 			goto out_put;
 		}
 	}
diff --git a/drivers/acpi/osi.c b/drivers/acpi/osi.c
index 9f6853809138..d4405e1ca9b9 100644
--- a/drivers/acpi/osi.c
+++ b/drivers/acpi/osi.c
@@ -44,30 +44,6 @@ osi_setup_entries[OSI_STRING_ENTRIES_MAX] __initdata = {
 	{"Processor Device", true},
 	{"3.0 _SCP Extensions", true},
 	{"Processor Aggregator Device", true},
-	/*
-	 * Linux-Dell-Video is used by BIOS to disable RTD3 for NVidia graphics
-	 * cards as RTD3 is not supported by drivers now.  Systems with NVidia
-	 * cards will hang without RTD3 disabled.
-	 *
-	 * Once NVidia drivers officially support RTD3, this _OSI strings can
-	 * be removed if both new and old graphics cards are supported.
-	 */
-	{"Linux-Dell-Video", true},
-	/*
-	 * Linux-Lenovo-NV-HDMI-Audio is used by BIOS to power on NVidia's HDMI
-	 * audio device which is turned off for power-saving in Windows OS.
-	 * This power management feature observed on some Lenovo Thinkpad
-	 * systems which will not be able to output audio via HDMI without
-	 * a BIOS workaround.
-	 */
-	{"Linux-Lenovo-NV-HDMI-Audio", true},
-	/*
-	 * Linux-HPI-Hybrid-Graphics is used by BIOS to enable dGPU to
-	 * output video directly to external monitors on HP Inc. mobile
-	 * workstations as Nvidia and AMD VGA drivers provide limited
-	 * hybrid graphics supports.
-	 */
-	{"Linux-HPI-Hybrid-Graphics", true},
 };
 
 static u32 acpi_osi_handler(acpi_string interface, u32 supported)
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index d57cf8454b93..c8385ef54c37 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -312,76 +312,25 @@ struct acpi_handle_node {
  */
 struct pci_dev *acpi_get_pci_dev(acpi_handle handle)
 {
-	int dev, fn;
-	unsigned long long adr;
-	acpi_status status;
-	acpi_handle phandle;
-	struct pci_bus *pbus;
-	struct pci_dev *pdev = NULL;
-	struct acpi_handle_node *node, *tmp;
-	struct acpi_pci_root *root;
-	LIST_HEAD(device_list);
-
-	/*
-	 * Walk up the ACPI CA namespace until we reach a PCI root bridge.
-	 */
-	phandle = handle;
-	while (!acpi_is_root_bridge(phandle)) {
-		node = kzalloc(sizeof(struct acpi_handle_node), GFP_KERNEL);
-		if (!node)
-			goto out;
-
-		INIT_LIST_HEAD(&node->node);
-		node->handle = phandle;
-		list_add(&node->node, &device_list);
-
-		status = acpi_get_parent(phandle, &phandle);
-		if (ACPI_FAILURE(status))
-			goto out;
-	}
-
-	root = acpi_pci_find_root(phandle);
-	if (!root)
-		goto out;
+	struct acpi_device *adev = acpi_fetch_acpi_dev(handle);
+	struct acpi_device_physical_node *pn;
+	struct pci_dev *pci_dev = NULL;
 
-	pbus = root->bus;
-
-	/*
-	 * Now, walk back down the PCI device tree until we return to our
-	 * original handle. Assumes that everything between the PCI root
-	 * bridge and the device we're looking for must be a P2P bridge.
-	 */
-	list_for_each_entry(node, &device_list, node) {
-		acpi_handle hnd = node->handle;
-		status = acpi_evaluate_integer(hnd, "_ADR", NULL, &adr);
-		if (ACPI_FAILURE(status))
-			goto out;
-		dev = (adr >> 16) & 0xffff;
-		fn  = adr & 0xffff;
-
-		pdev = pci_get_slot(pbus, PCI_DEVFN(dev, fn));
-		if (!pdev || hnd == handle)
-			break;
+	if (!adev)
+		return NULL;
 
-		pbus = pdev->subordinate;
-		pci_dev_put(pdev);
+	mutex_lock(&adev->physical_node_lock);
 
-		/*
-		 * This function may be called for a non-PCI device that has a
-		 * PCI parent (eg. a disk under a PCI SATA controller).  In that
-		 * case pdev->subordinate will be NULL for the parent.
-		 */
-		if (!pbus) {
-			dev_dbg(&pdev->dev, "Not a PCI-to-PCI bridge\n");
-			pdev = NULL;
+	list_for_each_entry(pn, &adev->physical_node_list, node) {
+		if (dev_is_pci(pn->dev)) {
+			pci_dev = to_pci_dev(pn->dev);
 			break;
 		}
 	}
-out:
-	list_for_each_entry_safe(node, tmp, &device_list, node)
-		kfree(node);
 
-	return pdev;
+	mutex_unlock(&adev->physical_node_lock);
+
+	return pci_dev;
 }
 EXPORT_SYMBOL_GPL(acpi_get_pci_dev);
 
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index 8c4a73a1351e..f2588aba8421 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -944,13 +944,15 @@ struct acpi_device *acpi_add_power_resource(acpi_handle handle)
 		return NULL;
 
 	device = &resource->device;
-	acpi_init_device_object(device, handle, ACPI_BUS_TYPE_POWER);
+	acpi_init_device_object(device, handle, ACPI_BUS_TYPE_POWER,
+				acpi_release_power_resource);
 	mutex_init(&resource->resource_lock);
 	INIT_LIST_HEAD(&resource->list_node);
 	INIT_LIST_HEAD(&resource->dependents);
 	strcpy(acpi_device_name(device), ACPI_POWER_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_POWER_CLASS);
 	device->power.state = ACPI_STATE_UNKNOWN;
+	device->flags.match_driver = true;
 
 	/* Evaluate the object to get the system level and resource order. */
 	status = acpi_evaluate_object(handle, NULL, NULL, &buffer);
@@ -967,8 +969,11 @@ struct acpi_device *acpi_add_power_resource(acpi_handle handle)
 
 	pr_info("%s [%s]\n", acpi_device_name(device), acpi_device_bid(device));
 
-	device->flags.match_driver = true;
-	result = acpi_device_add(device, acpi_release_power_resource);
+	result = acpi_tie_acpi_dev(device);
+	if (result)
+		goto err;
+
+	result = acpi_device_add(device);
 	if (result)
 		goto err;
 
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 16a1663d02d4..acfabfe07c4f 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -531,10 +531,27 @@ static void wait_for_freeze(void)
 	/* No delay is needed if we are in guest */
 	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		return;
+	/*
+	 * Modern (>=Nehalem) Intel systems use ACPI via intel_idle,
+	 * not this code.  Assume that any Intel systems using this
+	 * are ancient and may need the dummy wait.  This also assumes
+	 * that the motivating chipset issue was Intel-only.
+	 */
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return;
 #endif
-	/* Dummy wait op - must do something useless after P_LVL2 read
-	   because chipsets cannot guarantee that STPCLK# signal
-	   gets asserted in time to freeze execution properly. */
+	/*
+	 * Dummy wait op - must do something useless after P_LVL2 read
+	 * because chipsets cannot guarantee that STPCLK# signal gets
+	 * asserted in time to freeze execution properly
+	 *
+	 * This workaround has been in place since the original ACPI
+	 * implementation was merged, circa 2002.
+	 *
+	 * If a profile is pointing to this instruction, please first
+	 * consider moving your system to a more modern idle
+	 * mechanism.
+	 */
 	inl(acpi_gbl_FADT.xpm_timer_block.address);
 }
 
@@ -787,7 +804,7 @@ static int acpi_processor_setup_cstates(struct acpi_processor *pr)
 
 		state = &drv->states[count];
 		snprintf(state->name, CPUIDLE_NAME_LEN, "C%d", i);
-		strlcpy(state->desc, cx->desc, CPUIDLE_DESC_LEN);
+		strscpy(state->desc, cx->desc, CPUIDLE_DESC_LEN);
 		state->exit_latency = cx->latency;
 		state->target_residency = cx->latency * latency_factor;
 		state->enter = acpi_idle_enter;
@@ -956,7 +973,7 @@ static int acpi_processor_evaluate_lpi(acpi_handle handle,
 
 		obj = pkg_elem + 9;
 		if (obj->type == ACPI_TYPE_STRING)
-			strlcpy(lpi_state->desc, obj->string.pointer,
+			strscpy(lpi_state->desc, obj->string.pointer,
 				ACPI_CX_DESC_LEN);
 
 		lpi_state->index = state_idx;
@@ -1022,7 +1039,7 @@ static bool combine_lpi_states(struct acpi_lpi_state *local,
 	result->arch_flags = parent->arch_flags;
 	result->index = parent->index;
 
-	strlcpy(result->desc, local->desc, ACPI_CX_DESC_LEN);
+	strscpy(result->desc, local->desc, ACPI_CX_DESC_LEN);
 	strlcat(result->desc, "+", ACPI_CX_DESC_LEN);
 	strlcat(result->desc, parent->desc, ACPI_CX_DESC_LEN);
 	return true;
@@ -1196,7 +1213,7 @@ static int acpi_processor_setup_lpi_states(struct acpi_processor *pr)
 
 		state = &drv->states[i];
 		snprintf(state->name, CPUIDLE_NAME_LEN, "LPI-%d", i);
-		strlcpy(state->desc, lpi->desc, CPUIDLE_DESC_LEN);
+		strscpy(state->desc, lpi->desc, CPUIDLE_DESC_LEN);
 		state->exit_latency = lpi->wake_latency;
 		state->target_residency = lpi->min_residency;
 		if (lpi->arch_flags)
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index db6ac540e924..e534fd49a67e 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -151,7 +151,7 @@ void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy)
 	unsigned int cpu;
 
 	for_each_cpu(cpu, policy->related_cpus) {
-		struct acpi_processor *pr = per_cpu(processors, policy->cpu);
+		struct acpi_processor *pr = per_cpu(processors, cpu);
 
 		if (pr)
 			freq_qos_remove_request(&pr->thermal_req);
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 7b3ad8ed2f4e..b8d9eb9a433e 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -304,8 +304,10 @@ static void acpi_init_of_compatible(struct acpi_device *adev)
 		ret = acpi_dev_get_property(adev, "compatible",
 					    ACPI_TYPE_STRING, &of_compatible);
 		if (ret) {
-			if (adev->parent
-			    && adev->parent->flags.of_compatible_ok)
+			struct acpi_device *parent;
+
+			parent = acpi_dev_parent(adev);
+			if (parent && parent->flags.of_compatible_ok)
 				goto out;
 
 			return;
@@ -370,7 +372,7 @@ static bool acpi_tie_nondev_subnodes(struct acpi_device_data *data)
 		bool ret;
 
 		status = acpi_attach_data(dn->handle, acpi_nondev_subnode_tag, dn);
-		if (ACPI_FAILURE(status)) {
+		if (ACPI_FAILURE(status) && status != AE_ALREADY_EXISTS) {
 			acpi_handle_err(dn->handle, "Can't tag data node\n");
 			return false;
 		}
@@ -1043,11 +1045,10 @@ static int acpi_data_prop_read_single(const struct acpi_device_data *data,
 				break;					\
 			}						\
 			if (__items[i].integer.value > _Generic(__val,	\
-								u8: U8_MAX, \
-								u16: U16_MAX, \
-								u32: U32_MAX, \
-								u64: U64_MAX, \
-								default: 0U)) { \
+								u8 *: U8_MAX, \
+								u16 *: U16_MAX, \
+								u32 *: U32_MAX, \
+								u64 *: U64_MAX)) { \
 				ret = -EOVERFLOW;			\
 				break;					\
 			}						\
@@ -1268,10 +1269,11 @@ acpi_node_get_parent(const struct fwnode_handle *fwnode)
 		return to_acpi_data_node(fwnode)->parent;
 	}
 	if (is_acpi_device_node(fwnode)) {
-		struct device *dev = to_acpi_device_node(fwnode)->dev.parent;
+		struct acpi_device *parent;
 
-		if (dev)
-			return acpi_fwnode_handle(to_acpi_device(dev));
+		parent = acpi_dev_parent(to_acpi_device_node(fwnode));
+		if (parent)
+			return acpi_fwnode_handle(parent);
 	}
 
 	return NULL;
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 510cdec375c4..514d89656dde 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -399,6 +399,31 @@ static const struct dmi_system_id medion_laptop[] = {
 	{ }
 };
 
+static const struct dmi_system_id asus_laptop[] = {
+	{
+		.ident = "Asus Vivobook K3402ZA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "K3402ZA"),
+		},
+	},
+	{
+		.ident = "Asus Vivobook K3502ZA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "K3502ZA"),
+		},
+	},
+	{
+		.ident = "Asus Vivobook S5402ZA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "S5402ZA"),
+		},
+	},
+	{ }
+};
+
 struct irq_override_cmp {
 	const struct dmi_system_id *system;
 	unsigned char irq;
@@ -409,6 +434,7 @@ struct irq_override_cmp {
 
 static const struct irq_override_cmp skip_override_table[] = {
 	{ medion_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0 },
+	{ asus_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0 },
 };
 
 static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity,
@@ -690,6 +716,9 @@ static int is_memory(struct acpi_resource *ares, void *not_used)
 
 	memset(&win, 0, sizeof(win));
 
+	if (acpi_dev_filter_resource_type(ares, IORESOURCE_MEM))
+		return 1;
+
 	return !(acpi_dev_resource_memory(ares, res)
 	       || acpi_dev_resource_address_space(ares, &win)
 	       || acpi_dev_resource_ext_address_space(ares, &win));
@@ -719,6 +748,23 @@ int acpi_dev_get_dma_resources(struct acpi_device *adev, struct list_head *list)
 EXPORT_SYMBOL_GPL(acpi_dev_get_dma_resources);
 
 /**
+ * acpi_dev_get_memory_resources - Get current memory resources of a device.
+ * @adev: ACPI device node to get the resources for.
+ * @list: Head of the resultant list of resources (must be empty).
+ *
+ * This is a helper function that locates all memory type resources of @adev
+ * with acpi_dev_get_resources().
+ *
+ * The number of resources in the output list is returned on success, an error
+ * code reflecting the error condition is returned otherwise.
+ */
+int acpi_dev_get_memory_resources(struct acpi_device *adev, struct list_head *list)
+{
+	return acpi_dev_get_resources(adev, list, is_memory, NULL);
+}
+EXPORT_SYMBOL_GPL(acpi_dev_get_memory_resources);
+
+/**
  * acpi_dev_filter_resource_type - Filter ACPI resource according to resource
  *				   types
  * @ares: Input ACPI resource object.
diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
index 4938010fcac7..e6a01a8df1b8 100644
--- a/drivers/acpi/sbs.c
+++ b/drivers/acpi/sbs.c
@@ -632,7 +632,7 @@ static int acpi_sbs_add(struct acpi_device *device)
 
 	mutex_init(&sbs->lock);
 
-	sbs->hc = acpi_driver_data(device->parent);
+	sbs->hc = acpi_driver_data(acpi_dev_parent(device));
 	sbs->device = device;
 	strcpy(acpi_device_name(device), ACPI_SBS_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_SBS_CLASS);
diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c
index 7c62e149a7a1..340e0b61587e 100644
--- a/drivers/acpi/sbshc.c
+++ b/drivers/acpi/sbshc.c
@@ -266,7 +266,7 @@ static int acpi_smbus_hc_add(struct acpi_device *device)
 	mutex_init(&hc->lock);
 	init_waitqueue_head(&hc->wait);
 
-	hc->ec = acpi_driver_data(device->parent);
+	hc->ec = acpi_driver_data(acpi_dev_parent(device));
 	hc->offset = (val >> 8) & 0xff;
 	hc->query_bit = val & 0xff;
 	device->driver_data = hc;
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 42cec8120f18..558664d169fc 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -20,6 +20,7 @@
 #include <linux/platform_data/x86/apple.h>
 #include <linux/pgtable.h>
 #include <linux/crc32.h>
+#include <linux/dma-direct.h>
 
 #include "internal.h"
 
@@ -29,8 +30,6 @@ extern struct acpi_device *acpi_root;
 #define ACPI_BUS_HID			"LNXSYBUS"
 #define ACPI_BUS_DEVICE_NAME		"System Bus"
 
-#define ACPI_IS_ROOT_DEVICE(device)    (!(device)->parent)
-
 #define INVALID_ACPI_HANDLE	((acpi_handle)empty_zero_page)
 
 static const char *dummy_hid = "device";
@@ -429,7 +428,7 @@ void acpi_device_hotplug(struct acpi_device *adev, u32 src)
 	acpi_evaluate_ost(adev->handle, src, ost_code, NULL);
 
  out:
-	acpi_bus_put_acpi_device(adev);
+	acpi_put_acpi_dev(adev);
 	mutex_unlock(&acpi_scan_lock);
 	unlock_device_hotplug();
 }
@@ -599,11 +598,22 @@ static void get_acpi_device(void *dev)
 	acpi_dev_get(dev);
 }
 
-struct acpi_device *acpi_bus_get_acpi_device(acpi_handle handle)
+/**
+ * acpi_get_acpi_dev - Retrieve ACPI device object and reference count it.
+ * @handle: ACPI handle associated with the requested ACPI device object.
+ *
+ * Return a pointer to the ACPI device object associated with @handle and bump
+ * up that object's reference counter (under the ACPI Namespace lock), if
+ * present, or return NULL otherwise.
+ *
+ * The ACPI device object reference acquired by this function needs to be
+ * dropped via acpi_dev_put().
+ */
+struct acpi_device *acpi_get_acpi_dev(acpi_handle handle)
 {
 	return handle_to_device(handle, get_acpi_device);
 }
-EXPORT_SYMBOL_GPL(acpi_bus_get_acpi_device);
+EXPORT_SYMBOL_GPL(acpi_get_acpi_dev);
 
 static struct acpi_device_bus_id *acpi_device_bus_id_match(const char *dev_id)
 {
@@ -632,7 +642,7 @@ static int acpi_device_set_name(struct acpi_device *device,
 	return 0;
 }
 
-static int acpi_tie_acpi_dev(struct acpi_device *adev)
+int acpi_tie_acpi_dev(struct acpi_device *adev)
 {
 	acpi_handle handle = adev->handle;
 	acpi_status status;
@@ -662,8 +672,7 @@ static void acpi_store_pld_crc(struct acpi_device *adev)
 	ACPI_FREE(pld);
 }
 
-static int __acpi_device_add(struct acpi_device *device,
-			     void (*release)(struct device *))
+int acpi_device_add(struct acpi_device *device)
 {
 	struct acpi_device_bus_id *acpi_device_bus_id;
 	int result;
@@ -719,11 +728,6 @@ static int __acpi_device_add(struct acpi_device *device,
 
 	mutex_unlock(&acpi_device_lock);
 
-	if (device->parent)
-		device->dev.parent = &device->parent->dev;
-
-	device->dev.bus = &acpi_bus_type;
-	device->dev.release = release;
 	result = device_add(&device->dev);
 	if (result) {
 		dev_err(&device->dev, "Error registering device\n");
@@ -750,17 +754,6 @@ err_unlock:
 	return result;
 }
 
-int acpi_device_add(struct acpi_device *adev, void (*release)(struct device *))
-{
-	int ret;
-
-	ret = acpi_tie_acpi_dev(adev);
-	if (ret)
-		return ret;
-
-	return __acpi_device_add(adev, release);
-}
-
 /* --------------------------------------------------------------------------
                                  Device Enumeration
    -------------------------------------------------------------------------- */
@@ -805,10 +798,9 @@ static const char * const acpi_honor_dep_ids[] = {
 	NULL
 };
 
-static struct acpi_device *acpi_bus_get_parent(acpi_handle handle)
+static struct acpi_device *acpi_find_parent_acpi_dev(acpi_handle handle)
 {
-	struct acpi_device *device;
-	acpi_status status;
+	struct acpi_device *adev;
 
 	/*
 	 * Fixed hardware devices do not appear in the namespace and do not
@@ -819,13 +811,18 @@ static struct acpi_device *acpi_bus_get_parent(acpi_handle handle)
 		return acpi_root;
 
 	do {
+		acpi_status status;
+
 		status = acpi_get_parent(handle, &handle);
-		if (ACPI_FAILURE(status))
-			return status == AE_NULL_ENTRY ? NULL : acpi_root;
+		if (ACPI_FAILURE(status)) {
+			if (status != AE_NULL_ENTRY)
+				return acpi_root;
 
-		device = acpi_fetch_acpi_dev(handle);
-	} while (!device);
-	return device;
+			return NULL;
+		}
+		adev = acpi_fetch_acpi_dev(handle);
+	} while (!adev);
+	return adev;
 }
 
 acpi_status
@@ -1112,7 +1109,7 @@ static void acpi_device_get_busid(struct acpi_device *device)
 	 * The device's Bus ID is simply the object name.
 	 * TBD: Shouldn't this value be unique (within the ACPI namespace)?
 	 */
-	if (ACPI_IS_ROOT_DEVICE(device)) {
+	if (!acpi_dev_parent(device)) {
 		strcpy(device->pnp.bus_id, "ACPI");
 		return;
 	}
@@ -1467,25 +1464,21 @@ enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev)
  * acpi_dma_get_range() - Get device DMA parameters.
  *
  * @dev: device to configure
- * @dma_addr: pointer device DMA address result
- * @offset: pointer to the DMA offset result
- * @size: pointer to DMA range size result
+ * @map: pointer to DMA ranges result
  *
- * Evaluate DMA regions and return respectively DMA region start, offset
- * and size in dma_addr, offset and size on parsing success; it does not
- * update the passed in values on failure.
+ * Evaluate DMA regions and return pointer to DMA regions on
+ * parsing success; it does not update the passed in values on failure.
  *
  * Return 0 on success, < 0 on failure.
  */
-int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset,
-		       u64 *size)
+int acpi_dma_get_range(struct device *dev, const struct bus_dma_region **map)
 {
 	struct acpi_device *adev;
 	LIST_HEAD(list);
 	struct resource_entry *rentry;
 	int ret;
 	struct device *dma_dev = dev;
-	u64 len, dma_start = U64_MAX, dma_end = 0, dma_offset = 0;
+	struct bus_dma_region *r;
 
 	/*
 	 * Walk the device tree chasing an ACPI companion with a _DMA
@@ -1510,31 +1503,28 @@ int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset,
 
 	ret = acpi_dev_get_dma_resources(adev, &list);
 	if (ret > 0) {
+		r = kcalloc(ret + 1, sizeof(*r), GFP_KERNEL);
+		if (!r) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
 		list_for_each_entry(rentry, &list, node) {
-			if (dma_offset && rentry->offset != dma_offset) {
+			if (rentry->res->start >= rentry->res->end) {
+				kfree(r);
 				ret = -EINVAL;
-				dev_warn(dma_dev, "Can't handle multiple windows with different offsets\n");
+				dev_dbg(dma_dev, "Invalid DMA regions configuration\n");
 				goto out;
 			}
-			dma_offset = rentry->offset;
 
-			/* Take lower and upper limits */
-			if (rentry->res->start < dma_start)
-				dma_start = rentry->res->start;
-			if (rentry->res->end > dma_end)
-				dma_end = rentry->res->end;
-		}
-
-		if (dma_start >= dma_end) {
-			ret = -EINVAL;
-			dev_dbg(dma_dev, "Invalid DMA regions configuration\n");
-			goto out;
+			r->cpu_start = rentry->res->start;
+			r->dma_start = rentry->res->start - rentry->offset;
+			r->size = resource_size(rentry->res);
+			r->offset = rentry->offset;
+			r++;
 		}
 
-		*dma_addr = dma_start - dma_offset;
-		len = dma_end - dma_start;
-		*size = max(len, len + 1);
-		*offset = dma_offset;
+		*map = r;
 	}
  out:
 	acpi_dev_free_resource_list(&list);
@@ -1624,20 +1614,19 @@ int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
 			  const u32 *input_id)
 {
 	const struct iommu_ops *iommu;
-	u64 dma_addr = 0, size = 0;
 
 	if (attr == DEV_DMA_NOT_SUPPORTED) {
 		set_dma_ops(dev, &dma_dummy_ops);
 		return 0;
 	}
 
-	acpi_arch_dma_setup(dev, &dma_addr, &size);
+	acpi_arch_dma_setup(dev);
 
 	iommu = acpi_iommu_configure_id(dev, input_id);
 	if (PTR_ERR(iommu) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
-	arch_setup_dma_ops(dev, dma_addr, size,
+	arch_setup_dma_ops(dev, 0, U64_MAX,
 				iommu, attr == DEV_DMA_COHERENT);
 
 	return 0;
@@ -1648,7 +1637,7 @@ static void acpi_init_coherency(struct acpi_device *adev)
 {
 	unsigned long long cca = 0;
 	acpi_status status;
-	struct acpi_device *parent = adev->parent;
+	struct acpi_device *parent = acpi_dev_parent(adev);
 
 	if (parent && parent->flags.cca_seen) {
 		/*
@@ -1692,7 +1681,7 @@ static int acpi_check_serial_bus_slave(struct acpi_resource *ares, void *data)
 
 static bool acpi_is_indirect_io_slave(struct acpi_device *device)
 {
-	struct acpi_device *parent = device->parent;
+	struct acpi_device *parent = acpi_dev_parent(device);
 	static const struct acpi_device_id indirect_io_hosts[] = {
 		{"HISI0191", 0},
 		{}
@@ -1762,12 +1751,16 @@ static bool acpi_device_enumeration_by_parent(struct acpi_device *device)
 }
 
 void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
-			     int type)
+			     int type, void (*release)(struct device *))
 {
+	struct acpi_device *parent = acpi_find_parent_acpi_dev(handle);
+
 	INIT_LIST_HEAD(&device->pnp.ids);
 	device->device_type = type;
 	device->handle = handle;
-	device->parent = acpi_bus_get_parent(handle);
+	device->dev.parent = parent ? &parent->dev : NULL;
+	device->dev.release = release;
+	device->dev.bus = &acpi_bus_type;
 	fwnode_init(&device->fwnode, &acpi_device_fwnode_ops);
 	acpi_set_device_status(device, ACPI_STA_DEFAULT);
 	acpi_device_get_busid(device);
@@ -1821,7 +1814,7 @@ static int acpi_add_single_object(struct acpi_device **child,
 	if (!device)
 		return -ENOMEM;
 
-	acpi_init_device_object(device, handle, type);
+	acpi_init_device_object(device, handle, type, acpi_device_release);
 	/*
 	 * Getting the status is delayed till here so that we can call
 	 * acpi_bus_get_status() and use its quirk handling.  Note that
@@ -1851,7 +1844,7 @@ static int acpi_add_single_object(struct acpi_device **child,
 		mutex_unlock(&acpi_dep_list_lock);
 
 	if (!result)
-		result = __acpi_device_add(device, acpi_device_release);
+		result = acpi_device_add(device);
 
 	if (result) {
 		acpi_device_release(&device->dev);
@@ -1862,8 +1855,8 @@ static int acpi_add_single_object(struct acpi_device **child,
 	acpi_device_add_finalize(device);
 
 	acpi_handle_debug(handle, "Added as %s, parent %s\n",
-			  dev_name(&device->dev), device->parent ?
-				dev_name(&device->parent->dev) : "(null)");
+			  dev_name(&device->dev), device->dev.parent ?
+				dev_name(device->dev.parent) : "(null)");
 
 	*child = device;
 	return 0;
@@ -2235,11 +2228,24 @@ ok:
 	return 0;
 }
 
-static int acpi_dev_get_first_consumer_dev_cb(struct acpi_dep_data *dep, void *data)
+static int acpi_dev_get_next_consumer_dev_cb(struct acpi_dep_data *dep, void *data)
 {
-	struct acpi_device *adev;
+	struct acpi_device **adev_p = data;
+	struct acpi_device *adev = *adev_p;
 
-	adev = acpi_bus_get_acpi_device(dep->consumer);
+	/*
+	 * If we're passed a 'previous' consumer device then we need to skip
+	 * any consumers until we meet the previous one, and then NULL @data
+	 * so the next one can be returned.
+	 */
+	if (adev) {
+		if (dep->consumer == adev->handle)
+			*adev_p = NULL;
+
+		return 0;
+	}
+
+	adev = acpi_get_acpi_dev(dep->consumer);
 	if (adev) {
 		*(struct acpi_device **)data = adev;
 		return 1;
@@ -2292,7 +2298,7 @@ static bool acpi_scan_clear_dep_queue(struct acpi_device *adev)
 
 static int acpi_scan_clear_dep(struct acpi_dep_data *dep, void *data)
 {
-	struct acpi_device *adev = acpi_bus_get_acpi_device(dep->consumer);
+	struct acpi_device *adev = acpi_get_acpi_dev(dep->consumer);
 
 	if (adev) {
 		adev->dep_unmet--;
@@ -2368,25 +2374,32 @@ bool acpi_dev_ready_for_enumeration(const struct acpi_device *device)
 EXPORT_SYMBOL_GPL(acpi_dev_ready_for_enumeration);
 
 /**
- * acpi_dev_get_first_consumer_dev - Return ACPI device dependent on @supplier
+ * acpi_dev_get_next_consumer_dev - Return the next adev dependent on @supplier
  * @supplier: Pointer to the dependee device
+ * @start: Pointer to the current dependent device
  *
- * Returns the first &struct acpi_device which declares itself dependent on
+ * Returns the next &struct acpi_device which declares itself dependent on
  * @supplier via the _DEP buffer, parsed from the acpi_dep_list.
  *
- * The caller is responsible for putting the reference to adev when it is no
- * longer needed.
+ * If the returned adev is not passed as @start to this function, the caller is
+ * responsible for putting the reference to adev when it is no longer needed.
  */
-struct acpi_device *acpi_dev_get_first_consumer_dev(struct acpi_device *supplier)
+struct acpi_device *acpi_dev_get_next_consumer_dev(struct acpi_device *supplier,
+						   struct acpi_device *start)
 {
-	struct acpi_device *adev = NULL;
+	struct acpi_device *adev = start;
 
 	acpi_walk_dep_device_list(supplier->handle,
-				  acpi_dev_get_first_consumer_dev_cb, &adev);
+				  acpi_dev_get_next_consumer_dev_cb, &adev);
+
+	acpi_dev_put(start);
+
+	if (adev == start)
+		return NULL;
 
 	return adev;
 }
-EXPORT_SYMBOL_GPL(acpi_dev_get_first_consumer_dev);
+EXPORT_SYMBOL_GPL(acpi_dev_get_next_consumer_dev);
 
 /**
  * acpi_bus_scan - Add ACPI device node objects in a given namespace scope.
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 5a7b8065e77f..2ea14648a661 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -794,6 +794,30 @@ bool acpi_dev_hid_uid_match(struct acpi_device *adev,
 EXPORT_SYMBOL(acpi_dev_hid_uid_match);
 
 /**
+ * acpi_dev_uid_to_integer - treat ACPI device _UID as integer
+ * @adev: ACPI device to get _UID from
+ * @integer: output buffer for integer
+ *
+ * Considers _UID as integer and converts it to @integer.
+ *
+ * Returns 0 on success, or negative error code otherwise.
+ */
+int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer)
+{
+	const char *uid;
+
+	if (!adev)
+		return -ENODEV;
+
+	uid = acpi_device_uid(adev);
+	if (!uid)
+		return -ENODATA;
+
+	return kstrtou64(uid, 0, integer);
+}
+EXPORT_SYMBOL(acpi_dev_uid_to_integer);
+
+/**
  * acpi_dev_found - Detect presence of a given ACPI device in the namespace.
  * @hid: Hardware ID of the device.
  *
@@ -878,7 +902,7 @@ bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
 	struct acpi_dev_match_info match = {};
 	struct device *dev;
 
-	strlcpy(match.hid[0].id, hid, sizeof(match.hid[0].id));
+	strscpy(match.hid[0].id, hid, sizeof(match.hid[0].id));
 	match.uid = uid;
 	match.hrv = hrv;
 
@@ -911,7 +935,7 @@ acpi_dev_get_next_match_dev(struct acpi_device *adev, const char *hid, const cha
 	struct acpi_dev_match_info match = {};
 	struct device *dev;
 
-	strlcpy(match.hid[0].id, hid, sizeof(match.hid[0].id));
+	strscpy(match.hid[0].id, hid, sizeof(match.hid[0].id));
 	match.uid = uid;
 	match.hrv = hrv;
 
@@ -961,7 +985,7 @@ EXPORT_SYMBOL(acpi_video_backlight_string);
 
 static int __init acpi_backlight(char *str)
 {
-	strlcpy(acpi_video_backlight_string, str,
+	strscpy(acpi_video_backlight_string, str,
 		sizeof(acpi_video_backlight_string));
 	return 1;
 }
diff --git a/drivers/acpi/x86/apple.c b/drivers/acpi/x86/apple.c
index c285c91a5e9c..8812ecd03d55 100644
--- a/drivers/acpi/x86/apple.c
+++ b/drivers/acpi/x86/apple.c
@@ -8,6 +8,7 @@
 #include <linux/bitmap.h>
 #include <linux/platform_data/x86/apple.h>
 #include <linux/uuid.h>
+#include "../internal.h"
 
 /* Apple _DSM device properties GUID */
 static const guid_t apple_prp_guid =
diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c
index f9ac12b778e6..0155c1d2d608 100644
--- a/drivers/acpi/x86/s2idle.c
+++ b/drivers/acpi/x86/s2idle.c
@@ -17,6 +17,7 @@
 
 #include <linux/acpi.h>
 #include <linux/device.h>
+#include <linux/dmi.h>
 #include <linux/suspend.h>
 
 #include "../sleep.h"
@@ -27,6 +28,10 @@ static bool sleep_no_lps0 __read_mostly;
 module_param(sleep_no_lps0, bool, 0644);
 MODULE_PARM_DESC(sleep_no_lps0, "Do not use the special LPS0 device interface");
 
+static bool prefer_microsoft_dsm_guid __read_mostly;
+module_param(prefer_microsoft_dsm_guid, bool, 0644);
+MODULE_PARM_DESC(prefer_microsoft_dsm_guid, "Prefer using Microsoft GUID in LPS0 device _DSM evaluation");
+
 static const struct acpi_device_id lps0_device_ids[] = {
 	{"PNP0D80", },
 	{"", },
@@ -363,40 +368,132 @@ out:
 	return ret;
 }
 
+struct amd_lps0_hid_device_data {
+	const unsigned int rev_id;
+	const bool check_off_by_one;
+	const bool prefer_amd_guid;
+};
+
+static const struct amd_lps0_hid_device_data amd_picasso = {
+	.rev_id = 0,
+	.check_off_by_one = true,
+	.prefer_amd_guid = false,
+};
+
+static const struct amd_lps0_hid_device_data amd_cezanne = {
+	.rev_id = 0,
+	.check_off_by_one = false,
+	.prefer_amd_guid = false,
+};
+
+static const struct amd_lps0_hid_device_data amd_rembrandt = {
+	.rev_id = 2,
+	.check_off_by_one = false,
+	.prefer_amd_guid = true,
+};
+
+static const struct acpi_device_id amd_hid_ids[] = {
+	{"AMD0004",	(kernel_ulong_t)&amd_picasso,	},
+	{"AMD0005",	(kernel_ulong_t)&amd_picasso,	},
+	{"AMDI0005",	(kernel_ulong_t)&amd_picasso,	},
+	{"AMDI0006",	(kernel_ulong_t)&amd_cezanne,	},
+	{"AMDI0007",	(kernel_ulong_t)&amd_rembrandt,	},
+	{}
+};
+
+static int lps0_prefer_microsoft(const struct dmi_system_id *id)
+{
+	pr_debug("Preferring Microsoft GUID.\n");
+	prefer_microsoft_dsm_guid = true;
+	return 0;
+}
+
+static const struct dmi_system_id s2idle_dmi_table[] __initconst = {
+	{
+		/*
+		 * ASUS TUF Gaming A17 FA707RE
+		 * https://bugzilla.kernel.org/show_bug.cgi?id=216101
+		 */
+		.callback = lps0_prefer_microsoft,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ASUS TUF Gaming A17"),
+		},
+	},
+	{
+		/* ASUS ROG Zephyrus G14 (2022) */
+		.callback = lps0_prefer_microsoft,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ROG Zephyrus G14 GA402"),
+		},
+	},
+	{
+		/*
+		 * Lenovo Yoga Slim 7 Pro X 14ARH7
+		 * https://bugzilla.kernel.org/show_bug.cgi?id=216473 : 82V2
+		 * https://bugzilla.kernel.org/show_bug.cgi?id=216438 : 82TL
+		 */
+		.callback = lps0_prefer_microsoft,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "82"),
+		},
+	},
+	{
+		/*
+		 * ASUSTeK COMPUTER INC. ROG Flow X13 GV301RE_GV301RE
+		 * https://gitlab.freedesktop.org/drm/amd/-/issues/2148
+		 */
+		.callback = lps0_prefer_microsoft,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ROG Flow X13 GV301"),
+		},
+	},
+	{
+		/*
+		 * ASUSTeK COMPUTER INC. ROG Flow X16 GV601RW_GV601RW
+		 * https://gitlab.freedesktop.org/drm/amd/-/issues/2148
+		 */
+		.callback = lps0_prefer_microsoft,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ROG Flow X16 GV601"),
+		},
+	},
+	{}
+};
+
 static int lps0_device_attach(struct acpi_device *adev,
 			      const struct acpi_device_id *not_used)
 {
 	if (lps0_device_handle)
 		return 0;
 
+	lps0_dsm_func_mask_microsoft = validate_dsm(adev->handle,
+						    ACPI_LPS0_DSM_UUID_MICROSOFT, 0,
+						    &lps0_dsm_guid_microsoft);
 	if (acpi_s2idle_vendor_amd()) {
-		/* AMD0004, AMD0005, AMDI0005:
-		 * - Should use rev_id 0x0
-		 * - function mask > 0x3: Should use AMD method, but has off by one bug
-		 * - function mask = 0x3: Should use Microsoft method
-		 * AMDI0006:
-		 * - should use rev_id 0x0
-		 * - function mask = 0x3: Should use Microsoft method
-		 * AMDI0007:
-		 * - Should use rev_id 0x2
-		 * - Should only use AMD method
-		 */
-		const char *hid = acpi_device_hid(adev);
-		rev_id = strcmp(hid, "AMDI0007") ? 0 : 2;
+		static const struct acpi_device_id *dev_id;
+		const struct amd_lps0_hid_device_data *data;
+
+		for (dev_id = &amd_hid_ids[0]; dev_id->id[0]; dev_id++)
+			if (acpi_dev_hid_uid_match(adev, dev_id->id, NULL))
+				break;
+		if (dev_id->id[0])
+			data = (const struct amd_lps0_hid_device_data *) dev_id->driver_data;
+		else
+			data = &amd_rembrandt;
+		rev_id = data->rev_id;
 		lps0_dsm_func_mask = validate_dsm(adev->handle,
 					ACPI_LPS0_DSM_UUID_AMD, rev_id, &lps0_dsm_guid);
-		lps0_dsm_func_mask_microsoft = validate_dsm(adev->handle,
-					ACPI_LPS0_DSM_UUID_MICROSOFT, 0,
-					&lps0_dsm_guid_microsoft);
-		if (lps0_dsm_func_mask > 0x3 && (!strcmp(hid, "AMD0004") ||
-						 !strcmp(hid, "AMD0005") ||
-						 !strcmp(hid, "AMDI0005"))) {
+		if (lps0_dsm_func_mask > 0x3 && data->check_off_by_one) {
 			lps0_dsm_func_mask = (lps0_dsm_func_mask << 1) | 0x1;
 			acpi_handle_debug(adev->handle, "_DSM UUID %s: Adjusted function mask: 0x%x\n",
 					  ACPI_LPS0_DSM_UUID_AMD, lps0_dsm_func_mask);
-		} else if (lps0_dsm_func_mask_microsoft > 0 &&
-				(!strcmp(hid, "AMDI0007") ||
-				 !strcmp(hid, "AMDI0008"))) {
+		} else if (lps0_dsm_func_mask_microsoft > 0 && data->prefer_amd_guid &&
+				!prefer_microsoft_dsm_guid) {
 			lps0_dsm_func_mask_microsoft = -EINVAL;
 			acpi_handle_debug(adev->handle, "_DSM Using AMD method\n");
 		}
@@ -404,7 +501,8 @@ static int lps0_device_attach(struct acpi_device *adev,
 		rev_id = 1;
 		lps0_dsm_func_mask = validate_dsm(adev->handle,
 					ACPI_LPS0_DSM_UUID, rev_id, &lps0_dsm_guid);
-		lps0_dsm_func_mask_microsoft = -EINVAL;
+		if (!prefer_microsoft_dsm_guid)
+			lps0_dsm_func_mask_microsoft = -EINVAL;
 	}
 
 	if (lps0_dsm_func_mask < 0 && lps0_dsm_func_mask_microsoft < 0)
@@ -533,8 +631,9 @@ static const struct platform_s2idle_ops acpi_s2idle_ops_lps0 = {
 	.end = acpi_s2idle_end,
 };
 
-void acpi_s2idle_setup(void)
+void __init acpi_s2idle_setup(void)
 {
+	dmi_check_system(s2idle_dmi_table);
 	acpi_scan_add_handler(&lps0_handler);
 	s2idle_set_ops(&acpi_s2idle_ops_lps0);
 }
diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c
index 664070fc8349..f8a2cbdc0ce2 100644
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@@ -207,9 +207,26 @@ static const struct x86_cpu_id storage_d3_cpu_ids[] = {
 	{}
 };
 
+static const struct dmi_system_id force_storage_d3_dmi[] = {
+	{
+		/*
+		 * _ADR is ambiguous between GPP1.DEV0 and GPP1.NVME
+		 * but .NVME is needed to get StorageD3Enable node
+		 * https://bugzilla.kernel.org/show_bug.cgi?id=216440
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 14 7425 2-in-1"),
+		}
+	},
+	{}
+};
+
 bool force_storage_d3(void)
 {
-	return x86_match_cpu(storage_d3_cpu_ids);
+	const struct dmi_system_id *dmi_id = dmi_first_match(force_storage_d3_dmi);
+
+	return dmi_id || x86_match_cpu(storage_d3_cpu_ids);
 }
 
 /*
@@ -351,11 +368,17 @@ int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *s
 	struct acpi_device *adev = ACPI_COMPANION(controller_parent);
 	const struct dmi_system_id *dmi_id;
 	long quirks = 0;
+	u64 uid;
+	int ret;
 
 	*skip = false;
 
-	/* !dev_is_platform() to not match on PNP enumerated debug UARTs */
-	if (!adev || !adev->pnp.unique_id || !dev_is_platform(controller_parent))
+	ret = acpi_dev_uid_to_integer(adev, &uid);
+	if (ret)
+		return 0;
+
+	/* to not match on PNP enumerated debug UARTs */
+	if (!dev_is_platform(controller_parent))
 		return 0;
 
 	dmi_id = dmi_first_match(acpi_quirk_skip_dmi_ids);
@@ -363,10 +386,10 @@ int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *s
 		quirks = (unsigned long)dmi_id->driver_data;
 
 	if (quirks & ACPI_QUIRK_UART1_TTY_UART2_SKIP) {
-		if (!strcmp(adev->pnp.unique_id, "1"))
+		if (uid == 1)
 			return -ENODEV; /* Create tty cdev instead of serdev */
 
-		if (!strcmp(adev->pnp.unique_id, "2"))
+		if (uid == 2)
 			*skip = true;
 	}
 
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 32b0e0b930c1..110a535648d2 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -209,6 +209,7 @@ static int amba_match(struct device *dev, struct device_driver *drv)
 	struct amba_device *pcdev = to_amba_device(dev);
 	struct amba_driver *pcdrv = to_amba_driver(drv);
 
+	mutex_lock(&pcdev->periphid_lock);
 	if (!pcdev->periphid) {
 		int ret = amba_read_periphid(pcdev);
 
@@ -218,11 +219,14 @@ static int amba_match(struct device *dev, struct device_driver *drv)
 		 * permanent failure in reading pid and cid, simply map it to
 		 * -EPROBE_DEFER.
 		 */
-		if (ret)
+		if (ret) {
+			mutex_unlock(&pcdev->periphid_lock);
 			return -EPROBE_DEFER;
+		}
 		dev_set_uevent_suppress(dev, false);
 		kobject_uevent(&dev->kobj, KOBJ_ADD);
 	}
+	mutex_unlock(&pcdev->periphid_lock);
 
 	/* When driver_override is set, only bind to the matching driver */
 	if (pcdev->driver_override)
@@ -532,6 +536,7 @@ static void amba_device_release(struct device *dev)
 
 	if (d->res.parent)
 		release_resource(&d->res);
+	mutex_destroy(&d->periphid_lock);
 	kfree(d);
 }
 
@@ -584,6 +589,7 @@ static void amba_device_initialize(struct amba_device *dev, const char *name)
 	dev->dev.dma_mask = &dev->dev.coherent_dma_mask;
 	dev->dev.dma_parms = &dev->dma_parms;
 	dev->res.name = dev_name(&dev->dev);
+	mutex_init(&dev->periphid_lock);
 }
 
 /**
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index c964d7c8c384..6428f6be69e3 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -1385,6 +1385,18 @@ static int binder_inc_ref_for_node(struct binder_proc *proc,
 	}
 	ret = binder_inc_ref_olocked(ref, strong, target_list);
 	*rdata = ref->data;
+	if (ret && ref == new_ref) {
+		/*
+		 * Cleanup the failed reference here as the target
+		 * could now be dead and have already released its
+		 * references by now. Calling on the new reference
+		 * with strong=0 and a tmp_refs will not decrement
+		 * the node. The new_ref gets kfree'd below.
+		 */
+		binder_cleanup_ref_olocked(new_ref);
+		ref = NULL;
+	}
+
 	binder_proc_unlock(proc);
 	if (new_ref && ref != new_ref)
 		/*
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 1014beb12802..9b1778c00610 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -322,7 +322,6 @@ static inline void binder_alloc_set_vma(struct binder_alloc *alloc,
 	 */
 	if (vma) {
 		vm_start = vma->vm_start;
-		alloc->vma_vm_mm = vma->vm_mm;
 		mmap_assert_write_locked(alloc->vma_vm_mm);
 	} else {
 		mmap_assert_locked(alloc->vma_vm_mm);
@@ -402,12 +401,15 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	size_t size, data_offsets_size;
 	int ret;
 
+	mmap_read_lock(alloc->vma_vm_mm);
 	if (!binder_alloc_get_vma(alloc)) {
+		mmap_read_unlock(alloc->vma_vm_mm);
 		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
 				   "%d: binder_alloc_buf, no vma\n",
 				   alloc->pid);
 		return ERR_PTR(-ESRCH);
 	}
+	mmap_read_unlock(alloc->vma_vm_mm);
 
 	data_offsets_size = ALIGN(data_size, sizeof(void *)) +
 		ALIGN(offsets_size, sizeof(void *));
@@ -792,7 +794,6 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 	binder_insert_free_buffer(alloc, buffer);
 	alloc->free_async_space = alloc->buffer_size / 2;
 	binder_alloc_set_vma(alloc, vma);
-	mmgrab(alloc->vma_vm_mm);
 
 	return 0;
 
@@ -929,17 +930,25 @@ void binder_alloc_print_pages(struct seq_file *m,
 	 * Make sure the binder_alloc is fully initialized, otherwise we might
 	 * read inconsistent state.
 	 */
-	if (binder_alloc_get_vma(alloc) != NULL) {
-		for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
-			page = &alloc->pages[i];
-			if (!page->page_ptr)
-				free++;
-			else if (list_empty(&page->lru))
-				active++;
-			else
-				lru++;
-		}
+
+	mmap_read_lock(alloc->vma_vm_mm);
+	if (binder_alloc_get_vma(alloc) == NULL) {
+		mmap_read_unlock(alloc->vma_vm_mm);
+		goto uninitialized;
 	}
+
+	mmap_read_unlock(alloc->vma_vm_mm);
+	for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
+		page = &alloc->pages[i];
+		if (!page->page_ptr)
+			free++;
+		else if (list_empty(&page->lru))
+			active++;
+		else
+			lru++;
+	}
+
+uninitialized:
 	mutex_unlock(&alloc->mutex);
 	seq_printf(m, "  pages: %d:%d:%d\n", active, lru, free);
 	seq_printf(m, "  pages high watermark: %zu\n", alloc->pages_high);
@@ -1080,6 +1089,8 @@ static struct shrinker binder_shrinker = {
 void binder_alloc_init(struct binder_alloc *alloc)
 {
 	alloc->pid = current->group_leader->pid;
+	alloc->vma_vm_mm = current->mm;
+	mmgrab(alloc->vma_vm_mm);
 	mutex_init(&alloc->mutex);
 	INIT_LIST_HEAD(&alloc->buffers);
 }
diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c
index 79aa9f285312..b734e069034d 100644
--- a/drivers/ata/ahci_imx.c
+++ b/drivers/ata/ahci_imx.c
@@ -327,7 +327,7 @@ static int read_adc_sum(void *dev, u16 rtune_ctl_reg, void __iomem * mmio)
 }
 
 /* SATA AHCI temperature monitor */
-static int sata_ahci_read_temperature(void *dev, int *temp)
+static int __sata_ahci_read_temperature(void *dev, int *temp)
 {
 	u16 mpll_test_reg, rtune_ctl_reg, dac_ctl_reg, read_sum;
 	u32 str1, str2, str3, str4;
@@ -416,6 +416,11 @@ static int sata_ahci_read_temperature(void *dev, int *temp)
 	return 0;
 }
 
+static int sata_ahci_read_temperature(struct thermal_zone_device *tz, int *temp)
+{
+	return __sata_ahci_read_temperature(tz->devdata, temp);
+}
+
 static ssize_t sata_ahci_show_temp(struct device *dev,
 				   struct device_attribute *da,
 				   char *buf)
@@ -423,14 +428,14 @@ static ssize_t sata_ahci_show_temp(struct device *dev,
 	unsigned int temp = 0;
 	int err;
 
-	err = sata_ahci_read_temperature(dev, &temp);
+	err = __sata_ahci_read_temperature(dev, &temp);
 	if (err < 0)
 		return err;
 
 	return sprintf(buf, "%u\n", temp);
 }
 
-static const struct thermal_zone_of_device_ops fsl_sata_ahci_of_thermal_ops = {
+static const struct thermal_zone_device_ops fsl_sata_ahci_of_thermal_ops = {
 	.get_temp = sata_ahci_read_temperature,
 };
 
@@ -1131,8 +1136,8 @@ static int imx_ahci_probe(struct platform_device *pdev)
 			ret = PTR_ERR(hwmon_dev);
 			goto disable_clk;
 		}
-		devm_thermal_zone_of_sensor_register(hwmon_dev, 0, hwmon_dev,
-					     &fsl_sata_ahci_of_thermal_ops);
+		devm_thermal_of_zone_register(hwmon_dev, 0, hwmon_dev,
+					      &fsl_sata_ahci_of_thermal_ops);
 		dev_info(dev, "%s: sensor 'sata_ahci'\n", dev_name(hwmon_dev));
 	}
 
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 826d41f341e4..c9a9aa607b62 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -3988,6 +3988,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "PIONEER DVD-RW  DVR-212D",	NULL,	ATA_HORKAGE_NOSETXFER },
 	{ "PIONEER DVD-RW  DVR-216D",	NULL,	ATA_HORKAGE_NOSETXFER },
 
+	/* These specific Pioneer models have LPM issues */
+	{ "PIONEER BD-RW   BDR-207M",	NULL,	ATA_HORKAGE_NOLPM },
+	{ "PIONEER BD-RW   BDR-205",	NULL,	ATA_HORKAGE_NOLPM },
+
 	/* Crucial BX100 SSD 500GB has broken LPM support */
 	{ "CT500BX100SSD1",		NULL,	ATA_HORKAGE_NOLPM },
 
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index ef4508d72c02..7c128c89b454 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -2122,6 +2122,7 @@ const char *ata_get_cmd_name(u8 command)
 		{ ATA_CMD_WRITE_QUEUED_FUA_EXT, "WRITE DMA QUEUED FUA EXT" },
 		{ ATA_CMD_FPDMA_READ,		"READ FPDMA QUEUED" },
 		{ ATA_CMD_FPDMA_WRITE,		"WRITE FPDMA QUEUED" },
+		{ ATA_CMD_NCQ_NON_DATA,		"NCQ NON-DATA" },
 		{ ATA_CMD_FPDMA_SEND,		"SEND FPDMA QUEUED" },
 		{ ATA_CMD_FPDMA_RECV,		"RECEIVE FPDMA QUEUED" },
 		{ ATA_CMD_PIO_READ,		"READ SECTOR(S)" },
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index 7a5fe41aa5ae..13b9d0fdd42c 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -1018,26 +1018,25 @@ DEVICE_ATTR(sw_activity, S_IWUSR | S_IRUGO, ata_scsi_activity_show,
 EXPORT_SYMBOL_GPL(dev_attr_sw_activity);
 
 /**
- *	__ata_change_queue_depth - helper for ata_scsi_change_queue_depth
- *	@ap: ATA port to which the device change the queue depth
+ *	ata_change_queue_depth - Set a device maximum queue depth
+ *	@ap: ATA port of the target device
+ *	@dev: target ATA device
  *	@sdev: SCSI device to configure queue depth for
  *	@queue_depth: new queue depth
  *
- *	libsas and libata have different approaches for associating a sdev to
- *	its ata_port.
+ *	Helper to set a device maximum queue depth, usable with both libsas
+ *	and libata.
  *
  */
-int __ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev,
-			     int queue_depth)
+int ata_change_queue_depth(struct ata_port *ap, struct ata_device *dev,
+			   struct scsi_device *sdev, int queue_depth)
 {
-	struct ata_device *dev;
 	unsigned long flags;
 
-	if (queue_depth < 1 || queue_depth == sdev->queue_depth)
+	if (!dev || !ata_dev_enabled(dev))
 		return sdev->queue_depth;
 
-	dev = ata_scsi_find_dev(ap, sdev);
-	if (!dev || !ata_dev_enabled(dev))
+	if (queue_depth < 1 || queue_depth == sdev->queue_depth)
 		return sdev->queue_depth;
 
 	/* NCQ enabled? */
@@ -1059,7 +1058,7 @@ int __ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev,
 
 	return scsi_change_queue_depth(sdev, queue_depth);
 }
-EXPORT_SYMBOL_GPL(__ata_change_queue_depth);
+EXPORT_SYMBOL_GPL(ata_change_queue_depth);
 
 /**
  *	ata_scsi_change_queue_depth - SCSI callback for queue depth config
@@ -1080,7 +1079,8 @@ int ata_scsi_change_queue_depth(struct scsi_device *sdev, int queue_depth)
 {
 	struct ata_port *ap = ata_shost_to_port(sdev->host);
 
-	return __ata_change_queue_depth(ap, sdev, queue_depth);
+	return ata_change_queue_depth(ap, ata_scsi_find_dev(ap, sdev),
+				      sdev, queue_depth);
 }
 EXPORT_SYMBOL_GPL(ata_scsi_change_queue_depth);
 
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 29e2f55c6faa..ff9602a0e54e 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1055,6 +1055,7 @@ EXPORT_SYMBOL_GPL(ata_scsi_dma_need_drain);
 int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev)
 {
 	struct request_queue *q = sdev->request_queue;
+	int depth = 1;
 
 	if (!ata_id_has_unload(dev->id))
 		dev->flags |= ATA_DFLAG_NO_UNLOAD;
@@ -1100,13 +1101,10 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev)
 	if (dev->flags & ATA_DFLAG_AN)
 		set_bit(SDEV_EVT_MEDIA_CHANGE, sdev->supported_events);
 
-	if (dev->flags & ATA_DFLAG_NCQ) {
-		int depth;
-
+	if (dev->flags & ATA_DFLAG_NCQ)
 		depth = min(sdev->host->can_queue, ata_id_queue_depth(dev->id));
-		depth = min(ATA_MAX_QUEUE, depth);
-		scsi_change_queue_depth(sdev, depth);
-	}
+	depth = min(ATA_MAX_QUEUE, depth);
+	scsi_change_queue_depth(sdev, depth);
 
 	if (dev->flags & ATA_DFLAG_TRUSTED)
 		sdev->security_supported = 1;
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 0424b59b695e..dd90591e51ba 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -353,7 +353,7 @@ void topology_init_cpu_capacity_cppc(void)
 	struct cppc_perf_caps perf_caps;
 	int cpu;
 
-	if (likely(acpi_disabled || !acpi_cpc_valid()))
+	if (likely(!acpi_cpc_valid()))
 		return;
 
 	raw_capacity = kcalloc(num_possible_cpus(), sizeof(*raw_capacity),
@@ -724,7 +724,7 @@ const struct cpumask *cpu_clustergroup_mask(int cpu)
 	 */
 	if (cpumask_subset(cpu_coregroup_mask(cpu),
 			   &cpu_topology[cpu].cluster_sibling))
-		return get_cpu_mask(cpu);
+		return topology_sibling_cpumask(cpu);
 
 	return &cpu_topology[cpu].cluster_sibling;
 }
@@ -735,7 +735,7 @@ void update_siblings_masks(unsigned int cpuid)
 	int cpu, ret;
 
 	ret = detect_cache_attributes(cpuid);
-	if (ret)
+	if (ret && ret != -ENOENT)
 		pr_info("Early cacheinfo failed, ret = %d\n", ret);
 
 	/* update core and thread sibling masks */
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 753e7cca0f40..5fb4bc51dd8b 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1625,7 +1625,7 @@ static int __init fw_devlink_setup(char *arg)
 }
 early_param("fw_devlink", fw_devlink_setup);
 
-static bool fw_devlink_strict = true;
+static bool fw_devlink_strict;
 static int __init fw_devlink_strict_setup(char *arg)
 {
 	return strtobool(arg, &fw_devlink_strict);
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 70f79fc71539..ec69b43f926a 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -274,12 +274,42 @@ static int __init deferred_probe_timeout_setup(char *str)
 }
 __setup("deferred_probe_timeout=", deferred_probe_timeout_setup);
 
+/**
+ * driver_deferred_probe_check_state() - Check deferred probe state
+ * @dev: device to check
+ *
+ * Return:
+ * * -ENODEV if initcalls have completed and modules are disabled.
+ * * -ETIMEDOUT if the deferred probe timeout was set and has expired
+ *   and modules are enabled.
+ * * -EPROBE_DEFER in other cases.
+ *
+ * Drivers or subsystems can opt-in to calling this function instead of directly
+ * returning -EPROBE_DEFER.
+ */
+int driver_deferred_probe_check_state(struct device *dev)
+{
+	if (!IS_ENABLED(CONFIG_MODULES) && initcalls_done) {
+		dev_warn(dev, "ignoring dependency for device, assuming no driver\n");
+		return -ENODEV;
+	}
+
+	if (!driver_deferred_probe_timeout && initcalls_done) {
+		dev_warn(dev, "deferred probe timeout, ignoring dependency\n");
+		return -ETIMEDOUT;
+	}
+
+	return -EPROBE_DEFER;
+}
+EXPORT_SYMBOL_GPL(driver_deferred_probe_check_state);
+
 static void deferred_probe_timeout_work_func(struct work_struct *work)
 {
 	struct device_private *p;
 
 	fw_devlink_drivers_done();
 
+	driver_deferred_probe_timeout = 0;
 	driver_deferred_probe_trigger();
 	flush_work(&deferred_probe_work);
 
@@ -881,6 +911,11 @@ static int __device_attach_driver(struct device_driver *drv, void *_data)
 		dev_dbg(dev, "Device match requests probe deferral\n");
 		dev->can_match = true;
 		driver_deferred_probe_add(dev);
+		/*
+		 * Device can't match with a driver right now, so don't attempt
+		 * to match or bind with other drivers on the bus.
+		 */
+		return ret;
 	} else if (ret < 0) {
 		dev_dbg(dev, "Bus failed to match device: %d\n", ret);
 		return ret;
@@ -1120,6 +1155,11 @@ static int __driver_attach(struct device *dev, void *data)
 		dev_dbg(dev, "Device match requests probe deferral\n");
 		dev->can_match = true;
 		driver_deferred_probe_add(dev);
+		/*
+		 * Driver could not match with device, but may match with
+		 * another device on the bus.
+		 */
+		return 0;
 	} else if (ret < 0) {
 		dev_dbg(dev, "Bus failed to match device: %d\n", ret);
 		return ret;
diff --git a/drivers/base/driver.c b/drivers/base/driver.c
index 15a75afe6b84..676b6275d5b5 100644
--- a/drivers/base/driver.c
+++ b/drivers/base/driver.c
@@ -63,6 +63,12 @@ int driver_set_override(struct device *dev, const char **override,
 	if (len >= (PAGE_SIZE - 1))
 		return -EINVAL;
 
+	/*
+	 * Compute the real length of the string in case userspace sends us a
+	 * bunch of \0 characters like python likes to do.
+	 */
+	len = strlen(s);
+
 	if (!len) {
 		/* Empty string passed - clear override */
 		device_lock(dev);
diff --git a/drivers/base/firmware_loader/sysfs.c b/drivers/base/firmware_loader/sysfs.c
index 77bad32c481a..5b66b3d1fa16 100644
--- a/drivers/base/firmware_loader/sysfs.c
+++ b/drivers/base/firmware_loader/sysfs.c
@@ -93,10 +93,9 @@ static void fw_dev_release(struct device *dev)
 {
 	struct fw_sysfs *fw_sysfs = to_fw_sysfs(dev);
 
-	if (fw_sysfs->fw_upload_priv) {
-		free_fw_priv(fw_sysfs->fw_priv);
-		kfree(fw_sysfs->fw_upload_priv);
-	}
+	if (fw_sysfs->fw_upload_priv)
+		fw_upload_free(fw_sysfs);
+
 	kfree(fw_sysfs);
 }
 
diff --git a/drivers/base/firmware_loader/sysfs.h b/drivers/base/firmware_loader/sysfs.h
index 5d8ff1675c79..df1d5add698f 100644
--- a/drivers/base/firmware_loader/sysfs.h
+++ b/drivers/base/firmware_loader/sysfs.h
@@ -106,12 +106,17 @@ extern struct device_attribute dev_attr_cancel;
 extern struct device_attribute dev_attr_remaining_size;
 
 int fw_upload_start(struct fw_sysfs *fw_sysfs);
+void fw_upload_free(struct fw_sysfs *fw_sysfs);
 umode_t fw_upload_is_visible(struct kobject *kobj, struct attribute *attr, int n);
 #else
 static inline int fw_upload_start(struct fw_sysfs *fw_sysfs)
 {
 	return 0;
 }
+
+static inline void fw_upload_free(struct fw_sysfs *fw_sysfs)
+{
+}
 #endif
 
 #endif /* __FIRMWARE_SYSFS_H */
diff --git a/drivers/base/firmware_loader/sysfs_upload.c b/drivers/base/firmware_loader/sysfs_upload.c
index 87044d52322a..a0af8f5f13d8 100644
--- a/drivers/base/firmware_loader/sysfs_upload.c
+++ b/drivers/base/firmware_loader/sysfs_upload.c
@@ -264,6 +264,15 @@ int fw_upload_start(struct fw_sysfs *fw_sysfs)
 	return 0;
 }
 
+void fw_upload_free(struct fw_sysfs *fw_sysfs)
+{
+	struct fw_upload_priv *fw_upload_priv = fw_sysfs->fw_upload_priv;
+
+	free_fw_priv(fw_sysfs->fw_priv);
+	kfree(fw_upload_priv->fw_upload);
+	kfree(fw_upload_priv);
+}
+
 /**
  * firmware_upload_register() - register for the firmware upload sysfs API
  * @module: kernel module of this device
@@ -377,6 +386,7 @@ void firmware_upload_unregister(struct fw_upload *fw_upload)
 {
 	struct fw_sysfs *fw_sysfs = fw_upload->priv;
 	struct fw_upload_priv *fw_upload_priv = fw_sysfs->fw_upload_priv;
+	struct module *module = fw_upload_priv->module;
 
 	mutex_lock(&fw_upload_priv->lock);
 	if (fw_upload_priv->progress == FW_UPLOAD_PROG_IDLE) {
@@ -392,6 +402,6 @@ void firmware_upload_unregister(struct fw_upload *fw_upload)
 
 unregister:
 	device_unregister(&fw_sysfs->dev);
-	module_put(fw_upload_priv->module);
+	module_put(module);
 }
 EXPORT_SYMBOL_GPL(firmware_upload_unregister);
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 5a2e0232862e..55a10e6d4e2a 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2733,7 +2733,7 @@ static int __genpd_dev_pm_attach(struct device *dev, struct device *base_dev,
 		mutex_unlock(&gpd_list_lock);
 		dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
 			__func__, PTR_ERR(pd));
-		return -ENODEV;
+		return driver_deferred_probe_check_state(base_dev);
 	}
 
 	dev_dbg(dev, "adding to PM domain %s\n", pd->name);
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 997be3ac20a7..b52049098d4e 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -792,10 +792,13 @@ static int rpm_resume(struct device *dev, int rpmflags)
 		DEFINE_WAIT(wait);
 
 		if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) {
-			if (dev->power.runtime_status == RPM_SUSPENDING)
+			if (dev->power.runtime_status == RPM_SUSPENDING) {
 				dev->power.deferred_resume = true;
-			else
+				if (rpmflags & RPM_NOWAIT)
+					retval = -EINPROGRESS;
+			} else {
 				retval = -EINPROGRESS;
+			}
 			goto out;
 		}
 
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index e3befa2c1b66..7cc0c0cf8eaa 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -944,6 +944,8 @@ void pm_system_irq_wakeup(unsigned int irq_number)
 	else
 		irq_number = 0;
 
+	pm_pr_dbg("Triggering wakeup from IRQ %d\n", irq_number);
+
 	raw_spin_unlock_irqrestore(&wakeup_irq_lock, flags);
 
 	if (irq_number)
diff --git a/drivers/base/regmap/regmap-spi.c b/drivers/base/regmap/regmap-spi.c
index 719323bc6c7f..37ab23a9d034 100644
--- a/drivers/base/regmap/regmap-spi.c
+++ b/drivers/base/regmap/regmap-spi.c
@@ -113,6 +113,7 @@ static const struct regmap_bus *regmap_get_spi_bus(struct spi_device *spi,
 						   const struct regmap_config *config)
 {
 	size_t max_size = spi_max_transfer_size(spi);
+	size_t max_msg_size, reg_reserve_size;
 	struct regmap_bus *bus;
 
 	if (max_size != SIZE_MAX) {
@@ -120,9 +121,16 @@ static const struct regmap_bus *regmap_get_spi_bus(struct spi_device *spi,
 		if (!bus)
 			return ERR_PTR(-ENOMEM);
 
+		max_msg_size = spi_max_message_size(spi);
+		reg_reserve_size = config->reg_bits / BITS_PER_BYTE
+				 + config->pad_bits / BITS_PER_BYTE;
+		if (max_size + reg_reserve_size > max_msg_size)
+			max_size -= reg_reserve_size;
+
 		bus->free_on_exit = true;
 		bus->max_raw_read = max_size;
 		bus->max_raw_write = max_size;
+
 		return bus;
 	}
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index e3c0ba93c1a3..ad92192c7d61 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -979,6 +979,11 @@ loop_set_status_from_info(struct loop_device *lo,
 
 	lo->lo_offset = info->lo_offset;
 	lo->lo_sizelimit = info->lo_sizelimit;
+
+	/* loff_t vars have been assigned __u64 */
+	if (lo->lo_offset < 0 || lo->lo_sizelimit < 0)
+		return -EOVERFLOW;
+
 	memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
 	lo->lo_file_name[LO_NAME_SIZE-1] = 0;
 	lo->lo_flags = info->lo_flags;
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 2b7d1db5c4a7..6a4a94b4cdf4 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -555,7 +555,7 @@ static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu(
 	return (struct ublk_uring_cmd_pdu *)&ioucmd->pdu;
 }
 
-static bool ubq_daemon_is_dying(struct ublk_queue *ubq)
+static inline bool ubq_daemon_is_dying(struct ublk_queue *ubq)
 {
 	return ubq->ubq_daemon->flags & PF_EXITING;
 }
@@ -605,8 +605,9 @@ static void ublk_complete_rq(struct request *req)
 }
 
 /*
- * __ublk_fail_req() may be called from abort context or ->ubq_daemon
- * context during exiting, so lock is required.
+ * Since __ublk_rq_task_work always fails requests immediately during
+ * exiting, __ublk_fail_req() is only called from abort context during
+ * exiting. So lock is unnecessary.
  *
  * Also aborting may not be started yet, keep in mind that one failed
  * request may be issued by block layer again.
@@ -644,8 +645,7 @@ static inline void __ublk_rq_task_work(struct request *req)
 	struct ublk_device *ub = ubq->dev;
 	int tag = req->tag;
 	struct ublk_io *io = &ubq->ios[tag];
-	bool task_exiting = current != ubq->ubq_daemon ||
-		(current->flags & PF_EXITING);
+	bool task_exiting = current != ubq->ubq_daemon || ubq_daemon_is_dying(ubq);
 	unsigned int mapped_bytes;
 
 	pr_devel("%s: complete: op %d, qid %d tag %d io_flags %x addr %llx\n",
@@ -680,6 +680,11 @@ static inline void __ublk_rq_task_work(struct request *req)
 		 * do the copy work.
 		 */
 		io->flags &= ~UBLK_IO_FLAG_NEED_GET_DATA;
+		/* update iod->addr because ublksrv may have passed a new io buffer */
+		ublk_get_iod(ubq, req->tag)->addr = io->addr;
+		pr_devel("%s: update iod->addr: op %d, qid %d tag %d io_flags %x addr %llx\n",
+				__func__, io->cmd->cmd_op, ubq->q_id, req->tag, io->flags,
+				ublk_get_iod(ubq, req->tag)->addr);
 	}
 
 	mapped_bytes = ublk_map_io(ubq, req, io);
@@ -751,9 +756,25 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
 		if (task_work_add(ubq->ubq_daemon, &data->work, notify_mode))
 			goto fail;
 	} else {
-		struct io_uring_cmd *cmd = ubq->ios[rq->tag].cmd;
+		struct ublk_io *io = &ubq->ios[rq->tag];
+		struct io_uring_cmd *cmd = io->cmd;
 		struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
 
+		/*
+		 * If the check pass, we know that this is a re-issued request aborted
+		 * previously in monitor_work because the ubq_daemon(cmd's task) is
+		 * PF_EXITING. We cannot call io_uring_cmd_complete_in_task() anymore
+		 * because this ioucmd's io_uring context may be freed now if no inflight
+		 * ioucmd exists. Otherwise we may cause null-deref in ctx->fallback_work.
+		 *
+		 * Note: monitor_work sets UBLK_IO_FLAG_ABORTED and ends this request(releasing
+		 * the tag). Then the request is re-started(allocating the tag) and we are here.
+		 * Since releasing/allocating a tag implies smp_mb(), finding UBLK_IO_FLAG_ABORTED
+		 * guarantees that here is a re-issued request aborted previously.
+		 */
+		if ((io->flags & UBLK_IO_FLAG_ABORTED))
+			goto fail;
+
 		pdu->req = rq;
 		io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb);
 	}
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 30255fcaf181..dd9a05174726 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -322,14 +322,14 @@ static blk_status_t virtblk_prep_rq(struct blk_mq_hw_ctx *hctx,
 	if (unlikely(status))
 		return status;
 
-	blk_mq_start_request(req);
-
 	vbr->sg_table.nents = virtblk_map_data(hctx, req, vbr);
 	if (unlikely(vbr->sg_table.nents < 0)) {
 		virtblk_cleanup_cmd(req);
 		return BLK_STS_RESOURCE;
 	}
 
+	blk_mq_start_request(req);
+
 	return BLK_STS_OK;
 }
 
@@ -391,8 +391,7 @@ static bool virtblk_prep_rq_batch(struct request *req)
 }
 
 static bool virtblk_add_req_batch(struct virtio_blk_vq *vq,
-					struct request **rqlist,
-					struct request **requeue_list)
+					struct request **rqlist)
 {
 	unsigned long flags;
 	int err;
@@ -408,7 +407,7 @@ static bool virtblk_add_req_batch(struct virtio_blk_vq *vq,
 		if (err) {
 			virtblk_unmap_data(req, vbr);
 			virtblk_cleanup_cmd(req);
-			rq_list_add(requeue_list, req);
+			blk_mq_requeue_request(req, true);
 		}
 	}
 
@@ -436,7 +435,7 @@ static void virtio_queue_rqs(struct request **rqlist)
 
 		if (!next || req->mq_hctx != next->mq_hctx) {
 			req->rq_next = NULL;
-			kick = virtblk_add_req_batch(vq, rqlist, &requeue_list);
+			kick = virtblk_add_req_batch(vq, rqlist);
 			if (kick)
 				virtqueue_notify(vq->vq);
 
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index bda5c815e441..a28473470e66 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -226,6 +226,9 @@ struct xen_vbd {
 	sector_t		size;
 	unsigned int		flush_support:1;
 	unsigned int		discard_secure:1;
+	/* Connect-time cached feature_persistent parameter value */
+	unsigned int		feature_gnt_persistent_parm:1;
+	/* Persistent grants feature negotiation result */
 	unsigned int		feature_gnt_persistent:1;
 	unsigned int		overflow_max_grants:1;
 };
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index ee7ad2fb432d..c0227dfa4688 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -907,7 +907,7 @@ again:
 	xen_blkbk_barrier(xbt, be, be->blkif->vbd.flush_support);
 
 	err = xenbus_printf(xbt, dev->nodename, "feature-persistent", "%u",
-			be->blkif->vbd.feature_gnt_persistent);
+			be->blkif->vbd.feature_gnt_persistent_parm);
 	if (err) {
 		xenbus_dev_fatal(dev, err, "writing %s/feature-persistent",
 				 dev->nodename);
@@ -1085,7 +1085,9 @@ static int connect_ring(struct backend_info *be)
 		return -ENOSYS;
 	}
 
-	blkif->vbd.feature_gnt_persistent = feature_persistent &&
+	blkif->vbd.feature_gnt_persistent_parm = feature_persistent;
+	blkif->vbd.feature_gnt_persistent =
+		blkif->vbd.feature_gnt_persistent_parm &&
 		xenbus_read_unsigned(dev->otherend, "feature-persistent", 0);
 
 	blkif->vbd.overflow_max_grants = 0;
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 8e56e69fb4c4..35b9bcad9db9 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -213,6 +213,9 @@ struct blkfront_info
 	unsigned int feature_fua:1;
 	unsigned int feature_discard:1;
 	unsigned int feature_secdiscard:1;
+	/* Connect-time cached feature_persistent parameter */
+	unsigned int feature_persistent_parm:1;
+	/* Persistent grants feature negotiation result */
 	unsigned int feature_persistent:1;
 	unsigned int bounce:1;
 	unsigned int discard_granularity;
@@ -1756,6 +1759,12 @@ abort_transaction:
 	return err;
 }
 
+/* Enable the persistent grants feature. */
+static bool feature_persistent = true;
+module_param(feature_persistent, bool, 0644);
+MODULE_PARM_DESC(feature_persistent,
+		"Enables the persistent grants feature");
+
 /* Common code used when first setting up, and when resuming. */
 static int talk_to_blkback(struct xenbus_device *dev,
 			   struct blkfront_info *info)
@@ -1847,8 +1856,9 @@ again:
 		message = "writing protocol";
 		goto abort_transaction;
 	}
+	info->feature_persistent_parm = feature_persistent;
 	err = xenbus_printf(xbt, dev->nodename, "feature-persistent", "%u",
-			info->feature_persistent);
+			info->feature_persistent_parm);
 	if (err)
 		dev_warn(&dev->dev,
 			 "writing persistent grants feature to xenbus");
@@ -1916,12 +1926,6 @@ static int negotiate_mq(struct blkfront_info *info)
 	return 0;
 }
 
-/* Enable the persistent grants feature. */
-static bool feature_persistent = true;
-module_param(feature_persistent, bool, 0644);
-MODULE_PARM_DESC(feature_persistent,
-		"Enables the persistent grants feature");
-
 /*
  * Entry point to this code when a new device is created.  Allocate the basic
  * structures and the ring buffer for communication with the backend, and
@@ -2281,7 +2285,7 @@ static void blkfront_gather_backend_features(struct blkfront_info *info)
 	if (xenbus_read_unsigned(info->xbdev->otherend, "feature-discard", 0))
 		blkfront_setup_discard(info);
 
-	if (feature_persistent)
+	if (info->feature_persistent_parm)
 		info->feature_persistent =
 			!!xenbus_read_unsigned(info->xbdev->otherend,
 					       "feature-persistent", 0);
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 92cb929a45b7..226ea76cc819 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1146,14 +1146,15 @@ static ssize_t bd_stat_show(struct device *dev,
 static ssize_t debug_stat_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	int version = 2;
+	int version = 1;
 	struct zram *zram = dev_to_zram(dev);
 	ssize_t ret;
 
 	down_read(&zram->init_lock);
 	ret = scnprintf(buf, PAGE_SIZE,
-			"version: %d\n%8llu\n",
+			"version: %d\n%8llu %8llu\n",
 			version,
+			(u64)atomic64_read(&zram->stats.writestall),
 			(u64)atomic64_read(&zram->stats.miss_free));
 	up_read(&zram->init_lock);
 
@@ -1351,7 +1352,7 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
 {
 	int ret = 0;
 	unsigned long alloced_pages;
-	unsigned long handle = 0;
+	unsigned long handle = -ENOMEM;
 	unsigned int comp_len = 0;
 	void *src, *dst, *mem;
 	struct zcomp_strm *zstrm;
@@ -1369,6 +1370,7 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
 	}
 	kunmap_atomic(mem);
 
+compress_again:
 	zstrm = zcomp_stream_get(zram->comp);
 	src = kmap_atomic(page);
 	ret = zcomp_compress(zstrm, src, &comp_len);
@@ -1377,20 +1379,39 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
 	if (unlikely(ret)) {
 		zcomp_stream_put(zram->comp);
 		pr_err("Compression failed! err=%d\n", ret);
+		zs_free(zram->mem_pool, handle);
 		return ret;
 	}
 
 	if (comp_len >= huge_class_size)
 		comp_len = PAGE_SIZE;
-
-	handle = zs_malloc(zram->mem_pool, comp_len,
-			__GFP_KSWAPD_RECLAIM |
-			__GFP_NOWARN |
-			__GFP_HIGHMEM |
-			__GFP_MOVABLE);
-
+	/*
+	 * handle allocation has 2 paths:
+	 * a) fast path is executed with preemption disabled (for
+	 *  per-cpu streams) and has __GFP_DIRECT_RECLAIM bit clear,
+	 *  since we can't sleep;
+	 * b) slow path enables preemption and attempts to allocate
+	 *  the page with __GFP_DIRECT_RECLAIM bit set. we have to
+	 *  put per-cpu compression stream and, thus, to re-do
+	 *  the compression once handle is allocated.
+	 *
+	 * if we have a 'non-null' handle here then we are coming
+	 * from the slow path and handle has already been allocated.
+	 */
+	if (IS_ERR((void *)handle))
+		handle = zs_malloc(zram->mem_pool, comp_len,
+				__GFP_KSWAPD_RECLAIM |
+				__GFP_NOWARN |
+				__GFP_HIGHMEM |
+				__GFP_MOVABLE);
 	if (IS_ERR((void *)handle)) {
 		zcomp_stream_put(zram->comp);
+		atomic64_inc(&zram->stats.writestall);
+		handle = zs_malloc(zram->mem_pool, comp_len,
+				GFP_NOIO | __GFP_HIGHMEM |
+				__GFP_MOVABLE);
+		if (!IS_ERR((void *)handle))
+			goto compress_again;
 		return PTR_ERR((void *)handle);
 	}
 
@@ -1948,6 +1969,7 @@ static int zram_add(void)
 	if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
 		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
 
+	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue);
 	ret = device_add_disk(NULL, zram->disk, zram_disk_groups);
 	if (ret)
 		goto out_cleanup_disk;
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 158c91e54850..80c3b43b4828 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -81,6 +81,7 @@ struct zram_stats {
 	atomic64_t huge_pages_since;	/* no. of huge pages since zram set up */
 	atomic64_t pages_stored;	/* no. of pages currently stored */
 	atomic_long_t max_used_pages;	/* no. of maximum pages stored */
+	atomic64_t writestall;		/* no. of write slow paths */
 	atomic64_t miss_free;		/* no. of missed free */
 #ifdef	CONFIG_ZRAM_WRITEBACK
 	atomic64_t bd_count;		/* no. of pages in backing device */
diff --git a/drivers/bus/mhi/host/main.c b/drivers/bus/mhi/host/main.c
index f3aef77a6a4a..df0fbfee7b78 100644
--- a/drivers/bus/mhi/host/main.c
+++ b/drivers/bus/mhi/host/main.c
@@ -430,12 +430,25 @@ irqreturn_t mhi_irq_handler(int irq_number, void *dev)
 {
 	struct mhi_event *mhi_event = dev;
 	struct mhi_controller *mhi_cntrl = mhi_event->mhi_cntrl;
-	struct mhi_event_ctxt *er_ctxt =
-		&mhi_cntrl->mhi_ctxt->er_ctxt[mhi_event->er_index];
+	struct mhi_event_ctxt *er_ctxt;
 	struct mhi_ring *ev_ring = &mhi_event->ring;
-	dma_addr_t ptr = le64_to_cpu(er_ctxt->rp);
+	dma_addr_t ptr;
 	void *dev_rp;
 
+	/*
+	 * If CONFIG_DEBUG_SHIRQ is set, the IRQ handler will get invoked during __free_irq()
+	 * and by that time mhi_ctxt() would've freed. So check for the existence of mhi_ctxt
+	 * before handling the IRQs.
+	 */
+	if (!mhi_cntrl->mhi_ctxt) {
+		dev_dbg(&mhi_cntrl->mhi_dev->dev,
+			"mhi_ctxt has been freed\n");
+		return IRQ_HANDLED;
+	}
+
+	er_ctxt = &mhi_cntrl->mhi_ctxt->er_ctxt[mhi_event->er_index];
+	ptr = le64_to_cpu(er_ctxt->rp);
+
 	if (!is_valid_ring_ptr(ev_ring, ptr)) {
 		dev_err(&mhi_cntrl->mhi_dev->dev,
 			"Event ring rp points outside of the event ring\n");
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 84ca98ed1dad..32a932a065a6 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -480,6 +480,11 @@ static ssize_t splice_write_null(struct pipe_inode_info *pipe, struct file *out,
 	return splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_null);
 }
 
+static int uring_cmd_null(struct io_uring_cmd *ioucmd, unsigned int issue_flags)
+{
+	return 0;
+}
+
 static ssize_t read_iter_zero(struct kiocb *iocb, struct iov_iter *iter)
 {
 	size_t written = 0;
@@ -663,6 +668,7 @@ static const struct file_operations null_fops = {
 	.read_iter	= read_iter_null,
 	.write_iter	= write_iter_null,
 	.splice_write	= splice_write_null,
+	.uring_cmd	= uring_cmd_null,
 };
 
 static const struct file_operations __maybe_unused port_fops = {
diff --git a/drivers/clk/bcm/clk-iproc-pll.c b/drivers/clk/bcm/clk-iproc-pll.c
index 1a098db12062..680f9d8d357c 100644
--- a/drivers/clk/bcm/clk-iproc-pll.c
+++ b/drivers/clk/bcm/clk-iproc-pll.c
@@ -726,6 +726,7 @@ void iproc_pll_clk_setup(struct device_node *node,
 	const char *parent_name;
 	struct iproc_clk *iclk_array;
 	struct clk_hw_onecell_data *clk_data;
+	const char *clk_name;
 
 	if (WARN_ON(!pll_ctrl) || WARN_ON(!clk_ctrl))
 		return;
@@ -773,7 +774,12 @@ void iproc_pll_clk_setup(struct device_node *node,
 	iclk = &iclk_array[0];
 	iclk->pll = pll;
 
-	init.name = node->name;
+	ret = of_property_read_string_index(node, "clock-output-names",
+					    0, &clk_name);
+	if (WARN_ON(ret))
+		goto err_pll_register;
+
+	init.name = clk_name;
 	init.ops = &iproc_pll_ops;
 	init.flags = 0;
 	parent_name = of_clk_get_parent_name(node, 0);
@@ -793,13 +799,11 @@ void iproc_pll_clk_setup(struct device_node *node,
 		goto err_pll_register;
 
 	clk_data->hws[0] = &iclk->hw;
+	parent_name = clk_name;
 
 	/* now initialize and register all leaf clocks */
 	for (i = 1; i < num_clks; i++) {
-		const char *clk_name;
-
 		memset(&init, 0, sizeof(init));
-		parent_name = node->name;
 
 		ret = of_property_read_string_index(node, "clock-output-names",
 						    i, &clk_name);
diff --git a/drivers/clk/bcm/clk-raspberrypi.c b/drivers/clk/bcm/clk-raspberrypi.c
index 73518009a0f2..876b37b8683c 100644
--- a/drivers/clk/bcm/clk-raspberrypi.c
+++ b/drivers/clk/bcm/clk-raspberrypi.c
@@ -203,7 +203,7 @@ static unsigned long raspberrypi_fw_get_rate(struct clk_hw *hw,
 	ret = raspberrypi_clock_property(rpi->firmware, data,
 					 RPI_FIRMWARE_GET_CLOCK_RATE, &val);
 	if (ret)
-		return ret;
+		return 0;
 
 	return val;
 }
@@ -220,7 +220,7 @@ static int raspberrypi_fw_set_rate(struct clk_hw *hw, unsigned long rate,
 	ret = raspberrypi_clock_property(rpi->firmware, data,
 					 RPI_FIRMWARE_SET_CLOCK_RATE, &_rate);
 	if (ret)
-		dev_err_ratelimited(rpi->dev, "Failed to change %s frequency: %d",
+		dev_err_ratelimited(rpi->dev, "Failed to change %s frequency: %d\n",
 				    clk_hw_get_name(hw), ret);
 
 	return ret;
@@ -288,7 +288,7 @@ static struct clk_hw *raspberrypi_clk_register(struct raspberrypi_clk *rpi,
 					 RPI_FIRMWARE_GET_MIN_CLOCK_RATE,
 					 &min_rate);
 	if (ret) {
-		dev_err(rpi->dev, "Failed to get clock %d min freq: %d",
+		dev_err(rpi->dev, "Failed to get clock %d min freq: %d\n",
 			id, ret);
 		return ERR_PTR(ret);
 	}
@@ -344,8 +344,13 @@ static int raspberrypi_discover_clocks(struct raspberrypi_clk *rpi,
 	struct rpi_firmware_get_clocks_response *clks;
 	int ret;
 
+	/*
+	 * The firmware doesn't guarantee that the last element of
+	 * RPI_FIRMWARE_GET_CLOCKS is zeroed. So allocate an additional
+	 * zero element as sentinel.
+	 */
 	clks = devm_kcalloc(rpi->dev,
-			    RPI_FIRMWARE_NUM_CLK_ID, sizeof(*clks),
+			    RPI_FIRMWARE_NUM_CLK_ID + 1, sizeof(*clks),
 			    GFP_KERNEL);
 	if (!clks)
 		return -ENOMEM;
@@ -360,7 +365,8 @@ static int raspberrypi_discover_clocks(struct raspberrypi_clk *rpi,
 		struct raspberrypi_clk_variant *variant;
 
 		if (clks->id > RPI_FIRMWARE_NUM_CLK_ID) {
-			dev_err(rpi->dev, "Unknown clock id: %u", clks->id);
+			dev_err(rpi->dev, "Unknown clock id: %u (max: %u)\n",
+					   clks->id, RPI_FIRMWARE_NUM_CLK_ID);
 			return -EINVAL;
 		}
 
diff --git a/drivers/clk/clk-tps68470.c b/drivers/clk/clk-tps68470.c
index e5fbefd6ac2d..38f44b5b9b1b 100644
--- a/drivers/clk/clk-tps68470.c
+++ b/drivers/clk/clk-tps68470.c
@@ -200,7 +200,9 @@ static int tps68470_clk_probe(struct platform_device *pdev)
 		.flags = CLK_SET_RATE_GATE,
 	};
 	struct tps68470_clkdata *tps68470_clkdata;
+	struct tps68470_clk_consumer *consumer;
 	int ret;
+	int i;
 
 	tps68470_clkdata = devm_kzalloc(&pdev->dev, sizeof(*tps68470_clkdata),
 					GFP_KERNEL);
@@ -223,10 +225,13 @@ static int tps68470_clk_probe(struct platform_device *pdev)
 		return ret;
 
 	if (pdata) {
-		ret = devm_clk_hw_register_clkdev(&pdev->dev,
-						  &tps68470_clkdata->clkout_hw,
-						  pdata->consumer_con_id,
-						  pdata->consumer_dev_name);
+		for (i = 0; i < pdata->n_consumers; i++) {
+			consumer = &pdata->consumers[i];
+			ret = devm_clk_hw_register_clkdev(&pdev->dev,
+							  &tps68470_clkdata->clkout_hw,
+							  consumer->consumer_con_id,
+							  consumer->consumer_dev_name);
+		}
 	}
 
 	return ret;
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 7fc191c15507..bd0b35cac83e 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -840,10 +840,9 @@ static void clk_core_unprepare(struct clk_core *core)
 	if (core->ops->unprepare)
 		core->ops->unprepare(core->hw);
 
-	clk_pm_runtime_put(core);
-
 	trace_clk_unprepare_complete(core);
 	clk_core_unprepare(core->parent);
+	clk_pm_runtime_put(core);
 }
 
 static void clk_core_unprepare_lock(struct clk_core *core)
diff --git a/drivers/clk/imx/clk-imx6sx.c b/drivers/clk/imx/clk-imx6sx.c
index fc1bd23d4583..598f3cf4eba4 100644
--- a/drivers/clk/imx/clk-imx6sx.c
+++ b/drivers/clk/imx/clk-imx6sx.c
@@ -280,13 +280,13 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	hws[IMX6SX_CLK_SSI3_SEL]           = imx_clk_hw_mux("ssi3_sel",         base + 0x1c,  14,     2,      ssi_sels,          ARRAY_SIZE(ssi_sels));
 	hws[IMX6SX_CLK_SSI2_SEL]           = imx_clk_hw_mux("ssi2_sel",         base + 0x1c,  12,     2,      ssi_sels,          ARRAY_SIZE(ssi_sels));
 	hws[IMX6SX_CLK_SSI1_SEL]           = imx_clk_hw_mux("ssi1_sel",         base + 0x1c,  10,     2,      ssi_sels,          ARRAY_SIZE(ssi_sels));
-	hws[IMX6SX_CLK_QSPI1_SEL]          = imx_clk_hw_mux_flags("qspi1_sel", base + 0x1c,  7, 3, qspi1_sels, ARRAY_SIZE(qspi1_sels), CLK_SET_RATE_PARENT);
+	hws[IMX6SX_CLK_QSPI1_SEL]          = imx_clk_hw_mux("qspi1_sel",        base + 0x1c,  7,      3,      qspi1_sels,        ARRAY_SIZE(qspi1_sels));
 	hws[IMX6SX_CLK_PERCLK_SEL]         = imx_clk_hw_mux("perclk_sel",       base + 0x1c,  6,      1,      perclk_sels,       ARRAY_SIZE(perclk_sels));
 	hws[IMX6SX_CLK_VID_SEL]            = imx_clk_hw_mux("vid_sel",          base + 0x20,  21,     3,      vid_sels,          ARRAY_SIZE(vid_sels));
 	hws[IMX6SX_CLK_ESAI_SEL]           = imx_clk_hw_mux("esai_sel",         base + 0x20,  19,     2,      audio_sels,        ARRAY_SIZE(audio_sels));
 	hws[IMX6SX_CLK_CAN_SEL]            = imx_clk_hw_mux("can_sel",          base + 0x20,  8,      2,      can_sels,          ARRAY_SIZE(can_sels));
 	hws[IMX6SX_CLK_UART_SEL]           = imx_clk_hw_mux("uart_sel",         base + 0x24,  6,      1,      uart_sels,         ARRAY_SIZE(uart_sels));
-	hws[IMX6SX_CLK_QSPI2_SEL]          = imx_clk_hw_mux_flags("qspi2_sel", base + 0x2c, 15, 3, qspi2_sels, ARRAY_SIZE(qspi2_sels), CLK_SET_RATE_PARENT);
+	hws[IMX6SX_CLK_QSPI2_SEL]          = imx_clk_hw_mux("qspi2_sel",        base + 0x2c,  15,     3,      qspi2_sels,        ARRAY_SIZE(qspi2_sels));
 	hws[IMX6SX_CLK_SPDIF_SEL]          = imx_clk_hw_mux("spdif_sel",        base + 0x30,  20,     2,      audio_sels,        ARRAY_SIZE(audio_sels));
 	hws[IMX6SX_CLK_AUDIO_SEL]          = imx_clk_hw_mux("audio_sel",        base + 0x30,  7,      2,      audio_sels,        ARRAY_SIZE(audio_sels));
 	hws[IMX6SX_CLK_ENET_PRE_SEL]       = imx_clk_hw_mux("enet_pre_sel",     base + 0x34,  15,     3,      enet_pre_sels,     ARRAY_SIZE(enet_pre_sels));
diff --git a/drivers/clk/imx/clk-imx93.c b/drivers/clk/imx/clk-imx93.c
index f5c9fa40491c..dcc41d178238 100644
--- a/drivers/clk/imx/clk-imx93.c
+++ b/drivers/clk/imx/clk-imx93.c
@@ -332,7 +332,7 @@ static struct platform_driver imx93_clk_driver = {
 	.driver = {
 		.name = "imx93-ccm",
 		.suppress_bind_attrs = true,
-		.of_match_table = of_match_ptr(imx93_clk_of_match),
+		.of_match_table = imx93_clk_of_match,
 	},
 };
 module_platform_driver(imx93_clk_driver);
diff --git a/drivers/clk/ingenic/tcu.c b/drivers/clk/ingenic/tcu.c
index 201bf6e6b6e0..d5544cbc5c48 100644
--- a/drivers/clk/ingenic/tcu.c
+++ b/drivers/clk/ingenic/tcu.c
@@ -101,15 +101,11 @@ static bool ingenic_tcu_enable_regs(struct clk_hw *hw)
 	bool enabled = false;
 
 	/*
-	 * If the SoC has no global TCU clock, we must ungate the channel's
-	 * clock to be able to access its registers.
-	 * If we have a TCU clock, it will be enabled automatically as it has
-	 * been attached to the regmap.
+	 * According to the programming manual, a timer channel's registers can
+	 * only be accessed when the channel's stop bit is clear.
 	 */
-	if (!tcu->clk) {
-		enabled = !!ingenic_tcu_is_enabled(hw);
-		regmap_write(tcu->map, TCU_REG_TSCR, BIT(info->gate_bit));
-	}
+	enabled = !!ingenic_tcu_is_enabled(hw);
+	regmap_write(tcu->map, TCU_REG_TSCR, BIT(info->gate_bit));
 
 	return enabled;
 }
@@ -120,8 +116,7 @@ static void ingenic_tcu_disable_regs(struct clk_hw *hw)
 	const struct ingenic_tcu_clk_info *info = tcu_clk->info;
 	struct ingenic_tcu *tcu = tcu_clk->tcu;
 
-	if (!tcu->clk)
-		regmap_write(tcu->map, TCU_REG_TSSR, BIT(info->gate_bit));
+	regmap_write(tcu->map, TCU_REG_TSSR, BIT(info->gate_bit));
 }
 
 static u8 ingenic_tcu_get_parent(struct clk_hw *hw)
diff --git a/drivers/clk/microchip/clk-mpfs.c b/drivers/clk/microchip/clk-mpfs.c
index 070c3b896559..b6b89413e090 100644
--- a/drivers/clk/microchip/clk-mpfs.c
+++ b/drivers/clk/microchip/clk-mpfs.c
@@ -239,6 +239,11 @@ static const struct clk_ops mpfs_clk_cfg_ops = {
 	.hw.init = CLK_HW_INIT(_name, _parent, &mpfs_clk_cfg_ops, 0),			\
 }
 
+#define CLK_CPU_OFFSET		0u
+#define CLK_AXI_OFFSET		1u
+#define CLK_AHB_OFFSET		2u
+#define CLK_RTCREF_OFFSET	3u
+
 static struct mpfs_cfg_hw_clock mpfs_cfg_clks[] = {
 	CLK_CFG(CLK_CPU, "clk_cpu", "clk_msspll", 0, 2, mpfs_div_cpu_axi_table, 0,
 		REG_CLOCK_CONFIG_CR),
@@ -362,7 +367,7 @@ static const struct clk_ops mpfs_periph_clk_ops = {
 				  _flags),					\
 }
 
-#define PARENT_CLK(PARENT) (&mpfs_cfg_clks[CLK_##PARENT].hw)
+#define PARENT_CLK(PARENT) (&mpfs_cfg_clks[CLK_##PARENT##_OFFSET].hw)
 
 /*
  * Critical clocks:
@@ -370,6 +375,8 @@ static const struct clk_ops mpfs_periph_clk_ops = {
  *   trap handler
  * - CLK_MMUART0: reserved by the hss
  * - CLK_DDRC: provides clock to the ddr subsystem
+ * - CLK_RTC: the onboard RTC's AHB bus clock must be kept running as the rtc will stop
+ *   if the AHB interface clock is disabled
  * - CLK_FICx: these provide the processor side clocks to the "FIC" (Fabric InterConnect)
  *   clock domain crossers which provide the interface to the FPGA fabric. Disabling them
  *   causes the FPGA fabric to go into reset.
@@ -394,7 +401,7 @@ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = {
 	CLK_PERIPH(CLK_CAN0, "clk_periph_can0", PARENT_CLK(AHB), 14, 0),
 	CLK_PERIPH(CLK_CAN1, "clk_periph_can1", PARENT_CLK(AHB), 15, 0),
 	CLK_PERIPH(CLK_USB, "clk_periph_usb", PARENT_CLK(AHB), 16, 0),
-	CLK_PERIPH(CLK_RTC, "clk_periph_rtc", PARENT_CLK(AHB), 18, 0),
+	CLK_PERIPH(CLK_RTC, "clk_periph_rtc", PARENT_CLK(AHB), 18, CLK_IS_CRITICAL),
 	CLK_PERIPH(CLK_QSPI, "clk_periph_qspi", PARENT_CLK(AHB), 19, 0),
 	CLK_PERIPH(CLK_GPIO0, "clk_periph_gpio0", PARENT_CLK(AHB), 20, 0),
 	CLK_PERIPH(CLK_GPIO1, "clk_periph_gpio1", PARENT_CLK(AHB), 21, 0),
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c
index 30056da3e0af..42568c616181 100644
--- a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c
@@ -1191,9 +1191,13 @@ static int sun50i_h6_ccu_probe(struct platform_device *pdev)
 	if (IS_ERR(reg))
 		return PTR_ERR(reg);
 
-	/* Force PLL_GPU output divider bits to 0 */
+	/*
+	 * Force PLL_GPU output divider bits to 0 and adjust
+	 * multiplier to sensible default value of 432 MHz.
+	 */
 	val = readl(reg + SUN50I_H6_PLL_GPU_REG);
-	val &= ~BIT(0);
+	val &= ~(GENMASK(15, 8) | BIT(0));
+	val |= 17 << 8;
 	writel(val, reg + SUN50I_H6_PLL_GPU_REG);
 
 	/* Force GPU_CLK divider bits to 0 */
diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c
index ef2a445c63a3..373e9438b57a 100644
--- a/drivers/clk/ti/clk.c
+++ b/drivers/clk/ti/clk.c
@@ -135,6 +135,7 @@ static struct device_node *ti_find_clock_provider(struct device_node *from,
 			continue;
 
 		if (!strncmp(n, tmp, strlen(tmp))) {
+			of_node_get(np);
 			found = true;
 			break;
 		}
diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c
index 62c2b7ac4339..4407203e0c9b 100644
--- a/drivers/counter/104-quad-8.c
+++ b/drivers/counter/104-quad-8.c
@@ -449,6 +449,9 @@ static int quad8_events_configure(struct counter_device *counter)
 			return -EINVAL;
 		}
 
+		/* Enable IRQ line */
+		irq_enabled |= BIT(event_node->channel);
+
 		/* Skip configuration if it is the same as previously set */
 		if (priv->irq_trigger[event_node->channel] == next_irq_trigger)
 			continue;
@@ -462,9 +465,6 @@ static int quad8_events_configure(struct counter_device *counter)
 			  priv->irq_trigger[event_node->channel] << 3;
 		iowrite8(QUAD8_CTR_IOR | ior_cfg,
 			 &priv->reg->channel[event_node->channel].control);
-
-		/* Enable IRQ line */
-		irq_enabled |= BIT(event_node->channel);
 	}
 
 	iowrite8(irq_enabled, &priv->reg->index_interrupt);
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 9ac75c1cde9c..f52b8f2fe529 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -46,8 +46,8 @@
 #include <asm/cpu_device_id.h>
 #include "amd-pstate-trace.h"
 
-#define AMD_PSTATE_TRANSITION_LATENCY	0x20000
-#define AMD_PSTATE_TRANSITION_DELAY	500
+#define AMD_PSTATE_TRANSITION_LATENCY	20000
+#define AMD_PSTATE_TRANSITION_DELAY	1000
 
 /*
  * TODO: We need more time to fine tune processors with shared memory solution
@@ -120,7 +120,7 @@ struct amd_cpudata {
 	struct amd_aperf_mperf cur;
 	struct amd_aperf_mperf prev;
 
-	u64 freq;
+	u64 	freq;
 	bool	boost_supported;
 };
 
@@ -152,6 +152,7 @@ static inline int amd_pstate_enable(bool enable)
 static int pstate_init_perf(struct amd_cpudata *cpudata)
 {
 	u64 cap1;
+	u32 highest_perf;
 
 	int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1,
 				     &cap1);
@@ -163,7 +164,11 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 	 *
 	 * CPPC entry doesn't indicate the highest performance in some ASICs.
 	 */
-	WRITE_ONCE(cpudata->highest_perf, amd_get_highest_perf());
+	highest_perf = amd_get_highest_perf();
+	if (highest_perf > AMD_CPPC_HIGHEST_PERF(cap1))
+		highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
+
+	WRITE_ONCE(cpudata->highest_perf, highest_perf);
 
 	WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1));
@@ -175,12 +180,17 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 static int cppc_init_perf(struct amd_cpudata *cpudata)
 {
 	struct cppc_perf_caps cppc_perf;
+	u32 highest_perf;
 
 	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
 	if (ret)
 		return ret;
 
-	WRITE_ONCE(cpudata->highest_perf, amd_get_highest_perf());
+	highest_perf = amd_get_highest_perf();
+	if (highest_perf > cppc_perf.highest_perf)
+		highest_perf = cppc_perf.highest_perf;
+
+	WRITE_ONCE(cpudata->highest_perf, highest_perf);
 
 	WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf);
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
@@ -269,6 +279,7 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
 	u64 prev = READ_ONCE(cpudata->cppc_req_cached);
 	u64 value = prev;
 
+	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
 	value &= ~AMD_CPPC_MIN_PERF(~0L);
 	value |= AMD_CPPC_MIN_PERF(min_perf);
 
@@ -312,7 +323,7 @@ static int amd_pstate_target(struct cpufreq_policy *policy,
 		return -ENODEV;
 
 	cap_perf = READ_ONCE(cpudata->highest_perf);
-	min_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
+	min_perf = READ_ONCE(cpudata->lowest_perf);
 	max_perf = cap_perf;
 
 	freqs.old = policy->cur;
@@ -357,8 +368,6 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
 	if (max_perf < min_perf)
 		max_perf = min_perf;
 
-	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
-
 	amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true);
 }
 
@@ -555,9 +564,7 @@ free_cpudata1:
 
 static int amd_pstate_cpu_exit(struct cpufreq_policy *policy)
 {
-	struct amd_cpudata *cpudata;
-
-	cpudata = policy->driver_data;
+	struct amd_cpudata *cpudata = policy->driver_data;
 
 	freq_qos_remove_request(&cpudata->req[1]);
 	freq_qos_remove_request(&cpudata->req[0]);
@@ -599,9 +606,7 @@ static ssize_t show_amd_pstate_max_freq(struct cpufreq_policy *policy,
 					char *buf)
 {
 	int max_freq;
-	struct amd_cpudata *cpudata;
-
-	cpudata = policy->driver_data;
+	struct amd_cpudata *cpudata = policy->driver_data;
 
 	max_freq = amd_get_max_freq(cpudata);
 	if (max_freq < 0)
@@ -614,9 +619,7 @@ static ssize_t show_amd_pstate_lowest_nonlinear_freq(struct cpufreq_policy *poli
 						     char *buf)
 {
 	int freq;
-	struct amd_cpudata *cpudata;
-
-	cpudata = policy->driver_data;
+	struct amd_cpudata *cpudata = policy->driver_data;
 
 	freq = amd_get_lowest_nonlinear_freq(cpudata);
 	if (freq < 0)
@@ -662,7 +665,7 @@ static struct cpufreq_driver amd_pstate_driver = {
 	.resume		= amd_pstate_cpu_resume,
 	.set_boost	= amd_pstate_set_boost,
 	.name		= "amd-pstate",
-	.attr           = amd_pstate_attr,
+	.attr		= amd_pstate_attr,
 };
 
 static int __init amd_pstate_init(void)
@@ -673,7 +676,7 @@ static int __init amd_pstate_init(void)
 		return -ENODEV;
 
 	if (!acpi_cpc_valid()) {
-		pr_debug("the _CPC object is not present in SBIOS\n");
+		pr_warn_once("the _CPC object is not present in SBIOS or ACPI disabled\n");
 		return -ENODEV;
 	}
 
diff --git a/drivers/cpufreq/bmips-cpufreq.c b/drivers/cpufreq/bmips-cpufreq.c
index f7c23fa468f0..39221a9a187a 100644
--- a/drivers/cpufreq/bmips-cpufreq.c
+++ b/drivers/cpufreq/bmips-cpufreq.c
@@ -156,7 +156,7 @@ static struct cpufreq_driver bmips_cpufreq_driver = {
 	.name		= BMIPS_CPUFREQ_PREFIX,
 };
 
-static int __init bmips_cpufreq_probe(void)
+static int __init bmips_cpufreq_driver_init(void)
 {
 	struct cpufreq_compat *cc;
 	struct device_node *np;
@@ -176,7 +176,13 @@ static int __init bmips_cpufreq_probe(void)
 
 	return cpufreq_register_driver(&bmips_cpufreq_driver);
 }
-device_initcall(bmips_cpufreq_probe);
+module_init(bmips_cpufreq_driver_init);
+
+static void __exit bmips_cpufreq_driver_exit(void)
+{
+	cpufreq_unregister_driver(&bmips_cpufreq_driver);
+}
+module_exit(bmips_cpufreq_driver_exit);
 
 MODULE_AUTHOR("Markus Mayer <mmayer@broadcom.com>");
 MODULE_DESCRIPTION("CPUfreq driver for Broadcom BMIPS SoCs");
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 24eaf0ec344d..432dfb4e8027 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -63,7 +63,15 @@ static struct cppc_workaround_oem_info wa_info[] = {
 
 static struct cpufreq_driver cppc_cpufreq_driver;
 
+static enum {
+	FIE_UNSET = -1,
+	FIE_ENABLED,
+	FIE_DISABLED
+} fie_disabled = FIE_UNSET;
+
 #ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE
+module_param(fie_disabled, int, 0444);
+MODULE_PARM_DESC(fie_disabled, "Disable Frequency Invariance Engine (FIE)");
 
 /* Frequency invariance support */
 struct cppc_freq_invariance {
@@ -158,7 +166,7 @@ static void cppc_cpufreq_cpu_fie_init(struct cpufreq_policy *policy)
 	struct cppc_freq_invariance *cppc_fi;
 	int cpu, ret;
 
-	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
+	if (fie_disabled)
 		return;
 
 	for_each_cpu(cpu, policy->cpus) {
@@ -199,7 +207,7 @@ static void cppc_cpufreq_cpu_fie_exit(struct cpufreq_policy *policy)
 	struct cppc_freq_invariance *cppc_fi;
 	int cpu;
 
-	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
+	if (fie_disabled)
 		return;
 
 	/* policy->cpus will be empty here, use related_cpus instead */
@@ -229,7 +237,15 @@ static void __init cppc_freq_invariance_init(void)
 	};
 	int ret;
 
-	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
+	if (fie_disabled != FIE_ENABLED && fie_disabled != FIE_DISABLED) {
+		fie_disabled = FIE_ENABLED;
+		if (cppc_perf_ctrs_in_pcc()) {
+			pr_info("FIE not enabled on systems with registers in PCC\n");
+			fie_disabled = FIE_DISABLED;
+		}
+	}
+
+	if (fie_disabled)
 		return;
 
 	kworker_fie = kthread_create_worker(0, "cppc_fie");
@@ -247,7 +263,7 @@ static void __init cppc_freq_invariance_init(void)
 
 static void cppc_freq_invariance_exit(void)
 {
-	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
+	if (fie_disabled)
 		return;
 
 	kthread_destroy_worker(kworker_fie);
@@ -936,6 +952,7 @@ static void cppc_check_hisi_workaround(void)
 		    wa_info[i].oem_revision == tbl->oem_revision) {
 			/* Overwrite the get() callback */
 			cppc_cpufreq_driver.get = hisi_cppc_cpufreq_get_rate;
+			fie_disabled = FIE_DISABLED;
 			break;
 		}
 	}
@@ -947,7 +964,7 @@ static int __init cppc_cpufreq_init(void)
 {
 	int ret;
 
-	if ((acpi_disabled) || !acpi_cpc_valid())
+	if (!acpi_cpc_valid())
 		return -ENODEV;
 
 	cppc_check_hisi_workaround();
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 2c96de3f2d83..6ac3800db450 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -146,6 +146,7 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "qcom,sc8180x", },
 	{ .compatible = "qcom,sc8280xp", },
 	{ .compatible = "qcom,sdm845", },
+	{ .compatible = "qcom,sm6115", },
 	{ .compatible = "qcom,sm6350", },
 	{ .compatible = "qcom,sm8150", },
 	{ .compatible = "qcom,sm8250", },
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 7820c4e74289..69b3d61852ac 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -532,7 +532,7 @@ static unsigned int __resolve_freq(struct cpufreq_policy *policy,
 
 	target_freq = clamp_val(target_freq, policy->min, policy->max);
 
-	if (!cpufreq_driver->target_index)
+	if (!policy->freq_table)
 		return target_freq;
 
 	idx = cpufreq_frequency_table_target(policy, target_freq, relation);
diff --git a/drivers/cpufreq/highbank-cpufreq.c b/drivers/cpufreq/highbank-cpufreq.c
index ac57cddc5f2f..a45864701143 100644
--- a/drivers/cpufreq/highbank-cpufreq.c
+++ b/drivers/cpufreq/highbank-cpufreq.c
@@ -55,7 +55,7 @@ static struct notifier_block hb_cpufreq_clk_nb = {
 	.notifier_call = hb_cpufreq_clk_notify,
 };
 
-static int hb_cpufreq_driver_init(void)
+static int __init hb_cpufreq_driver_init(void)
 {
 	struct platform_device_info devinfo = { .name = "cpufreq-dt", };
 	struct device *cpu_dev;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 57cdb3679885..fc3ebeb0bbe5 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2416,6 +2416,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	X86_MATCH(SKYLAKE_X,		core_funcs),
 	X86_MATCH(COMETLAKE,		core_funcs),
 	X86_MATCH(ICELAKE_X,		core_funcs),
+	X86_MATCH(TIGERLAKE,		core_funcs),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index d5ef3c66c762..833589bc95e4 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -13,6 +13,7 @@
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <linux/pm_opp.h>
+#include <linux/pm_qos.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/units.h>
@@ -56,6 +57,8 @@ struct qcom_cpufreq_data {
 	struct cpufreq_policy *policy;
 
 	bool per_core_dcvs;
+
+	struct freq_qos_request throttle_freq_req;
 };
 
 static unsigned long cpu_hw_rate, xo_rate;
@@ -316,14 +319,16 @@ static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
 	if (IS_ERR(opp)) {
 		dev_warn(dev, "Can't find the OPP for throttling: %pe!\n", opp);
 	} else {
-		throttled_freq = freq_hz / HZ_PER_KHZ;
-
-		/* Update thermal pressure (the boost frequencies are accepted) */
-		arch_update_thermal_pressure(policy->related_cpus, throttled_freq);
-
 		dev_pm_opp_put(opp);
 	}
 
+	throttled_freq = freq_hz / HZ_PER_KHZ;
+
+	freq_qos_update_request(&data->throttle_freq_req, throttled_freq);
+
+	/* Update thermal pressure (the boost frequencies are accepted) */
+	arch_update_thermal_pressure(policy->related_cpus, throttled_freq);
+
 	/*
 	 * In the unlikely case policy is unregistered do not enable
 	 * polling or h/w interrupt
@@ -413,6 +418,14 @@ static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index)
 	if (data->throttle_irq < 0)
 		return data->throttle_irq;
 
+	ret = freq_qos_add_request(&policy->constraints,
+				   &data->throttle_freq_req, FREQ_QOS_MAX,
+				   FREQ_QOS_MAX_DEFAULT_VALUE);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to add freq constraint (%d)\n", ret);
+		return ret;
+	}
+
 	data->cancel_throttle = false;
 	data->policy = policy;
 
@@ -479,6 +492,7 @@ static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data)
 	if (data->throttle_irq <= 0)
 		return;
 
+	freq_qos_remove_request(&data->throttle_freq_req);
 	free_irq(data->throttle_irq, data);
 }
 
diff --git a/drivers/cpufreq/sti-cpufreq.c b/drivers/cpufreq/sti-cpufreq.c
index a67df90848c2..1a63aeea8711 100644
--- a/drivers/cpufreq/sti-cpufreq.c
+++ b/drivers/cpufreq/sti-cpufreq.c
@@ -252,7 +252,7 @@ static int sti_cpufreq_fetch_syscon_registers(void)
 	return 0;
 }
 
-static int sti_cpufreq_init(void)
+static int __init sti_cpufreq_init(void)
 {
 	int ret;
 
diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c
index 1216046cf4c2..c2004cae3f02 100644
--- a/drivers/cpufreq/tegra194-cpufreq.c
+++ b/drivers/cpufreq/tegra194-cpufreq.c
@@ -38,14 +38,6 @@
 /* cpufreq transisition latency */
 #define TEGRA_CPUFREQ_TRANSITION_LATENCY (300 * 1000) /* unit in nanoseconds */
 
-enum cluster {
-	CLUSTER0,
-	CLUSTER1,
-	CLUSTER2,
-	CLUSTER3,
-	MAX_CLUSTERS,
-};
-
 struct tegra_cpu_ctr {
 	u32 cpu;
 	u32 coreclk_cnt, last_coreclk_cnt;
@@ -67,12 +59,12 @@ struct tegra_cpufreq_ops {
 struct tegra_cpufreq_soc {
 	struct tegra_cpufreq_ops *ops;
 	int maxcpus_per_cluster;
+	unsigned int num_clusters;
 	phys_addr_t actmon_cntr_base;
 };
 
 struct tegra194_cpufreq_data {
 	void __iomem *regs;
-	size_t num_clusters;
 	struct cpufreq_frequency_table **tables;
 	const struct tegra_cpufreq_soc *soc;
 };
@@ -166,6 +158,14 @@ static const struct tegra_cpufreq_soc tegra234_cpufreq_soc = {
 	.ops = &tegra234_cpufreq_ops,
 	.actmon_cntr_base = 0x9000,
 	.maxcpus_per_cluster = 4,
+	.num_clusters = 3,
+};
+
+static const struct tegra_cpufreq_soc tegra239_cpufreq_soc = {
+	.ops = &tegra234_cpufreq_ops,
+	.actmon_cntr_base = 0x4000,
+	.maxcpus_per_cluster = 8,
+	.num_clusters = 1,
 };
 
 static void tegra194_get_cpu_cluster_id(u32 cpu, u32 *cpuid, u32 *clusterid)
@@ -314,11 +314,7 @@ static void tegra194_get_cpu_ndiv_sysreg(void *ndiv)
 
 static int tegra194_get_cpu_ndiv(u32 cpu, u32 cpuid, u32 clusterid, u64 *ndiv)
 {
-	int ret;
-
-	ret = smp_call_function_single(cpu, tegra194_get_cpu_ndiv_sysreg, &ndiv, true);
-
-	return ret;
+	return smp_call_function_single(cpu, tegra194_get_cpu_ndiv_sysreg, &ndiv, true);
 }
 
 static void tegra194_set_cpu_ndiv_sysreg(void *data)
@@ -382,7 +378,7 @@ static int tegra194_cpufreq_init(struct cpufreq_policy *policy)
 
 	data->soc->ops->get_cpu_cluster_id(policy->cpu, NULL, &clusterid);
 
-	if (clusterid >= data->num_clusters || !data->tables[clusterid])
+	if (clusterid >= data->soc->num_clusters || !data->tables[clusterid])
 		return -EINVAL;
 
 	start_cpu = rounddown(policy->cpu, maxcpus_per_cluster);
@@ -433,6 +429,7 @@ static struct tegra_cpufreq_ops tegra194_cpufreq_ops = {
 static const struct tegra_cpufreq_soc tegra194_cpufreq_soc = {
 	.ops = &tegra194_cpufreq_ops,
 	.maxcpus_per_cluster = 2,
+	.num_clusters = 4,
 };
 
 static void tegra194_cpufreq_free_resources(void)
@@ -525,15 +522,14 @@ static int tegra194_cpufreq_probe(struct platform_device *pdev)
 
 	soc = of_device_get_match_data(&pdev->dev);
 
-	if (soc->ops && soc->maxcpus_per_cluster) {
+	if (soc->ops && soc->maxcpus_per_cluster && soc->num_clusters) {
 		data->soc = soc;
 	} else {
 		dev_err(&pdev->dev, "soc data missing\n");
 		return -EINVAL;
 	}
 
-	data->num_clusters = MAX_CLUSTERS;
-	data->tables = devm_kcalloc(&pdev->dev, data->num_clusters,
+	data->tables = devm_kcalloc(&pdev->dev, data->soc->num_clusters,
 				    sizeof(*data->tables), GFP_KERNEL);
 	if (!data->tables)
 		return -ENOMEM;
@@ -558,7 +554,7 @@ static int tegra194_cpufreq_probe(struct platform_device *pdev)
 		goto put_bpmp;
 	}
 
-	for (i = 0; i < data->num_clusters; i++) {
+	for (i = 0; i < data->soc->num_clusters; i++) {
 		data->tables[i] = init_freq_table(pdev, bpmp, i);
 		if (IS_ERR(data->tables[i])) {
 			err = PTR_ERR(data->tables[i]);
@@ -590,6 +586,7 @@ static int tegra194_cpufreq_remove(struct platform_device *pdev)
 static const struct of_device_id tegra194_cpufreq_of_match[] = {
 	{ .compatible = "nvidia,tegra194-ccplex", .data = &tegra194_cpufreq_soc },
 	{ .compatible = "nvidia,tegra234-ccplex-cluster", .data = &tegra234_cpufreq_soc },
+	{ .compatible = "nvidia,tegra239-ccplex-cluster", .data = &tegra239_cpufreq_soc },
 	{ /* sentinel */ }
 };
 
diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c
index df85a77d476b..f64180dd2005 100644
--- a/drivers/cpufreq/ti-cpufreq.c
+++ b/drivers/cpufreq/ti-cpufreq.c
@@ -398,7 +398,7 @@ fail_put_node:
 	return ret;
 }
 
-static int ti_cpufreq_init(void)
+static int __init ti_cpufreq_init(void)
 {
 	const struct of_device_id *match;
 
diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c
index 74068742cef3..9acde71558d5 100644
--- a/drivers/cpuidle/coupled.c
+++ b/drivers/cpuidle/coupled.c
@@ -54,7 +54,7 @@
  * variable is not locked.  It is only written from the cpu that
  * it stores (or by the on/offlining cpu if that cpu is offline),
  * and only read after all the cpus are ready for the coupled idle
- * state are are no longer updating it.
+ * state are no longer updating it.
  *
  * Three atomic counters are used.  alive_count tracks the number
  * of cpus in the coupled set that are currently or soon will be
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index c32c600b3cf8..0b5461b3d7dd 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -233,8 +233,8 @@ static inline void add_powernv_state(int index, const char *name,
 				     unsigned int exit_latency,
 				     u64 psscr_val, u64 psscr_mask)
 {
-	strlcpy(powernv_states[index].name, name, CPUIDLE_NAME_LEN);
-	strlcpy(powernv_states[index].desc, name, CPUIDLE_NAME_LEN);
+	strscpy(powernv_states[index].name, name, CPUIDLE_NAME_LEN);
+	strscpy(powernv_states[index].desc, name, CPUIDLE_NAME_LEN);
 	powernv_states[index].flags = flags;
 	powernv_states[index].target_residency = target_residency;
 	powernv_states[index].exit_latency = exit_latency;
diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c
index 29acaf48e575..0d0f9751ff8f 100644
--- a/drivers/cpuidle/governor.c
+++ b/drivers/cpuidle/governor.c
@@ -63,12 +63,11 @@ int cpuidle_switch_governor(struct cpuidle_governor *gov)
 
 	cpuidle_curr_governor = gov;
 
-	if (gov) {
-		list_for_each_entry(dev, &cpuidle_detected_devices, device_list)
-			cpuidle_enable_device(dev);
-		cpuidle_install_idle_handler();
-		printk(KERN_INFO "cpuidle: using governor %s\n", gov->name);
-	}
+	list_for_each_entry(dev, &cpuidle_detected_devices, device_list)
+		cpuidle_enable_device(dev);
+
+	cpuidle_install_idle_handler();
+	pr_info("cpuidle: using governor %s\n", gov->name);
 
 	return 0;
 }
diff --git a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c
index 2a60d0525cde..168195672e2e 100644
--- a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c
+++ b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c
@@ -56,6 +56,10 @@ static void virtio_crypto_akcipher_finalize_req(
 	struct virtio_crypto_akcipher_request *vc_akcipher_req,
 	struct akcipher_request *req, int err)
 {
+	kfree(vc_akcipher_req->src_buf);
+	kfree(vc_akcipher_req->dst_buf);
+	vc_akcipher_req->src_buf = NULL;
+	vc_akcipher_req->dst_buf = NULL;
 	virtcrypto_clear_request(&vc_akcipher_req->base);
 
 	crypto_finalize_akcipher_request(vc_akcipher_req->base.dataq->engine, req, err);
diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c
index cb6401c9e9a4..acf31cc1dbcc 100644
--- a/drivers/dax/hmem/device.c
+++ b/drivers/dax/hmem/device.c
@@ -15,6 +15,7 @@ void hmem_register_device(int target_nid, struct resource *r)
 		.start = r->start,
 		.end = r->end,
 		.flags = IORESOURCE_MEM,
+		.desc = IORES_DESC_SOFT_RESERVED,
 	};
 	struct platform_device *pdev;
 	struct memregion_info info;
diff --git a/drivers/devfreq/event/rockchip-dfi.c b/drivers/devfreq/event/rockchip-dfi.c
index 9a88faaf8b27..39ac069cabc7 100644
--- a/drivers/devfreq/event/rockchip-dfi.c
+++ b/drivers/devfreq/event/rockchip-dfi.c
@@ -189,10 +189,9 @@ static int rockchip_dfi_probe(struct platform_device *pdev)
 		return PTR_ERR(data->regs);
 
 	data->clk = devm_clk_get(dev, "pclk_ddr_mon");
-	if (IS_ERR(data->clk)) {
-		dev_err(dev, "Cannot get the clk dmc_clk\n");
-		return PTR_ERR(data->clk);
-	}
+	if (IS_ERR(data->clk))
+		return dev_err_probe(dev, PTR_ERR(data->clk),
+				     "Cannot get the clk pclk_ddr_mon\n");
 
 	/* try to find the optional reference to the pmu syscon */
 	node = of_parse_phandle(np, "rockchip,pmu", 0);
diff --git a/drivers/devfreq/mtk-cci-devfreq.c b/drivers/devfreq/mtk-cci-devfreq.c
index 71abb3fbd042..e5458ada5197 100644
--- a/drivers/devfreq/mtk-cci-devfreq.c
+++ b/drivers/devfreq/mtk-cci-devfreq.c
@@ -291,9 +291,13 @@ static int mtk_ccifreq_probe(struct platform_device *pdev)
 	}
 
 	drv->sram_reg = devm_regulator_get_optional(dev, "sram");
-	if (IS_ERR(drv->sram_reg))
+	if (IS_ERR(drv->sram_reg)) {
+		ret = PTR_ERR(drv->sram_reg);
+		if (ret == -EPROBE_DEFER)
+			goto out_free_resources;
+
 		drv->sram_reg = NULL;
-	else {
+	} else {
 		ret = regulator_enable(drv->sram_reg);
 		if (ret) {
 			dev_err(dev, "failed to enable sram regulator\n");
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 205acb2c744d..e3885c90a3ac 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -295,7 +295,8 @@ void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence,
 		enum dma_resv_usage old_usage;
 
 		dma_resv_list_entry(fobj, i, obj, &old, &old_usage);
-		if ((old->context == fence->context && old_usage >= usage) ||
+		if ((old->context == fence->context && old_usage >= usage &&
+		     dma_fence_is_later(fence, old)) ||
 		    dma_fence_is_signaled(old)) {
 			dma_resv_list_set(fobj, i, fence, usage);
 			dma_fence_put(old);
diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c
index d4f1e4e9603a..85e00701473c 100644
--- a/drivers/dma/ti/k3-udma-private.c
+++ b/drivers/dma/ti/k3-udma-private.c
@@ -31,14 +31,14 @@ struct udma_dev *of_xudma_dev_get(struct device_node *np, const char *property)
 	}
 
 	pdev = of_find_device_by_node(udma_node);
+	if (np != udma_node)
+		of_node_put(udma_node);
+
 	if (!pdev) {
 		pr_debug("UDMA device not found\n");
 		return ERR_PTR(-EPROBE_DEFER);
 	}
 
-	if (np != udma_node)
-		of_node_put(udma_node);
-
 	ud = platform_get_drvdata(pdev);
 	if (!ud) {
 		pr_debug("UDMA has not been probed\n");
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index 6276934d4d2b..8cd4e69dc7b4 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -3040,9 +3040,10 @@ static int xilinx_dma_probe(struct platform_device *pdev)
 
 	/* Request and map I/O memory */
 	xdev->regs = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(xdev->regs))
-		return PTR_ERR(xdev->regs);
-
+	if (IS_ERR(xdev->regs)) {
+		err = PTR_ERR(xdev->regs);
+		goto disable_clks;
+	}
 	/* Retrieve the DMA engine properties from the device tree */
 	xdev->max_buffer_len = GENMASK(XILINX_DMA_MAX_TRANS_LEN_MAX - 1, 0);
 	xdev->s2mm_chan_id = xdev->dma_config->max_channels / 2;
@@ -3070,7 +3071,7 @@ static int xilinx_dma_probe(struct platform_device *pdev)
 		if (err < 0) {
 			dev_err(xdev->dev,
 				"missing xlnx,num-fstores property\n");
-			return err;
+			goto disable_clks;
 		}
 
 		err = of_property_read_u32(node, "xlnx,flush-fsync",
@@ -3090,7 +3091,11 @@ static int xilinx_dma_probe(struct platform_device *pdev)
 		xdev->ext_addr = false;
 
 	/* Set the dma mask bits */
-	dma_set_mask_and_coherent(xdev->dev, DMA_BIT_MASK(addr_width));
+	err = dma_set_mask_and_coherent(xdev->dev, DMA_BIT_MASK(addr_width));
+	if (err < 0) {
+		dev_err(xdev->dev, "DMA mask error %d\n", err);
+		goto disable_clks;
+	}
 
 	/* Initialize the DMA engine */
 	xdev->common.dev = &pdev->dev;
@@ -3137,7 +3142,7 @@ static int xilinx_dma_probe(struct platform_device *pdev)
 	for_each_child_of_node(node, child) {
 		err = xilinx_dma_child_probe(xdev, child);
 		if (err < 0)
-			goto disable_clks;
+			goto error;
 	}
 
 	if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) {
@@ -3172,12 +3177,12 @@ static int xilinx_dma_probe(struct platform_device *pdev)
 
 	return 0;
 
-disable_clks:
-	xdma_disable_allclks(xdev);
 error:
 	for (i = 0; i < xdev->dma_config->max_channels; i++)
 		if (xdev->chan[i])
 			xilinx_dma_chan_remove(xdev->chan[i]);
+disable_clks:
+	xdma_disable_allclks(xdev);
 
 	return err;
 }
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
index dc299ab36818..3f4ee3954384 100644
--- a/drivers/dma/xilinx/zynqmp_dma.c
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -849,7 +849,7 @@ static struct dma_async_tx_descriptor *zynqmp_dma_prep_memcpy(
 
 	zynqmp_dma_desc_config_eod(chan, desc);
 	async_tx_ack(&first->async_tx);
-	first->async_tx.flags = flags;
+	first->async_tx.flags = (enum dma_ctrl_flags)flags;
 	return &first->async_tx;
 }
 
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index eb58644bb019..6faeb2ab3960 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -103,7 +103,6 @@ static void edac_mc_dump_dimm(struct dimm_info *dimm)
 	edac_dbg(4, "  dimm->label = '%s'\n", dimm->label);
 	edac_dbg(4, "  dimm->nr_pages = 0x%x\n", dimm->nr_pages);
 	edac_dbg(4, "  dimm->grain = %d\n", dimm->grain);
-	edac_dbg(4, "  dimm->nr_pages = 0x%x\n", dimm->nr_pages);
 }
 
 static void edac_mc_dump_csrow(struct csrow_info *csrow)
diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h
index 96f6de0c8ff6..50ed9f2425bb 100644
--- a/drivers/edac/edac_module.h
+++ b/drivers/edac/edac_module.h
@@ -28,13 +28,9 @@ void edac_mc_sysfs_exit(void);
 extern int edac_create_sysfs_mci_device(struct mem_ctl_info *mci,
 					const struct attribute_group **groups);
 extern void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci);
-extern int edac_get_log_ue(void);
-extern int edac_get_log_ce(void);
-extern int edac_get_panic_on_ue(void);
 extern int edac_mc_get_log_ue(void);
 extern int edac_mc_get_log_ce(void);
 extern int edac_mc_get_panic_on_ue(void);
-extern int edac_get_poll_msec(void);
 extern unsigned int edac_mc_get_poll_msec(void);
 
 unsigned edac_dimm_info_location(struct dimm_info *dimm, char *buf,
diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c
index 6cf50ee0b77c..a22ea053f8e1 100644
--- a/drivers/edac/i10nm_base.c
+++ b/drivers/edac/i10nm_base.c
@@ -74,31 +74,47 @@ static struct list_head *i10nm_edac_list;
 
 static struct res_config *res_cfg;
 static int retry_rd_err_log;
+static int decoding_via_mca;
+static bool mem_cfg_2lm;
 
 static u32 offsets_scrub_icx[]  = {0x22c60, 0x22c54, 0x22c5c, 0x22c58, 0x22c28, 0x20ed8};
 static u32 offsets_scrub_spr[]  = {0x22c60, 0x22c54, 0x22f08, 0x22c58, 0x22c28, 0x20ed8};
+static u32 offsets_scrub_spr_hbm0[]  = {0x2860, 0x2854, 0x2b08, 0x2858, 0x2828, 0x0ed8};
+static u32 offsets_scrub_spr_hbm1[]  = {0x2c60, 0x2c54, 0x2f08, 0x2c58, 0x2c28, 0x0fa8};
 static u32 offsets_demand_icx[] = {0x22e54, 0x22e60, 0x22e64, 0x22e58, 0x22e5c, 0x20ee0};
 static u32 offsets_demand_spr[] = {0x22e54, 0x22e60, 0x22f10, 0x22e58, 0x22e5c, 0x20ee0};
+static u32 offsets_demand2_spr[] = {0x22c70, 0x22d80, 0x22f18, 0x22d58, 0x22c64, 0x20f10};
+static u32 offsets_demand_spr_hbm0[] = {0x2a54, 0x2a60, 0x2b10, 0x2a58, 0x2a5c, 0x0ee0};
+static u32 offsets_demand_spr_hbm1[] = {0x2e54, 0x2e60, 0x2f10, 0x2e58, 0x2e5c, 0x0fb0};
 
-static void __enable_retry_rd_err_log(struct skx_imc *imc, int chan, bool enable)
+static void __enable_retry_rd_err_log(struct skx_imc *imc, int chan, bool enable,
+				      u32 *offsets_scrub, u32 *offsets_demand,
+				      u32 *offsets_demand2)
 {
-	u32 s, d;
+	u32 s, d, d2;
 
-	if (!imc->mbase)
-		return;
-
-	s = I10NM_GET_REG32(imc, chan, res_cfg->offsets_scrub[0]);
-	d = I10NM_GET_REG32(imc, chan, res_cfg->offsets_demand[0]);
+	s = I10NM_GET_REG32(imc, chan, offsets_scrub[0]);
+	d = I10NM_GET_REG32(imc, chan, offsets_demand[0]);
+	if (offsets_demand2)
+		d2 = I10NM_GET_REG32(imc, chan, offsets_demand2[0]);
 
 	if (enable) {
 		/* Save default configurations */
 		imc->chan[chan].retry_rd_err_log_s = s;
 		imc->chan[chan].retry_rd_err_log_d = d;
+		if (offsets_demand2)
+			imc->chan[chan].retry_rd_err_log_d2 = d2;
 
 		s &= ~RETRY_RD_ERR_LOG_NOOVER_UC;
 		s |=  RETRY_RD_ERR_LOG_EN;
 		d &= ~RETRY_RD_ERR_LOG_NOOVER_UC;
 		d |=  RETRY_RD_ERR_LOG_EN;
+
+		if (offsets_demand2) {
+			d2 &= ~RETRY_RD_ERR_LOG_UC;
+			d2 |=  RETRY_RD_ERR_LOG_NOOVER;
+			d2 |=  RETRY_RD_ERR_LOG_EN;
+		}
 	} else {
 		/* Restore default configurations */
 		if (imc->chan[chan].retry_rd_err_log_s & RETRY_RD_ERR_LOG_UC)
@@ -113,23 +129,55 @@ static void __enable_retry_rd_err_log(struct skx_imc *imc, int chan, bool enable
 			d |=  RETRY_RD_ERR_LOG_NOOVER;
 		if (!(imc->chan[chan].retry_rd_err_log_d & RETRY_RD_ERR_LOG_EN))
 			d &= ~RETRY_RD_ERR_LOG_EN;
+
+		if (offsets_demand2) {
+			if (imc->chan[chan].retry_rd_err_log_d2 & RETRY_RD_ERR_LOG_UC)
+				d2 |=  RETRY_RD_ERR_LOG_UC;
+			if (!(imc->chan[chan].retry_rd_err_log_d2 & RETRY_RD_ERR_LOG_NOOVER))
+				d2 &=  ~RETRY_RD_ERR_LOG_NOOVER;
+			if (!(imc->chan[chan].retry_rd_err_log_d2 & RETRY_RD_ERR_LOG_EN))
+				d2 &= ~RETRY_RD_ERR_LOG_EN;
+		}
 	}
 
-	I10NM_SET_REG32(imc, chan, res_cfg->offsets_scrub[0], s);
-	I10NM_SET_REG32(imc, chan, res_cfg->offsets_demand[0], d);
+	I10NM_SET_REG32(imc, chan, offsets_scrub[0], s);
+	I10NM_SET_REG32(imc, chan, offsets_demand[0], d);
+	if (offsets_demand2)
+		I10NM_SET_REG32(imc, chan, offsets_demand2[0], d2);
 }
 
 static void enable_retry_rd_err_log(bool enable)
 {
+	struct skx_imc *imc;
 	struct skx_dev *d;
 	int i, j;
 
 	edac_dbg(2, "\n");
 
 	list_for_each_entry(d, i10nm_edac_list, list)
-		for (i = 0; i < I10NM_NUM_IMC; i++)
-			for (j = 0; j < I10NM_NUM_CHANNELS; j++)
-				__enable_retry_rd_err_log(&d->imc[i], j, enable);
+		for (i = 0; i < I10NM_NUM_IMC; i++) {
+			imc = &d->imc[i];
+			if (!imc->mbase)
+				continue;
+
+			for (j = 0; j < I10NM_NUM_CHANNELS; j++) {
+				if (imc->hbm_mc) {
+					__enable_retry_rd_err_log(imc, j, enable,
+								  res_cfg->offsets_scrub_hbm0,
+								  res_cfg->offsets_demand_hbm0,
+								  NULL);
+					__enable_retry_rd_err_log(imc, j, enable,
+								  res_cfg->offsets_scrub_hbm1,
+								  res_cfg->offsets_demand_hbm1,
+								  NULL);
+				} else {
+					__enable_retry_rd_err_log(imc, j, enable,
+								  res_cfg->offsets_scrub,
+								  res_cfg->offsets_demand,
+								  res_cfg->offsets_demand2);
+				}
+			}
+	}
 }
 
 static void show_retry_rd_err_log(struct decoded_addr *res, char *msg,
@@ -138,14 +186,33 @@ static void show_retry_rd_err_log(struct decoded_addr *res, char *msg,
 	struct skx_imc *imc = &res->dev->imc[res->imc];
 	u32 log0, log1, log2, log3, log4;
 	u32 corr0, corr1, corr2, corr3;
+	u32 lxg0, lxg1, lxg3, lxg4;
+	u32 *xffsets = NULL;
 	u64 log2a, log5;
+	u64 lxg2a, lxg5;
 	u32 *offsets;
-	int n;
+	int n, pch;
 
 	if (!imc->mbase)
 		return;
 
-	offsets = scrub_err ? res_cfg->offsets_scrub : res_cfg->offsets_demand;
+	if (imc->hbm_mc) {
+		pch = res->cs & 1;
+
+		if (pch)
+			offsets = scrub_err ? res_cfg->offsets_scrub_hbm1 :
+					      res_cfg->offsets_demand_hbm1;
+		else
+			offsets = scrub_err ? res_cfg->offsets_scrub_hbm0 :
+					      res_cfg->offsets_demand_hbm0;
+	} else {
+		if (scrub_err) {
+			offsets = res_cfg->offsets_scrub;
+		} else {
+			offsets = res_cfg->offsets_demand;
+			xffsets = res_cfg->offsets_demand2;
+		}
+	}
 
 	log0 = I10NM_GET_REG32(imc, res->channel, offsets[0]);
 	log1 = I10NM_GET_REG32(imc, res->channel, offsets[1]);
@@ -153,20 +220,52 @@ static void show_retry_rd_err_log(struct decoded_addr *res, char *msg,
 	log4 = I10NM_GET_REG32(imc, res->channel, offsets[4]);
 	log5 = I10NM_GET_REG64(imc, res->channel, offsets[5]);
 
+	if (xffsets) {
+		lxg0 = I10NM_GET_REG32(imc, res->channel, xffsets[0]);
+		lxg1 = I10NM_GET_REG32(imc, res->channel, xffsets[1]);
+		lxg3 = I10NM_GET_REG32(imc, res->channel, xffsets[3]);
+		lxg4 = I10NM_GET_REG32(imc, res->channel, xffsets[4]);
+		lxg5 = I10NM_GET_REG64(imc, res->channel, xffsets[5]);
+	}
+
 	if (res_cfg->type == SPR) {
 		log2a = I10NM_GET_REG64(imc, res->channel, offsets[2]);
-		n = snprintf(msg, len, " retry_rd_err_log[%.8x %.8x %.16llx %.8x %.8x %.16llx]",
+		n = snprintf(msg, len, " retry_rd_err_log[%.8x %.8x %.16llx %.8x %.8x %.16llx",
 			     log0, log1, log2a, log3, log4, log5);
+
+		if (len - n > 0) {
+			if (xffsets) {
+				lxg2a = I10NM_GET_REG64(imc, res->channel, xffsets[2]);
+				n += snprintf(msg + n, len - n, " %.8x %.8x %.16llx %.8x %.8x %.16llx]",
+					     lxg0, lxg1, lxg2a, lxg3, lxg4, lxg5);
+			} else {
+				n += snprintf(msg + n, len - n, "]");
+			}
+		}
 	} else {
 		log2 = I10NM_GET_REG32(imc, res->channel, offsets[2]);
 		n = snprintf(msg, len, " retry_rd_err_log[%.8x %.8x %.8x %.8x %.8x %.16llx]",
 			     log0, log1, log2, log3, log4, log5);
 	}
 
-	corr0 = I10NM_GET_REG32(imc, res->channel, 0x22c18);
-	corr1 = I10NM_GET_REG32(imc, res->channel, 0x22c1c);
-	corr2 = I10NM_GET_REG32(imc, res->channel, 0x22c20);
-	corr3 = I10NM_GET_REG32(imc, res->channel, 0x22c24);
+	if (imc->hbm_mc) {
+		if (pch) {
+			corr0 = I10NM_GET_REG32(imc, res->channel, 0x2c18);
+			corr1 = I10NM_GET_REG32(imc, res->channel, 0x2c1c);
+			corr2 = I10NM_GET_REG32(imc, res->channel, 0x2c20);
+			corr3 = I10NM_GET_REG32(imc, res->channel, 0x2c24);
+		} else {
+			corr0 = I10NM_GET_REG32(imc, res->channel, 0x2818);
+			corr1 = I10NM_GET_REG32(imc, res->channel, 0x281c);
+			corr2 = I10NM_GET_REG32(imc, res->channel, 0x2820);
+			corr3 = I10NM_GET_REG32(imc, res->channel, 0x2824);
+		}
+	} else {
+		corr0 = I10NM_GET_REG32(imc, res->channel, 0x22c18);
+		corr1 = I10NM_GET_REG32(imc, res->channel, 0x22c1c);
+		corr2 = I10NM_GET_REG32(imc, res->channel, 0x22c20);
+		corr3 = I10NM_GET_REG32(imc, res->channel, 0x22c24);
+	}
 
 	if (len - n > 0)
 		snprintf(msg + n, len - n,
@@ -177,9 +276,16 @@ static void show_retry_rd_err_log(struct decoded_addr *res, char *msg,
 			 corr3 & 0xffff, corr3 >> 16);
 
 	/* Clear status bits */
-	if (retry_rd_err_log == 2 && (log0 & RETRY_RD_ERR_LOG_OVER_UC_V)) {
-		log0 &= ~RETRY_RD_ERR_LOG_OVER_UC_V;
-		I10NM_SET_REG32(imc, res->channel, offsets[0], log0);
+	if (retry_rd_err_log == 2) {
+		if (log0 & RETRY_RD_ERR_LOG_OVER_UC_V) {
+			log0 &= ~RETRY_RD_ERR_LOG_OVER_UC_V;
+			I10NM_SET_REG32(imc, res->channel, offsets[0], log0);
+		}
+
+		if (xffsets && (lxg0 & RETRY_RD_ERR_LOG_OVER_UC_V)) {
+			lxg0 &= ~RETRY_RD_ERR_LOG_OVER_UC_V;
+			I10NM_SET_REG32(imc, res->channel, xffsets[0], lxg0);
+		}
 	}
 }
 
@@ -231,6 +337,103 @@ static bool i10nm_check_2lm(struct res_config *cfg)
 	return false;
 }
 
+/*
+ * Check whether the error comes from DDRT by ICX/Tremont model specific error code.
+ * Refer to SDM vol3B 16.11.3 Intel IMC MC error codes for IA32_MCi_STATUS.
+ */
+static bool i10nm_mscod_is_ddrt(u32 mscod)
+{
+	switch (mscod) {
+	case 0x0106: case 0x0107:
+	case 0x0800: case 0x0804:
+	case 0x0806 ... 0x0808:
+	case 0x080a ... 0x080e:
+	case 0x0810: case 0x0811:
+	case 0x0816: case 0x081e:
+	case 0x081f:
+		return true;
+	}
+
+	return false;
+}
+
+static bool i10nm_mc_decode_available(struct mce *mce)
+{
+	u8 bank;
+
+	if (!decoding_via_mca || mem_cfg_2lm)
+		return false;
+
+	if ((mce->status & (MCI_STATUS_MISCV | MCI_STATUS_ADDRV))
+			!= (MCI_STATUS_MISCV | MCI_STATUS_ADDRV))
+		return false;
+
+	bank = mce->bank;
+
+	switch (res_cfg->type) {
+	case I10NM:
+		if (bank < 13 || bank > 26)
+			return false;
+
+		/* DDRT errors can't be decoded from MCA bank registers */
+		if (MCI_MISC_ECC_MODE(mce->misc) == MCI_MISC_ECC_DDRT)
+			return false;
+
+		if (i10nm_mscod_is_ddrt(MCI_STATUS_MSCOD(mce->status)))
+			return false;
+
+		/* Check whether one of {13,14,17,18,21,22,25,26} */
+		return ((bank - 13) & BIT(1)) == 0;
+	default:
+		return false;
+	}
+}
+
+static bool i10nm_mc_decode(struct decoded_addr *res)
+{
+	struct mce *m = res->mce;
+	struct skx_dev *d;
+	u8 bank;
+
+	if (!i10nm_mc_decode_available(m))
+		return false;
+
+	list_for_each_entry(d, i10nm_edac_list, list) {
+		if (d->imc[0].src_id == m->socketid) {
+			res->socket = m->socketid;
+			res->dev = d;
+			break;
+		}
+	}
+
+	switch (res_cfg->type) {
+	case I10NM:
+		bank = m->bank - 13;
+		res->imc = bank / 4;
+		res->channel = bank % 2;
+		break;
+	default:
+		return false;
+	}
+
+	if (!res->dev) {
+		skx_printk(KERN_ERR, "No device for src_id %d imc %d\n",
+			   m->socketid, res->imc);
+		return false;
+	}
+
+	res->column       = GET_BITFIELD(m->misc, 9, 18) << 2;
+	res->row          = GET_BITFIELD(m->misc, 19, 39);
+	res->bank_group   = GET_BITFIELD(m->misc, 40, 41);
+	res->bank_address = GET_BITFIELD(m->misc, 42, 43);
+	res->bank_group  |= GET_BITFIELD(m->misc, 44, 44) << 2;
+	res->rank         = GET_BITFIELD(m->misc, 56, 58);
+	res->dimm         = res->rank >> 2;
+	res->rank         = res->rank % 4;
+
+	return true;
+}
+
 static int i10nm_get_ddr_munits(void)
 {
 	struct pci_dev *mdev;
@@ -420,7 +623,12 @@ static struct res_config spr_cfg = {
 	.sad_all_devfn		= PCI_DEVFN(10, 0),
 	.sad_all_offset		= 0x300,
 	.offsets_scrub		= offsets_scrub_spr,
+	.offsets_scrub_hbm0	= offsets_scrub_spr_hbm0,
+	.offsets_scrub_hbm1	= offsets_scrub_spr_hbm1,
 	.offsets_demand		= offsets_demand_spr,
+	.offsets_demand2	= offsets_demand2_spr,
+	.offsets_demand_hbm0	= offsets_demand_spr_hbm0,
+	.offsets_demand_hbm1	= offsets_demand_spr_hbm1,
 };
 
 static const struct x86_cpu_id i10nm_cpuids[] = {
@@ -574,7 +782,8 @@ static int __init i10nm_init(void)
 		return -ENODEV;
 	}
 
-	skx_set_mem_cfg(i10nm_check_2lm(cfg));
+	mem_cfg_2lm = i10nm_check_2lm(cfg);
+	skx_set_mem_cfg(mem_cfg_2lm);
 
 	rc = i10nm_get_ddr_munits();
 
@@ -626,9 +835,11 @@ static int __init i10nm_init(void)
 	setup_i10nm_debug();
 
 	if (retry_rd_err_log && res_cfg->offsets_scrub && res_cfg->offsets_demand) {
-		skx_set_decode(NULL, show_retry_rd_err_log);
+		skx_set_decode(i10nm_mc_decode, show_retry_rd_err_log);
 		if (retry_rd_err_log == 2)
 			enable_retry_rd_err_log(true);
+	} else {
+		skx_set_decode(i10nm_mc_decode, NULL);
 	}
 
 	i10nm_printk(KERN_INFO, "%s\n", I10NM_REVISION);
@@ -658,6 +869,34 @@ static void __exit i10nm_exit(void)
 module_init(i10nm_init);
 module_exit(i10nm_exit);
 
+static int set_decoding_via_mca(const char *buf, const struct kernel_param *kp)
+{
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul(buf, 0, &val);
+
+	if (ret || val > 1)
+		return -EINVAL;
+
+	if (val && mem_cfg_2lm) {
+		i10nm_printk(KERN_NOTICE, "Decoding errors via MCA banks for 2LM isn't supported yet\n");
+		return -EIO;
+	}
+
+	ret = param_set_int(buf, kp);
+
+	return ret;
+}
+
+static const struct kernel_param_ops decoding_via_mca_param_ops = {
+	.set = set_decoding_via_mca,
+	.get = param_get_int,
+};
+
+module_param_cb(decoding_via_mca, &decoding_via_mca_param_ops, &decoding_via_mca, 0644);
+MODULE_PARM_DESC(decoding_via_mca, "decoding_via_mca: 0=off(default), 1=enable");
+
 module_param(retry_rd_err_log, int, 0444);
 MODULE_PARM_DESC(retry_rd_err_log, "retry_rd_err_log: 0=off(default), 1=bios(Linux doesn't reset any control bits, but just reports values.), 2=linux(Linux tries to take control and resets mode bits, clear valid/UC bits after reading.)");
 
diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c
index 4f28b8c8d378..61adaa872ba7 100644
--- a/drivers/edac/i7300_edac.c
+++ b/drivers/edac/i7300_edac.c
@@ -1193,7 +1193,7 @@ static int __init i7300_init(void)
 }
 
 /**
- * i7300_init() - Unregisters the driver
+ * i7300_exit() - Unregisters the driver
  */
 static void __exit i7300_exit(void)
 {
diff --git a/drivers/edac/ie31200_edac.c b/drivers/edac/ie31200_edac.c
index 9a9ff5ad611a..9ef13570f2e5 100644
--- a/drivers/edac/ie31200_edac.c
+++ b/drivers/edac/ie31200_edac.c
@@ -20,11 +20,15 @@
  * 0c08: Xeon E3-1200 v3 Processor DRAM Controller
  * 1918: Xeon E3-1200 v5 Skylake Host Bridge/DRAM Registers
  * 5918: Xeon E3-1200 Xeon E3-1200 v6/7th Gen Core Processor Host Bridge/DRAM Registers
+ * 190f: 6th Gen Core Dual-Core Processor Host Bridge/DRAM Registers
+ * 191f: 6th Gen Core Quad-Core Processor Host Bridge/DRAM Registers
  * 3e..: 8th/9th Gen Core Processor Host Bridge/DRAM Registers
  *
  * Based on Intel specification:
  * https://www.intel.com/content/dam/www/public/us/en/documents/datasheets/xeon-e3-1200v3-vol-2-datasheet.pdf
  * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e3-1200-family-vol-2-datasheet.html
+ * https://www.intel.com/content/dam/www/public/us/en/documents/datasheets/desktop-6th-gen-core-family-datasheet-vol-2.pdf
+ * https://www.intel.com/content/dam/www/public/us/en/documents/datasheets/xeon-e3-1200v6-vol-2-datasheet.pdf
  * https://www.intel.com/content/www/us/en/processors/core/7th-gen-core-family-mobile-h-processor-lines-datasheet-vol-2.html
  * https://www.intel.com/content/www/us/en/products/docs/processors/core/8th-gen-core-family-datasheet-vol-2.html
  *
@@ -53,15 +57,17 @@
 #define ie31200_printk(level, fmt, arg...) \
 	edac_printk(level, "ie31200", fmt, ##arg)
 
-#define PCI_DEVICE_ID_INTEL_IE31200_HB_1 0x0108
-#define PCI_DEVICE_ID_INTEL_IE31200_HB_2 0x010c
-#define PCI_DEVICE_ID_INTEL_IE31200_HB_3 0x0150
-#define PCI_DEVICE_ID_INTEL_IE31200_HB_4 0x0158
-#define PCI_DEVICE_ID_INTEL_IE31200_HB_5 0x015c
-#define PCI_DEVICE_ID_INTEL_IE31200_HB_6 0x0c04
-#define PCI_DEVICE_ID_INTEL_IE31200_HB_7 0x0c08
-#define PCI_DEVICE_ID_INTEL_IE31200_HB_8 0x1918
-#define PCI_DEVICE_ID_INTEL_IE31200_HB_9 0x5918
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_1  0x0108
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_2  0x010c
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_3  0x0150
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_4  0x0158
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_5  0x015c
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_6  0x0c04
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_7  0x0c08
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_8  0x190F
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_9  0x1918
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_10 0x191F
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_11 0x5918
 
 /* Coffee Lake-S */
 #define PCI_DEVICE_ID_INTEL_IE31200_HB_CFL_MASK 0x3e00
@@ -80,6 +86,8 @@
 #define DEVICE_ID_SKYLAKE_OR_LATER(did)                                        \
 	(((did) == PCI_DEVICE_ID_INTEL_IE31200_HB_8) ||                        \
 	 ((did) == PCI_DEVICE_ID_INTEL_IE31200_HB_9) ||                        \
+	 ((did) == PCI_DEVICE_ID_INTEL_IE31200_HB_10) ||                       \
+	 ((did) == PCI_DEVICE_ID_INTEL_IE31200_HB_11) ||                       \
 	 (((did) & PCI_DEVICE_ID_INTEL_IE31200_HB_CFL_MASK) ==                 \
 	  PCI_DEVICE_ID_INTEL_IE31200_HB_CFL_MASK))
 
@@ -577,6 +585,8 @@ static const struct pci_device_id ie31200_pci_tbl[] = {
 	{ PCI_VEND_DEV(INTEL, IE31200_HB_7),      PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 },
 	{ PCI_VEND_DEV(INTEL, IE31200_HB_8),      PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 },
 	{ PCI_VEND_DEV(INTEL, IE31200_HB_9),      PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 },
+	{ PCI_VEND_DEV(INTEL, IE31200_HB_10),     PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 },
+	{ PCI_VEND_DEV(INTEL, IE31200_HB_11),     PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 },
 	{ PCI_VEND_DEV(INTEL, IE31200_HB_CFL_1),  PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 },
 	{ PCI_VEND_DEV(INTEL, IE31200_HB_CFL_2),  PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 },
 	{ PCI_VEND_DEV(INTEL, IE31200_HB_CFL_3),  PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 },
diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c
index 0bc670778c99..046969b4e82e 100644
--- a/drivers/edac/ppc4xx_edac.c
+++ b/drivers/edac/ppc4xx_edac.c
@@ -178,11 +178,6 @@ struct ppc4xx_ecc_status {
 	u32 wmirq;
 };
 
-/* Function Prototypes */
-
-static int ppc4xx_edac_probe(struct platform_device *device);
-static int ppc4xx_edac_remove(struct platform_device *device);
-
 /* Global Variables */
 
 /*
@@ -197,15 +192,6 @@ static const struct of_device_id ppc4xx_edac_match[] = {
 };
 MODULE_DEVICE_TABLE(of, ppc4xx_edac_match);
 
-static struct platform_driver ppc4xx_edac_driver = {
-	.probe			= ppc4xx_edac_probe,
-	.remove			= ppc4xx_edac_remove,
-	.driver = {
-		.name = PPC4XX_EDAC_MODULE_NAME,
-		.of_match_table = ppc4xx_edac_match,
-	},
-};
-
 /*
  * TODO: The row and channel parameters likely need to be dynamically
  * set based on the aforementioned variant controller realizations.
@@ -1391,6 +1377,15 @@ ppc4xx_edac_opstate_init(void)
 			     EDAC_OPSTATE_UNKNOWN_STR)));
 }
 
+static struct platform_driver ppc4xx_edac_driver = {
+	.probe			= ppc4xx_edac_probe,
+	.remove			= ppc4xx_edac_remove,
+	.driver = {
+		.name = PPC4XX_EDAC_MODULE_NAME,
+		.of_match_table = ppc4xx_edac_match,
+	},
+};
+
 /**
  * ppc4xx_edac_init - driver/module insertion entry point
  *
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 9678ab97c7ac..8e39370fdb5c 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -335,6 +335,12 @@ struct sbridge_info {
 struct sbridge_channel {
 	u32		ranks;
 	u32		dimms;
+	struct dimm {
+		u32 rowbits;
+		u32 colbits;
+		u32 bank_xor_enable;
+		u32 amap_fine;
+	} dimm[MAX_DIMMS];
 };
 
 struct pci_id_descr {
@@ -1603,7 +1609,7 @@ static int __populate_dimms(struct mem_ctl_info *mci,
 		banks = 8;
 
 	for (i = 0; i < channels; i++) {
-		u32 mtr;
+		u32 mtr, amap = 0;
 
 		int max_dimms_per_channel;
 
@@ -1615,6 +1621,7 @@ static int __populate_dimms(struct mem_ctl_info *mci,
 			max_dimms_per_channel = ARRAY_SIZE(mtr_regs);
 			if (!pvt->pci_tad[i])
 				continue;
+			pci_read_config_dword(pvt->pci_tad[i], 0x8c, &amap);
 		}
 
 		for (j = 0; j < max_dimms_per_channel; j++) {
@@ -1627,6 +1634,7 @@ static int __populate_dimms(struct mem_ctl_info *mci,
 					mtr_regs[j], &mtr);
 			}
 			edac_dbg(4, "Channel #%d  MTR%d = %x\n", i, j, mtr);
+
 			if (IS_DIMM_PRESENT(mtr)) {
 				if (!IS_ECC_ENABLED(pvt->info.mcmtr)) {
 					sbridge_printk(KERN_ERR, "CPU SrcID #%d, Ha #%d, Channel #%d has DIMMs, but ECC is disabled\n",
@@ -1661,6 +1669,11 @@ static int __populate_dimms(struct mem_ctl_info *mci,
 				dimm->dtype = pvt->info.get_width(pvt, mtr);
 				dimm->mtype = mtype;
 				dimm->edac_mode = mode;
+				pvt->channel[i].dimm[j].rowbits = order_base_2(rows);
+				pvt->channel[i].dimm[j].colbits = order_base_2(cols);
+				pvt->channel[i].dimm[j].bank_xor_enable =
+						GET_BITFIELD(pvt->info.mcmtr, 9, 9);
+				pvt->channel[i].dimm[j].amap_fine = GET_BITFIELD(amap, 0, 0);
 				snprintf(dimm->label, sizeof(dimm->label),
 						 "CPU_SrcID#%u_Ha#%u_Chan#%u_DIMM#%u",
 						 pvt->sbridge_dev->source_id, pvt->sbridge_dev->dom, i, j);
@@ -1922,6 +1935,99 @@ static struct mem_ctl_info *get_mci_for_node_id(u8 node_id, u8 ha)
 	return NULL;
 }
 
+static u8 sb_close_row[] = {
+	15, 16, 17, 18, 20, 21, 22, 28, 10, 11, 12, 13, 29, 30, 31, 32, 33
+};
+
+static u8 sb_close_column[] = {
+	3, 4, 5, 14, 19, 23, 24, 25, 26, 27
+};
+
+static u8 sb_open_row[] = {
+	14, 15, 16, 20, 28, 21, 22, 23, 24, 25, 26, 27, 29, 30, 31, 32, 33
+};
+
+static u8 sb_open_column[] = {
+	3, 4, 5, 6, 7, 8, 9, 10, 11, 12
+};
+
+static u8 sb_open_fine_column[] = {
+	3, 4, 5, 7, 8, 9, 10, 11, 12, 13
+};
+
+static int sb_bits(u64 addr, int nbits, u8 *bits)
+{
+	int i, res = 0;
+
+	for (i = 0; i < nbits; i++)
+		res |= ((addr >> bits[i]) & 1) << i;
+	return res;
+}
+
+static int sb_bank_bits(u64 addr, int b0, int b1, int do_xor, int x0, int x1)
+{
+	int ret = GET_BITFIELD(addr, b0, b0) | (GET_BITFIELD(addr, b1, b1) << 1);
+
+	if (do_xor)
+		ret ^= GET_BITFIELD(addr, x0, x0) | (GET_BITFIELD(addr, x1, x1) << 1);
+
+	return ret;
+}
+
+static bool sb_decode_ddr4(struct mem_ctl_info *mci, int ch, u8 rank,
+			   u64 rank_addr, char *msg)
+{
+	int dimmno = 0;
+	int row, col, bank_address, bank_group;
+	struct sbridge_pvt *pvt;
+	u32 bg0 = 0, rowbits = 0, colbits = 0;
+	u32 amap_fine = 0, bank_xor_enable = 0;
+
+	dimmno = (rank < 12) ? rank / 4 : 2;
+	pvt = mci->pvt_info;
+	amap_fine =  pvt->channel[ch].dimm[dimmno].amap_fine;
+	bg0 = amap_fine ? 6 : 13;
+	rowbits = pvt->channel[ch].dimm[dimmno].rowbits;
+	colbits = pvt->channel[ch].dimm[dimmno].colbits;
+	bank_xor_enable = pvt->channel[ch].dimm[dimmno].bank_xor_enable;
+
+	if (pvt->is_lockstep) {
+		pr_warn_once("LockStep row/column decode is not supported yet!\n");
+		msg[0] = '\0';
+		return false;
+	}
+
+	if (pvt->is_close_pg) {
+		row = sb_bits(rank_addr, rowbits, sb_close_row);
+		col = sb_bits(rank_addr, colbits, sb_close_column);
+		col |= 0x400; /* C10 is autoprecharge, always set */
+		bank_address = sb_bank_bits(rank_addr, 8, 9, bank_xor_enable, 22, 28);
+		bank_group = sb_bank_bits(rank_addr, 6, 7, bank_xor_enable, 20, 21);
+	} else {
+		row = sb_bits(rank_addr, rowbits, sb_open_row);
+		if (amap_fine)
+			col = sb_bits(rank_addr, colbits, sb_open_fine_column);
+		else
+			col = sb_bits(rank_addr, colbits, sb_open_column);
+		bank_address = sb_bank_bits(rank_addr, 18, 19, bank_xor_enable, 22, 23);
+		bank_group = sb_bank_bits(rank_addr, bg0, 17, bank_xor_enable, 20, 21);
+	}
+
+	row &= (1u << rowbits) - 1;
+
+	sprintf(msg, "row:0x%x col:0x%x bank_addr:%d bank_group:%d",
+		row, col, bank_address, bank_group);
+	return true;
+}
+
+static bool sb_decode_ddr3(struct mem_ctl_info *mci, int ch, u8 rank,
+			   u64 rank_addr, char *msg)
+{
+	pr_warn_once("DDR3 row/column decode not support yet!\n");
+	msg[0] = '\0';
+	return false;
+}
+
 static int get_memory_error_data(struct mem_ctl_info *mci,
 				 u64 addr,
 				 u8 *socket, u8 *ha,
@@ -1937,12 +2043,13 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 	int			interleave_mode, shiftup = 0;
 	unsigned int		sad_interleave[MAX_INTERLEAVE];
 	u32			reg, dram_rule;
-	u8			ch_way, sck_way, pkg, sad_ha = 0;
+	u8			ch_way, sck_way, pkg, sad_ha = 0, rankid = 0;
 	u32			tad_offset;
 	u32			rir_way;
 	u32			mb, gb;
 	u64			ch_addr, offset, limit = 0, prv = 0;
-
+	u64			rank_addr;
+	enum mem_type		mtype;
 
 	/*
 	 * Step 0) Check if the address is at special memory ranges
@@ -2226,6 +2333,28 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 	pci_read_config_dword(pvt->pci_tad[base_ch], rir_offset[n_rir][idx], &reg);
 	*rank = RIR_RNK_TGT(pvt->info.type, reg);
 
+	if (pvt->info.type == BROADWELL) {
+		if (pvt->is_close_pg)
+			shiftup = 6;
+		else
+			shiftup = 13;
+
+		rank_addr = ch_addr >> shiftup;
+		rank_addr /= (1 << rir_way);
+		rank_addr <<= shiftup;
+		rank_addr |= ch_addr & GENMASK_ULL(shiftup - 1, 0);
+		rank_addr -= RIR_OFFSET(pvt->info.type, reg);
+
+		mtype = pvt->info.get_memory_type(pvt);
+		rankid = *rank;
+		if (mtype == MEM_DDR4 || mtype == MEM_RDDR4)
+			sb_decode_ddr4(mci, base_ch, rankid, rank_addr, msg);
+		else
+			sb_decode_ddr3(mci, base_ch, rankid, rank_addr, msg);
+	} else {
+		msg[0] = '\0';
+	}
+
 	edac_dbg(0, "RIR#%d: channel address 0x%08Lx < 0x%08Lx, RIR interleave %d, index %d\n",
 		 n_rir,
 		 ch_addr,
@@ -2950,7 +3079,7 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci,
 	struct mem_ctl_info *new_mci;
 	struct sbridge_pvt *pvt = mci->pvt_info;
 	enum hw_event_mc_err_type tp_event;
-	char *optype, msg[256];
+	char *optype, msg[256], msg_full[512];
 	bool ripv = GET_BITFIELD(m->mcgstatus, 0, 0);
 	bool overflow = GET_BITFIELD(m->status, 62, 62);
 	bool uncorrected_error = GET_BITFIELD(m->status, 61, 61);
@@ -3089,18 +3218,17 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci,
 	 */
 	if (!pvt->is_lockstep && !pvt->is_cur_addr_mirrored && !pvt->is_close_pg)
 		channel = first_channel;
-
-	snprintf(msg, sizeof(msg),
-		 "%s%s area:%s err_code:%04x:%04x socket:%d ha:%d channel_mask:%ld rank:%d",
+	snprintf(msg_full, sizeof(msg_full),
+		 "%s%s area:%s err_code:%04x:%04x socket:%d ha:%d channel_mask:%ld rank:%d %s",
 		 overflow ? " OVERFLOW" : "",
 		 (uncorrected_error && recoverable) ? " recoverable" : "",
 		 area_type,
 		 mscod, errcode,
 		 socket, ha,
 		 channel_mask,
-		 rank);
+		 rank, msg);
 
-	edac_dbg(0, "%s\n", msg);
+	edac_dbg(0, "%s\n", msg_full);
 
 	/* FIXME: need support for channel mask */
 
@@ -3111,7 +3239,7 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci,
 	edac_mc_handle_error(tp_event, mci, core_err_cnt,
 			     m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0,
 			     channel, dimm, -1,
-			     optype, msg);
+			     optype, msg_full);
 	return;
 err_parsing:
 	edac_mc_handle_error(tp_event, mci, core_err_cnt, 0, 0, 0,
diff --git a/drivers/edac/skx_base.c b/drivers/edac/skx_base.c
index 1abc020d49ab..7e2762f62eec 100644
--- a/drivers/edac/skx_base.c
+++ b/drivers/edac/skx_base.c
@@ -714,8 +714,13 @@ static int __init skx_init(void)
 
 	skx_set_decode(skx_decode, skx_show_retry_rd_err_log);
 
-	if (nvdimm_count && skx_adxl_get() == -ENODEV)
-		skx_printk(KERN_NOTICE, "Only decoding DDR4 address!\n");
+	if (nvdimm_count && skx_adxl_get() != -ENODEV) {
+		skx_set_decode(NULL, skx_show_retry_rd_err_log);
+	} else {
+		if (nvdimm_count)
+			skx_printk(KERN_NOTICE, "Only decoding DDR4 address!\n");
+		skx_set_decode(skx_decode, skx_show_retry_rd_err_log);
+	}
 
 	/* Ensure that the OPSTATE is set correctly for POLL or NMI */
 	opstate_init();
diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c
index 19c17c5198c5..f0f8e98f6efb 100644
--- a/drivers/edac/skx_common.c
+++ b/drivers/edac/skx_common.c
@@ -27,9 +27,11 @@ static const char * const component_names[] = {
 	[INDEX_MEMCTRL]		= "MemoryControllerId",
 	[INDEX_CHANNEL]		= "ChannelId",
 	[INDEX_DIMM]		= "DimmSlotId",
+	[INDEX_CS]		= "ChipSelect",
 	[INDEX_NM_MEMCTRL]	= "NmMemoryControllerId",
 	[INDEX_NM_CHANNEL]	= "NmChannelId",
 	[INDEX_NM_DIMM]		= "NmDimmSlotId",
+	[INDEX_NM_CS]		= "NmChipSelect",
 };
 
 static int component_indices[ARRAY_SIZE(component_names)];
@@ -40,7 +42,7 @@ static char *adxl_msg;
 static unsigned long adxl_nm_bitmap;
 
 static char skx_msg[MSG_SIZE];
-static skx_decode_f skx_decode;
+static skx_decode_f driver_decode;
 static skx_show_retry_log_f skx_show_retry_rd_err_log;
 static u64 skx_tolm, skx_tohm;
 static LIST_HEAD(dev_edac_list);
@@ -139,10 +141,13 @@ static bool skx_adxl_decode(struct decoded_addr *res, bool error_in_1st_level_me
 			       (int)adxl_values[component_indices[INDEX_NM_CHANNEL]] : -1;
 		res->dimm    = (adxl_nm_bitmap & BIT_NM_DIMM) ?
 			       (int)adxl_values[component_indices[INDEX_NM_DIMM]] : -1;
+		res->cs      = (adxl_nm_bitmap & BIT_NM_CS) ?
+			       (int)adxl_values[component_indices[INDEX_NM_CS]] : -1;
 	} else {
 		res->imc     = (int)adxl_values[component_indices[INDEX_MEMCTRL]];
 		res->channel = (int)adxl_values[component_indices[INDEX_CHANNEL]];
 		res->dimm    = (int)adxl_values[component_indices[INDEX_DIMM]];
+		res->cs      = (int)adxl_values[component_indices[INDEX_CS]];
 	}
 
 	if (res->imc > NUM_IMC - 1 || res->imc < 0) {
@@ -173,6 +178,8 @@ static bool skx_adxl_decode(struct decoded_addr *res, bool error_in_1st_level_me
 			break;
 	}
 
+	res->decoded_by_adxl = true;
+
 	return true;
 }
 
@@ -183,7 +190,7 @@ void skx_set_mem_cfg(bool mem_cfg_2lm)
 
 void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log)
 {
-	skx_decode = decode;
+	driver_decode = decode;
 	skx_show_retry_rd_err_log = show_retry_log;
 }
 
@@ -591,19 +598,19 @@ static void skx_mce_output_error(struct mem_ctl_info *mci,
 			break;
 		}
 	}
-	if (adxl_component_count) {
+	if (res->decoded_by_adxl) {
 		len = snprintf(skx_msg, MSG_SIZE, "%s%s err_code:0x%04x:0x%04x %s",
 			 overflow ? " OVERFLOW" : "",
 			 (uncorrected_error && recoverable) ? " recoverable" : "",
 			 mscod, errcode, adxl_msg);
 	} else {
 		len = snprintf(skx_msg, MSG_SIZE,
-			 "%s%s err_code:0x%04x:0x%04x socket:%d imc:%d rank:%d bg:%d ba:%d row:0x%x col:0x%x",
+			 "%s%s err_code:0x%04x:0x%04x ProcessorSocketId:0x%x MemoryControllerId:0x%x PhysicalRankId:0x%x Row:0x%x Column:0x%x Bank:0x%x BankGroup:0x%x",
 			 overflow ? " OVERFLOW" : "",
 			 (uncorrected_error && recoverable) ? " recoverable" : "",
 			 mscod, errcode,
 			 res->socket, res->imc, res->rank,
-			 res->bank_group, res->bank_address, res->row, res->column);
+			 res->row, res->column, res->bank_address, res->bank_group);
 	}
 
 	if (skx_show_retry_rd_err_log)
@@ -649,13 +656,14 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
 		return NOTIFY_DONE;
 
 	memset(&res, 0, sizeof(res));
+	res.mce  = mce;
 	res.addr = mce->addr;
 
-	if (adxl_component_count) {
-		if (!skx_adxl_decode(&res, skx_error_in_1st_level_mem(mce)))
+	/* Try driver decoder first */
+	if (!(driver_decode && driver_decode(&res))) {
+		/* Then try firmware decoder (ACPI DSM methods) */
+		if (!(adxl_component_count && skx_adxl_decode(&res, skx_error_in_1st_level_mem(mce))))
 			return NOTIFY_DONE;
-	} else if (!skx_decode || !skx_decode(&res)) {
-		return NOTIFY_DONE;
 	}
 
 	mci = res.dev->imc[res.imc].mci;
diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h
index 03ac067a80b9..0cbadd3d2cd3 100644
--- a/drivers/edac/skx_common.h
+++ b/drivers/edac/skx_common.h
@@ -10,6 +10,7 @@
 #define _SKX_COMM_EDAC_H
 
 #include <linux/bits.h>
+#include <asm/mce.h>
 
 #define MSG_SIZE		1024
 
@@ -52,6 +53,9 @@
 #define IS_DIMM_PRESENT(r)		GET_BITFIELD(r, 15, 15)
 #define IS_NVDIMM_PRESENT(r, i)		GET_BITFIELD(r, i, i)
 
+#define MCI_MISC_ECC_MODE(m)	(((m) >> 59) & 15)
+#define MCI_MISC_ECC_DDRT	8	/* read from DDRT */
+
 /*
  * Each cpu socket contains some pci devices that provide global
  * information, and also some that are local to each of the two
@@ -82,6 +86,7 @@ struct skx_dev {
 			struct pci_dev	*edev;
 			u32 retry_rd_err_log_s;
 			u32 retry_rd_err_log_d;
+			u32 retry_rd_err_log_d2;
 			struct skx_dimm {
 				u8 close_pg;
 				u8 bank_xor_enable;
@@ -108,18 +113,22 @@ enum {
 	INDEX_MEMCTRL,
 	INDEX_CHANNEL,
 	INDEX_DIMM,
+	INDEX_CS,
 	INDEX_NM_FIRST,
 	INDEX_NM_MEMCTRL = INDEX_NM_FIRST,
 	INDEX_NM_CHANNEL,
 	INDEX_NM_DIMM,
+	INDEX_NM_CS,
 	INDEX_MAX
 };
 
 #define BIT_NM_MEMCTRL	BIT_ULL(INDEX_NM_MEMCTRL)
 #define BIT_NM_CHANNEL	BIT_ULL(INDEX_NM_CHANNEL)
 #define BIT_NM_DIMM	BIT_ULL(INDEX_NM_DIMM)
+#define BIT_NM_CS	BIT_ULL(INDEX_NM_CS)
 
 struct decoded_addr {
+	struct mce *mce;
 	struct skx_dev *dev;
 	u64	addr;
 	int	socket;
@@ -129,6 +138,7 @@ struct decoded_addr {
 	int	sktways;
 	int	chanways;
 	int	dimm;
+	int	cs;
 	int	rank;
 	int	channel_rank;
 	u64	rank_address;
@@ -136,6 +146,7 @@ struct decoded_addr {
 	int	column;
 	int	bank_address;
 	int	bank_group;
+	bool	decoded_by_adxl;
 };
 
 struct res_config {
@@ -154,7 +165,12 @@ struct res_config {
 	int sad_all_offset;
 	/* Offsets of retry_rd_err_log registers */
 	u32 *offsets_scrub;
+	u32 *offsets_scrub_hbm0;
+	u32 *offsets_scrub_hbm1;
 	u32 *offsets_demand;
+	u32 *offsets_demand2;
+	u32 *offsets_demand_hbm0;
+	u32 *offsets_demand_hbm1;
 };
 
 typedef int (*get_dimm_config_f)(struct mem_ctl_info *mci,
diff --git a/drivers/edac/wq.c b/drivers/edac/wq.c
index d021d287eaec..ad3f516627c5 100644
--- a/drivers/edac/wq.c
+++ b/drivers/edac/wq.c
@@ -37,7 +37,6 @@ int edac_workqueue_setup(void)
 
 void edac_workqueue_teardown(void)
 {
-	flush_workqueue(wq);
 	destroy_workqueue(wq);
 	wq = NULL;
 }
diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c
index 3ed7ae0d6781..96060bf90a24 100644
--- a/drivers/firmware/arm_scmi/clock.c
+++ b/drivers/firmware/arm_scmi/clock.c
@@ -450,9 +450,13 @@ static int scmi_clock_count_get(const struct scmi_protocol_handle *ph)
 static const struct scmi_clock_info *
 scmi_clock_info_get(const struct scmi_protocol_handle *ph, u32 clk_id)
 {
+	struct scmi_clock_info *clk;
 	struct clock_info *ci = ph->get_priv(ph);
-	struct scmi_clock_info *clk = ci->clk + clk_id;
 
+	if (clk_id >= ci->num_clocks)
+		return NULL;
+
+	clk = ci->clk + clk_id;
 	if (!clk->name[0])
 		return NULL;
 
diff --git a/drivers/firmware/arm_scmi/optee.c b/drivers/firmware/arm_scmi/optee.c
index 8abace56b958..f42dad997ac9 100644
--- a/drivers/firmware/arm_scmi/optee.c
+++ b/drivers/firmware/arm_scmi/optee.c
@@ -106,6 +106,7 @@ enum scmi_optee_pta_cmd {
  * @channel_id: OP-TEE channel ID used for this transport
  * @tee_session: TEE session identifier
  * @caps: OP-TEE SCMI channel capabilities
+ * @rx_len: Response size
  * @mu: Mutex protection on channel access
  * @cinfo: SCMI channel information
  * @shmem: Virtual base address of the shared memory
diff --git a/drivers/firmware/arm_scmi/reset.c b/drivers/firmware/arm_scmi/reset.c
index 673f3eb498f4..e9afa8cab730 100644
--- a/drivers/firmware/arm_scmi/reset.c
+++ b/drivers/firmware/arm_scmi/reset.c
@@ -166,9 +166,13 @@ static int scmi_domain_reset(const struct scmi_protocol_handle *ph, u32 domain,
 	struct scmi_xfer *t;
 	struct scmi_msg_reset_domain_reset *dom;
 	struct scmi_reset_info *pi = ph->get_priv(ph);
-	struct reset_dom_info *rdom = pi->dom_info + domain;
+	struct reset_dom_info *rdom;
 
-	if (rdom->async_reset)
+	if (domain >= pi->num_domains)
+		return -EINVAL;
+
+	rdom = pi->dom_info + domain;
+	if (rdom->async_reset && flags & AUTONOMOUS_RESET)
 		flags |= ASYNCHRONOUS_RESET;
 
 	ret = ph->xops->xfer_get_init(ph, RESET, sizeof(*dom), 0, &t);
@@ -180,7 +184,7 @@ static int scmi_domain_reset(const struct scmi_protocol_handle *ph, u32 domain,
 	dom->flags = cpu_to_le32(flags);
 	dom->reset_state = cpu_to_le32(state);
 
-	if (rdom->async_reset)
+	if (flags & ASYNCHRONOUS_RESET)
 		ret = ph->xops->do_xfer_with_response(ph, t);
 	else
 		ret = ph->xops->do_xfer(ph, t);
diff --git a/drivers/firmware/arm_scmi/scmi_pm_domain.c b/drivers/firmware/arm_scmi/scmi_pm_domain.c
index 581d34c95769..0e05a79de82d 100644
--- a/drivers/firmware/arm_scmi/scmi_pm_domain.c
+++ b/drivers/firmware/arm_scmi/scmi_pm_domain.c
@@ -8,7 +8,6 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/module.h>
-#include <linux/pm_clock.h>
 #include <linux/pm_domain.h>
 #include <linux/scmi_protocol.h>
 
@@ -53,27 +52,6 @@ static int scmi_pd_power_off(struct generic_pm_domain *domain)
 	return scmi_pd_power(domain, false);
 }
 
-static int scmi_pd_attach_dev(struct generic_pm_domain *pd, struct device *dev)
-{
-	int ret;
-
-	ret = pm_clk_create(dev);
-	if (ret)
-		return ret;
-
-	ret = of_pm_clk_add_clks(dev);
-	if (ret >= 0)
-		return 0;
-
-	pm_clk_destroy(dev);
-	return ret;
-}
-
-static void scmi_pd_detach_dev(struct generic_pm_domain *pd, struct device *dev)
-{
-	pm_clk_destroy(dev);
-}
-
 static int scmi_pm_domain_probe(struct scmi_device *sdev)
 {
 	int num_domains, i;
@@ -124,10 +102,6 @@ static int scmi_pm_domain_probe(struct scmi_device *sdev)
 		scmi_pd->genpd.name = scmi_pd->name;
 		scmi_pd->genpd.power_off = scmi_pd_power_off;
 		scmi_pd->genpd.power_on = scmi_pd_power_on;
-		scmi_pd->genpd.attach_dev = scmi_pd_attach_dev;
-		scmi_pd->genpd.detach_dev = scmi_pd_detach_dev;
-		scmi_pd->genpd.flags = GENPD_FLAG_PM_CLK |
-				       GENPD_FLAG_ACTIVE_WAKEUP;
 
 		pm_genpd_init(&scmi_pd->genpd, NULL,
 			      state == SCMI_POWER_STATE_GENERIC_OFF);
@@ -138,9 +112,28 @@ static int scmi_pm_domain_probe(struct scmi_device *sdev)
 	scmi_pd_data->domains = domains;
 	scmi_pd_data->num_domains = num_domains;
 
+	dev_set_drvdata(dev, scmi_pd_data);
+
 	return of_genpd_add_provider_onecell(np, scmi_pd_data);
 }
 
+static void scmi_pm_domain_remove(struct scmi_device *sdev)
+{
+	int i;
+	struct genpd_onecell_data *scmi_pd_data;
+	struct device *dev = &sdev->dev;
+	struct device_node *np = dev->of_node;
+
+	of_genpd_del_provider(np);
+
+	scmi_pd_data = dev_get_drvdata(dev);
+	for (i = 0; i < scmi_pd_data->num_domains; i++) {
+		if (!scmi_pd_data->domains[i])
+			continue;
+		pm_genpd_remove(scmi_pd_data->domains[i]);
+	}
+}
+
 static const struct scmi_device_id scmi_id_table[] = {
 	{ SCMI_PROTOCOL_POWER, "genpd" },
 	{ },
@@ -150,6 +143,7 @@ MODULE_DEVICE_TABLE(scmi, scmi_id_table);
 static struct scmi_driver scmi_power_domain_driver = {
 	.name = "scmi-power-domain",
 	.probe = scmi_pm_domain_probe,
+	.remove = scmi_pm_domain_remove,
 	.id_table = scmi_id_table,
 };
 module_scmi_driver(scmi_power_domain_driver);
diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c
index 7288c6117838..0b5853fa9d87 100644
--- a/drivers/firmware/arm_scmi/sensors.c
+++ b/drivers/firmware/arm_scmi/sensors.c
@@ -762,6 +762,10 @@ static int scmi_sensor_config_get(const struct scmi_protocol_handle *ph,
 {
 	int ret;
 	struct scmi_xfer *t;
+	struct sensors_info *si = ph->get_priv(ph);
+
+	if (sensor_id >= si->num_sensors)
+		return -EINVAL;
 
 	ret = ph->xops->xfer_get_init(ph, SENSOR_CONFIG_GET,
 				      sizeof(__le32), sizeof(__le32), &t);
@@ -771,7 +775,6 @@ static int scmi_sensor_config_get(const struct scmi_protocol_handle *ph,
 	put_unaligned_le32(sensor_id, t->tx.buf);
 	ret = ph->xops->do_xfer(ph, t);
 	if (!ret) {
-		struct sensors_info *si = ph->get_priv(ph);
 		struct scmi_sensor_info *s = si->sensors + sensor_id;
 
 		*sensor_config = get_unaligned_le64(t->rx.buf);
@@ -788,6 +791,10 @@ static int scmi_sensor_config_set(const struct scmi_protocol_handle *ph,
 	int ret;
 	struct scmi_xfer *t;
 	struct scmi_msg_sensor_config_set *msg;
+	struct sensors_info *si = ph->get_priv(ph);
+
+	if (sensor_id >= si->num_sensors)
+		return -EINVAL;
 
 	ret = ph->xops->xfer_get_init(ph, SENSOR_CONFIG_SET,
 				      sizeof(*msg), 0, &t);
@@ -800,7 +807,6 @@ static int scmi_sensor_config_set(const struct scmi_protocol_handle *ph,
 
 	ret = ph->xops->do_xfer(ph, t);
 	if (!ret) {
-		struct sensors_info *si = ph->get_priv(ph);
 		struct scmi_sensor_info *s = si->sensors + sensor_id;
 
 		s->sensor_config = sensor_config;
@@ -831,8 +837,11 @@ static int scmi_sensor_reading_get(const struct scmi_protocol_handle *ph,
 	int ret;
 	struct scmi_xfer *t;
 	struct scmi_msg_sensor_reading_get *sensor;
+	struct scmi_sensor_info *s;
 	struct sensors_info *si = ph->get_priv(ph);
-	struct scmi_sensor_info *s = si->sensors + sensor_id;
+
+	if (sensor_id >= si->num_sensors)
+		return -EINVAL;
 
 	ret = ph->xops->xfer_get_init(ph, SENSOR_READING_GET,
 				      sizeof(*sensor), 0, &t);
@@ -841,6 +850,7 @@ static int scmi_sensor_reading_get(const struct scmi_protocol_handle *ph,
 
 	sensor = t->tx.buf;
 	sensor->id = cpu_to_le32(sensor_id);
+	s = si->sensors + sensor_id;
 	if (s->async) {
 		sensor->flags = cpu_to_le32(SENSOR_READ_ASYNC);
 		ret = ph->xops->do_xfer_with_response(ph, t);
@@ -895,9 +905,13 @@ scmi_sensor_reading_get_timestamped(const struct scmi_protocol_handle *ph,
 	int ret;
 	struct scmi_xfer *t;
 	struct scmi_msg_sensor_reading_get *sensor;
+	struct scmi_sensor_info *s;
 	struct sensors_info *si = ph->get_priv(ph);
-	struct scmi_sensor_info *s = si->sensors + sensor_id;
 
+	if (sensor_id >= si->num_sensors)
+		return -EINVAL;
+
+	s = si->sensors + sensor_id;
 	if (!count || !readings ||
 	    (!s->num_axis && count > 1) || (s->num_axis && count > s->num_axis))
 		return -EINVAL;
@@ -948,6 +962,9 @@ scmi_sensor_info_get(const struct scmi_protocol_handle *ph, u32 sensor_id)
 {
 	struct sensors_info *si = ph->get_priv(ph);
 
+	if (sensor_id >= si->num_sensors)
+		return NULL;
+
 	return si->sensors + sensor_id;
 }
 
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index f191a1f901ac..0eb6b617f709 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -630,7 +630,7 @@ static int __init dmi_smbios3_present(const u8 *buf)
 {
 	if (memcmp(buf, "_SM3_", 5) == 0 &&
 	    buf[6] < 32 && dmi_checksum(buf, buf[6])) {
-		dmi_ver = get_unaligned_be32(buf + 6) & 0xFFFFFF;
+		dmi_ver = get_unaligned_be24(buf + 7);
 		dmi_num = 0;			/* No longer specified */
 		dmi_len = get_unaligned_le32(buf + 12);
 		dmi_base = get_unaligned_le64(buf + 16);
diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c
index 4dde8edd53b6..3e8d4b51a814 100644
--- a/drivers/firmware/efi/capsule-loader.c
+++ b/drivers/firmware/efi/capsule-loader.c
@@ -243,29 +243,6 @@ failed:
 }
 
 /**
- * efi_capsule_flush - called by file close or file flush
- * @file: file pointer
- * @id: not used
- *
- *	If a capsule is being partially uploaded then calling this function
- *	will be treated as upload termination and will free those completed
- *	buffer pages and -ECANCELED will be returned.
- **/
-static int efi_capsule_flush(struct file *file, fl_owner_t id)
-{
-	int ret = 0;
-	struct capsule_info *cap_info = file->private_data;
-
-	if (cap_info->index > 0) {
-		pr_err("capsule upload not complete\n");
-		efi_free_all_buff_pages(cap_info);
-		ret = -ECANCELED;
-	}
-
-	return ret;
-}
-
-/**
  * efi_capsule_release - called by file close
  * @inode: not used
  * @file: file pointer
@@ -277,6 +254,13 @@ static int efi_capsule_release(struct inode *inode, struct file *file)
 {
 	struct capsule_info *cap_info = file->private_data;
 
+	if (cap_info->index > 0 &&
+	    (cap_info->header.headersize == 0 ||
+	     cap_info->count < cap_info->total_size)) {
+		pr_err("capsule upload not complete\n");
+		efi_free_all_buff_pages(cap_info);
+	}
+
 	kfree(cap_info->pages);
 	kfree(cap_info->phys);
 	kfree(file->private_data);
@@ -324,7 +308,6 @@ static const struct file_operations efi_capsule_fops = {
 	.owner = THIS_MODULE,
 	.open = efi_capsule_open,
 	.write = efi_capsule_write,
-	.flush = efi_capsule_flush,
 	.release = efi_capsule_release,
 	.llseek = no_llseek,
 };
diff --git a/drivers/firmware/efi/dev-path-parser.c b/drivers/firmware/efi/dev-path-parser.c
index eb9c65f97841..f80d87c199c3 100644
--- a/drivers/firmware/efi/dev-path-parser.c
+++ b/drivers/firmware/efi/dev-path-parser.c
@@ -15,9 +15,11 @@
 static long __init parse_acpi_path(const struct efi_dev_path *node,
 				   struct device *parent, struct device **child)
 {
-	char hid[ACPI_ID_LEN], uid[11]; /* UINT_MAX + null byte */
 	struct acpi_device *adev;
 	struct device *phys_dev;
+	char hid[ACPI_ID_LEN];
+	u64 uid;
+	int ret;
 
 	if (node->header.length != 12)
 		return -EINVAL;
@@ -27,12 +29,12 @@ static long __init parse_acpi_path(const struct efi_dev_path *node,
 		'A' + ((node->acpi.hid >>  5) & 0x1f) - 1,
 		'A' + ((node->acpi.hid >>  0) & 0x1f) - 1,
 			node->acpi.hid >> 16);
-	sprintf(uid, "%u", node->acpi.uid);
 
 	for_each_acpi_dev_match(adev, hid, NULL, -1) {
-		if (adev->pnp.unique_id && !strcmp(adev->pnp.unique_id, uid))
+		ret = acpi_dev_uid_to_integer(adev, &uid);
+		if (ret == 0 && node->acpi.uid == uid)
 			break;
-		if (!adev->pnp.unique_id && node->acpi.uid == 0)
+		if (ret == -ENODATA && node->acpi.uid == 0)
 			break;
 	}
 	if (!adev)
diff --git a/drivers/firmware/efi/efibc.c b/drivers/firmware/efi/efibc.c
index 8ced7af8e56d..4f9fb086eab7 100644
--- a/drivers/firmware/efi/efibc.c
+++ b/drivers/firmware/efi/efibc.c
@@ -48,6 +48,9 @@ static int efibc_reboot_notifier_call(struct notifier_block *notifier,
 		return NOTIFY_DONE;
 
 	wdata = kmalloc(MAX_DATA_LEN * sizeof(efi_char16_t), GFP_KERNEL);
+	if (!wdata)
+		return NOTIFY_DONE;
+
 	for (l = 0; l < MAX_DATA_LEN - 1 && str[l] != '\0'; l++)
 		wdata[l] = str[l];
 	wdata[l] = L'\0';
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index d0537573501e..b43fdb319fd4 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -37,8 +37,17 @@ KBUILD_CFLAGS			:= $(cflags-y) -Os -DDISABLE_BRANCH_PROFILING \
 				   $(call cc-option,-fno-addrsig) \
 				   -D__DISABLE_EXPORTS
 
+#
+# struct randomization only makes sense for Linux internal types, which the EFI
+# stub code never touches, so let's turn off struct randomization for the stub
+# altogether
+#
+KBUILD_CFLAGS := $(filter-out $(RANDSTRUCT_CFLAGS), $(KBUILD_CFLAGS))
+
 # remove SCS flags from all objects in this directory
 KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_SCS), $(KBUILD_CFLAGS))
+# disable CFI
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_CFI), $(KBUILD_CFLAGS))
 # disable LTO
 KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO), $(KBUILD_CFLAGS))
 
diff --git a/drivers/firmware/efi/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c
index 8a18930f3eb6..516f4f0069bd 100644
--- a/drivers/firmware/efi/libstub/secureboot.c
+++ b/drivers/firmware/efi/libstub/secureboot.c
@@ -14,7 +14,7 @@
 
 /* SHIM variables */
 static const efi_guid_t shim_guid = EFI_SHIM_LOCK_GUID;
-static const efi_char16_t shim_MokSBState_name[] = L"MokSBState";
+static const efi_char16_t shim_MokSBState_name[] = L"MokSBStateRT";
 
 static efi_status_t get_var(efi_char16_t *name, efi_guid_t *vendor, u32 *attr,
 			    unsigned long *data_size, void *data)
@@ -43,8 +43,8 @@ enum efi_secureboot_mode efi_get_secureboot(void)
 
 	/*
 	 * See if a user has put the shim into insecure mode. If so, and if the
-	 * variable doesn't have the runtime attribute set, we might as well
-	 * honor that.
+	 * variable doesn't have the non-volatile attribute set, we might as
+	 * well honor that.
 	 */
 	size = sizeof(moksbstate);
 	status = get_efi_var(shim_MokSBState_name, &shim_guid,
@@ -53,7 +53,7 @@ enum efi_secureboot_mode efi_get_secureboot(void)
 	/* If it fails, we don't care why. Default to secure */
 	if (status != EFI_SUCCESS)
 		goto secure_boot_enabled;
-	if (!(attr & EFI_VARIABLE_RUNTIME_ACCESS) && moksbstate == 1)
+	if (!(attr & EFI_VARIABLE_NON_VOLATILE) && moksbstate == 1)
 		return efi_secureboot_mode_disabled;
 
 secure_boot_enabled:
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index 05ae8bcc9d67..7a7abc8959d2 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -220,7 +220,6 @@ adjust_memory_range_protection(unsigned long start, unsigned long size)
 	unsigned long end, next;
 	unsigned long rounded_start, rounded_end;
 	unsigned long unprotect_start, unprotect_size;
-	int has_system_memory = 0;
 
 	if (efi_dxe_table == NULL)
 		return;
@@ -517,6 +516,13 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 	hdr->ramdisk_image = 0;
 	hdr->ramdisk_size = 0;
 
+	/*
+	 * Disregard any setup data that was provided by the bootloader:
+	 * setup_data could be pointing anywhere, and we have no way of
+	 * authenticating or validating the payload.
+	 */
+	hdr->setup_data = 0;
+
 	efi_stub_entry(handle, sys_table_arg, boot_params);
 	/* not reached */
 
diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index cfb448eabdaa..bc6b5a12bf74 100644
--- a/drivers/firmware/psci/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -274,7 +274,7 @@ static void set_conduit(enum arm_smccc_conduit conduit)
 	psci_conduit = conduit;
 }
 
-static int get_set_conduit_method(struct device_node *np)
+static int get_set_conduit_method(const struct device_node *np)
 {
 	const char *method;
 
@@ -334,7 +334,7 @@ static int __init psci_features(u32 psci_func_id)
 static int psci_suspend_finisher(unsigned long state)
 {
 	u32 power_state = state;
-	phys_addr_t pa_cpu_resume = __pa_symbol(function_nocfi(cpu_resume));
+	phys_addr_t pa_cpu_resume = __pa_symbol(cpu_resume);
 
 	return psci_ops.cpu_suspend(power_state, pa_cpu_resume);
 }
@@ -359,7 +359,7 @@ int psci_cpu_suspend_enter(u32 state)
 
 static int psci_system_suspend(unsigned long unused)
 {
-	phys_addr_t pa_cpu_resume = __pa_symbol(function_nocfi(cpu_resume));
+	phys_addr_t pa_cpu_resume = __pa_symbol(cpu_resume);
 
 	return invoke_psci_fn(PSCI_FN_NATIVE(1_0, SYSTEM_SUSPEND),
 			      pa_cpu_resume, 0, 0);
@@ -528,7 +528,7 @@ typedef int (*psci_initcall_t)(const struct device_node *);
  *
  * Probe based on PSCI PSCI_VERSION function
  */
-static int __init psci_0_2_init(struct device_node *np)
+static int __init psci_0_2_init(const struct device_node *np)
 {
 	int err;
 
@@ -549,7 +549,7 @@ static int __init psci_0_2_init(struct device_node *np)
 /*
  * PSCI < v0.2 get PSCI Function IDs via DT.
  */
-static int __init psci_0_1_init(struct device_node *np)
+static int __init psci_0_1_init(const struct device_node *np)
 {
 	u32 id;
 	int err;
@@ -585,7 +585,7 @@ static int __init psci_0_1_init(struct device_node *np)
 	return 0;
 }
 
-static int __init psci_1_0_init(struct device_node *np)
+static int __init psci_1_0_init(const struct device_node *np)
 {
 	int err;
 
diff --git a/drivers/fpga/intel-m10-bmc-sec-update.c b/drivers/fpga/intel-m10-bmc-sec-update.c
index 72c677c910de..133e511355c9 100644
--- a/drivers/fpga/intel-m10-bmc-sec-update.c
+++ b/drivers/fpga/intel-m10-bmc-sec-update.c
@@ -148,10 +148,6 @@ static ssize_t flash_count_show(struct device *dev,
 	stride = regmap_get_reg_stride(sec->m10bmc->regmap);
 	num_bits = FLASH_COUNT_SIZE * 8;
 
-	flash_buf = kmalloc(FLASH_COUNT_SIZE, GFP_KERNEL);
-	if (!flash_buf)
-		return -ENOMEM;
-
 	if (FLASH_COUNT_SIZE % stride) {
 		dev_err(sec->dev,
 			"FLASH_COUNT_SIZE (0x%x) not aligned to stride (0x%x)\n",
@@ -160,6 +156,10 @@ static ssize_t flash_count_show(struct device *dev,
 		return -EINVAL;
 	}
 
+	flash_buf = kmalloc(FLASH_COUNT_SIZE, GFP_KERNEL);
+	if (!flash_buf)
+		return -ENOMEM;
+
 	ret = regmap_bulk_read(sec->m10bmc->regmap, STAGING_FLASH_COUNT,
 			       flash_buf, FLASH_COUNT_SIZE / stride);
 	if (ret) {
diff --git a/drivers/gpio/gpio-104-dio-48e.c b/drivers/gpio/gpio-104-dio-48e.c
index a41551870759..74cc71bb3984 100644
--- a/drivers/gpio/gpio-104-dio-48e.c
+++ b/drivers/gpio/gpio-104-dio-48e.c
@@ -164,6 +164,7 @@ static void dio48e_irq_mask(struct irq_data *data)
 		dio48egpio->irq_mask &= ~BIT(0);
 	else
 		dio48egpio->irq_mask &= ~BIT(1);
+	gpiochip_disable_irq(chip, offset);
 
 	if (!dio48egpio->irq_mask)
 		/* disable interrupts */
@@ -191,6 +192,7 @@ static void dio48e_irq_unmask(struct irq_data *data)
 		iowrite8(0x00, &dio48egpio->reg->enable_interrupt);
 	}
 
+	gpiochip_enable_irq(chip, offset);
 	if (offset == 19)
 		dio48egpio->irq_mask |= BIT(0);
 	else
@@ -213,12 +215,14 @@ static int dio48e_irq_set_type(struct irq_data *data, unsigned int flow_type)
 	return 0;
 }
 
-static struct irq_chip dio48e_irqchip = {
+static const struct irq_chip dio48e_irqchip = {
 	.name = "104-dio-48e",
 	.irq_ack = dio48e_irq_ack,
 	.irq_mask = dio48e_irq_mask,
 	.irq_unmask = dio48e_irq_unmask,
-	.irq_set_type = dio48e_irq_set_type
+	.irq_set_type = dio48e_irq_set_type,
+	.flags = IRQCHIP_IMMUTABLE,
+	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };
 
 static irqreturn_t dio48e_irq_handler(int irq, void *dev_id)
@@ -322,7 +326,7 @@ static int dio48e_probe(struct device *dev, unsigned int id)
 	dio48egpio->chip.set_multiple = dio48e_gpio_set_multiple;
 
 	girq = &dio48egpio->chip.irq;
-	girq->chip = &dio48e_irqchip;
+	gpio_irq_chip_set_chip(girq, &dio48e_irqchip);
 	/* This will let us handle the parent IRQ in the driver */
 	girq->parent_handler = NULL;
 	girq->num_parents = 0;
diff --git a/drivers/gpio/gpio-104-idi-48.c b/drivers/gpio/gpio-104-idi-48.c
index 40be76efeed7..3286b914a2cf 100644
--- a/drivers/gpio/gpio-104-idi-48.c
+++ b/drivers/gpio/gpio-104-idi-48.c
@@ -113,6 +113,7 @@ static void idi_48_irq_mask(struct irq_data *data)
 	spin_lock_irqsave(&idi48gpio->lock, flags);
 
 	idi48gpio->irq_mask[boundary] &= ~mask;
+	gpiochip_disable_irq(chip, offset);
 
 	/* Exit early if there are still input lines with IRQ unmasked */
 	if (idi48gpio->irq_mask[boundary])
@@ -140,6 +141,7 @@ static void idi_48_irq_unmask(struct irq_data *data)
 
 	prev_irq_mask = idi48gpio->irq_mask[boundary];
 
+	gpiochip_enable_irq(chip, offset);
 	idi48gpio->irq_mask[boundary] |= mask;
 
 	/* Exit early if IRQ was already unmasked for this boundary */
@@ -164,12 +166,14 @@ static int idi_48_irq_set_type(struct irq_data *data, unsigned int flow_type)
 	return 0;
 }
 
-static struct irq_chip idi_48_irqchip = {
+static const struct irq_chip idi_48_irqchip = {
 	.name = "104-idi-48",
 	.irq_ack = idi_48_irq_ack,
 	.irq_mask = idi_48_irq_mask,
 	.irq_unmask = idi_48_irq_unmask,
-	.irq_set_type = idi_48_irq_set_type
+	.irq_set_type = idi_48_irq_set_type,
+	.flags = IRQCHIP_IMMUTABLE,
+	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };
 
 static irqreturn_t idi_48_irq_handler(int irq, void *dev_id)
@@ -267,7 +271,7 @@ static int idi_48_probe(struct device *dev, unsigned int id)
 	idi48gpio->chip.get_multiple = idi_48_gpio_get_multiple;
 
 	girq = &idi48gpio->chip.irq;
-	girq->chip = &idi_48_irqchip;
+	gpio_irq_chip_set_chip(girq, &idi_48_irqchip);
 	/* This will let us handle the parent IRQ in the driver */
 	girq->parent_handler = NULL;
 	girq->num_parents = 0;
diff --git a/drivers/gpio/gpio-104-idio-16.c b/drivers/gpio/gpio-104-idio-16.c
index 65a5f581d981..4756e583f223 100644
--- a/drivers/gpio/gpio-104-idio-16.c
+++ b/drivers/gpio/gpio-104-idio-16.c
@@ -174,10 +174,11 @@ static void idio_16_irq_mask(struct irq_data *data)
 {
 	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
 	struct idio_16_gpio *const idio16gpio = gpiochip_get_data(chip);
-	const unsigned long mask = BIT(irqd_to_hwirq(data));
+	const unsigned long offset = irqd_to_hwirq(data);
 	unsigned long flags;
 
-	idio16gpio->irq_mask &= ~mask;
+	idio16gpio->irq_mask &= ~BIT(offset);
+	gpiochip_disable_irq(chip, offset);
 
 	if (!idio16gpio->irq_mask) {
 		raw_spin_lock_irqsave(&idio16gpio->lock, flags);
@@ -192,11 +193,12 @@ static void idio_16_irq_unmask(struct irq_data *data)
 {
 	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
 	struct idio_16_gpio *const idio16gpio = gpiochip_get_data(chip);
-	const unsigned long mask = BIT(irqd_to_hwirq(data));
+	const unsigned long offset = irqd_to_hwirq(data);
 	const unsigned long prev_irq_mask = idio16gpio->irq_mask;
 	unsigned long flags;
 
-	idio16gpio->irq_mask |= mask;
+	gpiochip_enable_irq(chip, offset);
+	idio16gpio->irq_mask |= BIT(offset);
 
 	if (!prev_irq_mask) {
 		raw_spin_lock_irqsave(&idio16gpio->lock, flags);
@@ -217,12 +219,14 @@ static int idio_16_irq_set_type(struct irq_data *data, unsigned int flow_type)
 	return 0;
 }
 
-static struct irq_chip idio_16_irqchip = {
+static const struct irq_chip idio_16_irqchip = {
 	.name = "104-idio-16",
 	.irq_ack = idio_16_irq_ack,
 	.irq_mask = idio_16_irq_mask,
 	.irq_unmask = idio_16_irq_unmask,
-	.irq_set_type = idio_16_irq_set_type
+	.irq_set_type = idio_16_irq_set_type,
+	.flags = IRQCHIP_IMMUTABLE,
+	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };
 
 static irqreturn_t idio_16_irq_handler(int irq, void *dev_id)
@@ -299,7 +303,7 @@ static int idio_16_probe(struct device *dev, unsigned int id)
 	idio16gpio->out_state = 0xFFFF;
 
 	girq = &idio16gpio->chip.irq;
-	girq->chip = &idio_16_irqchip;
+	gpio_irq_chip_set_chip(girq, &idio_16_irqchip);
 	/* This will let us handle the parent IRQ in the driver */
 	girq->parent_handler = NULL;
 	girq->num_parents = 0;
diff --git a/drivers/gpio/gpio-ftgpio010.c b/drivers/gpio/gpio-ftgpio010.c
index f422c3e129a0..f77a965f5780 100644
--- a/drivers/gpio/gpio-ftgpio010.c
+++ b/drivers/gpio/gpio-ftgpio010.c
@@ -41,14 +41,12 @@
  * struct ftgpio_gpio - Gemini GPIO state container
  * @dev: containing device for this instance
  * @gc: gpiochip for this instance
- * @irq: irqchip for this instance
  * @base: remapped I/O-memory base
  * @clk: silicon clock
  */
 struct ftgpio_gpio {
 	struct device *dev;
 	struct gpio_chip gc;
-	struct irq_chip irq;
 	void __iomem *base;
 	struct clk *clk;
 };
@@ -70,6 +68,7 @@ static void ftgpio_gpio_mask_irq(struct irq_data *d)
 	val = readl(g->base + GPIO_INT_EN);
 	val &= ~BIT(irqd_to_hwirq(d));
 	writel(val, g->base + GPIO_INT_EN);
+	gpiochip_disable_irq(gc, irqd_to_hwirq(d));
 }
 
 static void ftgpio_gpio_unmask_irq(struct irq_data *d)
@@ -78,6 +77,7 @@ static void ftgpio_gpio_unmask_irq(struct irq_data *d)
 	struct ftgpio_gpio *g = gpiochip_get_data(gc);
 	u32 val;
 
+	gpiochip_enable_irq(gc, irqd_to_hwirq(d));
 	val = readl(g->base + GPIO_INT_EN);
 	val |= BIT(irqd_to_hwirq(d));
 	writel(val, g->base + GPIO_INT_EN);
@@ -221,6 +221,16 @@ static int ftgpio_gpio_set_config(struct gpio_chip *gc, unsigned int offset,
 	return 0;
 }
 
+static const struct irq_chip ftgpio_irq_chip = {
+	.name = "FTGPIO010",
+	.irq_ack = ftgpio_gpio_ack_irq,
+	.irq_mask = ftgpio_gpio_mask_irq,
+	.irq_unmask = ftgpio_gpio_unmask_irq,
+	.irq_set_type = ftgpio_gpio_set_irq_type,
+	.flags = IRQCHIP_IMMUTABLE,
+	 GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
+
 static int ftgpio_gpio_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -277,14 +287,8 @@ static int ftgpio_gpio_probe(struct platform_device *pdev)
 	if (!IS_ERR(g->clk))
 		g->gc.set_config = ftgpio_gpio_set_config;
 
-	g->irq.name = "FTGPIO010";
-	g->irq.irq_ack = ftgpio_gpio_ack_irq;
-	g->irq.irq_mask = ftgpio_gpio_mask_irq;
-	g->irq.irq_unmask = ftgpio_gpio_unmask_irq;
-	g->irq.irq_set_type = ftgpio_gpio_set_irq_type;
-
 	girq = &g->gc.irq;
-	girq->chip = &g->irq;
+	gpio_irq_chip_set_chip(girq, &ftgpio_irq_chip);
 	girq->parent_handler = ftgpio_gpio_irq_handler;
 	girq->num_parents = 1;
 	girq->parents = devm_kcalloc(dev, 1, sizeof(*girq->parents),
diff --git a/drivers/gpio/gpio-ixp4xx.c b/drivers/gpio/gpio-ixp4xx.c
index 312309be0287..56656fb519f8 100644
--- a/drivers/gpio/gpio-ixp4xx.c
+++ b/drivers/gpio/gpio-ixp4xx.c
@@ -63,6 +63,14 @@ static void ixp4xx_gpio_irq_ack(struct irq_data *d)
 	__raw_writel(BIT(d->hwirq), g->base + IXP4XX_REG_GPIS);
 }
 
+static void ixp4xx_gpio_mask_irq(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+
+	irq_chip_mask_parent(d);
+	gpiochip_disable_irq(gc, d->hwirq);
+}
+
 static void ixp4xx_gpio_irq_unmask(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
@@ -72,6 +80,7 @@ static void ixp4xx_gpio_irq_unmask(struct irq_data *d)
 	if (!(g->irq_edge & BIT(d->hwirq)))
 		ixp4xx_gpio_irq_ack(d);
 
+	gpiochip_enable_irq(gc, d->hwirq);
 	irq_chip_unmask_parent(d);
 }
 
@@ -149,12 +158,14 @@ static int ixp4xx_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 	return irq_chip_set_type_parent(d, IRQ_TYPE_LEVEL_HIGH);
 }
 
-static struct irq_chip ixp4xx_gpio_irqchip = {
+static const struct irq_chip ixp4xx_gpio_irqchip = {
 	.name = "IXP4GPIO",
 	.irq_ack = ixp4xx_gpio_irq_ack,
-	.irq_mask = irq_chip_mask_parent,
+	.irq_mask = ixp4xx_gpio_mask_irq,
 	.irq_unmask = ixp4xx_gpio_irq_unmask,
 	.irq_set_type = ixp4xx_gpio_irq_set_type,
+	.flags = IRQCHIP_IMMUTABLE,
+	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };
 
 static int ixp4xx_gpio_child_to_parent_hwirq(struct gpio_chip *gc,
@@ -263,7 +274,7 @@ static int ixp4xx_gpio_probe(struct platform_device *pdev)
 	g->gc.owner = THIS_MODULE;
 
 	girq = &g->gc.irq;
-	girq->chip = &ixp4xx_gpio_irqchip;
+	gpio_irq_chip_set_chip(girq, &ixp4xx_gpio_irqchip);
 	girq->fwnode = g->fwnode;
 	girq->parent_domain = parent;
 	girq->child_to_parent_hwirq = ixp4xx_gpio_child_to_parent_hwirq;
diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c
index 8943cea92764..523dfd17dd92 100644
--- a/drivers/gpio/gpio-mockup.c
+++ b/drivers/gpio/gpio-mockup.c
@@ -373,6 +373,13 @@ static void gpio_mockup_debugfs_setup(struct device *dev,
 	}
 }
 
+static void gpio_mockup_debugfs_cleanup(void *data)
+{
+	struct gpio_mockup_chip *chip = data;
+
+	debugfs_remove_recursive(chip->dbg_dir);
+}
+
 static void gpio_mockup_dispose_mappings(void *data)
 {
 	struct gpio_mockup_chip *chip = data;
@@ -455,7 +462,7 @@ static int gpio_mockup_probe(struct platform_device *pdev)
 
 	gpio_mockup_debugfs_setup(dev, chip);
 
-	return 0;
+	return devm_add_action_or_reset(dev, gpio_mockup_debugfs_cleanup, chip);
 }
 
 static const struct of_device_id gpio_mockup_of_match[] = {
@@ -526,8 +533,10 @@ static int __init gpio_mockup_register_chip(int idx)
 	}
 
 	fwnode = fwnode_create_software_node(properties, NULL);
-	if (IS_ERR(fwnode))
+	if (IS_ERR(fwnode)) {
+		kfree_strarray(line_names, ngpio);
 		return PTR_ERR(fwnode);
+	}
 
 	pdevinfo.name = "gpio-mockup";
 	pdevinfo.id = idx;
@@ -590,9 +599,9 @@ static int __init gpio_mockup_init(void)
 
 static void __exit gpio_mockup_exit(void)
 {
+	gpio_mockup_unregister_pdevs();
 	debugfs_remove_recursive(gpio_mockup_dbg_dir);
 	platform_driver_unregister(&gpio_mockup_driver);
-	gpio_mockup_unregister_pdevs();
 }
 
 module_init(gpio_mockup_init);
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index 15049822937a..3eb08cd1fdc0 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -169,6 +169,7 @@ static int mpc8xxx_irq_set_type(struct irq_data *d, unsigned int flow_type)
 
 	switch (flow_type) {
 	case IRQ_TYPE_EDGE_FALLING:
+	case IRQ_TYPE_LEVEL_LOW:
 		raw_spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
 		gc->write_reg(mpc8xxx_gc->regs + GPIO_ICR,
 			gc->read_reg(mpc8xxx_gc->regs + GPIO_ICR)
diff --git a/drivers/gpio/gpio-mt7621.c b/drivers/gpio/gpio-mt7621.c
index d8a26e503ca5..f163f5ca857b 100644
--- a/drivers/gpio/gpio-mt7621.c
+++ b/drivers/gpio/gpio-mt7621.c
@@ -112,6 +112,8 @@ mediatek_gpio_irq_unmask(struct irq_data *d)
 	unsigned long flags;
 	u32 rise, fall, high, low;
 
+	gpiochip_enable_irq(gc, d->hwirq);
+
 	spin_lock_irqsave(&rg->lock, flags);
 	rise = mtk_gpio_r32(rg, GPIO_REG_REDGE);
 	fall = mtk_gpio_r32(rg, GPIO_REG_FEDGE);
@@ -143,6 +145,8 @@ mediatek_gpio_irq_mask(struct irq_data *d)
 	mtk_gpio_w32(rg, GPIO_REG_HLVL, high & ~BIT(pin));
 	mtk_gpio_w32(rg, GPIO_REG_LLVL, low & ~BIT(pin));
 	spin_unlock_irqrestore(&rg->lock, flags);
+
+	gpiochip_disable_irq(gc, d->hwirq);
 }
 
 static int
@@ -204,6 +208,16 @@ mediatek_gpio_xlate(struct gpio_chip *chip,
 	return gpio % MTK_BANK_WIDTH;
 }
 
+static const struct irq_chip mt7621_irq_chip = {
+	.name		= "mt7621-gpio",
+	.irq_mask_ack	= mediatek_gpio_irq_mask,
+	.irq_mask	= mediatek_gpio_irq_mask,
+	.irq_unmask	= mediatek_gpio_irq_unmask,
+	.irq_set_type	= mediatek_gpio_irq_type,
+	.flags		= IRQCHIP_IMMUTABLE,
+	GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
+
 static int
 mediatek_gpio_bank_probe(struct device *dev, int bank)
 {
@@ -238,11 +252,6 @@ mediatek_gpio_bank_probe(struct device *dev, int bank)
 		return -ENOMEM;
 
 	rg->chip.offset = bank * MTK_BANK_WIDTH;
-	rg->irq_chip.name = dev_name(dev);
-	rg->irq_chip.irq_unmask = mediatek_gpio_irq_unmask;
-	rg->irq_chip.irq_mask = mediatek_gpio_irq_mask;
-	rg->irq_chip.irq_mask_ack = mediatek_gpio_irq_mask;
-	rg->irq_chip.irq_set_type = mediatek_gpio_irq_type;
 
 	if (mtk->gpio_irq) {
 		struct gpio_irq_chip *girq;
@@ -262,7 +271,7 @@ mediatek_gpio_bank_probe(struct device *dev, int bank)
 		}
 
 		girq = &rg->chip.irq;
-		girq->chip = &rg->irq_chip;
+		gpio_irq_chip_set_chip(girq, &mt7621_irq_chip);
 		/* This will let us handle the parent IRQ in the driver */
 		girq->parent_handler = NULL;
 		girq->num_parents = 0;
diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c
index aa126ab80f0c..1bb317b8dcce 100644
--- a/drivers/gpio/gpio-mvebu.c
+++ b/drivers/gpio/gpio-mvebu.c
@@ -790,8 +790,12 @@ static int mvebu_pwm_probe(struct platform_device *pdev,
 	u32 offset;
 	u32 set;
 
-	if (of_device_is_compatible(mvchip->chip.of_node,
-				    "marvell,armada-370-gpio")) {
+	if (mvchip->soc_variant == MVEBU_GPIO_SOC_VARIANT_A8K) {
+		int ret = of_property_read_u32(dev->of_node,
+					       "marvell,pwm-offset", &offset);
+		if (ret < 0)
+			return 0;
+	} else {
 		/*
 		 * There are only two sets of PWM configuration registers for
 		 * all the GPIO lines on those SoCs which this driver reserves
@@ -801,13 +805,6 @@ static int mvebu_pwm_probe(struct platform_device *pdev,
 		if (!platform_get_resource_byname(pdev, IORESOURCE_MEM, "pwm"))
 			return 0;
 		offset = 0;
-	} else if (mvchip->soc_variant == MVEBU_GPIO_SOC_VARIANT_A8K) {
-		int ret = of_property_read_u32(dev->of_node,
-					       "marvell,pwm-offset", &offset);
-		if (ret < 0)
-			return 0;
-	} else {
-		return 0;
 	}
 
 	if (IS_ERR(mvchip->clk))
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index ecd7d169470b..2925f4d8cef3 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -1175,7 +1175,9 @@ static int pca953x_suspend(struct device *dev)
 {
 	struct pca953x_chip *chip = dev_get_drvdata(dev);
 
+	mutex_lock(&chip->i2c_lock);
 	regcache_cache_only(chip->regmap, true);
+	mutex_unlock(&chip->i2c_lock);
 
 	if (atomic_read(&chip->wakeup_path))
 		device_set_wakeup_path(dev);
@@ -1198,13 +1200,17 @@ static int pca953x_resume(struct device *dev)
 		}
 	}
 
+	mutex_lock(&chip->i2c_lock);
 	regcache_cache_only(chip->regmap, false);
 	regcache_mark_dirty(chip->regmap);
 	ret = pca953x_regcache_sync(dev);
-	if (ret)
+	if (ret) {
+		mutex_unlock(&chip->i2c_lock);
 		return ret;
+	}
 
 	ret = regcache_sync(chip->regmap);
+	mutex_unlock(&chip->i2c_lock);
 	if (ret) {
 		dev_err(dev, "Failed to restore register map: %d\n", ret);
 		return ret;
diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c
index c7fbfa3ae43b..1198ab0305d0 100644
--- a/drivers/gpio/gpio-pxa.c
+++ b/drivers/gpio/gpio-pxa.c
@@ -661,24 +661,17 @@ static int pxa_gpio_probe(struct platform_device *pdev)
 	if (IS_ERR(gpio_reg_base))
 		return PTR_ERR(gpio_reg_base);
 
-	clk = clk_get(&pdev->dev, NULL);
+	clk = devm_clk_get_enabled(&pdev->dev, NULL);
 	if (IS_ERR(clk)) {
 		dev_err(&pdev->dev, "Error %ld to get gpio clock\n",
 			PTR_ERR(clk));
 		return PTR_ERR(clk);
 	}
-	ret = clk_prepare_enable(clk);
-	if (ret) {
-		clk_put(clk);
-		return ret;
-	}
 
 	/* Initialize GPIO chips */
 	ret = pxa_init_gpio_chip(pchip, pxa_last_gpio + 1, gpio_reg_base);
-	if (ret) {
-		clk_put(clk);
+	if (ret)
 		return ret;
-	}
 
 	/* clear all GPIO edge detects */
 	for_each_gpio_bank(gpio, c, pchip) {
diff --git a/drivers/gpio/gpio-realtek-otto.c b/drivers/gpio/gpio-realtek-otto.c
index 63dcf42f7c20..d6418f89d3f6 100644
--- a/drivers/gpio/gpio-realtek-otto.c
+++ b/drivers/gpio/gpio-realtek-otto.c
@@ -46,10 +46,20 @@
  * @lock: Lock for accessing the IRQ registers and values
  * @intr_mask: Mask for interrupts lines
  * @intr_type: Interrupt type selection
+ * @bank_read: Read a bank setting as a single 32-bit value
+ * @bank_write: Write a bank setting as a single 32-bit value
+ * @imr_line_pos: Bit shift of an IRQ line's IMR value.
+ *
+ * The DIR, DATA, and ISR registers consist of four 8-bit port values, packed
+ * into a single 32-bit register. Use @bank_read (@bank_write) to get (assign)
+ * a value from (to) these registers. The IMR register consists of four 16-bit
+ * port values, packed into two 32-bit registers. Use @imr_line_pos to get the
+ * bit shift of the 2-bit field for a line's IMR settings. Shifts larger than
+ * 32 overflow into the second register.
  *
  * Because the interrupt mask register (IMR) combines the function of IRQ type
  * selection and masking, two extra values are stored. @intr_mask is used to
- * mask/unmask the interrupts for a GPIO port, and @intr_type is used to store
+ * mask/unmask the interrupts for a GPIO line, and @intr_type is used to store
  * the selected interrupt types. The logical AND of these values is written to
  * IMR on changes.
  */
@@ -59,10 +69,11 @@ struct realtek_gpio_ctrl {
 	void __iomem *cpumask_base;
 	struct cpumask cpu_irq_maskable;
 	raw_spinlock_t lock;
-	u16 intr_mask[REALTEK_GPIO_PORTS_PER_BANK];
-	u16 intr_type[REALTEK_GPIO_PORTS_PER_BANK];
-	unsigned int (*port_offset_u8)(unsigned int port);
-	unsigned int (*port_offset_u16)(unsigned int port);
+	u8 intr_mask[REALTEK_GPIO_MAX];
+	u8 intr_type[REALTEK_GPIO_MAX];
+	u32 (*bank_read)(void __iomem *reg);
+	void (*bank_write)(void __iomem *reg, u32 value);
+	unsigned int (*line_imr_pos)(unsigned int line);
 };
 
 /* Expand with more flags as devices with other quirks are added */
@@ -101,14 +112,22 @@ static struct realtek_gpio_ctrl *irq_data_to_ctrl(struct irq_data *data)
  * port. The two interrupt mask registers store two bits per GPIO, so use u16
  * values.
  */
-static unsigned int realtek_gpio_port_offset_u8(unsigned int port)
+static u32 realtek_gpio_bank_read_swapped(void __iomem *reg)
 {
-	return port;
+	return ioread32be(reg);
 }
 
-static unsigned int realtek_gpio_port_offset_u16(unsigned int port)
+static void realtek_gpio_bank_write_swapped(void __iomem *reg, u32 value)
 {
-	return 2 * port;
+	iowrite32be(value, reg);
+}
+
+static unsigned int realtek_gpio_line_imr_pos_swapped(unsigned int line)
+{
+	unsigned int port_pin = line % 8;
+	unsigned int port = line / 8;
+
+	return 2 * (8 * (port ^ 1) + port_pin);
 }
 
 /*
@@ -119,66 +138,67 @@ static unsigned int realtek_gpio_port_offset_u16(unsigned int port)
  * per GPIO, so use u16 values. The first register contains ports 1 and 0, the
  * second ports 3 and 2.
  */
-static unsigned int realtek_gpio_port_offset_u8_rev(unsigned int port)
+static u32 realtek_gpio_bank_read(void __iomem *reg)
 {
-	return 3 - port;
+	return ioread32(reg);
 }
 
-static unsigned int realtek_gpio_port_offset_u16_rev(unsigned int port)
+static void realtek_gpio_bank_write(void __iomem *reg, u32 value)
 {
-	return 2 * (port ^ 1);
+	iowrite32(value, reg);
 }
 
-static void realtek_gpio_write_imr(struct realtek_gpio_ctrl *ctrl,
-	unsigned int port, u16 irq_type, u16 irq_mask)
+static unsigned int realtek_gpio_line_imr_pos(unsigned int line)
 {
-	iowrite16(irq_type & irq_mask,
-		ctrl->base + REALTEK_GPIO_REG_IMR + ctrl->port_offset_u16(port));
+	return 2 * line;
 }
 
-static void realtek_gpio_clear_isr(struct realtek_gpio_ctrl *ctrl,
-	unsigned int port, u8 mask)
+static void realtek_gpio_clear_isr(struct realtek_gpio_ctrl *ctrl, u32 mask)
 {
-	iowrite8(mask, ctrl->base + REALTEK_GPIO_REG_ISR + ctrl->port_offset_u8(port));
+	ctrl->bank_write(ctrl->base + REALTEK_GPIO_REG_ISR, mask);
 }
 
-static u8 realtek_gpio_read_isr(struct realtek_gpio_ctrl *ctrl, unsigned int port)
+static u32 realtek_gpio_read_isr(struct realtek_gpio_ctrl *ctrl)
 {
-	return ioread8(ctrl->base + REALTEK_GPIO_REG_ISR + ctrl->port_offset_u8(port));
+	return ctrl->bank_read(ctrl->base + REALTEK_GPIO_REG_ISR);
 }
 
-/* Set the rising and falling edge mask bits for a GPIO port pin */
-static u16 realtek_gpio_imr_bits(unsigned int pin, u16 value)
+/* Set the rising and falling edge mask bits for a GPIO pin */
+static void realtek_gpio_update_line_imr(struct realtek_gpio_ctrl *ctrl, unsigned int line)
 {
-	return (value & REALTEK_GPIO_IMR_LINE_MASK) << 2 * pin;
+	void __iomem *reg = ctrl->base + REALTEK_GPIO_REG_IMR;
+	unsigned int line_shift = ctrl->line_imr_pos(line);
+	unsigned int shift = line_shift % 32;
+	u32 irq_type = ctrl->intr_type[line];
+	u32 irq_mask = ctrl->intr_mask[line];
+	u32 reg_val;
+
+	reg += 4 * (line_shift / 32);
+	reg_val = ioread32(reg);
+	reg_val &= ~(REALTEK_GPIO_IMR_LINE_MASK << shift);
+	reg_val |= (irq_type & irq_mask & REALTEK_GPIO_IMR_LINE_MASK) << shift;
+	iowrite32(reg_val, reg);
 }
 
 static void realtek_gpio_irq_ack(struct irq_data *data)
 {
 	struct realtek_gpio_ctrl *ctrl = irq_data_to_ctrl(data);
 	irq_hw_number_t line = irqd_to_hwirq(data);
-	unsigned int port = line / 8;
-	unsigned int port_pin = line % 8;
 
-	realtek_gpio_clear_isr(ctrl, port, BIT(port_pin));
+	realtek_gpio_clear_isr(ctrl, BIT(line));
 }
 
 static void realtek_gpio_irq_unmask(struct irq_data *data)
 {
 	struct realtek_gpio_ctrl *ctrl = irq_data_to_ctrl(data);
 	unsigned int line = irqd_to_hwirq(data);
-	unsigned int port = line / 8;
-	unsigned int port_pin = line % 8;
 	unsigned long flags;
-	u16 m;
 
 	gpiochip_enable_irq(&ctrl->gc, line);
 
 	raw_spin_lock_irqsave(&ctrl->lock, flags);
-	m = ctrl->intr_mask[port];
-	m |= realtek_gpio_imr_bits(port_pin, REALTEK_GPIO_IMR_LINE_MASK);
-	ctrl->intr_mask[port] = m;
-	realtek_gpio_write_imr(ctrl, port, ctrl->intr_type[port], m);
+	ctrl->intr_mask[line] = REALTEK_GPIO_IMR_LINE_MASK;
+	realtek_gpio_update_line_imr(ctrl, line);
 	raw_spin_unlock_irqrestore(&ctrl->lock, flags);
 }
 
@@ -186,16 +206,11 @@ static void realtek_gpio_irq_mask(struct irq_data *data)
 {
 	struct realtek_gpio_ctrl *ctrl = irq_data_to_ctrl(data);
 	unsigned int line = irqd_to_hwirq(data);
-	unsigned int port = line / 8;
-	unsigned int port_pin = line % 8;
 	unsigned long flags;
-	u16 m;
 
 	raw_spin_lock_irqsave(&ctrl->lock, flags);
-	m = ctrl->intr_mask[port];
-	m &= ~realtek_gpio_imr_bits(port_pin, REALTEK_GPIO_IMR_LINE_MASK);
-	ctrl->intr_mask[port] = m;
-	realtek_gpio_write_imr(ctrl, port, ctrl->intr_type[port], m);
+	ctrl->intr_mask[line] = 0;
+	realtek_gpio_update_line_imr(ctrl, line);
 	raw_spin_unlock_irqrestore(&ctrl->lock, flags);
 
 	gpiochip_disable_irq(&ctrl->gc, line);
@@ -205,10 +220,8 @@ static int realtek_gpio_irq_set_type(struct irq_data *data, unsigned int flow_ty
 {
 	struct realtek_gpio_ctrl *ctrl = irq_data_to_ctrl(data);
 	unsigned int line = irqd_to_hwirq(data);
-	unsigned int port = line / 8;
-	unsigned int port_pin = line % 8;
 	unsigned long flags;
-	u16 type, t;
+	u8 type;
 
 	switch (flow_type & IRQ_TYPE_SENSE_MASK) {
 	case IRQ_TYPE_EDGE_FALLING:
@@ -227,11 +240,8 @@ static int realtek_gpio_irq_set_type(struct irq_data *data, unsigned int flow_ty
 	irq_set_handler_locked(data, handle_edge_irq);
 
 	raw_spin_lock_irqsave(&ctrl->lock, flags);
-	t = ctrl->intr_type[port];
-	t &= ~realtek_gpio_imr_bits(port_pin, REALTEK_GPIO_IMR_LINE_MASK);
-	t |= realtek_gpio_imr_bits(port_pin, type);
-	ctrl->intr_type[port] = t;
-	realtek_gpio_write_imr(ctrl, port, t, ctrl->intr_mask[port]);
+	ctrl->intr_type[line] = type;
+	realtek_gpio_update_line_imr(ctrl, line);
 	raw_spin_unlock_irqrestore(&ctrl->lock, flags);
 
 	return 0;
@@ -242,28 +252,21 @@ static void realtek_gpio_irq_handler(struct irq_desc *desc)
 	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
 	struct realtek_gpio_ctrl *ctrl = gpiochip_get_data(gc);
 	struct irq_chip *irq_chip = irq_desc_get_chip(desc);
-	unsigned int lines_done;
-	unsigned int port_pin_count;
 	unsigned long status;
 	int offset;
 
 	chained_irq_enter(irq_chip, desc);
 
-	for (lines_done = 0; lines_done < gc->ngpio; lines_done += 8) {
-		status = realtek_gpio_read_isr(ctrl, lines_done / 8);
-		port_pin_count = min(gc->ngpio - lines_done, 8U);
-		for_each_set_bit(offset, &status, port_pin_count)
-			generic_handle_domain_irq(gc->irq.domain, offset + lines_done);
-	}
+	status = realtek_gpio_read_isr(ctrl);
+	for_each_set_bit(offset, &status, gc->ngpio)
+		generic_handle_domain_irq(gc->irq.domain, offset);
 
 	chained_irq_exit(irq_chip, desc);
 }
 
-static inline void __iomem *realtek_gpio_irq_cpu_mask(struct realtek_gpio_ctrl *ctrl,
-	unsigned int port, int cpu)
+static inline void __iomem *realtek_gpio_irq_cpu_mask(struct realtek_gpio_ctrl *ctrl, int cpu)
 {
-	return ctrl->cpumask_base + ctrl->port_offset_u8(port) +
-		REALTEK_GPIO_PORTS_PER_BANK * cpu;
+	return ctrl->cpumask_base + REALTEK_GPIO_PORTS_PER_BANK * cpu;
 }
 
 static int realtek_gpio_irq_set_affinity(struct irq_data *data,
@@ -271,12 +274,10 @@ static int realtek_gpio_irq_set_affinity(struct irq_data *data,
 {
 	struct realtek_gpio_ctrl *ctrl = irq_data_to_ctrl(data);
 	unsigned int line = irqd_to_hwirq(data);
-	unsigned int port = line / 8;
-	unsigned int port_pin = line % 8;
 	void __iomem *irq_cpu_mask;
 	unsigned long flags;
 	int cpu;
-	u8 v;
+	u32 v;
 
 	if (!ctrl->cpumask_base)
 		return -ENXIO;
@@ -284,15 +285,15 @@ static int realtek_gpio_irq_set_affinity(struct irq_data *data,
 	raw_spin_lock_irqsave(&ctrl->lock, flags);
 
 	for_each_cpu(cpu, &ctrl->cpu_irq_maskable) {
-		irq_cpu_mask = realtek_gpio_irq_cpu_mask(ctrl, port, cpu);
-		v = ioread8(irq_cpu_mask);
+		irq_cpu_mask = realtek_gpio_irq_cpu_mask(ctrl, cpu);
+		v = ctrl->bank_read(irq_cpu_mask);
 
 		if (cpumask_test_cpu(cpu, dest))
-			v |= BIT(port_pin);
+			v |= BIT(line);
 		else
-			v &= ~BIT(port_pin);
+			v &= ~BIT(line);
 
-		iowrite8(v, irq_cpu_mask);
+		ctrl->bank_write(irq_cpu_mask, v);
 	}
 
 	raw_spin_unlock_irqrestore(&ctrl->lock, flags);
@@ -305,16 +306,17 @@ static int realtek_gpio_irq_set_affinity(struct irq_data *data,
 static int realtek_gpio_irq_init(struct gpio_chip *gc)
 {
 	struct realtek_gpio_ctrl *ctrl = gpiochip_get_data(gc);
-	unsigned int port;
+	u32 mask_all = GENMASK(gc->ngpio - 1, 0);
+	unsigned int line;
 	int cpu;
 
-	for (port = 0; (port * 8) < gc->ngpio; port++) {
-		realtek_gpio_write_imr(ctrl, port, 0, 0);
-		realtek_gpio_clear_isr(ctrl, port, GENMASK(7, 0));
+	for (line = 0; line < gc->ngpio; line++)
+		realtek_gpio_update_line_imr(ctrl, line);
 
-		for_each_cpu(cpu, &ctrl->cpu_irq_maskable)
-			iowrite8(GENMASK(7, 0), realtek_gpio_irq_cpu_mask(ctrl, port, cpu));
-	}
+	realtek_gpio_clear_isr(ctrl, mask_all);
+
+	for_each_cpu(cpu, &ctrl->cpu_irq_maskable)
+		ctrl->bank_write(realtek_gpio_irq_cpu_mask(ctrl, cpu), mask_all);
 
 	return 0;
 }
@@ -387,12 +389,14 @@ static int realtek_gpio_probe(struct platform_device *pdev)
 
 	if (dev_flags & GPIO_PORTS_REVERSED) {
 		bgpio_flags = 0;
-		ctrl->port_offset_u8 = realtek_gpio_port_offset_u8_rev;
-		ctrl->port_offset_u16 = realtek_gpio_port_offset_u16_rev;
+		ctrl->bank_read = realtek_gpio_bank_read;
+		ctrl->bank_write = realtek_gpio_bank_write;
+		ctrl->line_imr_pos = realtek_gpio_line_imr_pos;
 	} else {
 		bgpio_flags = BGPIOF_BIG_ENDIAN_BYTE_ORDER;
-		ctrl->port_offset_u8 = realtek_gpio_port_offset_u8;
-		ctrl->port_offset_u16 = realtek_gpio_port_offset_u16;
+		ctrl->bank_read = realtek_gpio_bank_read_swapped;
+		ctrl->bank_write = realtek_gpio_bank_write_swapped;
+		ctrl->line_imr_pos = realtek_gpio_line_imr_pos_swapped;
 	}
 
 	err = bgpio_init(&ctrl->gc, dev, 4,
diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c
index f91e876fd969..bb50335239ac 100644
--- a/drivers/gpio/gpio-rockchip.c
+++ b/drivers/gpio/gpio-rockchip.c
@@ -419,11 +419,11 @@ static int rockchip_irq_set_type(struct irq_data *d, unsigned int type)
 			goto out;
 		} else {
 			bank->toggle_edge_mode |= mask;
-			level |= mask;
+			level &= ~mask;
 
 			/*
 			 * Determine gpio state. If 1 next interrupt should be
-			 * falling otherwise rising.
+			 * low otherwise high.
 			 */
 			data = readl(bank->reg_base + bank->gpio_regs->ext_port);
 			if (data & mask)
diff --git a/drivers/gpio/gpio-tqmx86.c b/drivers/gpio/gpio-tqmx86.c
index fa4bc7481f9a..e739dcea61b2 100644
--- a/drivers/gpio/gpio-tqmx86.c
+++ b/drivers/gpio/gpio-tqmx86.c
@@ -307,6 +307,8 @@ static int tqmx86_gpio_probe(struct platform_device *pdev)
 		girq->default_type = IRQ_TYPE_NONE;
 		girq->handler = handle_simple_irq;
 		girq->init_valid_mask = tqmx86_init_irq_valid_mask;
+
+		irq_domain_set_pm_device(girq->domain, dev);
 	}
 
 	ret = devm_gpiochip_add_data(dev, chip, gpio);
@@ -315,8 +317,6 @@ static int tqmx86_gpio_probe(struct platform_device *pdev)
 		goto out_pm_dis;
 	}
 
-	irq_domain_set_pm_device(girq->domain, dev);
-
 	dev_info(dev, "GPIO functionality initialized with %d pins\n",
 		 chip->ngpio);
 
diff --git a/drivers/gpio/gpio-ws16c48.c b/drivers/gpio/gpio-ws16c48.c
index b098f2dc196b..59fb10641598 100644
--- a/drivers/gpio/gpio-ws16c48.c
+++ b/drivers/gpio/gpio-ws16c48.c
@@ -265,6 +265,7 @@ static void ws16c48_irq_mask(struct irq_data *data)
 	raw_spin_lock_irqsave(&ws16c48gpio->lock, flags);
 
 	ws16c48gpio->irq_mask &= ~mask;
+	gpiochip_disable_irq(chip, offset);
 	port_state = ws16c48gpio->irq_mask >> (8 * port);
 
 	/* Select Register Page 2; Unlock all I/O ports */
@@ -295,6 +296,7 @@ static void ws16c48_irq_unmask(struct irq_data *data)
 
 	raw_spin_lock_irqsave(&ws16c48gpio->lock, flags);
 
+	gpiochip_enable_irq(chip, offset);
 	ws16c48gpio->irq_mask |= mask;
 	port_state = ws16c48gpio->irq_mask >> (8 * port);
 
@@ -356,12 +358,14 @@ static int ws16c48_irq_set_type(struct irq_data *data, unsigned flow_type)
 	return 0;
 }
 
-static struct irq_chip ws16c48_irqchip = {
+static const struct irq_chip ws16c48_irqchip = {
 	.name = "ws16c48",
 	.irq_ack = ws16c48_irq_ack,
 	.irq_mask = ws16c48_irq_mask,
 	.irq_unmask = ws16c48_irq_unmask,
-	.irq_set_type = ws16c48_irq_set_type
+	.irq_set_type = ws16c48_irq_set_type,
+	.flags = IRQCHIP_IMMUTABLE,
+	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };
 
 static irqreturn_t ws16c48_irq_handler(int irq, void *dev_id)
@@ -463,7 +467,7 @@ static int ws16c48_probe(struct device *dev, unsigned int id)
 	ws16c48gpio->chip.set_multiple = ws16c48_gpio_set_multiple;
 
 	girq = &ws16c48gpio->chip.irq;
-	girq->chip = &ws16c48_irqchip;
+	gpio_irq_chip_set_chip(girq, &ws16c48_irqchip);
 	/* This will let us handle the parent IRQ in the driver */
 	girq->parent_handler = NULL;
 	girq->num_parents = 0;
diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c
index f8041d4898d1..92f185575e94 100644
--- a/drivers/gpio/gpiolib-cdev.c
+++ b/drivers/gpio/gpiolib-cdev.c
@@ -1986,7 +1986,6 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
 		ret = -ENODEV;
 		goto out_free_le;
 	}
-	le->irq = irq;
 
 	if (eflags & GPIOEVENT_REQUEST_RISING_EDGE)
 		irqflags |= test_bit(FLAG_ACTIVE_LOW, &desc->flags) ?
@@ -2000,7 +1999,7 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
 	init_waitqueue_head(&le->wait);
 
 	/* Request a thread to read the events */
-	ret = request_threaded_irq(le->irq,
+	ret = request_threaded_irq(irq,
 				   lineevent_irq_handler,
 				   lineevent_irq_thread,
 				   irqflags,
@@ -2009,6 +2008,8 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
 	if (ret)
 		goto out_free_le;
 
+	le->irq = irq;
+
 	fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC);
 	if (fd < 0) {
 		ret = fd;
diff --git a/drivers/gpu/drm/amd/amdgpu/aldebaran.c b/drivers/gpu/drm/amd/amdgpu/aldebaran.c
index c6cc493a5486..2b97b8a96fb4 100644
--- a/drivers/gpu/drm/amd/amdgpu/aldebaran.c
+++ b/drivers/gpu/drm/amd/amdgpu/aldebaran.c
@@ -148,30 +148,22 @@ aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl,
 			      struct amdgpu_reset_context *reset_context)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle;
+	struct list_head *reset_device_list = reset_context->reset_device_list;
 	struct amdgpu_device *tmp_adev = NULL;
-	struct list_head reset_device_list;
 	int r = 0;
 
 	dev_dbg(adev->dev, "aldebaran perform hw reset\n");
+
+	if (reset_device_list == NULL)
+		return -EINVAL;
+
 	if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 2) &&
 	    reset_context->hive == NULL) {
 		/* Wrong context, return error */
 		return -EINVAL;
 	}
 
-	INIT_LIST_HEAD(&reset_device_list);
-	if (reset_context->hive) {
-		list_for_each_entry (tmp_adev,
-				     &reset_context->hive->device_list,
-				     gmc.xgmi.head)
-			list_add_tail(&tmp_adev->reset_list,
-				      &reset_device_list);
-	} else {
-		list_add_tail(&reset_context->reset_req_dev->reset_list,
-			      &reset_device_list);
-	}
-
-	list_for_each_entry (tmp_adev, &reset_device_list, reset_list) {
+	list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
 		mutex_lock(&tmp_adev->reset_cntl->reset_lock);
 		tmp_adev->reset_cntl->active_reset = AMD_RESET_METHOD_MODE2;
 	}
@@ -179,7 +171,7 @@ aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl,
 	 * Mode2 reset doesn't need any sync between nodes in XGMI hive, instead launch
 	 * them together so that they can be completed asynchronously on multiple nodes
 	 */
-	list_for_each_entry (tmp_adev, &reset_device_list, reset_list) {
+	list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
 		/* For XGMI run all resets in parallel to speed up the process */
 		if (tmp_adev->gmc.xgmi.num_physical_nodes > 1) {
 			if (!queue_work(system_unbound_wq,
@@ -197,7 +189,7 @@ aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl,
 
 	/* For XGMI wait for all resets to complete before proceed */
 	if (!r) {
-		list_for_each_entry (tmp_adev, &reset_device_list, reset_list) {
+		list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
 			if (tmp_adev->gmc.xgmi.num_physical_nodes > 1) {
 				flush_work(&tmp_adev->reset_cntl->reset_work);
 				r = tmp_adev->asic_reset_res;
@@ -207,7 +199,7 @@ aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl,
 		}
 	}
 
-	list_for_each_entry (tmp_adev, &reset_device_list, reset_list) {
+	list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
 		mutex_unlock(&tmp_adev->reset_cntl->reset_lock);
 		tmp_adev->reset_cntl->active_reset = AMD_RESET_METHOD_NONE;
 	}
@@ -339,10 +331,13 @@ static int
 aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 				  struct amdgpu_reset_context *reset_context)
 {
+	struct list_head *reset_device_list = reset_context->reset_device_list;
 	struct amdgpu_device *tmp_adev = NULL;
-	struct list_head reset_device_list;
 	int r;
 
+	if (reset_device_list == NULL)
+		return -EINVAL;
+
 	if (reset_context->reset_req_dev->ip_versions[MP1_HWIP][0] ==
 		    IP_VERSION(13, 0, 2) &&
 	    reset_context->hive == NULL) {
@@ -350,19 +345,7 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 		return -EINVAL;
 	}
 
-	INIT_LIST_HEAD(&reset_device_list);
-	if (reset_context->hive) {
-		list_for_each_entry (tmp_adev,
-				     &reset_context->hive->device_list,
-				     gmc.xgmi.head)
-			list_add_tail(&tmp_adev->reset_list,
-				      &reset_device_list);
-	} else {
-		list_add_tail(&reset_context->reset_req_dev->reset_list,
-			      &reset_device_list);
-	}
-
-	list_for_each_entry (tmp_adev, &reset_device_list, reset_list) {
+	list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
 		dev_info(tmp_adev->dev,
 			 "GPU reset succeeded, trying to resume\n");
 		r = aldebaran_mode2_restore_ip(tmp_adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index e146810c700b..d597e2656c47 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -317,7 +317,7 @@ enum amdgpu_kiq_irq {
 	AMDGPU_CP_KIQ_IRQ_DRIVER0 = 0,
 	AMDGPU_CP_KIQ_IRQ_LAST
 };
-
+#define SRIOV_USEC_TIMEOUT  1200000 /* wait 12 * 100ms for SRIOV */
 #define MAX_KIQ_REG_WAIT       5000 /* in usecs, 5ms */
 #define MAX_KIQ_REG_BAILOUT_INTERVAL   5 /* in msecs, 5ms */
 #define MAX_KIQ_REG_TRY 1000
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 130060834b4e..48bd660ddb85 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -1050,6 +1050,10 @@ bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev)
 {
 	if (adev->flags & AMD_IS_APU)
 		return false;
+
+	if (amdgpu_sriov_vf(adev))
+		return false;
+
 	return pm_suspend_target_state != PM_SUSPEND_TO_IDLE;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 3c09dcc0986e..647220a8762d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -96,6 +96,7 @@ struct amdgpu_amdkfd_fence {
 struct amdgpu_kfd_dev {
 	struct kfd_dev *dev;
 	uint64_t vram_used;
+	uint64_t vram_used_aligned;
 	bool init_complete;
 	struct work_struct reset_work;
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index a699134a1e8c..2170db83e41d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -40,10 +40,10 @@
 #define AMDGPU_USERPTR_RESTORE_DELAY_MS 1
 
 /*
- * Align VRAM allocations to 2MB to avoid fragmentation caused by 4K allocations in the tail 2MB
+ * Align VRAM availability to 2MB to avoid fragmentation caused by 4K allocations in the tail 2MB
  * BO chunk
  */
-#define VRAM_ALLOCATION_ALIGN (1 << 21)
+#define VRAM_AVAILABLITY_ALIGN (1 << 21)
 
 /* Impose limit on how much memory KFD can use */
 static struct {
@@ -149,7 +149,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 		 * to avoid fragmentation caused by 4K allocations in the tail
 		 * 2M BO chunk.
 		 */
-		vram_needed = ALIGN(size, VRAM_ALLOCATION_ALIGN);
+		vram_needed = size;
 	} else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_USERPTR) {
 		system_mem_needed = size;
 	} else if (!(alloc_flag &
@@ -182,8 +182,10 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 	 */
 	WARN_ONCE(vram_needed && !adev,
 		  "adev reference can't be null when vram is used");
-	if (adev)
+	if (adev) {
 		adev->kfd.vram_used += vram_needed;
+		adev->kfd.vram_used_aligned += ALIGN(vram_needed, VRAM_AVAILABLITY_ALIGN);
+	}
 	kfd_mem_limit.system_mem_used += system_mem_needed;
 	kfd_mem_limit.ttm_mem_used += ttm_mem_needed;
 
@@ -203,8 +205,10 @@ void amdgpu_amdkfd_unreserve_mem_limit(struct amdgpu_device *adev,
 	} else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) {
 		WARN_ONCE(!adev,
 			  "adev reference can't be null when alloc mem flags vram is set");
-		if (adev)
-			adev->kfd.vram_used -= ALIGN(size, VRAM_ALLOCATION_ALIGN);
+		if (adev) {
+			adev->kfd.vram_used -= size;
+			adev->kfd.vram_used_aligned -= ALIGN(size, VRAM_AVAILABLITY_ALIGN);
+		}
 	} else if (alloc_flag & KFD_IOC_ALLOC_MEM_FLAGS_USERPTR) {
 		kfd_mem_limit.system_mem_used -= size;
 	} else if (!(alloc_flag &
@@ -1608,15 +1612,14 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev)
 	uint64_t reserved_for_pt =
 		ESTIMATE_PT_SIZE(amdgpu_amdkfd_total_mem_size);
 	size_t available;
-
 	spin_lock(&kfd_mem_limit.mem_limit_lock);
 	available = adev->gmc.real_vram_size
-		- adev->kfd.vram_used
+		- adev->kfd.vram_used_aligned
 		- atomic64_read(&adev->vram_pin_size)
 		- reserved_for_pt;
 	spin_unlock(&kfd_mem_limit.mem_limit_lock);
 
-	return ALIGN_DOWN(available, VRAM_ALLOCATION_ALIGN);
+	return ALIGN_DOWN(available, VRAM_AVAILABLITY_ALIGN);
 }
 
 int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
@@ -1725,7 +1728,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	add_kgd_mem_to_kfd_bo_list(*mem, avm->process_info, user_addr);
 
 	if (user_addr) {
-		pr_debug("creating userptr BO for user_addr = %llu\n", user_addr);
+		pr_debug("creating userptr BO for user_addr = %llx\n", user_addr);
 		ret = init_user_pages(*mem, user_addr, criu_resume);
 		if (ret)
 			goto allocate_init_user_pages_failed;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index fd8f3731758e..b81b77a9efa6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -314,7 +314,7 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 					mem_channel_number = vram_info->v30.channel_num;
 					mem_channel_width = vram_info->v30.channel_width;
 					if (vram_width)
-						*vram_width = mem_channel_number * mem_channel_width;
+						*vram_width = mem_channel_number * (1 << mem_channel_width);
 					break;
 				default:
 					return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index d8f1335bc68f..b7bae833c804 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -837,16 +837,12 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 			continue;
 
 		r = amdgpu_vm_bo_update(adev, bo_va, false);
-		if (r) {
-			mutex_unlock(&p->bo_list->bo_list_mutex);
+		if (r)
 			return r;
-		}
 
 		r = amdgpu_sync_fence(&p->job->sync, bo_va->last_pt_update);
-		if (r) {
-			mutex_unlock(&p->bo_list->bo_list_mutex);
+		if (r)
 			return r;
-		}
 	}
 
 	r = amdgpu_vm_handle_moved(adev, vm);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index e2eec985adb3..cb00c7d6f50b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1705,7 +1705,7 @@ static ssize_t amdgpu_reset_dump_register_list_write(struct file *f,
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private;
 	char reg_offset[11];
-	uint32_t *new, *tmp = NULL;
+	uint32_t *new = NULL, *tmp = NULL;
 	int ret, i = 0, len = 0;
 
 	do {
@@ -1747,7 +1747,8 @@ static ssize_t amdgpu_reset_dump_register_list_write(struct file *f,
 	ret = size;
 
 error_free:
-	kfree(tmp);
+	if (tmp != new)
+		kfree(tmp);
 	kfree(new);
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c4a6fe3070b6..25e1f5ed7ead 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2365,8 +2365,16 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 		}
 		adev->ip_blocks[i].status.sw = true;
 
-		/* need to do gmc hw init early so we can allocate gpu mem */
-		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
+		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON) {
+			/* need to do common hw init early so everything is set up for gmc */
+			r = adev->ip_blocks[i].version->funcs->hw_init((void *)adev);
+			if (r) {
+				DRM_ERROR("hw_init %d failed %d\n", i, r);
+				goto init_failed;
+			}
+			adev->ip_blocks[i].status.hw = true;
+		} else if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
+			/* need to do gmc hw init early so we can allocate gpu mem */
 			/* Try to reserve bad pages early */
 			if (amdgpu_sriov_vf(adev))
 				amdgpu_virt_exchange_data(adev);
@@ -2456,12 +2464,14 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 			if (!hive->reset_domain ||
 			    !amdgpu_reset_get_reset_domain(hive->reset_domain)) {
 				r = -ENOENT;
+				amdgpu_put_xgmi_hive(hive);
 				goto init_failed;
 			}
 
 			/* Drop the early temporary reset domain we created for device */
 			amdgpu_reset_put_reset_domain(adev->reset_domain);
 			adev->reset_domain = hive->reset_domain;
+			amdgpu_put_xgmi_hive(hive);
 		}
 	}
 
@@ -3050,8 +3060,8 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev)
 	int i, r;
 
 	static enum amd_ip_block_type ip_order[] = {
-		AMD_IP_BLOCK_TYPE_GMC,
 		AMD_IP_BLOCK_TYPE_COMMON,
+		AMD_IP_BLOCK_TYPE_GMC,
 		AMD_IP_BLOCK_TYPE_PSP,
 		AMD_IP_BLOCK_TYPE_IH,
 	};
@@ -3142,7 +3152,8 @@ static int amdgpu_device_ip_resume_phase1(struct amdgpu_device *adev)
 			continue;
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON ||
 		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC ||
-		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH) {
+		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH ||
+		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP && amdgpu_sriov_vf(adev))) {
 
 			r = adev->ip_blocks[i].version->funcs->resume(adev);
 			if (r) {
@@ -4054,12 +4065,20 @@ static void amdgpu_device_evict_resources(struct amdgpu_device *adev)
 int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 {
 	struct amdgpu_device *adev = drm_to_adev(dev);
+	int r = 0;
 
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
 	adev->in_suspend = true;
 
+	if (amdgpu_sriov_vf(adev)) {
+		amdgpu_virt_fini_data_exchange(adev);
+		r = amdgpu_virt_request_full_gpu(adev, false);
+		if (r)
+			return r;
+	}
+
 	if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D3))
 		DRM_WARN("smart shift update failed\n");
 
@@ -4083,6 +4102,9 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 
 	amdgpu_device_ip_suspend_phase2(adev);
 
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_release_full_gpu(adev, false);
+
 	return 0;
 }
 
@@ -4101,6 +4123,12 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	int r = 0;
 
+	if (amdgpu_sriov_vf(adev)) {
+		r = amdgpu_virt_request_full_gpu(adev, true);
+		if (r)
+			return r;
+	}
+
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
@@ -4115,6 +4143,13 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 	}
 
 	r = amdgpu_device_ip_resume(adev);
+
+	/* no matter what r is, always need to properly release full GPU */
+	if (amdgpu_sriov_vf(adev)) {
+		amdgpu_virt_init_data_exchange(adev);
+		amdgpu_virt_release_full_gpu(adev, true);
+	}
+
 	if (r) {
 		dev_err(adev->dev, "amdgpu_device_ip_resume failed (%d).\n", r);
 		return r;
@@ -4413,8 +4448,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 retry:
 	amdgpu_amdkfd_pre_reset(adev);
 
-	amdgpu_amdkfd_pre_reset(adev);
-
 	if (from_hypervisor)
 		r = amdgpu_virt_request_full_gpu(adev, true);
 	else
@@ -4742,6 +4775,8 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 	tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
 				    reset_list);
 	amdgpu_reset_reg_dumps(tmp_adev);
+
+	reset_context->reset_device_list = device_list_handle;
 	r = amdgpu_reset_perform_reset(tmp_adev, reset_context);
 	/* If reset handler not implemented, continue; otherwise return */
 	if (r == -ENOSYS)
@@ -5522,7 +5557,8 @@ bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev,
 		~*peer_adev->dev->dma_mask : ~((1ULL << 32) - 1);
 	resource_size_t aper_limit =
 		adev->gmc.aper_base + adev->gmc.aper_size - 1;
-	bool p2p_access = !(pci_p2pdma_distance_many(adev->pdev,
+	bool p2p_access = !adev->gmc.xgmi.connected_to_cpu &&
+			  !(pci_p2pdma_distance_many(adev->pdev,
 					&peer_adev->dev, 1, true) < 0);
 
 	return pcie_p2p && p2p_access && (adev->gmc.visible_vram_size &&
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index c20922a5af9f..23998f727c7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -38,6 +38,8 @@
 #include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_damage_helper.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_fb_helper.h>
@@ -498,6 +500,12 @@ static const struct drm_framebuffer_funcs amdgpu_fb_funcs = {
 	.create_handle = drm_gem_fb_create_handle,
 };
 
+static const struct drm_framebuffer_funcs amdgpu_fb_funcs_atomic = {
+	.destroy = drm_gem_fb_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.dirty = drm_atomic_helper_dirtyfb,
+};
+
 uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev,
 					  uint64_t bo_flags)
 {
@@ -1100,7 +1108,10 @@ static int amdgpu_display_gem_fb_verify_and_init(struct drm_device *dev,
 	if (ret)
 		goto err;
 
-	ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs);
+	if (drm_drv_uses_atomic_modeset(dev))
+		ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs_atomic);
+	else
+		ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs);
 	if (ret)
 		goto err;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 8adeb7469f1e..d0d99ed607dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -400,7 +400,6 @@ unsigned amdgpu_fence_count_emitted(struct amdgpu_ring *ring)
 	/* We are not protected by ring lock when reading the last sequence
 	 * but it's ok to report slightly wrong fence count here.
 	 */
-	amdgpu_fence_process(ring);
 	emitted = 0x100000000ull;
 	emitted -= atomic_read(&ring->fence_drv.last_seq);
 	emitted += READ_ONCE(ring->fence_drv.sync_seq);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
index ecada5eadfe3..e325150879df 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fru_eeprom.c
@@ -66,10 +66,15 @@ static bool is_fru_eeprom_supported(struct amdgpu_device *adev)
 		return true;
 	case CHIP_SIENNA_CICHLID:
 		if (strnstr(atom_ctx->vbios_version, "D603",
+		    sizeof(atom_ctx->vbios_version))) {
+			if (strnstr(atom_ctx->vbios_version, "D603GLXE",
 			    sizeof(atom_ctx->vbios_version)))
-			return true;
-		else
+				return false;
+			else
+				return true;
+		} else {
 			return false;
+		}
 	default:
 		return false;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 23a696d38390..de5b936b016d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -304,6 +304,10 @@ struct amdgpu_gfx {
 	uint32_t			rlc_srlg_feature_version;
 	uint32_t			rlc_srls_fw_version;
 	uint32_t			rlc_srls_feature_version;
+	uint32_t			rlcp_ucode_version;
+	uint32_t			rlcp_ucode_feature_version;
+	uint32_t			rlcv_ucode_version;
+	uint32_t			rlcv_ucode_feature_version;
 	uint32_t			mec_feature_version;
 	uint32_t			mec2_feature_version;
 	bool				mec_fw_write_wait;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 5071b96be982..c2fd6f3076a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -159,7 +159,10 @@ void amdgpu_job_free(struct amdgpu_job *job)
 	amdgpu_sync_free(&job->sync);
 	amdgpu_sync_free(&job->sched_sync);
 
-	dma_fence_put(&job->hw_fence);
+	if (!job->hw_fence.ops)
+		kfree(job);
+	else
+		dma_fence_put(&job->hw_fence);
 }
 
 int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
@@ -272,10 +275,6 @@ void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched)
 	/* Signal all jobs not yet scheduled */
 	for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
 		struct drm_sched_rq *rq = &sched->sched_rq[i];
-
-		if (!rq)
-			continue;
-
 		spin_lock(&rq->lock);
 		list_for_each_entry(s_entity, &rq->entities, list) {
 			while ((s_job = to_drm_sched_job(spsc_queue_pop(&s_entity->job_queue)))) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index fe82b8b19a4e..0c546245793b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -181,6 +181,9 @@ int amdgpu_mes_init(struct amdgpu_device *adev)
 	for (i = 0; i < AMDGPU_MES_MAX_SDMA_PIPES; i++) {
 		if (adev->ip_versions[SDMA0_HWIP][0] < IP_VERSION(6, 0, 0))
 			adev->mes.sdma_hqd_mask[i] = i ? 0 : 0x3fc;
+		/* zero sdma_hqd_mask for non-existent engine */
+		else if (adev->sdma.num_instances == 1)
+			adev->mes.sdma_hqd_mask[i] = i ? 0 : 0xfc;
 		else
 			adev->mes.sdma_hqd_mask[i] = 0xfc;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index 7b46f6bf4187..ad980f4b66e1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -222,6 +222,8 @@ struct mes_add_queue_input {
 	uint64_t	tba_addr;
 	uint64_t	tma_addr;
 	uint32_t	is_kfd_process;
+	uint32_t	is_aql_queue;
+	uint32_t	queue_size;
 };
 
 struct mes_remove_queue_input {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index b067ce45d226..c9dec2434f37 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -486,11 +486,14 @@ static int psp_sw_fini(void *handle)
 		release_firmware(psp->ta_fw);
 		psp->ta_fw = NULL;
 	}
-	if (adev->psp.cap_fw) {
+	if (psp->cap_fw) {
 		release_firmware(psp->cap_fw);
 		psp->cap_fw = NULL;
 	}
-
+	if (psp->toc_fw) {
+		release_firmware(psp->toc_fw);
+		psp->toc_fw = NULL;
+	}
 	if (adev->ip_versions[MP0_HWIP][0] == IP_VERSION(11, 0, 0) ||
 	    adev->ip_versions[MP0_HWIP][0] == IP_VERSION(11, 0, 7))
 		psp_sysfs_fini(adev);
@@ -753,7 +756,7 @@ static int psp_tmr_init(struct psp_context *psp)
 	}
 
 	pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL;
-	ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_SIZE(psp->adev),
+	ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_ALIGNMENT,
 				      AMDGPU_GEM_DOMAIN_VRAM,
 				      &psp->tmr_bo, &psp->tmr_mc_addr, pptr);
 
@@ -2401,7 +2404,7 @@ static int psp_load_smu_fw(struct psp_context *psp)
 static bool fw_load_skip_check(struct psp_context *psp,
 			       struct amdgpu_firmware_info *ucode)
 {
-	if (!ucode->fw)
+	if (!ucode->fw || !ucode->ucode_size)
 		return true;
 
 	if (ucode->ucode_id == AMDGPU_UCODE_ID_SMC &&
@@ -2641,6 +2644,9 @@ static int psp_hw_fini(void *handle)
 		psp_rap_terminate(psp);
 		psp_dtm_terminate(psp);
 		psp_hdcp_terminate(psp);
+
+		if (adev->gmc.xgmi.num_physical_nodes > 1)
+			psp_xgmi_terminate(psp);
 	}
 
 	psp_asd_terminate(psp);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index c32b74bd970f..e593e8c2a54d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -36,6 +36,7 @@
 #define PSP_CMD_BUFFER_SIZE	0x1000
 #define PSP_1_MEG		0x100000
 #define PSP_TMR_SIZE(adev)	((adev)->asic_type == CHIP_ALDEBARAN ? 0x800000 : 0x400000)
+#define PSP_TMR_ALIGNMENT	0x100000
 #define PSP_FW_NAME_LEN		0x24
 
 enum psp_shared_mem_size {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index ff5361f5c2d4..12c6f97945a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1811,7 +1811,8 @@ static void amdgpu_ras_log_on_err_counter(struct amdgpu_device *adev)
 		amdgpu_ras_query_error_status(adev, &info);
 
 		if (adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) &&
-		    adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) {
+		    adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4) &&
+		    adev->ip_versions[MP0_HWIP][0] != IP_VERSION(13, 0, 0)) {
 			if (amdgpu_ras_reset_error_status(adev, info.head.block))
 				dev_warn(adev->dev, "Failed to reset error counter and error status");
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
index 9e55a5d7a825..ffda1560c648 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
@@ -37,6 +37,7 @@ struct amdgpu_reset_context {
 	struct amdgpu_device *reset_req_dev;
 	struct amdgpu_job *job;
 	struct amdgpu_hive_info *hive;
+	struct list_head *reset_device_list;
 	unsigned long flags;
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
index 6373bfb47d55..e23f6192c50e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
@@ -272,3 +272,267 @@ void amdgpu_gfx_rlc_fini(struct amdgpu_device *adev)
 			      &adev->gfx.rlc.cp_table_gpu_addr,
 			      (void **)&adev->gfx.rlc.cp_table_ptr);
 }
+
+static int amdgpu_gfx_rlc_init_microcode_v2_0(struct amdgpu_device *adev)
+{
+	const struct common_firmware_header *common_hdr;
+	const struct rlc_firmware_header_v2_0 *rlc_hdr;
+	struct amdgpu_firmware_info *info;
+	unsigned int *tmp;
+	unsigned int i;
+
+	rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
+
+	adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version);
+	adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version);
+	adev->gfx.rlc.save_and_restore_offset =
+		le32_to_cpu(rlc_hdr->save_and_restore_offset);
+	adev->gfx.rlc.clear_state_descriptor_offset =
+		le32_to_cpu(rlc_hdr->clear_state_descriptor_offset);
+	adev->gfx.rlc.avail_scratch_ram_locations =
+		le32_to_cpu(rlc_hdr->avail_scratch_ram_locations);
+	adev->gfx.rlc.reg_restore_list_size =
+		le32_to_cpu(rlc_hdr->reg_restore_list_size);
+	adev->gfx.rlc.reg_list_format_start =
+		le32_to_cpu(rlc_hdr->reg_list_format_start);
+	adev->gfx.rlc.reg_list_format_separate_start =
+		le32_to_cpu(rlc_hdr->reg_list_format_separate_start);
+	adev->gfx.rlc.starting_offsets_start =
+		le32_to_cpu(rlc_hdr->starting_offsets_start);
+	adev->gfx.rlc.reg_list_format_size_bytes =
+		le32_to_cpu(rlc_hdr->reg_list_format_size_bytes);
+	adev->gfx.rlc.reg_list_size_bytes =
+		le32_to_cpu(rlc_hdr->reg_list_size_bytes);
+	adev->gfx.rlc.register_list_format =
+		kmalloc(adev->gfx.rlc.reg_list_format_size_bytes +
+			adev->gfx.rlc.reg_list_size_bytes, GFP_KERNEL);
+	if (!adev->gfx.rlc.register_list_format) {
+		dev_err(adev->dev, "failed to allocate memory for rlc register_list_format\n");
+		return -ENOMEM;
+	}
+
+	tmp = (unsigned int *)((uintptr_t)rlc_hdr +
+			le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes));
+	for (i = 0 ; i < (rlc_hdr->reg_list_format_size_bytes >> 2); i++)
+		adev->gfx.rlc.register_list_format[i] = le32_to_cpu(tmp[i]);
+
+	adev->gfx.rlc.register_restore = adev->gfx.rlc.register_list_format + i;
+
+	tmp = (unsigned int *)((uintptr_t)rlc_hdr +
+			le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes));
+	for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++)
+		adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]);
+
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_G];
+		info->ucode_id = AMDGPU_UCODE_ID_RLC_G;
+		info->fw = adev->gfx.rlc_fw;
+		if (info->fw) {
+			common_hdr = (const struct common_firmware_header *)info->fw->data;
+			adev->firmware.fw_size +=
+				ALIGN(le32_to_cpu(common_hdr->ucode_size_bytes), PAGE_SIZE);
+		}
+	}
+
+	return 0;
+}
+
+static void amdgpu_gfx_rlc_init_microcode_v2_1(struct amdgpu_device *adev)
+{
+	const struct rlc_firmware_header_v2_1 *rlc_hdr;
+	struct amdgpu_firmware_info *info;
+
+	rlc_hdr = (const struct rlc_firmware_header_v2_1 *)adev->gfx.rlc_fw->data;
+	adev->gfx.rlc_srlc_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_ucode_ver);
+	adev->gfx.rlc_srlc_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_feature_ver);
+	adev->gfx.rlc.save_restore_list_cntl_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_cntl_size_bytes);
+	adev->gfx.rlc.save_restore_list_cntl = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_cntl_offset_bytes);
+	adev->gfx.rlc_srlg_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_ucode_ver);
+	adev->gfx.rlc_srlg_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_feature_ver);
+	adev->gfx.rlc.save_restore_list_gpm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_gpm_size_bytes);
+	adev->gfx.rlc.save_restore_list_gpm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_gpm_offset_bytes);
+	adev->gfx.rlc_srls_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_ucode_ver);
+	adev->gfx.rlc_srls_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_feature_ver);
+	adev->gfx.rlc.save_restore_list_srm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_srm_size_bytes);
+	adev->gfx.rlc.save_restore_list_srm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_srm_offset_bytes);
+	adev->gfx.rlc.reg_list_format_direct_reg_list_length =
+		le32_to_cpu(rlc_hdr->reg_list_format_direct_reg_list_length);
+
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+		if (adev->gfx.rlc.save_restore_list_gpm_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM];
+			info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.save_restore_list_gpm_size_bytes, PAGE_SIZE);
+		}
+
+		if (adev->gfx.rlc.save_restore_list_srm_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM];
+			info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.save_restore_list_srm_size_bytes, PAGE_SIZE);
+		}
+	}
+}
+
+static void amdgpu_gfx_rlc_init_microcode_v2_2(struct amdgpu_device *adev)
+{
+	const struct rlc_firmware_header_v2_2 *rlc_hdr;
+	struct amdgpu_firmware_info *info;
+
+	rlc_hdr = (const struct rlc_firmware_header_v2_2 *)adev->gfx.rlc_fw->data;
+	adev->gfx.rlc.rlc_iram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_iram_ucode_size_bytes);
+	adev->gfx.rlc.rlc_iram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_iram_ucode_offset_bytes);
+	adev->gfx.rlc.rlc_dram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_dram_ucode_size_bytes);
+	adev->gfx.rlc.rlc_dram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_dram_ucode_offset_bytes);
+
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+		if (adev->gfx.rlc.rlc_iram_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_IRAM];
+			info->ucode_id = AMDGPU_UCODE_ID_RLC_IRAM;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.rlc_iram_ucode_size_bytes, PAGE_SIZE);
+		}
+
+		if (adev->gfx.rlc.rlc_dram_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_DRAM];
+			info->ucode_id = AMDGPU_UCODE_ID_RLC_DRAM;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.rlc_dram_ucode_size_bytes, PAGE_SIZE);
+		}
+	}
+}
+
+static void amdgpu_gfx_rlc_init_microcode_v2_3(struct amdgpu_device *adev)
+{
+	const struct rlc_firmware_header_v2_3 *rlc_hdr;
+	struct amdgpu_firmware_info *info;
+
+	rlc_hdr = (const struct rlc_firmware_header_v2_3 *)adev->gfx.rlc_fw->data;
+	adev->gfx.rlcp_ucode_version = le32_to_cpu(rlc_hdr->rlcp_ucode_version);
+	adev->gfx.rlcp_ucode_feature_version = le32_to_cpu(rlc_hdr->rlcp_ucode_feature_version);
+	adev->gfx.rlc.rlcp_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcp_ucode_size_bytes);
+	adev->gfx.rlc.rlcp_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcp_ucode_offset_bytes);
+
+	adev->gfx.rlcv_ucode_version = le32_to_cpu(rlc_hdr->rlcv_ucode_version);
+	adev->gfx.rlcv_ucode_feature_version = le32_to_cpu(rlc_hdr->rlcv_ucode_feature_version);
+	adev->gfx.rlc.rlcv_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcv_ucode_size_bytes);
+	adev->gfx.rlc.rlcv_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcv_ucode_offset_bytes);
+
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+		if (adev->gfx.rlc.rlcp_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_P];
+			info->ucode_id = AMDGPU_UCODE_ID_RLC_P;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.rlcp_ucode_size_bytes, PAGE_SIZE);
+		}
+
+		if (adev->gfx.rlc.rlcv_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_V];
+			info->ucode_id = AMDGPU_UCODE_ID_RLC_V;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.rlcv_ucode_size_bytes, PAGE_SIZE);
+		}
+	}
+}
+
+static void amdgpu_gfx_rlc_init_microcode_v2_4(struct amdgpu_device *adev)
+{
+	const struct rlc_firmware_header_v2_4 *rlc_hdr;
+	struct amdgpu_firmware_info *info;
+
+	rlc_hdr = (const struct rlc_firmware_header_v2_4 *)adev->gfx.rlc_fw->data;
+	adev->gfx.rlc.global_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->global_tap_delays_ucode_size_bytes);
+	adev->gfx.rlc.global_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->global_tap_delays_ucode_offset_bytes);
+	adev->gfx.rlc.se0_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se0_tap_delays_ucode_size_bytes);
+	adev->gfx.rlc.se0_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se0_tap_delays_ucode_offset_bytes);
+	adev->gfx.rlc.se1_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se1_tap_delays_ucode_size_bytes);
+	adev->gfx.rlc.se1_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se1_tap_delays_ucode_offset_bytes);
+	adev->gfx.rlc.se2_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se2_tap_delays_ucode_size_bytes);
+	adev->gfx.rlc.se2_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se2_tap_delays_ucode_offset_bytes);
+	adev->gfx.rlc.se3_tap_delays_ucode_size_bytes = le32_to_cpu(rlc_hdr->se3_tap_delays_ucode_size_bytes);
+	adev->gfx.rlc.se3_tap_delays_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->se3_tap_delays_ucode_offset_bytes);
+
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+		if (adev->gfx.rlc.global_tap_delays_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS];
+			info->ucode_id = AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.global_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		}
+
+		if (adev->gfx.rlc.se0_tap_delays_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE0_TAP_DELAYS];
+			info->ucode_id = AMDGPU_UCODE_ID_SE0_TAP_DELAYS;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.se0_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		}
+
+		if (adev->gfx.rlc.se1_tap_delays_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE1_TAP_DELAYS];
+			info->ucode_id = AMDGPU_UCODE_ID_SE1_TAP_DELAYS;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.se1_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		}
+
+		if (adev->gfx.rlc.se2_tap_delays_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE2_TAP_DELAYS];
+			info->ucode_id = AMDGPU_UCODE_ID_SE2_TAP_DELAYS;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.se2_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		}
+
+		if (adev->gfx.rlc.se3_tap_delays_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE3_TAP_DELAYS];
+			info->ucode_id = AMDGPU_UCODE_ID_SE3_TAP_DELAYS;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.se3_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		}
+	}
+}
+
+int amdgpu_gfx_rlc_init_microcode(struct amdgpu_device *adev,
+				  uint16_t version_major,
+				  uint16_t version_minor)
+{
+	int err;
+
+	if (version_major < 2) {
+		/* only support rlc_hdr v2.x and onwards */
+		dev_err(adev->dev, "unsupported rlc fw hdr\n");
+		return -EINVAL;
+	}
+
+	/* is_rlc_v2_1 is still used in APU code path */
+	if (version_major == 2 && version_minor == 1)
+		adev->gfx.rlc.is_rlc_v2_1 = true;
+
+	if (version_minor >= 0) {
+		err = amdgpu_gfx_rlc_init_microcode_v2_0(adev);
+		if (err) {
+			dev_err(adev->dev, "fail to init rlc v2_0 microcode\n");
+			return err;
+		}
+	}
+	if (version_minor >= 1)
+		amdgpu_gfx_rlc_init_microcode_v2_1(adev);
+	if (version_minor >= 2)
+		amdgpu_gfx_rlc_init_microcode_v2_2(adev);
+	if (version_minor == 3)
+		amdgpu_gfx_rlc_init_microcode_v2_3(adev);
+	if (version_minor == 4)
+		amdgpu_gfx_rlc_init_microcode_v2_4(adev);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
index 03ac36b2c2cf..23f060db9255 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
@@ -267,5 +267,7 @@ int amdgpu_gfx_rlc_init_csb(struct amdgpu_device *adev);
 int amdgpu_gfx_rlc_init_cpt(struct amdgpu_device *adev);
 void amdgpu_gfx_rlc_setup_cp_table(struct amdgpu_device *adev);
 void amdgpu_gfx_rlc_fini(struct amdgpu_device *adev);
-
+int amdgpu_gfx_rlc_init_microcode(struct amdgpu_device *adev,
+				  uint16_t version_major,
+				  uint16_t version_minor);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 3b4c19412625..134575a3893c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -637,6 +637,8 @@ struct amdgpu_ttm_tt {
 #endif
 };
 
+#define ttm_to_amdgpu_ttm_tt(ptr)	container_of(ptr, struct amdgpu_ttm_tt, ttm)
+
 #ifdef CONFIG_DRM_AMDGPU_USERPTR
 /*
  * amdgpu_ttm_tt_get_user_pages - get device accessible pages that back user
@@ -648,7 +650,7 @@ struct amdgpu_ttm_tt {
 int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 {
 	struct ttm_tt *ttm = bo->tbo.ttm;
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	unsigned long start = gtt->userptr;
 	struct vm_area_struct *vma;
 	struct mm_struct *mm;
@@ -702,7 +704,7 @@ out_unlock:
  */
 bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	bool r = false;
 
 	if (!gtt || !gtt->userptr)
@@ -751,7 +753,7 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_device *bdev,
 				     struct ttm_tt *ttm)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	int write = !(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY);
 	enum dma_data_direction direction = write ?
 		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
@@ -788,7 +790,7 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_device *bdev,
 					struct ttm_tt *ttm)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	int write = !(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY);
 	enum dma_data_direction direction = write ?
 		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
@@ -822,7 +824,7 @@ static void amdgpu_ttm_gart_bind(struct amdgpu_device *adev,
 {
 	struct amdgpu_bo *abo = ttm_to_amdgpu_bo(tbo);
 	struct ttm_tt *ttm = tbo->ttm;
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	if (amdgpu_bo_encrypted(abo))
 		flags |= AMDGPU_PTE_TMZ;
@@ -860,7 +862,7 @@ static int amdgpu_ttm_backend_bind(struct ttm_device *bdev,
 				   struct ttm_resource *bo_mem)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	struct amdgpu_ttm_tt *gtt = (void*)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	uint64_t flags;
 	int r;
 
@@ -927,7 +929,7 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 	struct ttm_operation_ctx ctx = { false, false };
-	struct amdgpu_ttm_tt *gtt = (void *)bo->ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(bo->ttm);
 	struct ttm_placement placement;
 	struct ttm_place placements;
 	struct ttm_resource *tmp;
@@ -998,7 +1000,7 @@ static void amdgpu_ttm_backend_unbind(struct ttm_device *bdev,
 				      struct ttm_tt *ttm)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	/* if the pages have userptr pinning then clear that first */
 	if (gtt->userptr) {
@@ -1025,7 +1027,7 @@ static void amdgpu_ttm_backend_unbind(struct ttm_device *bdev,
 static void amdgpu_ttm_backend_destroy(struct ttm_device *bdev,
 				       struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	if (gtt->usertask)
 		put_task_struct(gtt->usertask);
@@ -1079,7 +1081,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_device *bdev,
 				  struct ttm_operation_ctx *ctx)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	pgoff_t i;
 	int ret;
 
@@ -1113,7 +1115,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_device *bdev,
 static void amdgpu_ttm_tt_unpopulate(struct ttm_device *bdev,
 				     struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	struct amdgpu_device *adev;
 	pgoff_t i;
 
@@ -1182,7 +1184,7 @@ int amdgpu_ttm_tt_set_userptr(struct ttm_buffer_object *bo,
 	/* Set TTM_TT_FLAG_EXTERNAL before populate but after create. */
 	bo->ttm->page_flags |= TTM_TT_FLAG_EXTERNAL;
 
-	gtt = (void *)bo->ttm;
+	gtt = ttm_to_amdgpu_ttm_tt(bo->ttm);
 	gtt->userptr = addr;
 	gtt->userflags = flags;
 
@@ -1199,7 +1201,7 @@ int amdgpu_ttm_tt_set_userptr(struct ttm_buffer_object *bo,
  */
 struct mm_struct *amdgpu_ttm_tt_get_usermm(struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	if (gtt == NULL)
 		return NULL;
@@ -1218,7 +1220,7 @@ struct mm_struct *amdgpu_ttm_tt_get_usermm(struct ttm_tt *ttm)
 bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
 				  unsigned long end, unsigned long *userptr)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 	unsigned long size;
 
 	if (gtt == NULL || !gtt->userptr)
@@ -1241,7 +1243,7 @@ bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
  */
 bool amdgpu_ttm_tt_is_userptr(struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	if (gtt == NULL || !gtt->userptr)
 		return false;
@@ -1254,7 +1256,7 @@ bool amdgpu_ttm_tt_is_userptr(struct ttm_tt *ttm)
  */
 bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm)
 {
-	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm);
 
 	if (gtt == NULL)
 		return false;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index ebed3f5226db..59edf32f775e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -260,8 +260,12 @@ struct rlc_firmware_header_v2_2 {
 /* version_major=2, version_minor=3 */
 struct rlc_firmware_header_v2_3 {
     struct rlc_firmware_header_v2_2 v2_2;
+    uint32_t rlcp_ucode_version;
+    uint32_t rlcp_ucode_feature_version;
     uint32_t rlcp_ucode_size_bytes;
     uint32_t rlcp_ucode_offset_bytes;
+    uint32_t rlcv_ucode_version;
+    uint32_t rlcv_ucode_feature_version;
     uint32_t rlcv_ucode_size_bytes;
     uint32_t rlcv_ucode_offset_bytes;
 };
@@ -390,6 +394,7 @@ union amdgpu_firmware_header {
 	struct rlc_firmware_header_v2_1 rlc_v2_1;
 	struct rlc_firmware_header_v2_2 rlc_v2_2;
 	struct rlc_firmware_header_v2_3 rlc_v2_3;
+	struct rlc_firmware_header_v2_4 rlc_v2_4;
 	struct sdma_firmware_header_v1_0 sdma;
 	struct sdma_firmware_header_v1_1 sdma_v1_1;
 	struct sdma_firmware_header_v2_0 sdma_v2_0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index f36e4f08db6d..0b52af415b28 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -191,7 +191,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 		fw_name = FIRMWARE_VCN4_0_2;
 		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
 			(adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
-			adev->vcn.indirect_sram = false;
+			adev->vcn.indirect_sram = true;
 		break;
 	case IP_VERSION(4, 0, 4):
 		fw_name = FIRMWARE_VCN4_0_4;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
index 108e8e8a1a36..576849e95296 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
@@ -496,8 +496,7 @@ static int amdgpu_vkms_sw_init(void *handle)
 	adev_to_drm(adev)->mode_config.max_height = YRES_MAX;
 
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 
 	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 59cac347baa3..690fd4f639f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2484,8 +2484,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
 		/* Intentionally setting invalid PTE flag
 		 * combination to force a no-retry-fault
 		 */
-		flags = AMDGPU_PTE_EXECUTABLE | AMDGPU_PDE_PTE |
-			AMDGPU_PTE_TF;
+		flags = AMDGPU_PTE_SNOOPED | AMDGPU_PTE_PRT;
 		value = 0;
 	} else if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_NEVER) {
 		/* Redirect the access to the dummy page */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 1b108d03e785..f2aebbf3fbe3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -742,7 +742,7 @@ int amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
 		amdgpu_put_xgmi_hive(hive);
 	}
 
-	return psp_xgmi_terminate(&adev->psp);
+	return 0;
 }
 
 static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block)
diff --git a/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c b/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c
index 33a8a7365aef..f0e235f98afb 100644
--- a/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/athub_v3_0.c
@@ -28,13 +28,44 @@
 #include "navi10_enum.h"
 #include "soc15_common.h"
 
+#define regATHUB_MISC_CNTL_V3_0_1			0x00d7
+#define regATHUB_MISC_CNTL_V3_0_1_BASE_IDX		0
+
+
+static uint32_t athub_v3_0_get_cg_cntl(struct amdgpu_device *adev)
+{
+	uint32_t data;
+
+	switch (adev->ip_versions[ATHUB_HWIP][0]) {
+	case IP_VERSION(3, 0, 1):
+		data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_0_1);
+		break;
+	default:
+		data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL);
+		break;
+	}
+	return data;
+}
+
+static void athub_v3_0_set_cg_cntl(struct amdgpu_device *adev, uint32_t data)
+{
+	switch (adev->ip_versions[ATHUB_HWIP][0]) {
+	case IP_VERSION(3, 0, 1):
+		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL_V3_0_1, data);
+		break;
+	default:
+		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL, data);
+		break;
+	}
+}
+
 static void
 athub_v3_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 					    bool enable)
 {
 	uint32_t def, data;
 
-	def = data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL);
+	def = data = athub_v3_0_get_cg_cntl(adev);
 
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_ATHUB_MGCG))
 		data |= ATHUB_MISC_CNTL__CG_ENABLE_MASK;
@@ -42,7 +73,7 @@ athub_v3_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 		data &= ~ATHUB_MISC_CNTL__CG_ENABLE_MASK;
 
 	if (def != data)
-		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL, data);
+		athub_v3_0_set_cg_cntl(adev, data);
 }
 
 static void
@@ -51,7 +82,7 @@ athub_v3_0_update_medium_grain_light_sleep(struct amdgpu_device *adev,
 {
 	uint32_t def, data;
 
-	def = data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL);
+	def = data = athub_v3_0_get_cg_cntl(adev);
 
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_ATHUB_LS))
 		data |= ATHUB_MISC_CNTL__CG_MEM_LS_ENABLE_MASK;
@@ -59,7 +90,7 @@ athub_v3_0_update_medium_grain_light_sleep(struct amdgpu_device *adev,
 		data &= ~ATHUB_MISC_CNTL__CG_MEM_LS_ENABLE_MASK;
 
 	if (def != data)
-		WREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL, data);
+		athub_v3_0_set_cg_cntl(adev, data);
 }
 
 int athub_v3_0_set_clockgating(struct amdgpu_device *adev,
@@ -70,6 +101,7 @@ int athub_v3_0_set_clockgating(struct amdgpu_device *adev,
 
 	switch (adev->ip_versions[ATHUB_HWIP][0]) {
 	case IP_VERSION(3, 0, 0):
+	case IP_VERSION(3, 0, 1):
 	case IP_VERSION(3, 0, 2):
 		athub_v3_0_update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE);
@@ -88,7 +120,7 @@ void athub_v3_0_get_clockgating(struct amdgpu_device *adev, u64 *flags)
 	int data;
 
 	/* AMD_CG_SUPPORT_ATHUB_MGCG */
-	data = RREG32_SOC15(ATHUB, 0, regATHUB_MISC_CNTL);
+	data = athub_v3_0_get_cg_cntl(adev);
 	if (data & ATHUB_MISC_CNTL__CG_ENABLE_MASK)
 		*flags |= AMD_CG_SUPPORT_ATHUB_MGCG;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 9c964cd3b5d4..288fce7dc0ed 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -2796,8 +2796,7 @@ static int dce_v10_0_sw_init(void *handle)
 	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 
 	adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index e0ad9f27dc3f..cbe5250b31cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -2914,8 +2914,7 @@ static int dce_v11_0_sw_init(void *handle)
 	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 
 	adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index 77f5e998a120..b1c44fab074f 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -2673,8 +2673,7 @@ static int dce_v6_0_sw_init(void *handle)
 	adev_to_drm(adev)->mode_config.max_width = 16384;
 	adev_to_drm(adev)->mode_config.max_height = 16384;
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 	adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true;
 	adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 802e5c753271..a22b45c92792 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -2693,8 +2693,11 @@ static int dce_v8_0_sw_init(void *handle)
 	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	if (adev->asic_type == CHIP_HAWAII)
+		/* disable prefer shadow for now due to hibernation issues */
+		adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	else
+		adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 
 	adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index fafbad3cf08d..a3cd5c1e8529 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -4274,35 +4274,45 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 
 		}
 
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS];
-		info->ucode_id = AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS;
-		info->fw = adev->gfx.rlc_fw;
-		adev->firmware.fw_size +=
-			ALIGN(adev->gfx.rlc.global_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		if (adev->gfx.rlc.global_tap_delays_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS];
+			info->ucode_id = AMDGPU_UCODE_ID_GLOBAL_TAP_DELAYS;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.global_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		}
 
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE0_TAP_DELAYS];
-		info->ucode_id = AMDGPU_UCODE_ID_SE0_TAP_DELAYS;
-		info->fw = adev->gfx.rlc_fw;
-		adev->firmware.fw_size +=
-			ALIGN(adev->gfx.rlc.se0_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		if (adev->gfx.rlc.se0_tap_delays_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE0_TAP_DELAYS];
+			info->ucode_id = AMDGPU_UCODE_ID_SE0_TAP_DELAYS;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.se0_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		}
 
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE1_TAP_DELAYS];
-		info->ucode_id = AMDGPU_UCODE_ID_SE1_TAP_DELAYS;
-		info->fw = adev->gfx.rlc_fw;
-		adev->firmware.fw_size +=
-			ALIGN(adev->gfx.rlc.se1_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		if (adev->gfx.rlc.se1_tap_delays_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE1_TAP_DELAYS];
+			info->ucode_id = AMDGPU_UCODE_ID_SE1_TAP_DELAYS;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.se1_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		}
 
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE2_TAP_DELAYS];
-		info->ucode_id = AMDGPU_UCODE_ID_SE2_TAP_DELAYS;
-		info->fw = adev->gfx.rlc_fw;
-		adev->firmware.fw_size +=
-			ALIGN(adev->gfx.rlc.se2_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		if (adev->gfx.rlc.se2_tap_delays_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE2_TAP_DELAYS];
+			info->ucode_id = AMDGPU_UCODE_ID_SE2_TAP_DELAYS;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.se2_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		}
 
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE3_TAP_DELAYS];
-		info->ucode_id = AMDGPU_UCODE_ID_SE3_TAP_DELAYS;
-		info->fw = adev->gfx.rlc_fw;
-		adev->firmware.fw_size +=
-			ALIGN(adev->gfx.rlc.se3_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		if (adev->gfx.rlc.se3_tap_delays_ucode_size_bytes) {
+			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SE3_TAP_DELAYS];
+			info->ucode_id = AMDGPU_UCODE_ID_SE3_TAP_DELAYS;
+			info->fw = adev->gfx.rlc_fw;
+			adev->firmware.fw_size +=
+				ALIGN(adev->gfx.rlc.se3_tap_delays_ucode_size_bytes, PAGE_SIZE);
+		}
 
 		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1];
 		info->ucode_id = AMDGPU_UCODE_ID_CP_MEC1;
@@ -4846,7 +4856,7 @@ static int gfx_v10_0_sw_init(void *handle)
 	case IP_VERSION(10, 3, 3):
 	case IP_VERSION(10, 3, 7):
 		adev->gfx.me.num_me = 1;
-		adev->gfx.me.num_pipe_per_me = 2;
+		adev->gfx.me.num_pipe_per_me = 1;
 		adev->gfx.me.num_queue_per_pipe = 1;
 		adev->gfx.mec.num_mec = 2;
 		adev->gfx.mec.num_pipe_per_mec = 4;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 6fd71cb10e54..daf8ba8235cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -53,6 +53,7 @@
 #define GFX11_MEC_HPD_SIZE	2048
 
 #define RLCG_UCODE_LOADING_START_ADDRESS	0x00002000L
+#define RLC_PG_DELAY_3_DEFAULT_GC_11_0_1	0x1388
 
 #define regCGTT_WD_CLK_CTRL		0x5086
 #define regCGTT_WD_CLK_CTRL_BASE_IDX	1
@@ -130,6 +131,8 @@ static void gfx_v11_0_ring_invalidate_tlbs(struct amdgpu_ring *ring,
 					   bool all_hub, uint8_t dst_sel);
 static void gfx_v11_0_set_safe_mode(struct amdgpu_device *adev);
 static void gfx_v11_0_unset_safe_mode(struct amdgpu_device *adev);
+static void gfx_v11_0_update_perf_clk(struct amdgpu_device *adev,
+				      bool enable);
 
 static void gfx11_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue_mask)
 {
@@ -471,49 +474,6 @@ static void gfx_v11_0_free_microcode(struct amdgpu_device *adev)
 	kfree(adev->gfx.rlc.register_list_format);
 }
 
-static void gfx_v11_0_init_rlc_ext_microcode(struct amdgpu_device *adev)
-{
-	const struct rlc_firmware_header_v2_1 *rlc_hdr;
-
-	rlc_hdr = (const struct rlc_firmware_header_v2_1 *)adev->gfx.rlc_fw->data;
-	adev->gfx.rlc_srlc_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_ucode_ver);
-	adev->gfx.rlc_srlc_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_cntl_feature_ver);
-	adev->gfx.rlc.save_restore_list_cntl_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_cntl_size_bytes);
-	adev->gfx.rlc.save_restore_list_cntl = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_cntl_offset_bytes);
-	adev->gfx.rlc_srlg_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_ucode_ver);
-	adev->gfx.rlc_srlg_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_gpm_feature_ver);
-	adev->gfx.rlc.save_restore_list_gpm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_gpm_size_bytes);
-	adev->gfx.rlc.save_restore_list_gpm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_gpm_offset_bytes);
-	adev->gfx.rlc_srls_fw_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_ucode_ver);
-	adev->gfx.rlc_srls_feature_version = le32_to_cpu(rlc_hdr->save_restore_list_srm_feature_ver);
-	adev->gfx.rlc.save_restore_list_srm_size_bytes = le32_to_cpu(rlc_hdr->save_restore_list_srm_size_bytes);
-	adev->gfx.rlc.save_restore_list_srm = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->save_restore_list_srm_offset_bytes);
-	adev->gfx.rlc.reg_list_format_direct_reg_list_length =
-			le32_to_cpu(rlc_hdr->reg_list_format_direct_reg_list_length);
-}
-
-static void gfx_v11_0_init_rlc_iram_dram_microcode(struct amdgpu_device *adev)
-{
-	const struct rlc_firmware_header_v2_2 *rlc_hdr;
-
-	rlc_hdr = (const struct rlc_firmware_header_v2_2 *)adev->gfx.rlc_fw->data;
-	adev->gfx.rlc.rlc_iram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_iram_ucode_size_bytes);
-	adev->gfx.rlc.rlc_iram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_iram_ucode_offset_bytes);
-	adev->gfx.rlc.rlc_dram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_dram_ucode_size_bytes);
-	adev->gfx.rlc.rlc_dram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_dram_ucode_offset_bytes);
-}
-
-static void gfx_v11_0_init_rlcp_rlcv_microcode(struct amdgpu_device *adev)
-{
-	const struct rlc_firmware_header_v2_3 *rlc_hdr;
-
-	rlc_hdr = (const struct rlc_firmware_header_v2_3 *)adev->gfx.rlc_fw->data;
-	adev->gfx.rlc.rlcp_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcp_ucode_size_bytes);
-	adev->gfx.rlc.rlcp_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcp_ucode_offset_bytes);
-	adev->gfx.rlc.rlcv_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlcv_ucode_size_bytes);
-	adev->gfx.rlc.rlcv_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlcv_ucode_offset_bytes);
-}
-
 static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
 {
 	char fw_name[40];
@@ -524,8 +484,6 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
 	const struct gfx_firmware_header_v1_0 *cp_hdr;
 	const struct gfx_firmware_header_v2_0 *cp_hdr_v2_0;
 	const struct rlc_firmware_header_v2_0 *rlc_hdr;
-	unsigned int *tmp = NULL;
-	unsigned int i = 0;
 	uint16_t version_major;
 	uint16_t version_minor;
 
@@ -580,58 +538,14 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
 		if (err)
 			goto out;
 		err = amdgpu_ucode_validate(adev->gfx.rlc_fw);
+		if (err)
+			goto out;
 		rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
 		version_major = le16_to_cpu(rlc_hdr->header.header_version_major);
 		version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor);
-
-		adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version);
-		adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version);
-		adev->gfx.rlc.save_and_restore_offset =
-			le32_to_cpu(rlc_hdr->save_and_restore_offset);
-		adev->gfx.rlc.clear_state_descriptor_offset =
-			le32_to_cpu(rlc_hdr->clear_state_descriptor_offset);
-		adev->gfx.rlc.avail_scratch_ram_locations =
-			le32_to_cpu(rlc_hdr->avail_scratch_ram_locations);
-		adev->gfx.rlc.reg_restore_list_size =
-			le32_to_cpu(rlc_hdr->reg_restore_list_size);
-		adev->gfx.rlc.reg_list_format_start =
-			le32_to_cpu(rlc_hdr->reg_list_format_start);
-		adev->gfx.rlc.reg_list_format_separate_start =
-			le32_to_cpu(rlc_hdr->reg_list_format_separate_start);
-		adev->gfx.rlc.starting_offsets_start =
-			le32_to_cpu(rlc_hdr->starting_offsets_start);
-		adev->gfx.rlc.reg_list_format_size_bytes =
-			le32_to_cpu(rlc_hdr->reg_list_format_size_bytes);
-		adev->gfx.rlc.reg_list_size_bytes =
-			le32_to_cpu(rlc_hdr->reg_list_size_bytes);
-		adev->gfx.rlc.register_list_format =
-			kmalloc(adev->gfx.rlc.reg_list_format_size_bytes +
-					adev->gfx.rlc.reg_list_size_bytes, GFP_KERNEL);
-		if (!adev->gfx.rlc.register_list_format) {
-			err = -ENOMEM;
+		err = amdgpu_gfx_rlc_init_microcode(adev, version_major, version_minor);
+		if (err)
 			goto out;
-		}
-
-		tmp = (unsigned int *)((uintptr_t)rlc_hdr +
-							   le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes));
-		for (i = 0 ; i < (rlc_hdr->reg_list_format_size_bytes >> 2); i++)
-			adev->gfx.rlc.register_list_format[i] =	le32_to_cpu(tmp[i]);
-
-		adev->gfx.rlc.register_restore = adev->gfx.rlc.register_list_format + i;
-
-		tmp = (unsigned int *)((uintptr_t)rlc_hdr +
-							   le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes));
-		for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++)
-			adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]);
-
-		if (version_major == 2) {
-			if (version_minor >= 1)
-				gfx_v11_0_init_rlc_ext_microcode(adev);
-			if (version_minor >= 2)
-				gfx_v11_0_init_rlc_iram_dram_microcode(adev);
-			if (version_minor == 3)
-				gfx_v11_0_init_rlcp_rlcv_microcode(adev);
-		}
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", ucode_prefix);
@@ -766,60 +680,6 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
 			adev->firmware.fw_size +=
 				ALIGN(le32_to_cpu(cp_hdr->jt_size) * 4, PAGE_SIZE);
 		}
-
-		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_G];
-		info->ucode_id = AMDGPU_UCODE_ID_RLC_G;
-		info->fw = adev->gfx.rlc_fw;
-		if (info->fw) {
-			header = (const struct common_firmware_header *)info->fw->data;
-			adev->firmware.fw_size +=
-				ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
-		}
-		if (adev->gfx.rlc.save_restore_list_gpm_size_bytes &&
-		    adev->gfx.rlc.save_restore_list_srm_size_bytes) {
-			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM];
-			info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM;
-			info->fw = adev->gfx.rlc_fw;
-			adev->firmware.fw_size +=
-				ALIGN(adev->gfx.rlc.save_restore_list_gpm_size_bytes, PAGE_SIZE);
-
-			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM];
-			info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM;
-			info->fw = adev->gfx.rlc_fw;
-			adev->firmware.fw_size +=
-				ALIGN(adev->gfx.rlc.save_restore_list_srm_size_bytes, PAGE_SIZE);
-		}
-
-		if (adev->gfx.rlc.rlc_iram_ucode_size_bytes &&
-		    adev->gfx.rlc.rlc_dram_ucode_size_bytes) {
-			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_IRAM];
-			info->ucode_id = AMDGPU_UCODE_ID_RLC_IRAM;
-			info->fw = adev->gfx.rlc_fw;
-			adev->firmware.fw_size +=
-				ALIGN(adev->gfx.rlc.rlc_iram_ucode_size_bytes, PAGE_SIZE);
-
-			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_DRAM];
-			info->ucode_id = AMDGPU_UCODE_ID_RLC_DRAM;
-			info->fw = adev->gfx.rlc_fw;
-			adev->firmware.fw_size +=
-				ALIGN(adev->gfx.rlc.rlc_dram_ucode_size_bytes, PAGE_SIZE);
-		}
-
-		if (adev->gfx.rlc.rlcp_ucode_size_bytes) {
-			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_P];
-			info->ucode_id = AMDGPU_UCODE_ID_RLC_P;
-			info->fw = adev->gfx.rlc_fw;
-			adev->firmware.fw_size +=
-				ALIGN(adev->gfx.rlc.rlcp_ucode_size_bytes, PAGE_SIZE);
-		}
-
-		if (adev->gfx.rlc.rlcv_ucode_size_bytes) {
-			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_V];
-			info->ucode_id = AMDGPU_UCODE_ID_RLC_V;
-			info->fw = adev->gfx.rlc_fw;
-			adev->firmware.fw_size +=
-				ALIGN(adev->gfx.rlc.rlcv_ucode_size_bytes, PAGE_SIZE);
-		}
 	}
 
 out:
@@ -1138,6 +998,7 @@ static const struct amdgpu_gfx_funcs gfx_v11_0_gfx_funcs = {
 	.read_wave_vgprs = &gfx_v11_0_read_wave_vgprs,
 	.select_me_pipe_q = &gfx_v11_0_select_me_pipe_q,
 	.init_spm_golden = &gfx_v11_0_init_spm_golden_registers,
+	.update_perfmon_mgcg = &gfx_v11_0_update_perf_clk,
 };
 
 static int gfx_v11_0_gpu_early_init(struct amdgpu_device *adev)
@@ -5181,9 +5042,12 @@ static void gfx_v11_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade
 		data = REG_SET_FIELD(data, SDMA0_RLC_CGCG_CTRL, CGCG_INT_ENABLE, 1);
 		WREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL, data);
 
-		data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL);
-		data = REG_SET_FIELD(data, SDMA1_RLC_CGCG_CTRL, CGCG_INT_ENABLE, 1);
-		WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data);
+		/* Some ASICs only have one SDMA instance, not need to configure SDMA1 */
+		if (adev->sdma.num_instances > 1) {
+			data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL);
+			data = REG_SET_FIELD(data, SDMA1_RLC_CGCG_CTRL, CGCG_INT_ENABLE, 1);
+			WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data);
+		}
 	} else {
 		/* Program RLC_CGCG_CGLS_CTRL */
 		def = data = RREG32_SOC15(GC, 0, regRLC_CGCG_CGLS_CTRL);
@@ -5212,9 +5076,12 @@ static void gfx_v11_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade
 		data &= ~SDMA0_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK;
 		WREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL, data);
 
-		data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL);
-		data &= ~SDMA1_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK;
-		WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data);
+		/* Some ASICs only have one SDMA instance, not need to configure SDMA1 */
+		if (adev->sdma.num_instances > 1) {
+			data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL);
+			data &= ~SDMA1_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK;
+			WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data);
+		}
 	}
 }
 
@@ -5250,6 +5117,8 @@ static void gfx_v11_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
 	u32 reg, data;
 
+	amdgpu_gfx_off_ctrl(adev, false);
+
 	reg = SOC15_REG_OFFSET(GC, 0, regRLC_SPM_MC_CNTL);
 	if (amdgpu_sriov_is_pp_one_vf(adev))
 		data = RREG32_NO_KIQ(reg);
@@ -5263,6 +5132,8 @@ static void gfx_v11_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 		WREG32_SOC15_NO_KIQ(GC, 0, regRLC_SPM_MC_CNTL, data);
 	else
 		WREG32_SOC15(GC, 0, regRLC_SPM_MC_CNTL, data);
+
+	amdgpu_gfx_off_ctrl(adev, true);
 }
 
 static const struct amdgpu_rlc_funcs gfx_v11_0_rlc_funcs = {
@@ -5279,6 +5150,38 @@ static const struct amdgpu_rlc_funcs gfx_v11_0_rlc_funcs = {
 	.update_spm_vmid = gfx_v11_0_update_spm_vmid,
 };
 
+static void gfx_v11_cntl_power_gating(struct amdgpu_device *adev, bool enable)
+{
+	u32 data = RREG32_SOC15(GC, 0, regRLC_PG_CNTL);
+
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG))
+		data |= RLC_PG_CNTL__GFX_POWER_GATING_ENABLE_MASK;
+	else
+		data &= ~RLC_PG_CNTL__GFX_POWER_GATING_ENABLE_MASK;
+
+	WREG32_SOC15(GC, 0, regRLC_PG_CNTL, data);
+
+	// Program RLC_PG_DELAY3 for CGPG hysteresis
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) {
+		switch (adev->ip_versions[GC_HWIP][0]) {
+		case IP_VERSION(11, 0, 1):
+			WREG32_SOC15(GC, 0, regRLC_PG_DELAY_3, RLC_PG_DELAY_3_DEFAULT_GC_11_0_1);
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+static void gfx_v11_cntl_pg(struct amdgpu_device *adev, bool enable)
+{
+	amdgpu_gfx_rlc_enter_safe_mode(adev);
+
+	gfx_v11_cntl_power_gating(adev, enable);
+
+	amdgpu_gfx_rlc_exit_safe_mode(adev);
+}
+
 static int gfx_v11_0_set_powergating_state(void *handle,
 					   enum amd_powergating_state state)
 {
@@ -5293,6 +5196,10 @@ static int gfx_v11_0_set_powergating_state(void *handle,
 	case IP_VERSION(11, 0, 2):
 		amdgpu_gfx_off_ctrl(adev, enable);
 		break;
+	case IP_VERSION(11, 0, 1):
+		gfx_v11_cntl_pg(adev, enable);
+		amdgpu_gfx_off_ctrl(adev, enable);
+		break;
 	default:
 		break;
 	}
@@ -5310,6 +5217,7 @@ static int gfx_v11_0_set_clockgating_state(void *handle,
 
 	switch (adev->ip_versions[GC_HWIP][0]) {
 	case IP_VERSION(11, 0, 0):
+	case IP_VERSION(11, 0, 1):
 	case IP_VERSION(11, 0, 2):
 	        gfx_v11_0_update_gfx_clock_gating(adev,
 	                        state ==  AMD_CG_STATE_GATE);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index c6e0f9313a7f..037af8352677 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -2587,7 +2587,8 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev)
 
 	gfx_v9_0_tiling_mode_table_init(adev);
 
-	gfx_v9_0_setup_rb(adev);
+	if (adev->gfx.num_gfx_rings)
+		gfx_v9_0_setup_rb(adev);
 	gfx_v9_0_get_cu_info(adev, &adev->gfx.cu_info);
 	adev->gfx.config.db_debug2 = RREG32_SOC15(GC, 0, mmDB_DEBUG2);
 
@@ -5596,7 +5597,7 @@ static void gfx_v9_0_ring_emit_patch_cond_exec(struct amdgpu_ring *ring, unsigne
 	BUG_ON(offset > ring->buf_mask);
 	BUG_ON(ring->ring[offset] != 0x55aa55aa);
 
-	cur = (ring->wptr & ring->buf_mask) - 1;
+	cur = (ring->wptr - 1) & ring->buf_mask;
 	if (likely(cur > offset))
 		ring->ring[offset] = cur - offset;
 	else
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 9ae8cdaa033e..f513e2c2e964 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -419,6 +419,7 @@ static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 	uint32_t seq;
 	uint16_t queried_pasid;
 	bool ret;
+	u32 usec_timeout = amdgpu_sriov_vf(adev) ? SRIOV_USEC_TIMEOUT : adev->usec_timeout;
 	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 
@@ -437,7 +438,7 @@ static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 
 		amdgpu_ring_commit(ring);
 		spin_unlock(&adev->gfx.kiq.ring_lock);
-		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
+		r = amdgpu_fence_wait_polling(ring, seq, usec_timeout);
 		if (r < 1) {
 			dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r);
 			return -ETIME;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 22761a3bb818..67ca16a8027c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -896,6 +896,7 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 	uint32_t seq;
 	uint16_t queried_pasid;
 	bool ret;
+	u32 usec_timeout = amdgpu_sriov_vf(adev) ? SRIOV_USEC_TIMEOUT : adev->usec_timeout;
 	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 
@@ -935,7 +936,7 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 
 		amdgpu_ring_commit(ring);
 		spin_unlock(&adev->gfx.kiq.ring_lock);
-		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
+		r = amdgpu_fence_wait_polling(ring, seq, usec_timeout);
 		if (r < 1) {
 			dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r);
 			up_read(&adev->reset_domain->sem);
@@ -1102,10 +1103,13 @@ static void gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, int level,
 			*flags |= AMDGPU_PDE_BFS(0x9);
 
 	} else if (level == AMDGPU_VM_PDB0) {
-		if (*flags & AMDGPU_PDE_PTE)
+		if (*flags & AMDGPU_PDE_PTE) {
 			*flags &= ~AMDGPU_PDE_PTE;
-		else
+			if (!(*flags & AMDGPU_PTE_VALID))
+				*addr |= 1 << PAGE_SHIFT;
+		} else {
 			*flags |= AMDGPU_PTE_TF;
+		}
 	}
 }
 
@@ -1624,12 +1628,15 @@ static int gmc_v9_0_sw_init(void *handle)
 			amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 47);
 		else
 			amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 48);
+		if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2))
+			adev->gmc.translate_further = adev->vm_manager.num_level > 1;
 		break;
 	case IP_VERSION(9, 4, 1):
 		adev->num_vmhubs = 3;
 
 		/* Keep the vm size same with Vega20 */
 		amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 48);
+		adev->gmc.translate_further = adev->vm_manager.num_level > 1;
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
index 39a696cd45b5..29c3484ae1f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c
@@ -40,6 +40,156 @@ static void hdp_v5_2_flush_hdp(struct amdgpu_device *adev,
 			0);
 }
 
+static void hdp_v5_2_update_mem_power_gating(struct amdgpu_device *adev,
+					     bool enable)
+{
+	uint32_t hdp_clk_cntl;
+	uint32_t hdp_mem_pwr_cntl;
+
+	if (!(adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS |
+				AMD_CG_SUPPORT_HDP_DS |
+				AMD_CG_SUPPORT_HDP_SD)))
+		return;
+
+	hdp_clk_cntl = RREG32_SOC15(HDP, 0, regHDP_CLK_CNTL);
+	hdp_mem_pwr_cntl = RREG32_SOC15(HDP, 0, regHDP_MEM_POWER_CTRL);
+
+	/* Before doing clock/power mode switch, forced on MEM clock */
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     ATOMIC_MEM_CLK_SOFT_OVERRIDE, 1);
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     RC_MEM_CLK_SOFT_OVERRIDE, 1);
+	WREG32_SOC15(HDP, 0, regHDP_CLK_CNTL, hdp_clk_cntl);
+
+	/* disable clock and power gating before any changing */
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 ATOMIC_MEM_POWER_CTRL_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 ATOMIC_MEM_POWER_LS_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 ATOMIC_MEM_POWER_DS_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 ATOMIC_MEM_POWER_SD_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 RC_MEM_POWER_CTRL_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 RC_MEM_POWER_LS_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 RC_MEM_POWER_DS_EN, 0);
+	hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+					 RC_MEM_POWER_SD_EN, 0);
+	WREG32_SOC15(HDP, 0, regHDP_MEM_POWER_CTRL, hdp_mem_pwr_cntl);
+
+	/* Already disabled above. The actions below are for "enabled" only */
+	if (enable) {
+		/* only one clock gating mode (LS/DS/SD) can be enabled */
+		if (adev->cg_flags & AMD_CG_SUPPORT_HDP_SD) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 ATOMIC_MEM_POWER_SD_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_SD_EN, 1);
+		} else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 ATOMIC_MEM_POWER_LS_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_LS_EN, 1);
+		} else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_DS) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 ATOMIC_MEM_POWER_DS_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_DS_EN, 1);
+		}
+
+		/* confirmed that ATOMIC/RC_MEM_POWER_CTRL_EN have to be set for SRAM LS/DS/SD */
+		if (adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_HDP_DS |
+				      AMD_CG_SUPPORT_HDP_SD)) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+							 ATOMIC_MEM_POWER_CTRL_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_CTRL_EN, 1);
+			WREG32_SOC15(HDP, 0, regHDP_MEM_POWER_CTRL, hdp_mem_pwr_cntl);
+		}
+	}
+
+	/* disable MEM clock override after clock/power mode changing */
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     ATOMIC_MEM_CLK_SOFT_OVERRIDE, 0);
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     RC_MEM_CLK_SOFT_OVERRIDE, 0);
+	WREG32_SOC15(HDP, 0, regHDP_CLK_CNTL, hdp_clk_cntl);
+}
+
+static void hdp_v5_2_update_medium_grain_clock_gating(struct amdgpu_device *adev,
+						      bool enable)
+{
+	uint32_t hdp_clk_cntl;
+
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_HDP_MGCG))
+		return;
+
+	hdp_clk_cntl = RREG32_SOC15(HDP, 0, regHDP_CLK_CNTL);
+
+	if (enable) {
+		hdp_clk_cntl &=
+			~(uint32_t)
+			(HDP_CLK_CNTL__ATOMIC_MEM_CLK_SOFT_OVERRIDE_MASK |
+			 HDP_CLK_CNTL__RC_MEM_CLK_SOFT_OVERRIDE_MASK |
+			 HDP_CLK_CNTL__DBUS_CLK_SOFT_OVERRIDE_MASK |
+			 HDP_CLK_CNTL__DYN_CLK_SOFT_OVERRIDE_MASK |
+			 HDP_CLK_CNTL__XDP_REG_CLK_SOFT_OVERRIDE_MASK |
+			 HDP_CLK_CNTL__HDP_REG_CLK_SOFT_OVERRIDE_MASK);
+	} else {
+		hdp_clk_cntl |= HDP_CLK_CNTL__ATOMIC_MEM_CLK_SOFT_OVERRIDE_MASK |
+			HDP_CLK_CNTL__RC_MEM_CLK_SOFT_OVERRIDE_MASK |
+			HDP_CLK_CNTL__DBUS_CLK_SOFT_OVERRIDE_MASK |
+			HDP_CLK_CNTL__DYN_CLK_SOFT_OVERRIDE_MASK |
+			HDP_CLK_CNTL__XDP_REG_CLK_SOFT_OVERRIDE_MASK |
+			HDP_CLK_CNTL__HDP_REG_CLK_SOFT_OVERRIDE_MASK;
+	}
+
+	WREG32_SOC15(HDP, 0, regHDP_CLK_CNTL, hdp_clk_cntl);
+}
+
+static void hdp_v5_2_get_clockgating_state(struct amdgpu_device *adev,
+					   u64 *flags)
+{
+	uint32_t tmp;
+
+	/* AMD_CG_SUPPORT_HDP_MGCG */
+	tmp = RREG32_SOC15(HDP, 0, regHDP_CLK_CNTL);
+	if (!(tmp & (HDP_CLK_CNTL__ATOMIC_MEM_CLK_SOFT_OVERRIDE_MASK |
+		     HDP_CLK_CNTL__RC_MEM_CLK_SOFT_OVERRIDE_MASK |
+		     HDP_CLK_CNTL__DBUS_CLK_SOFT_OVERRIDE_MASK |
+		     HDP_CLK_CNTL__DYN_CLK_SOFT_OVERRIDE_MASK |
+		     HDP_CLK_CNTL__XDP_REG_CLK_SOFT_OVERRIDE_MASK |
+		     HDP_CLK_CNTL__HDP_REG_CLK_SOFT_OVERRIDE_MASK)))
+		*flags |= AMD_CG_SUPPORT_HDP_MGCG;
+
+	/* AMD_CG_SUPPORT_HDP_LS/DS/SD */
+	tmp = RREG32_SOC15(HDP, 0, regHDP_MEM_POWER_CTRL);
+	if (tmp & HDP_MEM_POWER_CTRL__ATOMIC_MEM_POWER_LS_EN_MASK)
+		*flags |= AMD_CG_SUPPORT_HDP_LS;
+	else if (tmp & HDP_MEM_POWER_CTRL__ATOMIC_MEM_POWER_DS_EN_MASK)
+		*flags |= AMD_CG_SUPPORT_HDP_DS;
+	else if (tmp & HDP_MEM_POWER_CTRL__ATOMIC_MEM_POWER_SD_EN_MASK)
+		*flags |= AMD_CG_SUPPORT_HDP_SD;
+}
+
+static void hdp_v5_2_update_clock_gating(struct amdgpu_device *adev,
+					      bool enable)
+{
+	hdp_v5_2_update_mem_power_gating(adev, enable);
+	hdp_v5_2_update_medium_grain_clock_gating(adev, enable);
+}
+
 const struct amdgpu_hdp_funcs hdp_v5_2_funcs = {
 	.flush_hdp = hdp_v5_2_flush_hdp,
+	.update_clock_gating = hdp_v5_2_update_clock_gating,
+	.get_clock_gating_state = hdp_v5_2_get_clockgating_state,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
index 92dc60a9d209..085e613f3646 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
@@ -727,6 +727,7 @@ static const struct amd_ip_funcs ih_v6_0_ip_funcs = {
 static const struct amdgpu_ih_funcs ih_v6_0_funcs = {
 	.get_wptr = ih_v6_0_get_wptr,
 	.decode_iv = amdgpu_ih_decode_iv_helper,
+	.decode_iv_ts = amdgpu_ih_decode_iv_ts_helper,
 	.set_rptr = ih_v6_0_set_rptr
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 120ea294abef..f92744b8d79d 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -183,6 +183,11 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes,
 	mes_add_queue_pkt.trap_handler_addr = input->tba_addr;
 	mes_add_queue_pkt.tma_addr = input->tma_addr;
 	mes_add_queue_pkt.is_kfd_process = input->is_kfd_process;
+	mes_add_queue_pkt.trap_en = 1;
+
+	/* For KFD, gds_size is re-used for queue size (needed in MES for AQL queues) */
+	mes_add_queue_pkt.is_aql_queue = input->is_aql_queue;
+	mes_add_queue_pkt.gds_size = input->queue_size;
 
 	return mes_v11_0_submit_pkt_and_poll_completion(mes,
 			&mes_add_queue_pkt, sizeof(mes_add_queue_pkt),
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 3f44a099c52a..3e51e773f92b 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -176,6 +176,7 @@ static void mmhub_v1_0_init_cache_regs(struct amdgpu_device *adev)
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_L2_CACHE, 1);
 	WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL2, tmp);
 
+	tmp = mmVM_L2_CNTL3_DEFAULT;
 	if (adev->gmc.translate_further) {
 		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 12);
 		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c
index cac72ced94c8..e8058edc1d10 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c
@@ -518,18 +518,41 @@ static u64 mmhub_v3_0_1_get_mc_fb_offset(struct amdgpu_device *adev)
 static void mmhub_v3_0_1_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 							  bool enable)
 {
-	//TODO
+	uint32_t def, data;
+
+	def = data = RREG32_SOC15(MMHUB, 0, regMM_ATC_L2_MISC_CG);
+
+	if (enable)
+		data |= MM_ATC_L2_MISC_CG__ENABLE_MASK;
+	else
+		data &= ~MM_ATC_L2_MISC_CG__ENABLE_MASK;
+
+	if (def != data)
+		WREG32_SOC15(MMHUB, 0, regMM_ATC_L2_MISC_CG, data);
 }
 
 static void mmhub_v3_0_1_update_medium_grain_light_sleep(struct amdgpu_device *adev,
 							 bool enable)
 {
-	//TODO
+	uint32_t def, data;
+
+	def = data = RREG32_SOC15(MMHUB, 0, regMM_ATC_L2_MISC_CG);
+
+	if (enable)
+		data |= MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
+	else
+		data &= ~MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
+
+	if (def != data)
+		WREG32_SOC15(MMHUB, 0, regMM_ATC_L2_MISC_CG, data);
 }
 
 static int mmhub_v3_0_1_set_clockgating(struct amdgpu_device *adev,
 					enum amd_clockgating_state state)
 {
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	mmhub_v3_0_1_update_medium_grain_clock_gating(adev,
 			state == AMD_CG_STATE_GATE);
 	mmhub_v3_0_1_update_medium_grain_light_sleep(adev,
@@ -539,7 +562,20 @@ static int mmhub_v3_0_1_set_clockgating(struct amdgpu_device *adev,
 
 static void mmhub_v3_0_1_get_clockgating(struct amdgpu_device *adev, u64 *flags)
 {
-	//TODO
+	int data;
+
+	if (amdgpu_sriov_vf(adev))
+		*flags = 0;
+
+	data = RREG32_SOC15(MMHUB, 0, regMM_ATC_L2_MISC_CG);
+
+	/* AMD_CG_SUPPORT_MC_MGCG */
+	if (data & MM_ATC_L2_MISC_CG__ENABLE_MASK)
+		*flags |= AMD_CG_SUPPORT_MC_MGCG;
+
+	/* AMD_CG_SUPPORT_MC_LS */
+	if (data & MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK)
+		*flags |= AMD_CG_SUPPORT_MC_LS;
 }
 
 const struct amdgpu_mmhub_funcs mmhub_v3_0_1_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index 6e0145b2b408..445cb06b9d26 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -295,9 +295,17 @@ static void mmhub_v9_4_disable_identity_aperture(struct amdgpu_device *adev,
 static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid)
 {
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_MMHUB_0];
+	unsigned int num_level, block_size;
 	uint32_t tmp;
 	int i;
 
+	num_level = adev->vm_manager.num_level;
+	block_size = adev->vm_manager.block_size;
+	if (adev->gmc.translate_further)
+		num_level -= 1;
+	else
+		block_size -= 9;
+
 	for (i = 0; i <= 14; i++) {
 		tmp = RREG32_SOC15_OFFSET(MMHUB, 0, mmVML2VC0_VM_CONTEXT1_CNTL,
 				hubid * MMHUB_INSTANCE_REGISTER_OFFSET + i);
@@ -305,7 +313,7 @@ static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid)
 				    ENABLE_CONTEXT, 1);
 		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
 				    PAGE_TABLE_DEPTH,
-				    adev->vm_manager.num_level);
+				    num_level);
 		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
 				    RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
@@ -323,7 +331,7 @@ static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid)
 				    EXECUTE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
 		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
 				    PAGE_TABLE_BLOCK_SIZE,
-				    adev->vm_manager.block_size - 9);
+				    block_size);
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index 4b5396d3e60f..eec13cb5bf75 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -409,9 +409,11 @@ static u32 navi10_ih_get_wptr(struct amdgpu_device *adev,
 	u32 wptr, tmp;
 	struct amdgpu_ih_regs *ih_regs;
 
-	if (ih == &adev->irq.ih) {
+	if (ih == &adev->irq.ih || ih == &adev->irq.ih_soft) {
 		/* Only ring0 supports writeback. On other rings fall back
 		 * to register-based code with overflow checking below.
+		 * ih_soft ring doesn't have any backing hardware registers,
+		 * update wptr and return.
 		 */
 		wptr = le32_to_cpu(*ih->wptr_cpu);
 
@@ -483,6 +485,9 @@ static void navi10_ih_set_rptr(struct amdgpu_device *adev,
 {
 	struct amdgpu_ih_regs *ih_regs;
 
+	if (ih == &adev->irq.ih_soft)
+		return;
+
 	if (ih->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
 		*ih->rptr_cpu = ih->rptr;
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
index b465baa26762..aa761ff3a5fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
@@ -380,6 +380,7 @@ static void nbio_v2_3_enable_aspm(struct amdgpu_device *adev,
 		WREG32_PCIE(smnPCIE_LC_CNTL, data);
 }
 
+#ifdef CONFIG_PCIEASPM
 static void nbio_v2_3_program_ltr(struct amdgpu_device *adev)
 {
 	uint32_t def, data;
@@ -401,9 +402,11 @@ static void nbio_v2_3_program_ltr(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data);
 }
+#endif
 
 static void nbio_v2_3_program_aspm(struct amdgpu_device *adev)
 {
+#ifdef CONFIG_PCIEASPM
 	uint32_t def, data;
 
 	def = data = RREG32_PCIE(smnPCIE_LC_CNTL);
@@ -459,7 +462,10 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_PCIE(smnPCIE_LC_CNTL6, data);
 
-	nbio_v2_3_program_ltr(adev);
+	/* Don't bother about LTR if LTR is not enabled
+	 * in the path */
+	if (adev->pdev->ltr_path)
+		nbio_v2_3_program_ltr(adev);
 
 	def = data = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP3);
 	data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT;
@@ -483,6 +489,7 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev)
 	data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK;
 	if (def != data)
 		WREG32_PCIE(smnPCIE_LC_CNTL3, data);
+#endif
 }
 
 static void nbio_v2_3_apply_lc_spc_mode_wa(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
index f7f6ddebd3e4..37615a77287b 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
@@ -282,6 +282,7 @@ static void nbio_v6_1_init_registers(struct amdgpu_device *adev)
 			mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2;
 }
 
+#ifdef CONFIG_PCIEASPM
 static void nbio_v6_1_program_ltr(struct amdgpu_device *adev)
 {
 	uint32_t def, data;
@@ -303,9 +304,11 @@ static void nbio_v6_1_program_ltr(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data);
 }
+#endif
 
 static void nbio_v6_1_program_aspm(struct amdgpu_device *adev)
 {
+#ifdef CONFIG_PCIEASPM
 	uint32_t def, data;
 
 	def = data = RREG32_PCIE(smnPCIE_LC_CNTL);
@@ -361,7 +364,10 @@ static void nbio_v6_1_program_aspm(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_PCIE(smnPCIE_LC_CNTL6, data);
 
-	nbio_v6_1_program_ltr(adev);
+	/* Don't bother about LTR if LTR is not enabled
+	 * in the path */
+	if (adev->pdev->ltr_path)
+		nbio_v6_1_program_ltr(adev);
 
 	def = data = RREG32_PCIE(smnRCC_BIF_STRAP3);
 	data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT;
@@ -385,6 +391,7 @@ static void nbio_v6_1_program_aspm(struct amdgpu_device *adev)
 	data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK;
 	if (def != data)
 		WREG32_PCIE(smnPCIE_LC_CNTL3, data);
+#endif
 }
 
 const struct amdgpu_nbio_funcs nbio_v6_1_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index 11848d1e238b..19455a725939 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -673,6 +673,7 @@ struct amdgpu_nbio_ras nbio_v7_4_ras = {
 };
 
 
+#ifdef CONFIG_PCIEASPM
 static void nbio_v7_4_program_ltr(struct amdgpu_device *adev)
 {
 	uint32_t def, data;
@@ -694,9 +695,11 @@ static void nbio_v7_4_program_ltr(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data);
 }
+#endif
 
 static void nbio_v7_4_program_aspm(struct amdgpu_device *adev)
 {
+#ifdef CONFIG_PCIEASPM
 	uint32_t def, data;
 
 	if (adev->ip_versions[NBIO_HWIP][0] == IP_VERSION(7, 4, 4))
@@ -755,7 +758,10 @@ static void nbio_v7_4_program_aspm(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_PCIE(smnPCIE_LC_CNTL6, data);
 
-	nbio_v7_4_program_ltr(adev);
+	/* Don't bother about LTR if LTR is not enabled
+	 * in the path */
+	if (adev->pdev->ltr_path)
+		nbio_v7_4_program_ltr(adev);
 
 	def = data = RREG32_PCIE(smnRCC_BIF_STRAP3);
 	data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT;
@@ -779,6 +785,7 @@ static void nbio_v7_4_program_aspm(struct amdgpu_device *adev)
 	data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK;
 	if (def != data)
 		WREG32_PCIE(smnPCIE_LC_CNTL3, data);
+#endif
 }
 
 const struct amdgpu_nbio_funcs nbio_v7_4_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
index 01e8288d09a8..def89379b51a 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
@@ -28,6 +28,14 @@
 #include "nbio/nbio_7_7_0_sh_mask.h"
 #include <uapi/linux/kfd_ioctl.h>
 
+static void nbio_v7_7_remap_hdp_registers(struct amdgpu_device *adev)
+{
+	WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_MEM_FLUSH_CNTL,
+		     adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL);
+	WREG32_SOC15(NBIO, 0, regBIF_BX0_REMAP_HDP_REG_FLUSH_CNTL,
+		     adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_REG_FLUSH_CNTL);
+}
+
 static u32 nbio_v7_7_get_rev_id(struct amdgpu_device *adev)
 {
 	u32 tmp;
@@ -68,12 +76,6 @@ static void nbio_v7_7_sdma_doorbell_range(struct amdgpu_device *adev, int instan
 		doorbell_range = REG_SET_FIELD(doorbell_range,
 					       GDC0_BIF_CSDMA_DOORBELL_RANGE,
 					       SIZE, doorbell_size);
-		doorbell_range = REG_SET_FIELD(doorbell_range,
-					       GDC0_BIF_SDMA0_DOORBELL_RANGE,
-					       OFFSET, doorbell_index);
-		doorbell_range = REG_SET_FIELD(doorbell_range,
-					       GDC0_BIF_SDMA0_DOORBELL_RANGE,
-					       SIZE, doorbell_size);
 	} else {
 		doorbell_range = REG_SET_FIELD(doorbell_range,
 					       GDC0_BIF_SDMA0_DOORBELL_RANGE,
@@ -247,6 +249,81 @@ static void nbio_v7_7_init_registers(struct amdgpu_device *adev)
 
 }
 
+static void nbio_v7_7_update_medium_grain_clock_gating(struct amdgpu_device *adev,
+						       bool enable)
+{
+	uint32_t def, data;
+
+	if (enable && !(adev->cg_flags & AMD_CG_SUPPORT_BIF_MGCG))
+		return;
+
+	def = data = RREG32_SOC15(NBIO, 0, regBIF0_CPM_CONTROL);
+	if (enable) {
+		data |= (BIF0_CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK |
+			 BIF0_CPM_CONTROL__TXCLK_DYN_GATE_ENABLE_MASK |
+			 BIF0_CPM_CONTROL__TXCLK_LCNT_GATE_ENABLE_MASK |
+			 BIF0_CPM_CONTROL__TXCLK_REGS_GATE_ENABLE_MASK |
+			 BIF0_CPM_CONTROL__TXCLK_PRBS_GATE_ENABLE_MASK |
+			 BIF0_CPM_CONTROL__REFCLK_REGS_GATE_ENABLE_MASK);
+	} else {
+		data &= ~(BIF0_CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK |
+			  BIF0_CPM_CONTROL__TXCLK_DYN_GATE_ENABLE_MASK |
+			  BIF0_CPM_CONTROL__TXCLK_LCNT_GATE_ENABLE_MASK |
+			  BIF0_CPM_CONTROL__TXCLK_REGS_GATE_ENABLE_MASK |
+			  BIF0_CPM_CONTROL__TXCLK_PRBS_GATE_ENABLE_MASK |
+			  BIF0_CPM_CONTROL__REFCLK_REGS_GATE_ENABLE_MASK);
+	}
+
+	if (def != data)
+		WREG32_SOC15(NBIO, 0, regBIF0_CPM_CONTROL, data);
+}
+
+static void nbio_v7_7_update_medium_grain_light_sleep(struct amdgpu_device *adev,
+						      bool enable)
+{
+	uint32_t def, data;
+
+	if (enable && !(adev->cg_flags & AMD_CG_SUPPORT_BIF_LS))
+		return;
+
+	def = data = RREG32_SOC15(NBIO, 0, regBIF0_PCIE_CNTL2);
+	if (enable)
+		data |= BIF0_PCIE_CNTL2__SLV_MEM_LS_EN_MASK;
+	else
+		data &= ~BIF0_PCIE_CNTL2__SLV_MEM_LS_EN_MASK;
+
+	if (def != data)
+		WREG32_SOC15(NBIO, 0, regBIF0_PCIE_CNTL2, data);
+
+	def = data = RREG32_SOC15(NBIO, 0, regBIF0_PCIE_TX_POWER_CTRL_1);
+	if (enable) {
+		data |= (BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_LS_EN_MASK |
+			BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_LS_EN_MASK);
+	} else {
+		data &= ~(BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_LS_EN_MASK |
+			BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_LS_EN_MASK);
+	}
+
+	if (def != data)
+		WREG32_SOC15(NBIO, 0, regBIF0_PCIE_TX_POWER_CTRL_1, data);
+}
+
+static void nbio_v7_7_get_clockgating_state(struct amdgpu_device *adev,
+					    u64 *flags)
+{
+	uint32_t data;
+
+	/* AMD_CG_SUPPORT_BIF_MGCG */
+	data = RREG32_SOC15(NBIO, 0, regBIF0_CPM_CONTROL);
+	if (data & BIF0_CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK)
+		*flags |= AMD_CG_SUPPORT_BIF_MGCG;
+
+	/* AMD_CG_SUPPORT_BIF_LS */
+	data = RREG32_SOC15(NBIO, 0, regBIF0_PCIE_CNTL2);
+	if (data & BIF0_PCIE_CNTL2__SLV_MEM_LS_EN_MASK)
+		*flags |= AMD_CG_SUPPORT_BIF_LS;
+}
+
 const struct amdgpu_nbio_funcs nbio_v7_7_funcs = {
 	.get_hdp_flush_req_offset = nbio_v7_7_get_hdp_flush_req_offset,
 	.get_hdp_flush_done_offset = nbio_v7_7_get_hdp_flush_done_offset,
@@ -262,6 +339,10 @@ const struct amdgpu_nbio_funcs nbio_v7_7_funcs = {
 	.enable_doorbell_aperture = nbio_v7_7_enable_doorbell_aperture,
 	.enable_doorbell_selfring_aperture = nbio_v7_7_enable_doorbell_selfring_aperture,
 	.ih_doorbell_range = nbio_v7_7_ih_doorbell_range,
+	.update_medium_grain_clock_gating = nbio_v7_7_update_medium_grain_clock_gating,
+	.update_medium_grain_light_sleep = nbio_v7_7_update_medium_grain_light_sleep,
+	.get_clockgating_state = nbio_v7_7_get_clockgating_state,
 	.ih_control = nbio_v7_7_ih_control,
 	.init_registers = nbio_v7_7_init_registers,
+	.remap_hdp_registers = nbio_v7_7_remap_hdp_registers,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
index a2588200ea58..0b2ac418e4ac 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
@@ -101,6 +101,16 @@ static int psp_v12_0_init_microcode(struct psp_context *psp)
 		adev->psp.dtm_context.context.bin_desc.start_addr =
 			(uint8_t *)adev->psp.hdcp_context.context.bin_desc.start_addr +
 			le32_to_cpu(ta_hdr->dtm.offset_bytes);
+
+		if (adev->apu_flags & AMD_APU_IS_RENOIR) {
+			adev->psp.securedisplay_context.context.bin_desc.fw_version =
+				le32_to_cpu(ta_hdr->securedisplay.fw_version);
+			adev->psp.securedisplay_context.context.bin_desc.size_bytes =
+				le32_to_cpu(ta_hdr->securedisplay.size_bytes);
+			adev->psp.securedisplay_context.context.bin_desc.start_addr =
+				(uint8_t *)adev->psp.hdcp_context.context.bin_desc.start_addr +
+				le32_to_cpu(ta_hdr->securedisplay.offset_bytes);
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index 726a5bba40b2..a75a286e1ecf 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -20,7 +20,6 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  */
-#include <linux/dev_printk.h>
 #include <drm/drm_drv.h>
 #include <linux/vmalloc.h>
 #include "amdgpu.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 65181efba50e..56424f75dd2c 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -1504,6 +1504,11 @@ static int sdma_v4_0_start(struct amdgpu_device *adev)
 		WREG32_SDMA(i, mmSDMA0_CNTL, temp);
 
 		if (!amdgpu_sriov_vf(adev)) {
+			ring = &adev->sdma.instance[i].ring;
+			adev->nbio.funcs->sdma_doorbell_range(adev, i,
+				ring->use_doorbell, ring->doorbell_index,
+				adev->doorbell_index.sdma_doorbell_range);
+
 			/* unhalt engine */
 			temp = RREG32_SDMA(i, mmSDMA0_F32_CNTL);
 			temp = REG_SET_FIELD(temp, SDMA0_F32_CNTL, HALT, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index fde6154f2009..183024d7c184 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1211,25 +1211,6 @@ static int soc15_common_sw_fini(void *handle)
 	return 0;
 }
 
-static void soc15_doorbell_range_init(struct amdgpu_device *adev)
-{
-	int i;
-	struct amdgpu_ring *ring;
-
-	/* sdma/ih doorbell range are programed by hypervisor */
-	if (!amdgpu_sriov_vf(adev)) {
-		for (i = 0; i < adev->sdma.num_instances; i++) {
-			ring = &adev->sdma.instance[i].ring;
-			adev->nbio.funcs->sdma_doorbell_range(adev, i,
-				ring->use_doorbell, ring->doorbell_index,
-				adev->doorbell_index.sdma_doorbell_range);
-		}
-
-		adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell,
-						adev->irq.ih.doorbell_index);
-	}
-}
-
 static int soc15_common_hw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1249,12 +1230,6 @@ static int soc15_common_hw_init(void *handle)
 
 	/* enable the doorbell aperture */
 	soc15_enable_doorbell_aperture(adev, true);
-	/* HW doorbell routing policy: doorbell writing not
-	 * in SDMA/IH/MM/ACV range will be routed to CP. So
-	 * we need to init SDMA/IH/MM/ACV doorbell range prior
-	 * to CP ip block init and ring test.
-	 */
-	soc15_doorbell_range_init(adev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 52816de5e17b..6e564b549b9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -421,6 +421,7 @@ static bool soc21_need_full_reset(struct amdgpu_device *adev)
 {
 	switch (adev->ip_versions[GC_HWIP][0]) {
 	case IP_VERSION(11, 0, 0):
+		return amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC);
 	case IP_VERSION(11, 0, 2):
 		return false;
 	default:
@@ -494,6 +495,20 @@ static void soc21_pre_asic_init(struct amdgpu_device *adev)
 {
 }
 
+static int soc21_update_umd_stable_pstate(struct amdgpu_device *adev,
+					  bool enter)
+{
+	if (enter)
+		amdgpu_gfx_rlc_enter_safe_mode(adev);
+	else
+		amdgpu_gfx_rlc_exit_safe_mode(adev);
+
+	if (adev->gfx.funcs->update_perfmon_mgcg)
+		adev->gfx.funcs->update_perfmon_mgcg(adev, !enter);
+
+	return 0;
+}
+
 static const struct amdgpu_asic_funcs soc21_asic_funcs =
 {
 	.read_disabled_bios = &soc21_read_disabled_bios,
@@ -513,6 +528,7 @@ static const struct amdgpu_asic_funcs soc21_asic_funcs =
 	.supports_baco = &amdgpu_dpm_is_baco_supported,
 	.pre_asic_init = &soc21_pre_asic_init,
 	.query_video_codecs = &soc21_query_video_codecs,
+	.update_umd_stable_pstate = &soc21_update_umd_stable_pstate,
 };
 
 static int soc21_common_early_init(void *handle)
@@ -546,8 +562,10 @@ static int soc21_common_early_init(void *handle)
 	case IP_VERSION(11, 0, 0):
 		adev->cg_flags = AMD_CG_SUPPORT_GFX_CGCG |
 			AMD_CG_SUPPORT_GFX_CGLS |
+#if 0
 			AMD_CG_SUPPORT_GFX_3D_CGCG |
 			AMD_CG_SUPPORT_GFX_3D_CGLS |
+#endif
 			AMD_CG_SUPPORT_GFX_MGCG |
 			AMD_CG_SUPPORT_REPEATER_FGCG |
 			AMD_CG_SUPPORT_GFX_FGCG |
@@ -575,7 +593,9 @@ static int soc21_common_early_init(void *handle)
 			AMD_CG_SUPPORT_VCN_MGCG |
 			AMD_CG_SUPPORT_JPEG_MGCG |
 			AMD_CG_SUPPORT_ATHUB_MGCG |
-			AMD_CG_SUPPORT_ATHUB_LS;
+			AMD_CG_SUPPORT_ATHUB_LS |
+			AMD_CG_SUPPORT_IH_CG |
+			AMD_CG_SUPPORT_HDP_SD;
 		adev->pg_flags =
 			AMD_PG_SUPPORT_VCN |
 			AMD_PG_SUPPORT_VCN_DPG |
@@ -586,9 +606,26 @@ static int soc21_common_early_init(void *handle)
 		break;
 	case IP_VERSION(11, 0, 1):
 		adev->cg_flags =
+			AMD_CG_SUPPORT_GFX_CGCG |
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_FGCG |
+			AMD_CG_SUPPORT_REPEATER_FGCG |
+			AMD_CG_SUPPORT_GFX_PERF_CLK |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_HDP_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_ATHUB_MGCG |
+			AMD_CG_SUPPORT_ATHUB_LS |
+			AMD_CG_SUPPORT_IH_CG |
+			AMD_CG_SUPPORT_BIF_MGCG |
+			AMD_CG_SUPPORT_BIF_LS |
 			AMD_CG_SUPPORT_VCN_MGCG |
 			AMD_CG_SUPPORT_JPEG_MGCG;
 		adev->pg_flags =
+			AMD_PG_SUPPORT_GFX_PG |
+			AMD_PG_SUPPORT_VCN_DPG |
 			AMD_PG_SUPPORT_JPEG;
 		adev->external_rev_id = adev->rev_id + 0x1;
 		break;
@@ -683,6 +720,8 @@ static int soc21_common_set_clockgating_state(void *handle,
 
 	switch (adev->ip_versions[NBIO_HWIP][0]) {
 	case IP_VERSION(4, 3, 0):
+	case IP_VERSION(4, 3, 1):
+	case IP_VERSION(7, 7, 0):
 		adev->nbio.funcs->update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE);
 		adev->nbio.funcs->update_medium_grain_light_sleep(adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index ca14c3ef742e..fb2d74f30448 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -1115,7 +1115,7 @@ static int vcn_v4_0_start(struct amdgpu_device *adev)
  *
  * Stop VCN block with dpg mode
  */
-static int vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
+static void vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 {
 	uint32_t tmp;
 
@@ -1133,7 +1133,6 @@ static int vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 	/* disable dynamic power gating mode */
 	WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, regUVD_POWER_STATUS), 0,
 		~UVD_POWER_STATUS__UVD_PG_MODE_MASK);
-	return 0;
 }
 
 /**
@@ -1154,7 +1153,7 @@ static int vcn_v4_0_stop(struct amdgpu_device *adev)
 		fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
 
 		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v4_0_stop_dpg_mode(adev, i);
+			vcn_v4_0_stop_dpg_mode(adev, i);
 			continue;
 		}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index cdd599a08125..1e83db0c5438 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -289,6 +289,10 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
 		}
 	}
 
+	if (!amdgpu_sriov_vf(adev))
+		adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell,
+						    adev->irq.ih.doorbell_index);
+
 	pci_set_master(adev->pdev);
 
 	/* enable interrupts */
@@ -334,9 +338,11 @@ static u32 vega10_ih_get_wptr(struct amdgpu_device *adev,
 	u32 wptr, tmp;
 	struct amdgpu_ih_regs *ih_regs;
 
-	if (ih == &adev->irq.ih) {
+	if (ih == &adev->irq.ih || ih == &adev->irq.ih_soft) {
 		/* Only ring0 supports writeback. On other rings fall back
 		 * to register-based code with overflow checking below.
+		 * ih_soft ring doesn't have any backing hardware registers,
+		 * update wptr and return.
 		 */
 		wptr = le32_to_cpu(*ih->wptr_cpu);
 
@@ -409,6 +415,9 @@ static void vega10_ih_set_rptr(struct amdgpu_device *adev,
 {
 	struct amdgpu_ih_regs *ih_regs;
 
+	if (ih == &adev->irq.ih_soft)
+		return;
+
 	if (ih->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
 		*ih->rptr_cpu = ih->rptr;
diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
index 3b4eb8285943..59dfca093155 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
@@ -340,6 +340,10 @@ static int vega20_ih_irq_init(struct amdgpu_device *adev)
 		}
 	}
 
+	if (!amdgpu_sriov_vf(adev))
+		adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell,
+						    adev->irq.ih.doorbell_index);
+
 	pci_set_master(adev->pdev);
 
 	/* enable interrupts */
@@ -385,9 +389,11 @@ static u32 vega20_ih_get_wptr(struct amdgpu_device *adev,
 	u32 wptr, tmp;
 	struct amdgpu_ih_regs *ih_regs;
 
-	if (ih == &adev->irq.ih) {
+	if (ih == &adev->irq.ih || ih == &adev->irq.ih_soft) {
 		/* Only ring0 supports writeback. On other rings fall back
 		 * to register-based code with overflow checking below.
+		 * ih_soft ring doesn't have any backing hardware registers,
+		 * update wptr and return.
 		 */
 		wptr = le32_to_cpu(*ih->wptr_cpu);
 
@@ -461,6 +467,9 @@ static void vega20_ih_set_rptr(struct amdgpu_device *adev,
 {
 	struct amdgpu_ih_regs *ih_regs;
 
+	if (ih == &adev->irq.ih_soft)
+		return;
+
 	if (ih->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
 		*ih->rptr_cpu = ih->rptr;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 2b3d8bc8f0aa..dc774ddf3445 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -874,7 +874,7 @@ static int kfd_ioctl_wait_events(struct file *filp, struct kfd_process *p,
 	err = kfd_wait_on_events(p, args->num_events,
 			(void __user *)args->events_ptr,
 			(args->wait_for_all != 0),
-			args->timeout, &args->wait_result);
+			&args->timeout, &args->wait_result);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index f5853835f03a..22c0929d410b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -102,13 +102,18 @@ static void kfd_device_info_set_sdma_info(struct kfd_dev *kfd)
 
 	switch (sdma_version) {
 	case IP_VERSION(6, 0, 0):
-	case IP_VERSION(6, 0, 1):
 	case IP_VERSION(6, 0, 2):
 		/* Reserve 1 for paging and 1 for gfx */
 		kfd->device_info.num_reserved_sdma_queues_per_engine = 2;
 		/* BIT(0)=engine-0 queue-0; BIT(1)=engine-1 queue-0; BIT(2)=engine-0 queue-1; ... */
 		kfd->device_info.reserved_sdma_queues_bitmap = 0xFULL;
 		break;
+	case IP_VERSION(6, 0, 1):
+		/* Reserve 1 for paging and 1 for gfx */
+		kfd->device_info.num_reserved_sdma_queues_per_engine = 2;
+		/* BIT(0)=engine-0 queue-0; BIT(1)=engine-0 queue-1; ... */
+		kfd->device_info.reserved_sdma_queues_bitmap = 0x3ULL;
+		break;
 	default:
 		break;
 	}
@@ -377,12 +382,8 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf)
 				f2g = &gfx_v10_3_kfd2kgd;
 			break;
 		case IP_VERSION(10, 3, 6):
-			gfx_target_version = 100306;
-			if (!vf)
-				f2g = &gfx_v10_3_kfd2kgd;
-			break;
 		case IP_VERSION(10, 3, 7):
-			gfx_target_version = 100307;
+			gfx_target_version = 100306;
 			if (!vf)
 				f2g = &gfx_v10_3_kfd2kgd;
 			break;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index e83725a28106..007a3db69df1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -205,6 +205,8 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q,
 	}
 
 	queue_input.is_kfd_process = 1;
+	queue_input.is_aql_queue = (q->properties.format == KFD_QUEUE_FORMAT_AQL);
+	queue_input.queue_size = q->properties.queue_size >> 2;
 
 	queue_input.paging = false;
 	queue_input.tba_addr = qpd->tba_addr;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 3942a56c28bb..83e3ce9f6049 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -894,7 +894,8 @@ static long user_timeout_to_jiffies(uint32_t user_timeout_ms)
 	return msecs_to_jiffies(user_timeout_ms) + 1;
 }
 
-static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
+static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters,
+			 bool undo_auto_reset)
 {
 	uint32_t i;
 
@@ -903,6 +904,9 @@ static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
 			spin_lock(&waiters[i].event->lock);
 			remove_wait_queue(&waiters[i].event->wq,
 					  &waiters[i].wait);
+			if (undo_auto_reset && waiters[i].activated &&
+			    waiters[i].event && waiters[i].event->auto_reset)
+				set_event(waiters[i].event);
 			spin_unlock(&waiters[i].event->lock);
 		}
 
@@ -911,7 +915,7 @@ static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
 
 int kfd_wait_on_events(struct kfd_process *p,
 		       uint32_t num_events, void __user *data,
-		       bool all, uint32_t user_timeout_ms,
+		       bool all, uint32_t *user_timeout_ms,
 		       uint32_t *wait_result)
 {
 	struct kfd_event_data __user *events =
@@ -920,7 +924,7 @@ int kfd_wait_on_events(struct kfd_process *p,
 	int ret = 0;
 
 	struct kfd_event_waiter *event_waiters = NULL;
-	long timeout = user_timeout_to_jiffies(user_timeout_ms);
+	long timeout = user_timeout_to_jiffies(*user_timeout_ms);
 
 	event_waiters = alloc_event_waiters(num_events);
 	if (!event_waiters) {
@@ -970,15 +974,11 @@ int kfd_wait_on_events(struct kfd_process *p,
 		}
 
 		if (signal_pending(current)) {
-			/*
-			 * This is wrong when a nonzero, non-infinite timeout
-			 * is specified. We need to use
-			 * ERESTARTSYS_RESTARTBLOCK, but struct restart_block
-			 * contains a union with data for each user and it's
-			 * in generic kernel code that I don't want to
-			 * touch yet.
-			 */
 			ret = -ERESTARTSYS;
+			if (*user_timeout_ms != KFD_EVENT_TIMEOUT_IMMEDIATE &&
+			    *user_timeout_ms != KFD_EVENT_TIMEOUT_INFINITE)
+				*user_timeout_ms = jiffies_to_msecs(
+					max(0l, timeout-1));
 			break;
 		}
 
@@ -1019,7 +1019,7 @@ int kfd_wait_on_events(struct kfd_process *p,
 					       event_waiters, events);
 
 out_unlock:
-	free_waiters(num_events, event_waiters);
+	free_waiters(num_events, event_waiters, ret == -ERESTARTSYS);
 	mutex_unlock(&p->event_mutex);
 out:
 	if (ret)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
index a6fcbeeb7428..0d53f6067422 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
@@ -350,11 +350,11 @@ static void event_interrupt_wq_v11(struct kfd_dev *dev,
 				print_sq_intr_info_inst(context_id0, context_id1);
 				sq_int_priv = REG_GET_FIELD(context_id0,
 						SQ_INTERRUPT_WORD_WAVE_CTXID0, PRIV);
-				if (sq_int_priv /*&& (kfd_set_dbg_ev_from_interrupt(dev, pasid,
+				/*if (sq_int_priv && (kfd_set_dbg_ev_from_interrupt(dev, pasid,
 						KFD_CTXID0_DOORBELL_ID(context_id0),
 						KFD_CTXID0_TRAP_CODE(context_id0),
-						NULL, 0))*/)
-					return;
+						NULL, 0)))
+					return;*/
 				break;
 			case SQ_INTERRUPT_WORD_ENCODING_ERROR:
 				print_sq_intr_info_error(context_id0, context_id1);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index b8e14c2cc295..3ae350220d42 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -126,6 +126,10 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->compute_static_thread_mgmt_se1 = 0xFFFFFFFF;
 	m->compute_static_thread_mgmt_se2 = 0xFFFFFFFF;
 	m->compute_static_thread_mgmt_se3 = 0xFFFFFFFF;
+	m->compute_static_thread_mgmt_se4 = 0xFFFFFFFF;
+	m->compute_static_thread_mgmt_se5 = 0xFFFFFFFF;
+	m->compute_static_thread_mgmt_se6 = 0xFFFFFFFF;
+	m->compute_static_thread_mgmt_se7 = 0xFFFFFFFF;
 
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index d03a3b9c9c5d..bf610e3b683b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1317,7 +1317,7 @@ void kfd_event_free_process(struct kfd_process *p);
 int kfd_event_mmap(struct kfd_process *process, struct vm_area_struct *vma);
 int kfd_wait_on_events(struct kfd_process *p,
 		       uint32_t num_events, void __user *data,
-		       bool all, uint32_t user_timeout_ms,
+		       bool all, uint32_t *user_timeout_ms,
 		       uint32_t *wait_result);
 void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
 				uint32_t valid_id_bits);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index a67ba8879a56..11074cc8c333 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -541,7 +541,6 @@ svm_range_vram_node_new(struct amdgpu_device *adev, struct svm_range *prange,
 		kfree(svm_bo);
 		return -ESRCH;
 	}
-	svm_bo->svms = prange->svms;
 	svm_bo->eviction_fence =
 		amdgpu_amdkfd_fence_create(dma_fence_context_alloc(1),
 					   mm,
@@ -3273,7 +3272,6 @@ int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence)
 static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 {
 	struct svm_range_bo *svm_bo;
-	struct kfd_process *p;
 	struct mm_struct *mm;
 	int r = 0;
 
@@ -3281,13 +3279,12 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 	if (!svm_bo_ref_unless_zero(svm_bo))
 		return; /* svm_bo was freed while eviction was pending */
 
-	/* svm_range_bo_release destroys this worker thread. So during
-	 * the lifetime of this thread, kfd_process and mm will be valid.
-	 */
-	p = container_of(svm_bo->svms, struct kfd_process, svms);
-	mm = p->mm;
-	if (!mm)
+	if (mmget_not_zero(svm_bo->eviction_fence->mm)) {
+		mm = svm_bo->eviction_fence->mm;
+	} else {
+		svm_range_bo_unref(svm_bo);
 		return;
+	}
 
 	mmap_read_lock(mm);
 	spin_lock(&svm_bo->list_lock);
@@ -3305,8 +3302,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 
 		mutex_lock(&prange->migrate_mutex);
 		do {
-			r = svm_migrate_vram_to_ram(prange,
-						svm_bo->eviction_fence->mm,
+			r = svm_migrate_vram_to_ram(prange, mm,
 						KFD_MIGRATE_TRIGGER_TTM_EVICTION);
 		} while (!r && prange->actual_loc && --retries);
 
@@ -3324,6 +3320,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 	}
 	spin_unlock(&svm_bo->list_lock);
 	mmap_read_unlock(mm);
+	mmput(mm);
 
 	dma_fence_signal(&svm_bo->eviction_fence->base);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index 9156b041ef17..cfac13ad06ef 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -46,7 +46,6 @@ struct svm_range_bo {
 	spinlock_t			list_lock;
 	struct amdgpu_amdkfd_fence	*eviction_fence;
 	struct work_struct		eviction_work;
-	struct svm_range_list		*svms;
 	uint32_t			evicting;
 	struct work_struct		release_work;
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 25990bec600d..3f0a4a415907 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1392,8 +1392,8 @@ static int kfd_build_p2p_node_entry(struct kfd_topology_device *dev,
 
 static int kfd_create_indirect_link_prop(struct kfd_topology_device *kdev, int gpu_node)
 {
+	struct kfd_iolink_properties *gpu_link, *tmp_link, *cpu_link;
 	struct kfd_iolink_properties *props = NULL, *props2 = NULL;
-	struct kfd_iolink_properties *gpu_link, *cpu_link;
 	struct kfd_topology_device *cpu_dev;
 	int ret = 0;
 	int i, num_cpu;
@@ -1416,16 +1416,19 @@ static int kfd_create_indirect_link_prop(struct kfd_topology_device *kdev, int g
 			continue;
 
 		/* find CPU <-->  CPU links */
+		cpu_link = NULL;
 		cpu_dev = kfd_topology_device_by_proximity_domain(i);
 		if (cpu_dev) {
-			list_for_each_entry(cpu_link,
+			list_for_each_entry(tmp_link,
 					&cpu_dev->io_link_props, list) {
-				if (cpu_link->node_to == gpu_link->node_to)
+				if (tmp_link->node_to == gpu_link->node_to) {
+					cpu_link = tmp_link;
 					break;
+				}
 			}
 		}
 
-		if (cpu_link->node_to != gpu_link->node_to)
+		if (!cpu_link)
 			return -ENOMEM;
 
 		/* CPU <--> CPU <--> GPU, GPU node*/
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 8660d93cc405..1efe7fa5bc58 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3825,8 +3825,11 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev)
 	adev_to_drm(adev)->mode_config.max_height = 16384;
 
 	adev_to_drm(adev)->mode_config.preferred_depth = 24;
-	/* disable prefer shadow for now due to hibernation issues */
-	adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	if (adev->asic_type == CHIP_HAWAII)
+		/* disable prefer shadow for now due to hibernation issues */
+		adev_to_drm(adev)->mode_config.prefer_shadow = 0;
+	else
+		adev_to_drm(adev)->mode_config.prefer_shadow = 1;
 	/* indicates support for immediate flip */
 	adev_to_drm(adev)->mode_config.async_page_flip = true;
 
@@ -4135,6 +4138,7 @@ static void register_backlight_device(struct amdgpu_display_manager *dm,
 	}
 }
 
+static void amdgpu_set_panel_orientation(struct drm_connector *connector);
 
 /*
  * In this architecture, the association
@@ -4326,6 +4330,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 					adev_to_drm(adev)->vblank_disable_immediate = false;
 			}
 		}
+		amdgpu_set_panel_orientation(&aconnector->base);
 	}
 
 	/* Software is initialized. Now we can register interrupt handlers. */
@@ -4754,7 +4759,7 @@ fill_dc_plane_info_and_addr(struct amdgpu_device *adev,
 	plane_info->visible = true;
 	plane_info->stereo_format = PLANE_STEREO_FORMAT_NONE;
 
-	plane_info->layer_index = 0;
+	plane_info->layer_index = plane_state->normalized_zpos;
 
 	ret = fill_plane_color_attributes(plane_state, plane_info->format,
 					  &plane_info->color_space);
@@ -4822,7 +4827,7 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev,
 	dc_plane_state->global_alpha = plane_info.global_alpha;
 	dc_plane_state->global_alpha_value = plane_info.global_alpha_value;
 	dc_plane_state->dcc = plane_info.dcc;
-	dc_plane_state->layer_index = plane_info.layer_index; // Always returns 0
+	dc_plane_state->layer_index = plane_info.layer_index;
 	dc_plane_state->flip_int_enabled = true;
 
 	/*
@@ -6684,6 +6689,10 @@ static void amdgpu_set_panel_orientation(struct drm_connector *connector)
 	    connector->connector_type != DRM_MODE_CONNECTOR_LVDS)
 		return;
 
+	mutex_lock(&connector->dev->mode_config.mutex);
+	amdgpu_dm_connector_get_modes(connector);
+	mutex_unlock(&connector->dev->mode_config.mutex);
+
 	encoder = amdgpu_dm_connector_to_encoder(connector);
 	if (!encoder)
 		return;
@@ -6728,8 +6737,6 @@ static void amdgpu_dm_connector_ddc_get_modes(struct drm_connector *connector,
 		 * restored here.
 		 */
 		amdgpu_dm_update_freesync_caps(connector, edid);
-
-		amdgpu_set_panel_orientation(connector);
 	} else {
 		amdgpu_dm_connector->num_modes = 0;
 	}
@@ -9478,6 +9485,14 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 		}
 	}
 
+	/*
+	 * DC consults the zpos (layer_index in DC terminology) to determine the
+	 * hw plane on which to enable the hw cursor (see
+	 * `dcn10_can_pipe_disable_cursor`). By now, all modified planes are in
+	 * atomic state, so call drm helper to normalize zpos.
+	 */
+	drm_atomic_normalize_zpos(dev, state);
+
 	/* Remove exiting planes if they are modified */
 	for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) {
 		ret = dm_update_plane_state(dc, state, plane,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 0e48824f55e3..ee242d9d8b06 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -3288,6 +3288,7 @@ void crtc_debugfs_init(struct drm_crtc *crtc)
 				   &crc_win_y_end_fops);
 	debugfs_create_file_unsafe("crc_win_update", 0644, dir, crtc,
 				   &crc_win_update_fops);
+	dput(dir);
 #endif
 	debugfs_create_file("amdgpu_current_bpc", 0644, crtc->debugfs_entry,
 			    crtc, &amdgpu_current_bpc_fops);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index b841b8b0a9d8..987bde4dca3d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -34,6 +34,7 @@
 #include "dal_asic_id.h"
 #include "amdgpu_display.h"
 #include "amdgpu_dm_trace.h"
+#include "amdgpu_dm_plane.h"
 #include "gc/gc_11_0_0_offset.h"
 #include "gc/gc_11_0_0_sh_mask.h"
 
@@ -149,12 +150,12 @@ static void add_modifier(uint64_t **mods, uint64_t *size, uint64_t *cap, uint64_
 	*size += 1;
 }
 
-bool modifier_has_dcc(uint64_t modifier)
+static bool modifier_has_dcc(uint64_t modifier)
 {
 	return IS_AMD_FMT_MOD(modifier) && AMD_FMT_MOD_GET(DCC, modifier);
 }
 
-unsigned modifier_gfx9_swizzle_mode(uint64_t modifier)
+static unsigned modifier_gfx9_swizzle_mode(uint64_t modifier)
 {
 	if (modifier == DRM_FORMAT_MOD_LINEAR)
 		return 0;
@@ -660,7 +661,7 @@ static int get_plane_modifiers(struct amdgpu_device *adev, unsigned int plane_ty
 			add_gfx10_1_modifiers(adev, mods, &size, &capacity);
 		break;
 	case AMDGPU_FAMILY_GC_11_0_0:
-	case AMDGPU_FAMILY_GC_11_0_2:
+	case AMDGPU_FAMILY_GC_11_0_1:
 		add_gfx11_modifiers(adev, mods, &size, &capacity);
 		break;
 	}
@@ -1412,7 +1413,7 @@ static bool dm_plane_format_mod_supported(struct drm_plane *plane,
 		}
 		break;
 	case AMDGPU_FAMILY_GC_11_0_0:
-	case AMDGPU_FAMILY_GC_11_0_2:
+	case AMDGPU_FAMILY_GC_11_0_1:
 		switch (AMD_FMT_MOD_GET(TILE, modifier)) {
 		case AMD_FMT_MOD_TILE_GFX11_256K_R_X:
 		case AMD_FMT_MOD_TILE_GFX9_64K_R_X:
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h
index 95168c2cfa6f..286981a2dd40 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.h
@@ -36,17 +36,9 @@ int fill_dc_scaling_info(struct amdgpu_device *adev,
 			 const struct drm_plane_state *state,
 			 struct dc_scaling_info *scaling_info);
 
-void get_min_max_dc_plane_scaling(struct drm_device *dev,
-				  struct drm_framebuffer *fb,
-				  int *min_downscale, int *max_upscale);
-
 int dm_plane_helper_check_state(struct drm_plane_state *state,
 				struct drm_crtc_state *new_crtc_state);
 
-bool modifier_has_dcc(uint64_t modifier);
-
-unsigned int modifier_gfx9_swizzle_mode(uint64_t modifier);
-
 int fill_plane_buffer_attributes(struct amdgpu_device *adev,
 				 const struct amdgpu_framebuffer *afb,
 				 const enum surface_pixel_format format,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
index c8da18e45b0e..8ca10ab3dfc1 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
@@ -170,7 +170,13 @@ bool amdgpu_dm_psr_enable(struct dc_stream_state *stream)
 					   &stream, 1,
 					   &params);
 
-	power_opt |= psr_power_opt_z10_static_screen;
+	/*
+	 * Only enable static-screen optimizations for PSR1. For PSR SU, this
+	 * causes vstartup interrupt issues, used by amdgpu_dm to send vblank
+	 * events.
+	 */
+	if (link->psr_settings.psr_version < DC_PSR_VERSION_SU_1)
+		power_opt |= psr_power_opt_z10_static_screen;
 
 	return dc_link_set_psr_allow_active(link, &psr_enable, false, false, &power_opt);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/basics/conversion.c b/drivers/gpu/drm/amd/display/dc/basics/conversion.c
index 6767fab55c26..352e9afb85c6 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/conversion.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/conversion.c
@@ -100,3 +100,24 @@ void convert_float_matrix(
 		matrix[i] = (uint16_t)reg_value;
 	}
 }
+
+static uint32_t find_gcd(uint32_t a, uint32_t b)
+{
+	uint32_t remainder = 0;
+	while (b != 0) {
+		remainder = a % b;
+		a = b;
+		b = remainder;
+	}
+	return a;
+}
+
+void reduce_fraction(uint32_t num, uint32_t den,
+		uint32_t *out_num, uint32_t *out_den)
+{
+	uint32_t gcd = 0;
+
+	gcd = find_gcd(num, den);
+	*out_num = num / gcd;
+	*out_den = den / gcd;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/basics/conversion.h b/drivers/gpu/drm/amd/display/dc/basics/conversion.h
index ade785c4fdc7..81da4e6f7a1a 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/conversion.h
+++ b/drivers/gpu/drm/amd/display/dc/basics/conversion.h
@@ -38,6 +38,9 @@ void convert_float_matrix(
 	struct fixed31_32 *flt,
 	uint32_t buffer_size);
 
+void reduce_fraction(uint32_t num, uint32_t den,
+		uint32_t *out_num, uint32_t *out_den);
+
 static inline unsigned int log_2(unsigned int num)
 {
 	return ilog2(num);
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
index 4c76091fd1f2..f276abb63bcd 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
@@ -337,7 +337,7 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p
 	    break;
 	}
 
-	case AMDGPU_FAMILY_GC_11_0_2: {
+	case AMDGPU_FAMILY_GC_11_0_1: {
 		struct clk_mgr_dcn314 *clk_mgr = kzalloc(sizeof(*clk_mgr), GFP_KERNEL);
 
 		if (clk_mgr == NULL) {
@@ -397,7 +397,7 @@ void dc_destroy_clk_mgr(struct clk_mgr *clk_mgr_base)
 		dcn32_clk_mgr_destroy(clk_mgr);
 		break;
 
-	case AMDGPU_FAMILY_GC_11_0_2:
+	case AMDGPU_FAMILY_GC_11_0_1:
 		dcn314_clk_mgr_destroy(clk_mgr);
 		break;
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
index 0202dc682682..ca6dfd2d7561 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
@@ -24,10 +24,9 @@
  */
 
 #include "dccg.h"
-#include "clk_mgr_internal.h"
+#include "rn_clk_mgr.h"
 
 #include "dcn20/dcn20_clk_mgr.h"
-#include "rn_clk_mgr.h"
 #include "dml/dcn20/dcn20_fpu.h"
 
 #include "dce100/dce_clk_mgr.h"
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h
index 2e088c5171b2..f1319957e400 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h
@@ -28,6 +28,7 @@
 
 #include "clk_mgr.h"
 #include "dm_pp_smu.h"
+#include "clk_mgr_internal.h"
 
 extern struct wm_table ddr4_wm_table_gs;
 extern struct wm_table lpddr4_wm_table_gs;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
index c09be3f15fe6..23a299c929a1 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
@@ -99,7 +99,7 @@ static int dcn31_get_active_display_cnt_wa(
 	return display_count;
 }
 
-static void dcn31_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable)
+static void dcn31_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable)
 {
 	struct dc *dc = clk_mgr_base->ctx->dc;
 	int i;
@@ -110,9 +110,10 @@ static void dcn31_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable)
 		if (pipe->top_pipe || pipe->prev_odm_pipe)
 			continue;
 		if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal))) {
-			if (disable)
+			if (disable) {
 				pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg);
-			else
+				reset_sync_context_for_pipe(dc, context, i);
+			} else
 				pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg);
 		}
 	}
@@ -211,11 +212,11 @@ void dcn31_update_clocks(struct clk_mgr *clk_mgr_base,
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
-		dcn31_disable_otg_wa(clk_mgr_base, true);
+		dcn31_disable_otg_wa(clk_mgr_base, context, true);
 
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
 		dcn31_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz);
-		dcn31_disable_otg_wa(clk_mgr_base, false);
+		dcn31_disable_otg_wa(clk_mgr_base, context, false);
 
 		update_dispclk = true;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
index ee99974b3b62..4a15aa7a375f 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
@@ -119,7 +119,7 @@ static int dcn314_get_active_display_cnt_wa(
 	return display_count;
 }
 
-static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable)
+static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable)
 {
 	struct dc *dc = clk_mgr_base->ctx->dc;
 	int i;
@@ -129,12 +129,21 @@ static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable)
 
 		if (pipe->top_pipe || pipe->prev_odm_pipe)
 			continue;
-		if (pipe->stream && (pipe->stream->dpms_off || pipe->plane_state == NULL ||
-				     dc_is_virtual_signal(pipe->stream->signal))) {
-			if (disable)
+		if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal))) {
+			struct stream_encoder *stream_enc = pipe->stream_res.stream_enc;
+
+			if (disable) {
+				if (stream_enc && stream_enc->funcs->disable_fifo)
+					pipe->stream_res.stream_enc->funcs->disable_fifo(stream_enc);
+
 				pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg);
-			else
+				reset_sync_context_for_pipe(dc, context, i);
+			} else {
 				pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg);
+
+				if (stream_enc && stream_enc->funcs->enable_fifo)
+					pipe->stream_res.stream_enc->funcs->enable_fifo(stream_enc);
+			}
 		}
 	}
 }
@@ -233,11 +242,11 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
-		dcn314_disable_otg_wa(clk_mgr_base, true);
+		dcn314_disable_otg_wa(clk_mgr_base, context, true);
 
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
 		dcn314_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz);
-		dcn314_disable_otg_wa(clk_mgr_base, false);
+		dcn314_disable_otg_wa(clk_mgr_base, context, false);
 
 		update_dispclk = true;
 	}
@@ -307,16 +316,6 @@ static void dcn314_enable_pme_wa(struct clk_mgr *clk_mgr_base)
 	dcn314_smu_enable_pme_wa(clk_mgr);
 }
 
-void dcn314_init_clocks(struct clk_mgr *clk_mgr)
-{
-	memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks));
-	// Assumption is that boot state always supports pstate
-	clk_mgr->clks.p_state_change_support = true;
-	clk_mgr->clks.prev_p_state_change_support = true;
-	clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN;
-	clk_mgr->clks.zstate_support = DCN_ZSTATE_SUPPORT_UNKNOWN;
-}
-
 bool dcn314_are_clock_states_equal(struct dc_clocks *a,
 		struct dc_clocks *b)
 {
@@ -425,7 +424,7 @@ static struct wm_table lpddr5_wm_table = {
 	}
 };
 
-static DpmClocks_t dummy_clocks;
+static DpmClocks314_t dummy_clocks;
 
 static struct dcn314_watermarks dummy_wms = { 0 };
 
@@ -510,7 +509,7 @@ static void dcn314_notify_wm_ranges(struct clk_mgr *clk_mgr_base)
 static void dcn314_get_dpm_table_from_smu(struct clk_mgr_internal *clk_mgr,
 		struct dcn314_smu_dpm_clks *smu_dpm_clks)
 {
-	DpmClocks_t *table = smu_dpm_clks->dpm_clks;
+	DpmClocks314_t *table = smu_dpm_clks->dpm_clks;
 
 	if (!clk_mgr->smu_ver)
 		return;
@@ -527,6 +526,26 @@ static void dcn314_get_dpm_table_from_smu(struct clk_mgr_internal *clk_mgr,
 	dcn314_smu_transfer_dpm_table_smu_2_dram(clk_mgr);
 }
 
+static inline bool is_valid_clock_value(uint32_t clock_value)
+{
+	return clock_value > 1 && clock_value < 100000;
+}
+
+static unsigned int convert_wck_ratio(uint8_t wck_ratio)
+{
+	switch (wck_ratio) {
+	case WCK_RATIO_1_2:
+		return 2;
+
+	case WCK_RATIO_1_4:
+		return 4;
+
+	default:
+		break;
+	}
+	return 1;
+}
+
 static uint32_t find_max_clk_value(const uint32_t clocks[], uint32_t num_clocks)
 {
 	uint32_t max = 0;
@@ -540,89 +559,129 @@ static uint32_t find_max_clk_value(const uint32_t clocks[], uint32_t num_clocks)
 	return max;
 }
 
-static unsigned int find_clk_for_voltage(
-		const DpmClocks_t *clock_table,
-		const uint32_t clocks[],
-		unsigned int voltage)
-{
-	int i;
-	int max_voltage = 0;
-	int clock = 0;
-
-	for (i = 0; i < NUM_SOC_VOLTAGE_LEVELS; i++) {
-		if (clock_table->SocVoltage[i] == voltage) {
-			return clocks[i];
-		} else if (clock_table->SocVoltage[i] >= max_voltage &&
-				clock_table->SocVoltage[i] < voltage) {
-			max_voltage = clock_table->SocVoltage[i];
-			clock = clocks[i];
-		}
-	}
-
-	ASSERT(clock);
-	return clock;
-}
-
 static void dcn314_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk_mgr,
 						    struct integrated_info *bios_info,
-						    const DpmClocks_t *clock_table)
+						    const DpmClocks314_t *clock_table)
 {
-	int i, j;
 	struct clk_bw_params *bw_params = clk_mgr->base.bw_params;
-	uint32_t max_dispclk = 0, max_dppclk = 0;
-
-	j = -1;
-
-	ASSERT(NUM_DF_PSTATE_LEVELS <= MAX_NUM_DPM_LVL);
-
-	/* Find lowest DPM, FCLK is filled in reverse order*/
+	struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1];
+	uint32_t max_pstate = 0,  max_fclk = 0,  min_pstate = 0, max_dispclk = 0, max_dppclk = 0;
+	int i;
 
-	for (i = NUM_DF_PSTATE_LEVELS - 1; i >= 0; i--) {
-		if (clock_table->DfPstateTable[i].FClk != 0) {
-			j = i;
-			break;
+	/* Find highest valid fclk pstate */
+	for (i = 0; i < clock_table->NumDfPstatesEnabled; i++) {
+		if (is_valid_clock_value(clock_table->DfPstateTable[i].FClk) &&
+		    clock_table->DfPstateTable[i].FClk > max_fclk) {
+			max_fclk = clock_table->DfPstateTable[i].FClk;
+			max_pstate = i;
 		}
 	}
 
-	if (j == -1) {
-		/* clock table is all 0s, just use our own hardcode */
-		ASSERT(0);
-		return;
-	}
-
-	bw_params->clk_table.num_entries = j + 1;
+	/* We expect the table to contain at least one valid fclk entry. */
+	ASSERT(is_valid_clock_value(max_fclk));
 
-	/* dispclk and dppclk can be max at any voltage, same number of levels for both */
+	/* Dispclk and dppclk can be max at any voltage, same number of levels for both */
 	if (clock_table->NumDispClkLevelsEnabled <= NUM_DISPCLK_DPM_LEVELS &&
 	    clock_table->NumDispClkLevelsEnabled <= NUM_DPPCLK_DPM_LEVELS) {
 		max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled);
 		max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled);
 	} else {
+		/* Invalid number of entries in the table from PMFW. */
 		ASSERT(0);
 	}
 
-	for (i = 0; i < bw_params->clk_table.num_entries; i++, j--) {
-		bw_params->clk_table.entries[i].fclk_mhz = clock_table->DfPstateTable[j].FClk;
-		bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[j].MemClk;
-		bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[j].Voltage;
-		switch (clock_table->DfPstateTable[j].WckRatio) {
-		case WCK_RATIO_1_2:
-			bw_params->clk_table.entries[i].wck_ratio = 2;
-			break;
-		case WCK_RATIO_1_4:
-			bw_params->clk_table.entries[i].wck_ratio = 4;
-			break;
-		default:
-			bw_params->clk_table.entries[i].wck_ratio = 1;
+	/* Base the clock table on dcfclk, need at least one entry regardless of pmfw table */
+	for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) {
+		uint32_t min_fclk = clock_table->DfPstateTable[0].FClk;
+		int j;
+
+		for (j = 1; j < clock_table->NumDfPstatesEnabled; j++) {
+			if (is_valid_clock_value(clock_table->DfPstateTable[j].FClk) &&
+			    clock_table->DfPstateTable[j].FClk < min_fclk &&
+			    clock_table->DfPstateTable[j].Voltage <= clock_table->SocVoltage[i]) {
+				min_fclk = clock_table->DfPstateTable[j].FClk;
+				min_pstate = j;
+			}
 		}
-		bw_params->clk_table.entries[i].dcfclk_mhz = find_clk_for_voltage(clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[j].Voltage);
-		bw_params->clk_table.entries[i].socclk_mhz = find_clk_for_voltage(clock_table, clock_table->SocClocks, clock_table->DfPstateTable[j].Voltage);
+
+		/* First search defaults for the clocks we don't read using closest lower or equal default dcfclk */
+		for (j = bw_params->clk_table.num_entries - 1; j > 0; j--)
+			if (bw_params->clk_table.entries[j].dcfclk_mhz <= clock_table->DcfClocks[i])
+				break;
+
+		bw_params->clk_table.entries[i].phyclk_mhz = bw_params->clk_table.entries[j].phyclk_mhz;
+		bw_params->clk_table.entries[i].phyclk_d18_mhz = bw_params->clk_table.entries[j].phyclk_d18_mhz;
+		bw_params->clk_table.entries[i].dtbclk_mhz = bw_params->clk_table.entries[j].dtbclk_mhz;
+
+		/* Now update clocks we do read */
+		bw_params->clk_table.entries[i].fclk_mhz = min_fclk;
+		bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[min_pstate].MemClk;
+		bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[min_pstate].Voltage;
+		bw_params->clk_table.entries[i].dcfclk_mhz = clock_table->DcfClocks[i];
+		bw_params->clk_table.entries[i].socclk_mhz = clock_table->SocClocks[i];
 		bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk;
 		bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk;
+		bw_params->clk_table.entries[i].wck_ratio = convert_wck_ratio(
+			clock_table->DfPstateTable[min_pstate].WckRatio);
+	};
+
+	/* Make sure to include at least one entry at highest pstate */
+	if (max_pstate != min_pstate || i == 0) {
+		if (i > MAX_NUM_DPM_LVL - 1)
+			i = MAX_NUM_DPM_LVL - 1;
+
+		bw_params->clk_table.entries[i].fclk_mhz = max_fclk;
+		bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[max_pstate].MemClk;
+		bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[max_pstate].Voltage;
+		bw_params->clk_table.entries[i].dcfclk_mhz = find_max_clk_value(clock_table->DcfClocks, NUM_DCFCLK_DPM_LEVELS);
+		bw_params->clk_table.entries[i].socclk_mhz = find_max_clk_value(clock_table->SocClocks, NUM_SOCCLK_DPM_LEVELS);
+		bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk;
+		bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk;
+		bw_params->clk_table.entries[i].wck_ratio = convert_wck_ratio(
+			clock_table->DfPstateTable[max_pstate].WckRatio);
+		i++;
 	}
+	bw_params->clk_table.num_entries = i--;
+
+	/* Make sure all highest clocks are included*/
+	bw_params->clk_table.entries[i].socclk_mhz = find_max_clk_value(clock_table->SocClocks, NUM_SOCCLK_DPM_LEVELS);
+	bw_params->clk_table.entries[i].dispclk_mhz = find_max_clk_value(clock_table->DispClocks, NUM_DISPCLK_DPM_LEVELS);
+	bw_params->clk_table.entries[i].dppclk_mhz = find_max_clk_value(clock_table->DppClocks, NUM_DPPCLK_DPM_LEVELS);
+	ASSERT(clock_table->DcfClocks[i] == find_max_clk_value(clock_table->DcfClocks, NUM_DCFCLK_DPM_LEVELS));
+	bw_params->clk_table.entries[i].phyclk_mhz = def_max.phyclk_mhz;
+	bw_params->clk_table.entries[i].phyclk_d18_mhz = def_max.phyclk_d18_mhz;
+	bw_params->clk_table.entries[i].dtbclk_mhz = def_max.dtbclk_mhz;
 
+	/*
+	 * Set any 0 clocks to max default setting. Not an issue for
+	 * power since we aren't doing switching in such case anyway
+	 */
+	for (i = 0; i < bw_params->clk_table.num_entries; i++) {
+		if (!bw_params->clk_table.entries[i].fclk_mhz) {
+			bw_params->clk_table.entries[i].fclk_mhz = def_max.fclk_mhz;
+			bw_params->clk_table.entries[i].memclk_mhz = def_max.memclk_mhz;
+			bw_params->clk_table.entries[i].voltage = def_max.voltage;
+		}
+		if (!bw_params->clk_table.entries[i].dcfclk_mhz)
+			bw_params->clk_table.entries[i].dcfclk_mhz = def_max.dcfclk_mhz;
+		if (!bw_params->clk_table.entries[i].socclk_mhz)
+			bw_params->clk_table.entries[i].socclk_mhz = def_max.socclk_mhz;
+		if (!bw_params->clk_table.entries[i].dispclk_mhz)
+			bw_params->clk_table.entries[i].dispclk_mhz = def_max.dispclk_mhz;
+		if (!bw_params->clk_table.entries[i].dppclk_mhz)
+			bw_params->clk_table.entries[i].dppclk_mhz = def_max.dppclk_mhz;
+		if (!bw_params->clk_table.entries[i].phyclk_mhz)
+			bw_params->clk_table.entries[i].phyclk_mhz = def_max.phyclk_mhz;
+		if (!bw_params->clk_table.entries[i].phyclk_d18_mhz)
+			bw_params->clk_table.entries[i].phyclk_d18_mhz = def_max.phyclk_d18_mhz;
+		if (!bw_params->clk_table.entries[i].dtbclk_mhz)
+			bw_params->clk_table.entries[i].dtbclk_mhz = def_max.dtbclk_mhz;
+	}
+	ASSERT(bw_params->clk_table.entries[i-1].dcfclk_mhz);
 	bw_params->vram_type = bios_info->memory_type;
-	bw_params->num_channels = bios_info->ma_channel_number;
+
+	bw_params->dram_channel_width_bytes = bios_info->memory_type == 0x22 ? 8 : 4;
+	bw_params->num_channels = bios_info->ma_channel_number ? bios_info->ma_channel_number : 4;
 
 	for (i = 0; i < WM_SET_COUNT; i++) {
 		bw_params->wm_table.entries[i].wm_inst = i;
@@ -641,7 +700,7 @@ static struct clk_mgr_funcs dcn314_funcs = {
 	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
 	.get_dtb_ref_clk_frequency = dcn31_get_dtb_ref_freq_khz,
 	.update_clocks = dcn314_update_clocks,
-	.init_clocks = dcn314_init_clocks,
+	.init_clocks = dcn31_init_clocks,
 	.enable_pme_wa = dcn314_enable_pme_wa,
 	.are_clock_states_equal = dcn314_are_clock_states_equal,
 	.notify_wm_ranges = dcn314_notify_wm_ranges
@@ -681,10 +740,10 @@ void dcn314_clk_mgr_construct(
 	}
 	ASSERT(clk_mgr->smu_wm_set.wm_set);
 
-	smu_dpm_clks.dpm_clks = (DpmClocks_t *)dm_helpers_allocate_gpu_mem(
+	smu_dpm_clks.dpm_clks = (DpmClocks314_t *)dm_helpers_allocate_gpu_mem(
 				clk_mgr->base.base.ctx,
 				DC_MEM_ALLOC_TYPE_FRAME_BUFFER,
-				sizeof(DpmClocks_t),
+				sizeof(DpmClocks314_t),
 				&smu_dpm_clks.mc_address.quad_part);
 
 	if (smu_dpm_clks.dpm_clks == NULL) {
@@ -729,7 +788,7 @@ void dcn314_clk_mgr_construct(
 	if (clk_mgr->base.base.ctx->dc->debug.pstate_enabled) {
 		dcn314_get_dpm_table_from_smu(&clk_mgr->base, &smu_dpm_clks);
 
-		if (ctx->dc_bios && ctx->dc_bios->integrated_info) {
+		if (ctx->dc_bios && ctx->dc_bios->integrated_info && ctx->dc->config.use_default_clock_table == false) {
 			dcn314_clk_mgr_helper_populate_bw_params(
 					&clk_mgr->base,
 					ctx->dc_bios->integrated_info,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
index c695a4498c50..171f84340eb2 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
@@ -42,7 +42,7 @@ struct clk_mgr_dcn314 {
 
 bool dcn314_are_clock_states_equal(struct dc_clocks *a,
 		struct dc_clocks *b);
-void dcn314_init_clocks(struct clk_mgr *clk_mgr);
+
 void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
 			struct dc_state *context,
 			bool safe_to_lower);
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.h
index a7958dc96581..047d19ea919c 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.h
@@ -36,6 +36,37 @@ typedef enum {
 	WCK_RATIO_MAX
 } WCK_RATIO_e;
 
+typedef struct {
+  uint32_t FClk;
+  uint32_t MemClk;
+  uint32_t Voltage;
+  uint8_t  WckRatio;
+  uint8_t  Spare[3];
+} DfPstateTable314_t;
+
+//Freq in MHz
+//Voltage in milli volts with 2 fractional bits
+typedef struct {
+  uint32_t DcfClocks[NUM_DCFCLK_DPM_LEVELS];
+  uint32_t DispClocks[NUM_DISPCLK_DPM_LEVELS];
+  uint32_t DppClocks[NUM_DPPCLK_DPM_LEVELS];
+  uint32_t SocClocks[NUM_SOCCLK_DPM_LEVELS];
+  uint32_t VClocks[NUM_VCN_DPM_LEVELS];
+  uint32_t DClocks[NUM_VCN_DPM_LEVELS];
+  uint32_t SocVoltage[NUM_SOC_VOLTAGE_LEVELS];
+  DfPstateTable314_t DfPstateTable[NUM_DF_PSTATE_LEVELS];
+
+  uint8_t  NumDcfClkLevelsEnabled;
+  uint8_t  NumDispClkLevelsEnabled; //Applies to both Dispclk and Dppclk
+  uint8_t  NumSocClkLevelsEnabled;
+  uint8_t  VcnClkLevelsEnabled;     //Applies to both Vclk and Dclk
+  uint8_t  NumDfPstatesEnabled;
+  uint8_t  spare[3];
+
+  uint32_t MinGfxClk;
+  uint32_t MaxGfxClk;
+} DpmClocks314_t;
+
 struct dcn314_watermarks {
 	// Watermarks
 	WatermarkRowGeneric_t WatermarkRow[WM_COUNT][NUM_WM_RANGES];
@@ -43,7 +74,7 @@ struct dcn314_watermarks {
 };
 
 struct dcn314_smu_dpm_clks {
-	DpmClocks_t *dpm_clks;
+	DpmClocks314_t *dpm_clks;
 	union large_integer mc_address;
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
index cc076621f5e6..98ad8e0fd2d8 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
@@ -46,6 +46,9 @@
 #define TO_CLK_MGR_DCN315(clk_mgr)\
 	container_of(clk_mgr, struct clk_mgr_dcn315, base)
 
+#define UNSUPPORTED_DCFCLK 10000000
+#define MIN_DPP_DISP_CLK     100000
+
 static int dcn315_get_active_display_cnt_wa(
 		struct dc *dc,
 		struct dc_state *context)
@@ -79,7 +82,7 @@ static int dcn315_get_active_display_cnt_wa(
 	return display_count;
 }
 
-static void dcn315_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable)
+static void dcn315_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable)
 {
 	struct dc *dc = clk_mgr_base->ctx->dc;
 	int i;
@@ -91,9 +94,10 @@ static void dcn315_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable)
 			continue;
 		if (pipe->stream && (pipe->stream->dpms_off || pipe->plane_state == NULL ||
 				     dc_is_virtual_signal(pipe->stream->signal))) {
-			if (disable)
+			if (disable) {
 				pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg);
-			else
+				reset_sync_context_for_pipe(dc, context, i);
+			} else
 				pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg);
 		}
 	}
@@ -146,6 +150,9 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base,
 		}
 	}
 
+	/* Lock pstate by requesting unsupported dcfclk if change is unsupported */
+	if (!new_clocks->p_state_change_support)
+		new_clocks->dcfclk_khz = UNSUPPORTED_DCFCLK;
 	if (should_set_clock(safe_to_lower, new_clocks->dcfclk_khz, clk_mgr_base->clks.dcfclk_khz)) {
 		clk_mgr_base->clks.dcfclk_khz = new_clocks->dcfclk_khz;
 		dcn315_smu_set_hard_min_dcfclk(clk_mgr, clk_mgr_base->clks.dcfclk_khz);
@@ -159,10 +166,10 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base,
 
 	// workaround: Limit dppclk to 100Mhz to avoid lower eDP panel switch to plus 4K monitor underflow.
 	if (!IS_DIAG_DC(dc->ctx->dce_environment)) {
-		if (new_clocks->dppclk_khz < 100000)
-			new_clocks->dppclk_khz = 100000;
-		if (new_clocks->dispclk_khz < 100000)
-			new_clocks->dispclk_khz = 100000;
+		if (new_clocks->dppclk_khz < MIN_DPP_DISP_CLK)
+			new_clocks->dppclk_khz = MIN_DPP_DISP_CLK;
+		if (new_clocks->dispclk_khz < MIN_DPP_DISP_CLK)
+			new_clocks->dispclk_khz = MIN_DPP_DISP_CLK;
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) {
@@ -175,12 +182,12 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base,
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
 		/* No need to apply the w/a if we haven't taken over from bios yet */
 		if (clk_mgr_base->clks.dispclk_khz)
-			dcn315_disable_otg_wa(clk_mgr_base, true);
+			dcn315_disable_otg_wa(clk_mgr_base, context, true);
 
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
 		dcn315_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz);
 		if (clk_mgr_base->clks.dispclk_khz)
-			dcn315_disable_otg_wa(clk_mgr_base, false);
+			dcn315_disable_otg_wa(clk_mgr_base, context, false);
 
 		update_dispclk = true;
 	}
@@ -275,7 +282,7 @@ static struct wm_table ddr5_wm_table = {
 		{
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 64.0,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
@@ -283,7 +290,7 @@ static struct wm_table ddr5_wm_table = {
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 64.0,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
@@ -291,7 +298,7 @@ static struct wm_table ddr5_wm_table = {
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 64.0,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
@@ -299,7 +306,7 @@ static struct wm_table ddr5_wm_table = {
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 64.0,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
@@ -556,8 +563,7 @@ static void dcn315_clk_mgr_helper_populate_bw_params(
 	ASSERT(bw_params->clk_table.entries[i-1].dcfclk_mhz);
 	bw_params->vram_type = bios_info->memory_type;
 	bw_params->num_channels = bios_info->ma_channel_number;
-	if (!bw_params->num_channels)
-		bw_params->num_channels = 2;
+	bw_params->dram_channel_width_bytes = bios_info->memory_type == 0x22 ? 8 : 4;
 
 	for (i = 0; i < WM_SET_COUNT; i++) {
 		bw_params->wm_table.entries[i].wm_inst = i;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c
index 0cd3d2eb7ac7..187f5b27fdc8 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c
@@ -112,7 +112,7 @@ static int dcn316_get_active_display_cnt_wa(
 	return display_count;
 }
 
-static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable)
+static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable)
 {
 	struct dc *dc = clk_mgr_base->ctx->dc;
 	int i;
@@ -124,9 +124,10 @@ static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable)
 			continue;
 		if (pipe->stream && (pipe->stream->dpms_off || pipe->plane_state == NULL ||
 				     dc_is_virtual_signal(pipe->stream->signal))) {
-			if (disable)
+			if (disable) {
 				pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg);
-			else
+				reset_sync_context_for_pipe(dc, context, i);
+			} else
 				pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg);
 		}
 	}
@@ -221,11 +222,11 @@ static void dcn316_update_clocks(struct clk_mgr *clk_mgr_base,
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
-		dcn316_disable_otg_wa(clk_mgr_base, true);
+		dcn316_disable_otg_wa(clk_mgr_base, context, true);
 
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
 		dcn316_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz);
-		dcn316_disable_otg_wa(clk_mgr_base, false);
+		dcn316_disable_otg_wa(clk_mgr_base, context, false);
 
 		update_dispclk = true;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
index c6785969eb1a..f0f3f66629cc 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
@@ -156,12 +156,14 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base)
 {
 	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
 	unsigned int num_levels;
+	unsigned int num_dcfclk_levels, num_dtbclk_levels, num_dispclk_levels;
 
 	memset(&(clk_mgr_base->clks), 0, sizeof(struct dc_clocks));
 	clk_mgr_base->clks.p_state_change_support = true;
 	clk_mgr_base->clks.prev_p_state_change_support = true;
 	clk_mgr_base->clks.fclk_prev_p_state_change_support = true;
 	clk_mgr->smu_present = false;
+	clk_mgr->dpm_present = false;
 
 	if (!clk_mgr_base->bw_params)
 		return;
@@ -179,6 +181,7 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base)
 	dcn32_init_single_clock(clk_mgr, PPCLK_DCFCLK,
 			&clk_mgr_base->bw_params->clk_table.entries[0].dcfclk_mhz,
 			&num_levels);
+	num_dcfclk_levels = num_levels;
 
 	/* SOCCLK */
 	dcn32_init_single_clock(clk_mgr, PPCLK_SOCCLK,
@@ -189,11 +192,16 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base)
 		dcn32_init_single_clock(clk_mgr, PPCLK_DTBCLK,
 				&clk_mgr_base->bw_params->clk_table.entries[0].dtbclk_mhz,
 				&num_levels);
+	num_dtbclk_levels = num_levels;
 
 	/* DISPCLK */
 	dcn32_init_single_clock(clk_mgr, PPCLK_DISPCLK,
 			&clk_mgr_base->bw_params->clk_table.entries[0].dispclk_mhz,
 			&num_levels);
+	num_dispclk_levels = num_levels;
+
+	if (num_dcfclk_levels && num_dtbclk_levels && num_dispclk_levels)
+		clk_mgr->dpm_present = true;
 
 	if (clk_mgr_base->ctx->dc->debug.min_disp_clk_khz) {
 		unsigned int i;
@@ -658,6 +666,12 @@ static void dcn32_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base)
 			&num_levels);
 	clk_mgr_base->bw_params->clk_table.num_entries = num_levels ? num_levels : 1;
 
+	if (clk_mgr->dpm_present && !num_levels)
+		clk_mgr->dpm_present = false;
+
+	if (!clk_mgr->dpm_present)
+		dcn32_patch_dpm_table(clk_mgr_base->bw_params);
+
 	DC_FP_START();
 	/* Refresh bounding box */
 	clk_mgr_base->ctx->dc->res_pool->funcs->update_bw_bounding_box(
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index e42f44fc1c08..fb22c3d70528 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1074,8 +1074,15 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 		struct dc_stream_state *old_stream =
 				dc->current_state->res_ctx.pipe_ctx[i].stream;
 		bool should_disable = true;
-		bool pipe_split_change =
-			context->res_ctx.pipe_ctx[i].top_pipe != dc->current_state->res_ctx.pipe_ctx[i].top_pipe;
+		bool pipe_split_change = false;
+
+		if ((context->res_ctx.pipe_ctx[i].top_pipe) &&
+			(dc->current_state->res_ctx.pipe_ctx[i].top_pipe))
+			pipe_split_change = context->res_ctx.pipe_ctx[i].top_pipe->pipe_idx !=
+				dc->current_state->res_ctx.pipe_ctx[i].top_pipe->pipe_idx;
+		else
+			pipe_split_change = context->res_ctx.pipe_ctx[i].top_pipe !=
+				dc->current_state->res_ctx.pipe_ctx[i].top_pipe;
 
 		for (j = 0; j < context->stream_count; j++) {
 			if (old_stream == context->streams[j]) {
@@ -1087,7 +1094,8 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 				dc->current_state->stream_count != context->stream_count)
 			should_disable = true;
 
-		if (old_stream && !dc->current_state->res_ctx.pipe_ctx[i].top_pipe) {
+		if (old_stream && !dc->current_state->res_ctx.pipe_ctx[i].top_pipe &&
+				!dc->current_state->res_ctx.pipe_ctx[i].prev_odm_pipe) {
 			struct pipe_ctx *old_pipe, *new_pipe;
 
 			old_pipe = &dc->current_state->res_ctx.pipe_ctx[i];
@@ -3229,7 +3237,7 @@ static void commit_planes_for_stream(struct dc *dc,
 				odm_pipe->ttu_regs.min_ttu_vblank = MAX_TTU;
 	}
 
-	if ((update_type != UPDATE_TYPE_FAST) && stream->update_flags.bits.dsc_changed) {
+	if ((update_type != UPDATE_TYPE_FAST) && stream->update_flags.bits.dsc_changed)
 		if (top_pipe_to_program &&
 			top_pipe_to_program->stream_res.tg->funcs->lock_doublebuffer_enable) {
 			if (should_use_dmub_lock(stream->link)) {
@@ -3247,7 +3255,6 @@ static void commit_planes_for_stream(struct dc *dc,
 				top_pipe_to_program->stream_res.tg->funcs->lock_doublebuffer_enable(
 						top_pipe_to_program->stream_res.tg);
 		}
-	}
 
 	if (should_lock_all_pipes && dc->hwss.interdependent_update_lock) {
 		if (dc->hwss.subvp_pipe_control_lock)
@@ -3466,7 +3473,7 @@ static void commit_planes_for_stream(struct dc *dc,
 		dc->hwss.pipe_control_lock(dc, top_pipe_to_program, false);
 	}
 
-	if ((update_type != UPDATE_TYPE_FAST) && stream->update_flags.bits.dsc_changed) {
+	if ((update_type != UPDATE_TYPE_FAST) && stream->update_flags.bits.dsc_changed)
 		if (top_pipe_to_program->stream_res.tg->funcs->lock_doublebuffer_enable) {
 			top_pipe_to_program->stream_res.tg->funcs->wait_for_state(
 				top_pipe_to_program->stream_res.tg,
@@ -3493,21 +3500,19 @@ static void commit_planes_for_stream(struct dc *dc,
 				top_pipe_to_program->stream_res.tg->funcs->lock_doublebuffer_disable(
 					top_pipe_to_program->stream_res.tg);
 		}
-	}
 
-	if (update_type != UPDATE_TYPE_FAST) {
+	if (update_type != UPDATE_TYPE_FAST)
 		dc->hwss.post_unlock_program_front_end(dc, context);
 
-		/* Since phantom pipe programming is moved to post_unlock_program_front_end,
-		 * move the SubVP lock to after the phantom pipes have been setup
-		 */
-		if (should_lock_all_pipes && dc->hwss.interdependent_update_lock) {
-			if (dc->hwss.subvp_pipe_control_lock)
-				dc->hwss.subvp_pipe_control_lock(dc, context, false, should_lock_all_pipes, NULL, subvp_prev_use);
-		} else {
-			if (dc->hwss.subvp_pipe_control_lock)
-				dc->hwss.subvp_pipe_control_lock(dc, context, false, should_lock_all_pipes, top_pipe_to_program, subvp_prev_use);
-		}
+	/* Since phantom pipe programming is moved to post_unlock_program_front_end,
+	 * move the SubVP lock to after the phantom pipes have been setup
+	 */
+	if (should_lock_all_pipes && dc->hwss.interdependent_update_lock) {
+		if (dc->hwss.subvp_pipe_control_lock)
+			dc->hwss.subvp_pipe_control_lock(dc, context, false, should_lock_all_pipes, NULL, subvp_prev_use);
+	} else {
+		if (dc->hwss.subvp_pipe_control_lock)
+			dc->hwss.subvp_pipe_control_lock(dc, context, false, should_lock_all_pipes, top_pipe_to_program, subvp_prev_use);
 	}
 
 	// Fire manual trigger only when bottom plane is flipped
@@ -4292,7 +4297,7 @@ bool dc_is_dmub_outbox_supported(struct dc *dc)
 	    !dc->debug.dpia_debug.bits.disable_dpia)
 		return true;
 
-	if (dc->ctx->asic_id.chip_family == AMDGPU_FAMILY_GC_11_0_2 &&
+	if (dc->ctx->asic_id.chip_family == AMDGPU_FAMILY_GC_11_0_1 &&
 	    !dc->debug.dpia_debug.bits.disable_dpia)
 		return true;
 
@@ -4340,6 +4345,7 @@ void dc_enable_dmub_outbox(struct dc *dc)
 	struct dc_context *dc_ctx = dc->ctx;
 
 	dmub_enable_outbox_notification(dc_ctx->dmub_srv);
+	DC_LOG_DC("%s: dmub outbox notifications enabled\n", __func__);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 9e51338441d0..66d2ae7aacf5 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -3372,7 +3372,7 @@ bool dc_link_setup_psr(struct dc_link *link,
 		switch(link->ctx->asic_id.chip_family) {
 		case FAMILY_YELLOW_CARP:
 		case AMDGPU_FAMILY_GC_10_3_6:
-		case AMDGPU_FAMILY_GC_11_0_2:
+		case AMDGPU_FAMILY_GC_11_0_1:
 			if(!dc->debug.disable_z10)
 				psr_context->psr_level.bits.SKIP_CRTC_DISABLE = false;
 			break;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 48dad093ae8b..780f7f4c28b6 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -2758,8 +2758,14 @@ bool perform_link_training_with_retries(
 						skip_video_pattern);
 
 				/* Transmit idle pattern once training successful. */
-				if (status == LINK_TRAINING_SUCCESS && !is_link_bw_low)
+				if (status == LINK_TRAINING_SUCCESS && !is_link_bw_low) {
 					dp_set_hw_test_pattern(link, &pipe_ctx->link_res, DP_TEST_PATTERN_VIDEO_MODE, NULL, 0);
+					/* Update verified link settings to current one
+					 * Because DPIA LT might fallback to lower link setting.
+					 */
+					link->verified_link_cap.link_rate = link->cur_link_settings.link_rate;
+					link->verified_link_cap.lane_count = link->cur_link_settings.lane_count;
+				}
 			} else {
 				status = dc_link_dp_perform_link_training(link,
 						&pipe_ctx->link_res,
@@ -5121,6 +5127,14 @@ bool dp_retrieve_lttpr_cap(struct dc_link *link)
 				lttpr_dpcd_data[DP_PHY_REPEATER_128B132B_RATES -
 								DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
 
+		/* If this chip cap is set, at least one retimer must exist in the chain
+		 * Override count to 1 if we receive a known bad count (0 or an invalid value) */
+		if (link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN &&
+				(dp_convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) == 0)) {
+			ASSERT(0);
+			link->dpcd_caps.lttpr_caps.phy_repeater_cnt = 0x80;
+		}
+
 		/* Attempt to train in LTTPR transparent mode if repeater count exceeds 8. */
 		is_lttpr_present = (link->dpcd_caps.lttpr_caps.max_lane_count > 0 &&
 				link->dpcd_caps.lttpr_caps.max_lane_count <= 4 &&
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index ffc0f1c0ea93..ccf7bd3d90fe 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -169,7 +169,7 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id)
 		if (ASICREV_IS_GC_11_0_2(asic_id.hw_internal_rev))
 			dc_version = DCN_VERSION_3_21;
 		break;
-	case AMDGPU_FAMILY_GC_11_0_2:
+	case AMDGPU_FAMILY_GC_11_0_1:
 		dc_version = DCN_VERSION_3_14;
 		break;
 	default:
@@ -3584,6 +3584,23 @@ void check_syncd_pipes_for_disabled_master_pipe(struct dc *dc,
 	}
 }
 
+void reset_sync_context_for_pipe(const struct dc *dc,
+	struct dc_state *context,
+	uint8_t pipe_idx)
+{
+	int i;
+	struct pipe_ctx *pipe_ctx_reset;
+
+	/* reset the otg sync context for the pipe and its slave pipes if any */
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		pipe_ctx_reset = &context->res_ctx.pipe_ctx[i];
+
+		if (((GET_PIPE_SYNCD_FROM_PIPE(pipe_ctx_reset) == pipe_idx) &&
+			IS_PIPE_SYNCD_VALID(pipe_ctx_reset)) || (i == pipe_idx))
+			SET_PIPE_SYNCD_TO_PIPE(pipe_ctx_reset, i);
+	}
+}
+
 uint8_t resource_transmitter_to_phy_idx(const struct dc *dc, enum transmitter transmitter)
 {
 	/* TODO - get transmitter to phy idx mapping from DMUB */
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index f62d50901d92..0c85ab5933b4 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -329,7 +329,7 @@ bool dc_stream_set_cursor_attributes(
 
 	dc = stream->ctx->dc;
 
-	if (attributes->height * attributes->width * 4 > 16384)
+	if (dc->debug.allow_sw_cursor_fallback && attributes->height * attributes->width * 4 > 16384)
 		if (stream->mall_stream_config.type == SUBVP_MAIN)
 			return false;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 8e1e40083ec8..dbf8158b832e 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -47,7 +47,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.196"
+#define DC_VER "3.2.198"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
@@ -213,6 +213,7 @@ struct dc_caps {
 	uint32_t cache_num_ways;
 	uint16_t subvp_fw_processing_delay_us;
 	uint16_t subvp_prefetch_end_to_mall_start_us;
+	uint8_t subvp_swath_height_margin_lines; // subvp start line must be aligned to 2 x swath height
 	uint16_t subvp_pstate_allow_width_us;
 	uint16_t subvp_vertical_int_margin_us;
 	bool seamless_odm;
@@ -352,6 +353,7 @@ struct dc_config {
 	bool use_pipe_ctx_sync_logic;
 	bool ignore_dpref_ss;
 	bool enable_mipi_converter_optimization;
+	bool use_default_clock_table;
 };
 
 enum visual_confirm {
@@ -609,6 +611,7 @@ struct dc_bounding_box_overrides {
 	int percent_of_ideal_drambw;
 	int dram_clock_change_latency_ns;
 	int dummy_clock_change_latency_ns;
+	int fclk_clock_change_latency_ns;
 	/* This forces a hard min on the DCFCLK we use
 	 * for DML.  Unlike the debug option for forcing
 	 * DCFCLK, this override affects watermark calculations
@@ -742,6 +745,7 @@ struct dc_debug_options {
 	bool disable_fixed_vs_aux_timeout_wa;
 	bool force_disable_subvp;
 	bool force_subvp_mclk_switch;
+	bool allow_sw_cursor_fallback;
 	bool force_usr_allow;
 	/* uses value at boot and disables switch */
 	bool disable_dtb_ref_clk_switch;
@@ -751,6 +755,7 @@ struct dc_debug_options {
 	uint32_t mst_start_top_delay;
 	uint8_t psr_power_use_phy_fsm;
 	enum dml_hostvm_override_opts dml_hostvm_override;
+	bool dml_disallow_alternate_prefetch_modes;
 	bool use_legacy_soc_bb_mechanism;
 	bool exit_idle_opt_for_cursor_updates;
 	bool enable_single_display_2to1_odm_policy;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
index 2d61c2a91cee..52a61b3e5a8b 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -29,6 +29,7 @@
 #include "dm_helpers.h"
 #include "dc_hw_types.h"
 #include "core_types.h"
+#include "../basics/conversion.h"
 
 #define CTX dc_dmub_srv->ctx
 #define DC_LOGGER CTX->logger
@@ -275,8 +276,7 @@ void dc_dmub_srv_set_drr_manual_trigger_cmd(struct dc *dc, uint32_t tg_inst)
 	union dmub_rb_cmd cmd = { 0 };
 
 	cmd.drr_update.header.type = DMUB_CMD__FW_ASSISTED_MCLK_SWITCH;
-	// TODO: Uncomment once FW headers are promoted
-	//cmd.drr_update.header.sub_type = DMUB_CMD__FAMS_SET_MANUAL_TRIGGER;
+	cmd.drr_update.header.sub_type = DMUB_CMD__FAMS_SET_MANUAL_TRIGGER;
 	cmd.drr_update.dmub_optc_state_req.tg_inst = tg_inst;
 
 	cmd.drr_update.header.payload_bytes = sizeof(cmd.drr_update) - sizeof(cmd.drr_update.header);
@@ -417,44 +417,42 @@ static void populate_subvp_cmd_drr_info(struct dc *dc,
 	struct dc_crtc_timing *main_timing = &subvp_pipe->stream->timing;
 	struct dc_crtc_timing *phantom_timing = &subvp_pipe->stream->mall_stream_config.paired_stream->timing;
 	struct dc_crtc_timing *drr_timing = &vblank_pipe->stream->timing;
-	int16_t drr_frame_us = 0;
-	int16_t min_drr_supported_us = 0;
-	int16_t max_drr_supported_us = 0;
-	int16_t max_drr_vblank_us = 0;
-	int16_t max_drr_mallregion_us = 0;
-	int16_t mall_region_us = 0;
-	int16_t prefetch_us = 0;
-	int16_t subvp_active_us = 0;
-	int16_t drr_active_us = 0;
-	int16_t min_vtotal_supported = 0;
-	int16_t max_vtotal_supported = 0;
+	uint16_t drr_frame_us = 0;
+	uint16_t min_drr_supported_us = 0;
+	uint16_t max_drr_supported_us = 0;
+	uint16_t max_drr_vblank_us = 0;
+	uint16_t max_drr_mallregion_us = 0;
+	uint16_t mall_region_us = 0;
+	uint16_t prefetch_us = 0;
+	uint16_t subvp_active_us = 0;
+	uint16_t drr_active_us = 0;
+	uint16_t min_vtotal_supported = 0;
+	uint16_t max_vtotal_supported = 0;
 
 	pipe_data->pipe_config.vblank_data.drr_info.drr_in_use = true;
 	pipe_data->pipe_config.vblank_data.drr_info.use_ramping = false; // for now don't use ramping
 	pipe_data->pipe_config.vblank_data.drr_info.drr_window_size_ms = 4; // hardcode 4ms DRR window for now
 
-	drr_frame_us = div64_s64(drr_timing->v_total * drr_timing->h_total,
-				 (int64_t)(drr_timing->pix_clk_100hz * 100) * 1000000);
+	drr_frame_us = div64_u64(((uint64_t)drr_timing->v_total * drr_timing->h_total * 1000000),
+			(((uint64_t)drr_timing->pix_clk_100hz * 100)));
 	// P-State allow width and FW delays already included phantom_timing->v_addressable
-	mall_region_us = div64_s64(phantom_timing->v_addressable * phantom_timing->h_total,
-				   (int64_t)(phantom_timing->pix_clk_100hz * 100) * 1000000);
+	mall_region_us = div64_u64(((uint64_t)phantom_timing->v_addressable * phantom_timing->h_total * 1000000),
+			(((uint64_t)phantom_timing->pix_clk_100hz * 100)));
 	min_drr_supported_us = drr_frame_us + mall_region_us + SUBVP_DRR_MARGIN_US;
-	min_vtotal_supported = div64_s64(drr_timing->pix_clk_100hz * 100 *
-					 (div64_s64((int64_t)min_drr_supported_us, 1000000)),
-					 (int64_t)drr_timing->h_total);
-
-	prefetch_us = div64_s64((phantom_timing->v_total - phantom_timing->v_front_porch) * phantom_timing->h_total,
-				(int64_t)(phantom_timing->pix_clk_100hz * 100) * 1000000 +
-				dc->caps.subvp_prefetch_end_to_mall_start_us);
-	subvp_active_us = div64_s64(main_timing->v_addressable * main_timing->h_total,
-				    (int64_t)(main_timing->pix_clk_100hz * 100) * 1000000);
-	drr_active_us = div64_s64(drr_timing->v_addressable * drr_timing->h_total,
-				  (int64_t)(drr_timing->pix_clk_100hz * 100) * 1000000);
-	max_drr_vblank_us = div64_s64((int64_t)(subvp_active_us - prefetch_us - drr_active_us), 2) + drr_active_us;
+	min_vtotal_supported = div64_u64(((uint64_t)drr_timing->pix_clk_100hz * 100 * min_drr_supported_us),
+			(((uint64_t)drr_timing->h_total * 1000000)));
+
+	prefetch_us = div64_u64(((uint64_t)(phantom_timing->v_total - phantom_timing->v_front_porch) * phantom_timing->h_total * 1000000),
+			(((uint64_t)phantom_timing->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us));
+	subvp_active_us = div64_u64(((uint64_t)main_timing->v_addressable * main_timing->h_total * 1000000),
+			(((uint64_t)main_timing->pix_clk_100hz * 100)));
+	drr_active_us = div64_u64(((uint64_t)drr_timing->v_addressable * drr_timing->h_total * 1000000),
+			(((uint64_t)drr_timing->pix_clk_100hz * 100)));
+	max_drr_vblank_us = div64_u64((subvp_active_us - prefetch_us - drr_active_us), 2) + drr_active_us;
 	max_drr_mallregion_us = subvp_active_us - prefetch_us - mall_region_us;
 	max_drr_supported_us = max_drr_vblank_us > max_drr_mallregion_us ? max_drr_vblank_us : max_drr_mallregion_us;
-	max_vtotal_supported = div64_s64(drr_timing->pix_clk_100hz * 100 * (div64_s64((int64_t)max_drr_supported_us, 1000000)),
-					 (int64_t)drr_timing->h_total);
+	max_vtotal_supported = div64_u64(((uint64_t)drr_timing->pix_clk_100hz * 100 * max_drr_supported_us),
+			(((uint64_t)drr_timing->h_total * 1000000)));
 
 	pipe_data->pipe_config.vblank_data.drr_info.min_vtotal_supported = min_vtotal_supported;
 	pipe_data->pipe_config.vblank_data.drr_info.max_vtotal_supported = max_vtotal_supported;
@@ -548,10 +546,12 @@ static void update_subvp_prefetch_end_to_mall_start(struct dc *dc,
 	struct dc_crtc_timing *phantom_timing1 = &subvp_pipes[1]->stream->mall_stream_config.paired_stream->timing;
 	struct dmub_cmd_fw_assisted_mclk_switch_pipe_data_v2 *pipe_data = NULL;
 
-	subvp0_prefetch_us = div64_s64((phantom_timing0->v_total - phantom_timing0->v_front_porch) * phantom_timing0->h_total,
-				       (int64_t)(phantom_timing0->pix_clk_100hz * 100) * 1000000 + dc->caps.subvp_prefetch_end_to_mall_start_us);
-	subvp1_prefetch_us = div64_s64((phantom_timing1->v_total - phantom_timing1->v_front_porch) * phantom_timing1->h_total,
-				       (int64_t)(phantom_timing1->pix_clk_100hz * 100) * 1000000 + dc->caps.subvp_prefetch_end_to_mall_start_us);
+	subvp0_prefetch_us = div64_u64(((uint64_t)(phantom_timing0->v_total - phantom_timing0->v_front_porch) *
+			(uint64_t)phantom_timing0->h_total * 1000000),
+			(((uint64_t)phantom_timing0->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us));
+	subvp1_prefetch_us = div64_u64(((uint64_t)(phantom_timing1->v_total - phantom_timing1->v_front_porch) *
+			(uint64_t)phantom_timing1->h_total * 1000000),
+			(((uint64_t)phantom_timing1->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us));
 
 	// Whichever SubVP PIPE has the smaller prefetch (including the prefetch end to mall start time)
 	// should increase it's prefetch time to match the other
@@ -559,16 +559,17 @@ static void update_subvp_prefetch_end_to_mall_start(struct dc *dc,
 		pipe_data = &cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[1];
 		prefetch_delta_us = subvp0_prefetch_us - subvp1_prefetch_us;
 		pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines =
-			div64_s64(((div64_s64((int64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us), 1000000)) *
-				   (phantom_timing1->pix_clk_100hz * 100) + phantom_timing1->h_total - 1),
-				  (int64_t)phantom_timing1->h_total);
+				div64_u64(((uint64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us) *
+					((uint64_t)phantom_timing1->pix_clk_100hz * 100) + ((uint64_t)phantom_timing1->h_total * 1000000 - 1)),
+					((uint64_t)phantom_timing1->h_total * 1000000));
+
 	} else if (subvp1_prefetch_us >  subvp0_prefetch_us) {
 		pipe_data = &cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[0];
 		prefetch_delta_us = subvp1_prefetch_us - subvp0_prefetch_us;
 		pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines =
-			div64_s64(((div64_s64((int64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us), 1000000)) *
-				   (phantom_timing0->pix_clk_100hz * 100) + phantom_timing0->h_total - 1),
-				  (int64_t)phantom_timing0->h_total);
+				div64_u64(((uint64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us) *
+					((uint64_t)phantom_timing0->pix_clk_100hz * 100) + ((uint64_t)phantom_timing0->h_total * 1000000 - 1)),
+					((uint64_t)phantom_timing0->h_total * 1000000));
 	}
 }
 
@@ -601,6 +602,7 @@ static void populate_subvp_cmd_pipe_info(struct dc *dc,
 			&cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[cmd_pipe_index];
 	struct dc_crtc_timing *main_timing = &subvp_pipe->stream->timing;
 	struct dc_crtc_timing *phantom_timing = &subvp_pipe->stream->mall_stream_config.paired_stream->timing;
+	uint32_t out_num, out_den;
 
 	pipe_data->mode = SUBVP;
 	pipe_data->pipe_config.subvp_data.pix_clk_100hz = subvp_pipe->stream->timing.pix_clk_100hz;
@@ -612,6 +614,16 @@ static void populate_subvp_cmd_pipe_info(struct dc *dc,
 			main_timing->v_total - main_timing->v_front_porch - main_timing->v_addressable;
 	pipe_data->pipe_config.subvp_data.mall_region_lines = phantom_timing->v_addressable;
 	pipe_data->pipe_config.subvp_data.main_pipe_index = subvp_pipe->pipe_idx;
+	pipe_data->pipe_config.subvp_data.is_drr = subvp_pipe->stream->ignore_msa_timing_param;
+
+	/* Calculate the scaling factor from the src and dst height.
+	 * e.g. If 3840x2160 being downscaled to 1920x1080, the scaling factor is 1/2.
+	 * Reduce the fraction 1080/2160 = 1/2 for the "scaling factor"
+	 */
+	reduce_fraction(subvp_pipe->stream->src.height, subvp_pipe->stream->dst.height, &out_num, &out_den);
+	// TODO: Uncomment below lines once DMCUB include headers are promoted
+	//pipe_data->pipe_config.subvp_data.scale_factor_numerator = out_num;
+	//pipe_data->pipe_config.subvp_data.scale_factor_denominator = out_den;
 
 	// Prefetch lines is equal to VACTIVE + BP + VSYNC
 	pipe_data->pipe_config.subvp_data.prefetch_lines =
@@ -619,13 +631,11 @@ static void populate_subvp_cmd_pipe_info(struct dc *dc,
 
 	// Round up
 	pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines =
-		div64_s64(((div64_s64((int64_t)dc->caps.subvp_prefetch_end_to_mall_start_us, 1000000)) *
-			   (phantom_timing->pix_clk_100hz * 100) + phantom_timing->h_total - 1),
-			  (int64_t)phantom_timing->h_total);
+			div64_u64(((uint64_t)dc->caps.subvp_prefetch_end_to_mall_start_us * ((uint64_t)phantom_timing->pix_clk_100hz * 100) +
+					((uint64_t)phantom_timing->h_total * 1000000 - 1)), ((uint64_t)phantom_timing->h_total * 1000000));
 	pipe_data->pipe_config.subvp_data.processing_delay_lines =
-		div64_s64(((div64_s64((int64_t)dc->caps.subvp_fw_processing_delay_us, 1000000)) *
-			   (phantom_timing->pix_clk_100hz * 100) + phantom_timing->h_total - 1),
-			  (int64_t)phantom_timing->h_total);
+			div64_u64(((uint64_t)(dc->caps.subvp_fw_processing_delay_us) * ((uint64_t)phantom_timing->pix_clk_100hz * 100) +
+					((uint64_t)phantom_timing->h_total * 1000000 - 1)), ((uint64_t)phantom_timing->h_total * 1000000));
 	// Find phantom pipe index based on phantom stream
 	for (j = 0; j < dc->res_pool->pipe_count; j++) {
 		struct pipe_ctx *phantom_pipe = &context->res_ctx.pipe_ctx[j];
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index a0af0f6afeef..9544abf75e84 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -344,6 +344,7 @@ enum dc_detect_reason {
 	DETECT_REASON_HPDRX,
 	DETECT_REASON_FALLBACK,
 	DETECT_REASON_RETRAIN,
+	DETECT_REASON_TDR,
 };
 
 bool dc_link_detect(struct dc_link *dc_link, enum dc_detect_reason reason);
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index 213de8cabfad..165392380842 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -543,9 +543,11 @@ static void dce112_get_pix_clk_dividers_helper (
 		switch (pix_clk_params->color_depth) {
 		case COLOR_DEPTH_101010:
 			actual_pixel_clock_100hz = (actual_pixel_clock_100hz * 5) >> 2;
+			actual_pixel_clock_100hz -= actual_pixel_clock_100hz % 10;
 			break;
 		case COLOR_DEPTH_121212:
 			actual_pixel_clock_100hz = (actual_pixel_clock_100hz * 6) >> 2;
+			actual_pixel_clock_100hz -= actual_pixel_clock_100hz % 10;
 			break;
 		case COLOR_DEPTH_161616:
 			actual_pixel_clock_100hz = actual_pixel_clock_100hz * 2;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
index d4a6504dfe00..db7ca4b0cdb9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
@@ -361,8 +361,6 @@ void dpp1_cnv_setup (
 		select = INPUT_CSC_SELECT_ICSC;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
-		pixel_format = 22;
-		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616:
 		pixel_format = 26; /* ARGB16161616_UNORM */
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index b54c12400323..564e061ccb58 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -278,9 +278,6 @@ void hubp1_program_pixel_format(
 				SURFACE_PIXEL_FORMAT, 10);
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
-		REG_UPDATE(DCSURF_SURFACE_CONFIG,
-				SURFACE_PIXEL_FORMAT, 22);
-		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616: /*we use crossbar already*/
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 26); /* ARGB16161616_UNORM */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index bed783747f16..5b5d952b2b8c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -110,6 +110,7 @@ void dcn10_lock_all_pipes(struct dc *dc,
 		 */
 		if (pipe_ctx->top_pipe ||
 		    !pipe_ctx->stream ||
+		    !pipe_ctx->plane_state ||
 		    !tg->funcs->is_tg_enabled(tg))
 			continue;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
index 769974375b4b..8e9384094f6d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -131,6 +131,12 @@ struct mpcc *mpc1_get_mpcc_for_dpp(struct mpc_tree *tree, int dpp_id)
 	while (tmp_mpcc != NULL) {
 		if (tmp_mpcc->dpp_id == dpp_id)
 			return tmp_mpcc;
+
+		/* avoid circular linked list */
+		ASSERT(tmp_mpcc != tmp_mpcc->mpcc_bot);
+		if (tmp_mpcc == tmp_mpcc->mpcc_bot)
+			break;
+
 		tmp_mpcc = tmp_mpcc->mpcc_bot;
 	}
 	return NULL;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
index e1a9a45b03b6..3fc300cd1ce9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
@@ -465,6 +465,11 @@ void optc1_enable_optc_clock(struct timing_generator *optc, bool enable)
 				OTG_CLOCK_ON, 1,
 				1, 1000);
 	} else  {
+
+		//last chance to clear underflow, otherwise, it will always there due to clock is off.
+		if (optc->funcs->is_optc_underflow_occurred(optc) == true)
+			optc->funcs->clear_optc_underflow(optc);
+
 		REG_UPDATE_2(OTG_CLOCK_CONTROL,
 				OTG_CLOCK_GATE_DIS, 0,
 				OTG_CLOCK_EN, 0);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
index ea1f14af0db7..eaa7032f0f1a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
@@ -166,8 +166,6 @@ static void dpp2_cnv_setup (
 		select = DCN2_ICSC_SELECT_ICSC_A;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
-		pixel_format = 22;
-		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616:
 		pixel_format = 26; /* ARGB16161616_UNORM */
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h
index cd2671161ef1..7ce64a3c1b02 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h
@@ -445,226 +445,6 @@
 	type DSCRM_DSC_FORWARD_EN; \
 	type DSCRM_DSC_OPP_PIPE_SOURCE
 
-#define DSC_REG_LIST_DCN314(id) \
-	SRI(DSC_TOP_CONTROL, DSC_TOP, id),\
-	SRI(DSC_DEBUG_CONTROL, DSC_TOP, id),\
-	SRI(DSCC_CONFIG0, DSCC, id),\
-	SRI(DSCC_CONFIG1, DSCC, id),\
-	SRI(DSCC_STATUS, DSCC, id),\
-	SRI(DSCC_INTERRUPT_CONTROL_STATUS, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG0, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG1, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG2, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG3, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG4, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG5, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG6, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG7, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG8, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG9, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG10, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG11, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG12, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG13, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG14, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG15, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG16, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG17, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG18, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG19, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG20, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG21, DSCC, id),\
-	SRI(DSCC_PPS_CONFIG22, DSCC, id),\
-	SRI(DSCC_MEM_POWER_CONTROL, DSCC, id),\
-	SRI(DSCC_R_Y_SQUARED_ERROR_LOWER, DSCC, id),\
-	SRI(DSCC_R_Y_SQUARED_ERROR_UPPER, DSCC, id),\
-	SRI(DSCC_G_CB_SQUARED_ERROR_LOWER, DSCC, id),\
-	SRI(DSCC_G_CB_SQUARED_ERROR_UPPER, DSCC, id),\
-	SRI(DSCC_B_CR_SQUARED_ERROR_LOWER, DSCC, id),\
-	SRI(DSCC_B_CR_SQUARED_ERROR_UPPER, DSCC, id),\
-	SRI(DSCC_MAX_ABS_ERROR0, DSCC, id),\
-	SRI(DSCC_MAX_ABS_ERROR1, DSCC, id),\
-	SRI(DSCC_RATE_BUFFER0_MAX_FULLNESS_LEVEL, DSCC, id),\
-	SRI(DSCC_RATE_BUFFER1_MAX_FULLNESS_LEVEL, DSCC, id),\
-	SRI(DSCC_RATE_BUFFER2_MAX_FULLNESS_LEVEL, DSCC, id),\
-	SRI(DSCC_RATE_BUFFER3_MAX_FULLNESS_LEVEL, DSCC, id),\
-	SRI(DSCC_RATE_CONTROL_BUFFER0_MAX_FULLNESS_LEVEL, DSCC, id),\
-	SRI(DSCC_RATE_CONTROL_BUFFER1_MAX_FULLNESS_LEVEL, DSCC, id),\
-	SRI(DSCC_RATE_CONTROL_BUFFER2_MAX_FULLNESS_LEVEL, DSCC, id),\
-	SRI(DSCC_RATE_CONTROL_BUFFER3_MAX_FULLNESS_LEVEL, DSCC, id),\
-	SRI(DSCCIF_CONFIG0, DSCCIF, id),\
-	SRI(DSCCIF_CONFIG1, DSCCIF, id),\
-	SRI(DSCRM_DSC_FORWARD_CONFIG, DSCRM, id)
-
-#define DSC_REG_LIST_SH_MASK_DCN314(mask_sh)\
-	DSC_SF(DSC_TOP0_DSC_TOP_CONTROL, DSC_CLOCK_EN, mask_sh), \
-	DSC_SF(DSC_TOP0_DSC_TOP_CONTROL, DSC_DISPCLK_R_GATE_DIS, mask_sh), \
-	DSC_SF(DSC_TOP0_DSC_TOP_CONTROL, DSC_DSCCLK_R_GATE_DIS, mask_sh), \
-	DSC_SF(DSC_TOP0_DSC_DEBUG_CONTROL, DSC_DBG_EN, mask_sh), \
-	DSC_SF(DSC_TOP0_DSC_DEBUG_CONTROL, DSC_TEST_CLOCK_MUX_SEL, mask_sh), \
-	DSC_SF(DSCC0_DSCC_CONFIG0, NUMBER_OF_SLICES_PER_LINE, mask_sh), \
-	DSC_SF(DSCC0_DSCC_CONFIG0, ALTERNATE_ICH_ENCODING_EN, mask_sh), \
-	DSC_SF(DSCC0_DSCC_CONFIG0, NUMBER_OF_SLICES_IN_VERTICAL_DIRECTION, mask_sh), \
-	DSC_SF(DSCC0_DSCC_CONFIG1, DSCC_RATE_CONTROL_BUFFER_MODEL_SIZE, mask_sh), \
-	/*DSC_SF(DSCC0_DSCC_CONFIG1, DSCC_DISABLE_ICH, mask_sh),*/ \
-	DSC_SF(DSCC0_DSCC_STATUS, DSCC_DOUBLE_BUFFER_REG_UPDATE_PENDING, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER0_OVERFLOW_OCCURRED, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER1_OVERFLOW_OCCURRED, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER2_OVERFLOW_OCCURRED, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER3_OVERFLOW_OCCURRED, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER0_UNDERFLOW_OCCURRED, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER1_UNDERFLOW_OCCURRED, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER2_UNDERFLOW_OCCURRED, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER3_UNDERFLOW_OCCURRED, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL0_OVERFLOW_OCCURRED, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL1_OVERFLOW_OCCURRED, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL2_OVERFLOW_OCCURRED, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL3_OVERFLOW_OCCURRED, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER0_OVERFLOW_OCCURRED_INT_EN, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER1_OVERFLOW_OCCURRED_INT_EN, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER2_OVERFLOW_OCCURRED_INT_EN, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER3_OVERFLOW_OCCURRED_INT_EN, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER0_UNDERFLOW_OCCURRED_INT_EN, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER1_UNDERFLOW_OCCURRED_INT_EN, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER2_UNDERFLOW_OCCURRED_INT_EN, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER3_UNDERFLOW_OCCURRED_INT_EN, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL0_OVERFLOW_OCCURRED_INT_EN, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL1_OVERFLOW_OCCURRED_INT_EN, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL2_OVERFLOW_OCCURRED_INT_EN, mask_sh), \
-	DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL3_OVERFLOW_OCCURRED_INT_EN, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG0, DSC_VERSION_MINOR, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG0, DSC_VERSION_MAJOR, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG0, PPS_IDENTIFIER, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG0, LINEBUF_DEPTH, mask_sh), \
-	DSC2_SF(DSCC0, DSCC_PPS_CONFIG0__BITS_PER_COMPONENT, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG1, BITS_PER_PIXEL, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG1, VBR_ENABLE, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG1, SIMPLE_422, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG1, CONVERT_RGB, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG1, BLOCK_PRED_ENABLE, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG1, NATIVE_422, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG1, NATIVE_420, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG1, CHUNK_SIZE, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG2, PIC_WIDTH, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG2, PIC_HEIGHT, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG3, SLICE_WIDTH, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG3, SLICE_HEIGHT, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG4, INITIAL_XMIT_DELAY, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG4, INITIAL_DEC_DELAY, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG5, INITIAL_SCALE_VALUE, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG5, SCALE_INCREMENT_INTERVAL, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG6, SCALE_DECREMENT_INTERVAL, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG6, FIRST_LINE_BPG_OFFSET, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG6, SECOND_LINE_BPG_OFFSET, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG7, NFL_BPG_OFFSET, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG7, SLICE_BPG_OFFSET, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG8, NSL_BPG_OFFSET, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG8, SECOND_LINE_OFFSET_ADJ, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG9, INITIAL_OFFSET, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG9, FINAL_OFFSET, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG10, FLATNESS_MIN_QP, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG10, FLATNESS_MAX_QP, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG10, RC_MODEL_SIZE, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG11, RC_EDGE_FACTOR, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG11, RC_QUANT_INCR_LIMIT0, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG11, RC_QUANT_INCR_LIMIT1, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG11, RC_TGT_OFFSET_LO, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG11, RC_TGT_OFFSET_HI, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG12, RC_BUF_THRESH0, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG12, RC_BUF_THRESH1, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG12, RC_BUF_THRESH2, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG12, RC_BUF_THRESH3, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG13, RC_BUF_THRESH4, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG13, RC_BUF_THRESH5, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG13, RC_BUF_THRESH6, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG13, RC_BUF_THRESH7, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG14, RC_BUF_THRESH8, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG14, RC_BUF_THRESH9, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG14, RC_BUF_THRESH10, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG14, RC_BUF_THRESH11, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG15, RC_BUF_THRESH12, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG15, RC_BUF_THRESH13, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG15, RANGE_MIN_QP0, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG15, RANGE_MAX_QP0, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG15, RANGE_BPG_OFFSET0, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_MIN_QP1, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_MAX_QP1, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_BPG_OFFSET1, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_MIN_QP2, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_MAX_QP2, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_BPG_OFFSET2, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_MIN_QP3, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_MAX_QP3, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_BPG_OFFSET3, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_MIN_QP4, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_MAX_QP4, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_BPG_OFFSET4, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_MIN_QP5, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_MAX_QP5, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_BPG_OFFSET5, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_MIN_QP6, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_MAX_QP6, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_BPG_OFFSET6, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_MIN_QP7, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_MAX_QP7, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_BPG_OFFSET7, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_MIN_QP8, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_MAX_QP8, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_BPG_OFFSET8, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_MIN_QP9, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_MAX_QP9, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_BPG_OFFSET9, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_MIN_QP10, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_MAX_QP10, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_BPG_OFFSET10, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_MIN_QP11, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_MAX_QP11, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_BPG_OFFSET11, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_MIN_QP12, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_MAX_QP12, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_BPG_OFFSET12, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_MIN_QP13, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_MAX_QP13, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_BPG_OFFSET13, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_MIN_QP14, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_MAX_QP14, mask_sh), \
-	DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_BPG_OFFSET14, mask_sh), \
-	DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_DEFAULT_MEM_LOW_POWER_STATE, mask_sh), \
-	DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_MEM_PWR_FORCE, mask_sh), \
-	DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_MEM_PWR_DIS, mask_sh), \
-	DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_MEM_PWR_STATE, mask_sh), \
-	DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_NATIVE_422_MEM_PWR_FORCE, mask_sh), \
-	DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_NATIVE_422_MEM_PWR_DIS, mask_sh), \
-	DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_NATIVE_422_MEM_PWR_STATE, mask_sh), \
-	DSC_SF(DSCC0_DSCC_R_Y_SQUARED_ERROR_LOWER, DSCC_R_Y_SQUARED_ERROR_LOWER, mask_sh), \
-	DSC_SF(DSCC0_DSCC_R_Y_SQUARED_ERROR_UPPER, DSCC_R_Y_SQUARED_ERROR_UPPER, mask_sh), \
-	DSC_SF(DSCC0_DSCC_G_CB_SQUARED_ERROR_LOWER, DSCC_G_CB_SQUARED_ERROR_LOWER, mask_sh), \
-	DSC_SF(DSCC0_DSCC_G_CB_SQUARED_ERROR_UPPER, DSCC_G_CB_SQUARED_ERROR_UPPER, mask_sh), \
-	DSC_SF(DSCC0_DSCC_B_CR_SQUARED_ERROR_LOWER, DSCC_B_CR_SQUARED_ERROR_LOWER, mask_sh), \
-	DSC_SF(DSCC0_DSCC_B_CR_SQUARED_ERROR_UPPER, DSCC_B_CR_SQUARED_ERROR_UPPER, mask_sh), \
-	DSC_SF(DSCC0_DSCC_MAX_ABS_ERROR0, DSCC_R_Y_MAX_ABS_ERROR, mask_sh), \
-	DSC_SF(DSCC0_DSCC_MAX_ABS_ERROR0, DSCC_G_CB_MAX_ABS_ERROR, mask_sh), \
-	DSC_SF(DSCC0_DSCC_MAX_ABS_ERROR1, DSCC_B_CR_MAX_ABS_ERROR, mask_sh), \
-	DSC_SF(DSCC0_DSCC_RATE_BUFFER0_MAX_FULLNESS_LEVEL, DSCC_RATE_BUFFER0_MAX_FULLNESS_LEVEL, mask_sh), \
-	DSC_SF(DSCC0_DSCC_RATE_BUFFER1_MAX_FULLNESS_LEVEL, DSCC_RATE_BUFFER1_MAX_FULLNESS_LEVEL, mask_sh), \
-	DSC_SF(DSCC0_DSCC_RATE_BUFFER2_MAX_FULLNESS_LEVEL, DSCC_RATE_BUFFER2_MAX_FULLNESS_LEVEL, mask_sh), \
-	DSC_SF(DSCC0_DSCC_RATE_BUFFER3_MAX_FULLNESS_LEVEL, DSCC_RATE_BUFFER3_MAX_FULLNESS_LEVEL, mask_sh), \
-	DSC_SF(DSCC0_DSCC_RATE_CONTROL_BUFFER0_MAX_FULLNESS_LEVEL, DSCC_RATE_CONTROL_BUFFER0_MAX_FULLNESS_LEVEL, mask_sh), \
-	DSC_SF(DSCC0_DSCC_RATE_CONTROL_BUFFER1_MAX_FULLNESS_LEVEL, DSCC_RATE_CONTROL_BUFFER1_MAX_FULLNESS_LEVEL, mask_sh), \
-	DSC_SF(DSCC0_DSCC_RATE_CONTROL_BUFFER2_MAX_FULLNESS_LEVEL, DSCC_RATE_CONTROL_BUFFER2_MAX_FULLNESS_LEVEL, mask_sh), \
-	DSC_SF(DSCC0_DSCC_RATE_CONTROL_BUFFER3_MAX_FULLNESS_LEVEL, DSCC_RATE_CONTROL_BUFFER3_MAX_FULLNESS_LEVEL, mask_sh), \
-	DSC_SF(DSCCIF0_DSCCIF_CONFIG0, INPUT_INTERFACE_UNDERFLOW_RECOVERY_EN, mask_sh), \
-	DSC_SF(DSCCIF0_DSCCIF_CONFIG0, INPUT_INTERFACE_UNDERFLOW_OCCURRED_INT_EN, mask_sh), \
-	DSC_SF(DSCCIF0_DSCCIF_CONFIG0, INPUT_INTERFACE_UNDERFLOW_OCCURRED_STATUS, mask_sh), \
-	DSC_SF(DSCCIF0_DSCCIF_CONFIG0, INPUT_PIXEL_FORMAT, mask_sh), \
-	DSC2_SF(DSCCIF0, DSCCIF_CONFIG0__BITS_PER_COMPONENT, mask_sh), \
-	DSC_SF(DSCCIF0_DSCCIF_CONFIG0, DOUBLE_BUFFER_REG_UPDATE_PENDING, mask_sh), \
-	DSC_SF(DSCCIF0_DSCCIF_CONFIG1, PIC_WIDTH, mask_sh), \
-	DSC_SF(DSCCIF0_DSCCIF_CONFIG1, PIC_HEIGHT, mask_sh), \
-	DSC_SF(DSCRM0_DSCRM_DSC_FORWARD_CONFIG, DSCRM_DSC_FORWARD_EN, mask_sh), \
-	DSC_SF(DSCRM0_DSCRM_DSC_FORWARD_CONFIG, DSCRM_DSC_OPP_PIPE_SOURCE, mask_sh)
-
-
 struct dcn20_dsc_registers {
 	uint32_t DSC_TOP_CONTROL;
 	uint32_t DSC_DEBUG_CONTROL;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
index 936af65381ef..9570c2118ccc 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
@@ -463,9 +463,6 @@ void hubp2_program_pixel_format(
 				SURFACE_PIXEL_FORMAT, 10);
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
-		REG_UPDATE(DCSURF_SURFACE_CONFIG,
-				SURFACE_PIXEL_FORMAT, 22);
-		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616: /*we use crossbar already*/
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 26); /* ARGB16161616_UNORM */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 884fa060f375..598ce872a8d7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1565,6 +1565,7 @@ static void dcn20_update_dchubp_dpp(
 	/* Any updates are handled in dc interface, just need
 	 * to apply existing for plane enable / opp change */
 	if (pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed
+			|| pipe_ctx->update_flags.bits.plane_changed
 			|| pipe_ctx->stream->update_flags.bits.gamut_remap
 			|| pipe_ctx->stream->update_flags.bits.out_csc) {
 		/* dpp/cm gamut remap*/
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
index 3d307dd58e9a..116f67a0b989 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
@@ -531,6 +531,12 @@ static struct mpcc *mpc2_get_mpcc_for_dpp(struct mpc_tree *tree, int dpp_id)
 	while (tmp_mpcc != NULL) {
 		if (tmp_mpcc->dpp_id == 0xf || tmp_mpcc->dpp_id == dpp_id)
 			return tmp_mpcc;
+
+		/* avoid circular linked list */
+		ASSERT(tmp_mpcc != tmp_mpcc->mpcc_bot);
+		if (tmp_mpcc == tmp_mpcc->mpcc_bot)
+			break;
+
 		tmp_mpcc = tmp_mpcc->mpcc_bot;
 	}
 	return NULL;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
index c5e200d09038..5752271f22df 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
@@ -67,9 +67,15 @@ static uint32_t convert_and_clamp(
 void dcn21_dchvm_init(struct hubbub *hubbub)
 {
 	struct dcn20_hubbub *hubbub1 = TO_DCN20_HUBBUB(hubbub);
-	uint32_t riommu_active;
+	uint32_t riommu_active, prefetch_done;
 	int i;
 
+	REG_GET(DCHVM_RIOMMU_STAT0, HOSTVM_PREFETCH_DONE, &prefetch_done);
+
+	if (prefetch_done) {
+		hubbub->riommu_active = true;
+		return;
+	}
 	//Init DCHVM block
 	REG_UPDATE(DCHVM_CTRL0, HOSTVM_INIT_REQ, 1);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c
index 77b00f86c216..4a668d6563df 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c
@@ -244,8 +244,6 @@ void dpp3_cnv_setup (
 		select = INPUT_CSC_SELECT_ICSC;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
-		pixel_format = 22;
-		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616:
 		pixel_format = 26; /* ARGB16161616_UNORM */
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c
index 6a4dcafb9bba..dc3e8df706b3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c
@@ -86,7 +86,7 @@ bool hubp3_program_surface_flip_and_addr(
 			VMID, address->vmid);
 
 	if (address->type == PLN_ADDR_TYPE_GRPH_STEREO) {
-		REG_UPDATE(DCSURF_FLIP_CONTROL, SURFACE_FLIP_MODE_FOR_STEREOSYNC, 0x1);
+		REG_UPDATE(DCSURF_FLIP_CONTROL, SURFACE_FLIP_MODE_FOR_STEREOSYNC, 0);
 		REG_UPDATE(DCSURF_FLIP_CONTROL, SURFACE_FLIP_IN_STEREOSYNC, 0x1);
 
 	} else {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
index 0a67f8a5656d..d97076648acb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
@@ -372,7 +372,7 @@ static struct stream_encoder *dcn303_stream_encoder_create(enum engine_id eng_id
 	int afmt_inst;
 
 	/* Mapping of VPG, AFMT, DME register blocks to DIO block instance */
-	if (eng_id <= ENGINE_ID_DIGE) {
+	if (eng_id <= ENGINE_ID_DIGB) {
 		vpg_inst = eng_id;
 		afmt_inst = eng_id;
 	} else
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c
index a788d160953b..ab70ebd8f223 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c
@@ -104,6 +104,9 @@ static bool has_query_dp_alt(struct link_encoder *enc)
 {
 	struct dc_dmub_srv *dc_dmub_srv = enc->ctx->dmub_srv;
 
+	if (enc->ctx->dce_version >= DCN_VERSION_3_15)
+		return true;
+
 	/* Supports development firmware and firmware >= 4.0.11 */
 	return dc_dmub_srv &&
 	       !(dc_dmub_srv->dmub->fw_version >= DMUB_FW_VERSION(4, 0, 0) &&
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.h
index 7c77c71591a0..82c3b3ac1f0d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.h
@@ -162,7 +162,8 @@
 	SE_SF(DP_SYM32_ENC0_DP_SYM32_ENC_SDP_AUDIO_CONTROL0, AIP_ENABLE, mask_sh),\
 	SE_SF(DP_SYM32_ENC0_DP_SYM32_ENC_SDP_AUDIO_CONTROL0, ACM_ENABLE, mask_sh),\
 	SE_SF(DP_SYM32_ENC0_DP_SYM32_ENC_VID_CRC_CONTROL, CRC_ENABLE, mask_sh),\
-	SE_SF(DP_SYM32_ENC0_DP_SYM32_ENC_VID_CRC_CONTROL, CRC_CONT_MODE_ENABLE, mask_sh)
+	SE_SF(DP_SYM32_ENC0_DP_SYM32_ENC_VID_CRC_CONTROL, CRC_CONT_MODE_ENABLE, mask_sh),\
+	SE_SF(DP_SYM32_ENC0_DP_SYM32_ENC_HBLANK_CONTROL, HBLANK_MINIMUM_SYMBOL_WIDTH, mask_sh)
 
 
 #define DCN3_1_HPO_DP_STREAM_ENC_REG_FIELD_LIST(type) \
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
index 468a893ff785..aedff18aff56 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
@@ -2153,7 +2153,7 @@ static bool dcn31_resource_construct(
 		pool->base.usb4_dpia_count = 4;
 	}
 
-	if (dc->ctx->asic_id.chip_family == AMDGPU_FAMILY_GC_11_0_2)
+	if (dc->ctx->asic_id.chip_family == AMDGPU_FAMILY_GC_11_0_1)
 		pool->base.usb4_dpia_count = 4;
 
 	/* Audio, Stream Encoders including HPO and virtual, MPC 3D LUTs */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h
index 41f8ec99da6b..901436591ed4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h
@@ -32,7 +32,6 @@
 	container_of(pool, struct dcn31_resource_pool, base)
 
 extern struct _vcs_dpi_ip_params_st dcn3_1_ip;
-extern struct _vcs_dpi_soc_bounding_box_st dcn3_1_soc;
 
 struct dcn31_resource_pool {
 	struct resource_pool base;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/Makefile b/drivers/gpu/drm/amd/display/dc/dcn314/Makefile
index e3b5a95e03b1..702c28c2560e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/Makefile
@@ -13,31 +13,6 @@
 DCN314 = dcn314_resource.o dcn314_hwseq.o dcn314_init.o \
 		dcn314_dio_stream_encoder.o dcn314_dccg.o dcn314_optc.o
 
-ifdef CONFIG_X86
-CFLAGS_$(AMDDALPATH)/dc/dcn314/dcn314_resource.o := -mhard-float -msse
-endif
-
-ifdef CONFIG_PPC64
-CFLAGS_$(AMDDALPATH)/dc/dcn314/dcn314_resource.o := -mhard-float -maltivec
-endif
-
-ifdef CONFIG_CC_IS_GCC
-ifeq ($(call cc-ifversion, -lt, 0701, y), y)
-IS_OLD_GCC = 1
-endif
-endif
-
-ifdef CONFIG_X86
-ifdef IS_OLD_GCC
-# Stack alignment mismatch, proceed with caution.
-# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
-# (8B stack alignment).
-CFLAGS_$(AMDDALPATH)/dc/dcn314/dcn314_resource.o += -mpreferred-stack-boundary=4
-else
-CFLAGS_$(AMDDALPATH)/dc/dcn314/dcn314_resource.o += -msse2
-endif
-endif
-
 AMD_DAL_DCN314 = $(addprefix $(AMDDALPATH)/dc/dcn314/,$(DCN314))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_DCN314)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c
index 232cc15979dd..fb729674953b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c
@@ -45,6 +45,48 @@
 #define DC_LOGGER \
 	dccg->ctx->logger
 
+static void dccg314_get_pixel_rate_div(
+		struct dccg *dccg,
+		uint32_t otg_inst,
+		enum pixel_rate_div *k1,
+		enum pixel_rate_div *k2)
+{
+	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
+	uint32_t val_k1 = PIXEL_RATE_DIV_NA, val_k2 = PIXEL_RATE_DIV_NA;
+
+	*k1 = PIXEL_RATE_DIV_NA;
+	*k2 = PIXEL_RATE_DIV_NA;
+
+	switch (otg_inst) {
+	case 0:
+		REG_GET_2(OTG_PIXEL_RATE_DIV,
+			OTG0_PIXEL_RATE_DIVK1, &val_k1,
+			OTG0_PIXEL_RATE_DIVK2, &val_k2);
+		break;
+	case 1:
+		REG_GET_2(OTG_PIXEL_RATE_DIV,
+			OTG1_PIXEL_RATE_DIVK1, &val_k1,
+			OTG1_PIXEL_RATE_DIVK2, &val_k2);
+		break;
+	case 2:
+		REG_GET_2(OTG_PIXEL_RATE_DIV,
+			OTG2_PIXEL_RATE_DIVK1, &val_k1,
+			OTG2_PIXEL_RATE_DIVK2, &val_k2);
+		break;
+	case 3:
+		REG_GET_2(OTG_PIXEL_RATE_DIV,
+			OTG3_PIXEL_RATE_DIVK1, &val_k1,
+			OTG3_PIXEL_RATE_DIVK2, &val_k2);
+		break;
+	default:
+		BREAK_TO_DEBUGGER();
+		return;
+	}
+
+	*k1 = (enum pixel_rate_div)val_k1;
+	*k2 = (enum pixel_rate_div)val_k2;
+}
+
 static void dccg314_set_pixel_rate_div(
 		struct dccg *dccg,
 		uint32_t otg_inst,
@@ -52,6 +94,11 @@ static void dccg314_set_pixel_rate_div(
 		enum pixel_rate_div k2)
 {
 	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
+	enum pixel_rate_div cur_k1 = PIXEL_RATE_DIV_NA, cur_k2 = PIXEL_RATE_DIV_NA;
+
+	dccg314_get_pixel_rate_div(dccg, otg_inst, &cur_k1, &cur_k2);
+	if (k1 == PIXEL_RATE_DIV_NA || k2 == PIXEL_RATE_DIV_NA || (k1 == cur_k1 && k2 == cur_k2))
+		return;
 
 	switch (otg_inst) {
 	case 0:
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c
index b384f30395d3..8c0ab013764e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c
@@ -56,7 +56,8 @@ static void enc314_enable_fifo(struct stream_encoder *enc)
 
 	/* TODO: Confirm if we need to wait for DIG_SYMCLK_FE_ON */
 	REG_WAIT(DIG_FE_CNTL, DIG_SYMCLK_FE_ON, 1, 10, 5000);
-	REG_UPDATE_2(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 1, DIG_FIFO_READ_START_LEVEL, 0x7);
+	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_READ_START_LEVEL, 0x7);
+	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 1);
 	REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 1, 10, 5000);
 	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 0);
 	REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 0, 10, 5000);
@@ -67,8 +68,7 @@ static void enc314_disable_fifo(struct stream_encoder *enc)
 {
 	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
 
-	REG_UPDATE_2(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 0,
-		     DIG_FIFO_READ_START_LEVEL, 0);
+	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 0);
 }
 
 static void enc314_dp_set_odm_combine(
@@ -262,6 +262,16 @@ static bool is_two_pixels_per_containter(const struct dc_crtc_timing *timing)
 	return two_pix;
 }
 
+void enc314_stream_encoder_dp_blank(
+	struct dc_link *link,
+	struct stream_encoder *enc)
+{
+	/* New to DCN314 - disable the FIFO before VID stream disable. */
+	enc314_disable_fifo(enc);
+
+	enc1_stream_encoder_dp_blank(link, enc);
+}
+
 static void enc314_stream_encoder_dp_unblank(
 		struct dc_link *link,
 		struct stream_encoder *enc,
@@ -322,9 +332,6 @@ static void enc314_stream_encoder_dp_unblank(
 
 	REG_UPDATE(DP_STEER_FIFO, DP_STEER_FIFO_RESET, 0);
 
-	/* DIG Resync FIFO now needs to be explicitly enabled. */
-	enc314_enable_fifo(enc);
-
 	/* wait 100us for DIG/DP logic to prime
 	 * (i.e. a few video lines)
 	 */
@@ -340,6 +347,12 @@ static void enc314_stream_encoder_dp_unblank(
 
 	REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, true);
 
+	/*
+	 * DIG Resync FIFO now needs to be explicitly enabled.
+	 * This should come after DP_VID_STREAM_ENABLE per HW docs.
+	 */
+	enc314_enable_fifo(enc);
+
 	dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_ENABLE_DP_VID_STREAM);
 }
 
@@ -408,7 +421,7 @@ static const struct stream_encoder_funcs dcn314_str_enc_funcs = {
 	.stop_dp_info_packets =
 		enc1_stream_encoder_stop_dp_info_packets,
 	.dp_blank =
-		enc1_stream_encoder_dp_blank,
+		enc314_stream_encoder_dp_blank,
 	.dp_unblank =
 		enc314_stream_encoder_dp_unblank,
 	.audio_mute_control = enc3_audio_mute_control,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c
index 755c715ad8dc..f4d1b83979fe 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c
@@ -343,7 +343,9 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig
 {
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	unsigned int odm_combine_factor = 0;
+	bool two_pix_per_container = false;
 
+	two_pix_per_container = optc2_is_two_pixels_per_containter(&stream->timing);
 	odm_combine_factor = get_odm_config(pipe_ctx, NULL);
 
 	if (is_dp_128b_132b_signal(pipe_ctx)) {
@@ -355,16 +357,13 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig
 		else
 			*k2_div = PIXEL_RATE_DIV_BY_4;
 	} else if (dc_is_dp_signal(pipe_ctx->stream->signal)) {
-		if (stream->timing.pixel_encoding == PIXEL_ENCODING_YCBCR420) {
+		if (two_pix_per_container) {
 			*k1_div = PIXEL_RATE_DIV_BY_1;
 			*k2_div = PIXEL_RATE_DIV_BY_2;
-		} else if (stream->timing.pixel_encoding == PIXEL_ENCODING_YCBCR422) {
-			*k1_div = PIXEL_RATE_DIV_BY_2;
-			*k2_div = PIXEL_RATE_DIV_BY_2;
 		} else {
-			if (odm_combine_factor == 1)
-				*k2_div = PIXEL_RATE_DIV_BY_4;
-			else if (odm_combine_factor == 2)
+			*k1_div = PIXEL_RATE_DIV_BY_1;
+			*k2_div = PIXEL_RATE_DIV_BY_4;
+			if (odm_combine_factor == 2)
 				*k2_div = PIXEL_RATE_DIV_BY_2;
 		}
 	}
@@ -374,3 +373,20 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig
 
 	return odm_combine_factor;
 }
+
+void dcn314_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx)
+{
+	uint32_t pix_per_cycle = 1;
+	uint32_t odm_combine_factor = 1;
+
+	if (!pipe_ctx || !pipe_ctx->stream || !pipe_ctx->stream_res.stream_enc)
+		return;
+
+	odm_combine_factor = get_odm_config(pipe_ctx, NULL);
+	if (optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing) || odm_combine_factor > 1)
+		pix_per_cycle = 2;
+
+	if (pipe_ctx->stream_res.stream_enc->funcs->set_input_mode)
+		pipe_ctx->stream_res.stream_enc->funcs->set_input_mode(pipe_ctx->stream_res.stream_enc,
+				pix_per_cycle);
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h
index be0f5e4d48e1..244280298212 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h
@@ -39,4 +39,6 @@ void dcn314_enable_power_gating_plane(struct dce_hwseq *hws, bool enable);
 
 unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *k1_div, unsigned int *k2_div);
 
+void dcn314_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx);
+
 #endif /* __DC_HWSS_DCN314_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c
index b9debeb081fd..72a563a4c3e8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c
@@ -145,6 +145,7 @@ static const struct hwseq_private_funcs dcn314_private_funcs = {
 	.set_shaper_3dlut = dcn20_set_shaper_3dlut,
 	.setup_hpo_hw_control = dcn31_setup_hpo_hw_control,
 	.calculate_dccg_k1_k2_values = dcn314_calculate_dccg_k1_k2_values,
+	.set_pixels_per_cycle = dcn314_set_pixels_per_cycle,
 };
 
 void dcn314_hw_sequencer_construct(struct dc *dc)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c
index 0c7980266b85..38aa28ec6b13 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_optc.c
@@ -98,7 +98,8 @@ static void optc314_set_odm_combine(struct timing_generator *optc, int *opp_id,
 	REG_UPDATE(OPTC_WIDTH_CONTROL,
 			OPTC_SEGMENT_WIDTH, mpcc_hactive);
 
-	REG_SET(OTG_H_TIMING_CNTL, 0, OTG_H_TIMING_DIV_MODE, opp_cnt - 1);
+	REG_UPDATE(OTG_H_TIMING_CNTL,
+			OTG_H_TIMING_DIV_MODE, opp_cnt - 1);
 	optc1->opp_count = opp_cnt;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
index 63861cdfb09f..44ac1c2aabf5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
@@ -70,6 +70,7 @@
 #include "dce110/dce110_resource.h"
 #include "dml/display_mode_vba.h"
 #include "dml/dcn31/dcn31_fpu.h"
+#include "dml/dcn314/dcn314_fpu.h"
 #include "dcn314/dcn314_dccg.h"
 #include "dcn10/dcn10_resource.h"
 #include "dcn31/dcn31_panel_cntl.h"
@@ -86,6 +87,9 @@
 #define DCHUBBUB_DEBUG_CTRL_0__DET_DEPTH__SHIFT		0x10
 #define DCHUBBUB_DEBUG_CTRL_0__DET_DEPTH_MASK		0x01FF0000L
 
+#define DSCC0_DSCC_CONFIG0__ICH_RESET_AT_END_OF_LINE__SHIFT                   0x0
+#define DSCC0_DSCC_CONFIG0__ICH_RESET_AT_END_OF_LINE_MASK                     0x0000000FL
+
 #include "reg_helper.h"
 #include "dce/dmub_abm.h"
 #include "dce/dmub_psr.h"
@@ -132,155 +136,6 @@ static const struct IP_BASE DCN_BASE = { { { { 0x00000012, 0x000000C0, 0x000034C
 
 #define DC_LOGGER_INIT(logger)
 
-#define DCN3_14_DEFAULT_DET_SIZE 384
-#define DCN3_14_MAX_DET_SIZE 384
-#define DCN3_14_MIN_COMPBUF_SIZE_KB 128
-#define DCN3_14_CRB_SEGMENT_SIZE_KB 64
-struct _vcs_dpi_ip_params_st dcn3_14_ip = {
-	.VBlankNomDefaultUS = 668,
-	.gpuvm_enable = 1,
-	.gpuvm_max_page_table_levels = 1,
-	.hostvm_enable = 1,
-	.hostvm_max_page_table_levels = 2,
-	.rob_buffer_size_kbytes = 64,
-	.det_buffer_size_kbytes = DCN3_14_DEFAULT_DET_SIZE,
-	.config_return_buffer_size_in_kbytes = 1792,
-	.compressed_buffer_segment_size_in_kbytes = 64,
-	.meta_fifo_size_in_kentries = 32,
-	.zero_size_buffer_entries = 512,
-	.compbuf_reserved_space_64b = 256,
-	.compbuf_reserved_space_zs = 64,
-	.dpp_output_buffer_pixels = 2560,
-	.opp_output_buffer_lines = 1,
-	.pixel_chunk_size_kbytes = 8,
-	.meta_chunk_size_kbytes = 2,
-	.min_meta_chunk_size_bytes = 256,
-	.writeback_chunk_size_kbytes = 8,
-	.ptoi_supported = false,
-	.num_dsc = 4,
-	.maximum_dsc_bits_per_component = 10,
-	.dsc422_native_support = false,
-	.is_line_buffer_bpp_fixed = true,
-	.line_buffer_fixed_bpp = 48,
-	.line_buffer_size_bits = 789504,
-	.max_line_buffer_lines = 12,
-	.writeback_interface_buffer_size_kbytes = 90,
-	.max_num_dpp = 4,
-	.max_num_otg = 4,
-	.max_num_hdmi_frl_outputs = 1,
-	.max_num_wb = 1,
-	.max_dchub_pscl_bw_pix_per_clk = 4,
-	.max_pscl_lb_bw_pix_per_clk = 2,
-	.max_lb_vscl_bw_pix_per_clk = 4,
-	.max_vscl_hscl_bw_pix_per_clk = 4,
-	.max_hscl_ratio = 6,
-	.max_vscl_ratio = 6,
-	.max_hscl_taps = 8,
-	.max_vscl_taps = 8,
-	.dpte_buffer_size_in_pte_reqs_luma = 64,
-	.dpte_buffer_size_in_pte_reqs_chroma = 34,
-	.dispclk_ramp_margin_percent = 1,
-	.max_inter_dcn_tile_repeaters = 8,
-	.cursor_buffer_size = 16,
-	.cursor_chunk_size = 2,
-	.writeback_line_buffer_buffer_size = 0,
-	.writeback_min_hscl_ratio = 1,
-	.writeback_min_vscl_ratio = 1,
-	.writeback_max_hscl_ratio = 1,
-	.writeback_max_vscl_ratio = 1,
-	.writeback_max_hscl_taps = 1,
-	.writeback_max_vscl_taps = 1,
-	.dppclk_delay_subtotal = 46,
-	.dppclk_delay_scl = 50,
-	.dppclk_delay_scl_lb_only = 16,
-	.dppclk_delay_cnvc_formatter = 27,
-	.dppclk_delay_cnvc_cursor = 6,
-	.dispclk_delay_subtotal = 119,
-	.dynamic_metadata_vm_enabled = false,
-	.odm_combine_4to1_supported = false,
-	.dcc_supported = true,
-};
-
-struct _vcs_dpi_soc_bounding_box_st dcn3_14_soc = {
-		/*TODO: correct dispclk/dppclk voltage level determination*/
-	.clock_limits = {
-		{
-			.state = 0,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
-			.phyclk_mhz = 600.0,
-			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 186.0,
-			.dtbclk_mhz = 625.0,
-		},
-		{
-			.state = 1,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
-			.phyclk_mhz = 810.0,
-			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 209.0,
-			.dtbclk_mhz = 625.0,
-		},
-		{
-			.state = 2,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
-			.phyclk_mhz = 810.0,
-			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 209.0,
-			.dtbclk_mhz = 625.0,
-		},
-		{
-			.state = 3,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
-			.phyclk_mhz = 810.0,
-			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 371.0,
-			.dtbclk_mhz = 625.0,
-		},
-		{
-			.state = 4,
-			.dispclk_mhz = 1200.0,
-			.dppclk_mhz = 1200.0,
-			.phyclk_mhz = 810.0,
-			.phyclk_d18_mhz = 667.0,
-			.dscclk_mhz = 417.0,
-			.dtbclk_mhz = 625.0,
-		},
-	},
-	.num_states = 5,
-	.sr_exit_time_us = 9.0,
-	.sr_enter_plus_exit_time_us = 11.0,
-	.sr_exit_z8_time_us = 442.0,
-	.sr_enter_plus_exit_z8_time_us = 560.0,
-	.writeback_latency_us = 12.0,
-	.dram_channel_width_bytes = 4,
-	.round_trip_ping_latency_dcfclk_cycles = 106,
-	.urgent_latency_pixel_data_only_us = 4.0,
-	.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
-	.urgent_latency_vm_data_only_us = 4.0,
-	.urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096,
-	.urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096,
-	.urgent_out_of_order_return_per_channel_vm_only_bytes = 4096,
-	.pct_ideal_sdp_bw_after_urgent = 80.0,
-	.pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 65.0,
-	.pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 60.0,
-	.pct_ideal_dram_sdp_bw_after_urgent_vm_only = 30.0,
-	.max_avg_sdp_bw_use_normal_percent = 60.0,
-	.max_avg_dram_bw_use_normal_percent = 60.0,
-	.fabric_datapath_to_dcn_data_return_bytes = 32,
-	.return_bus_width_bytes = 64,
-	.downspread_percent = 0.38,
-	.dcn_downspread_percent = 0.5,
-	.gpuvm_min_page_size_bytes = 4096,
-	.hostvm_min_page_size_bytes = 4096,
-	.do_urgent_latency_adjustment = false,
-	.urgent_latency_adjustment_fabric_clock_component_us = 0,
-	.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
-};
-
 enum dcn31_clk_src_array_id {
 	DCN31_CLK_SRC_PLL0,
 	DCN31_CLK_SRC_PLL1,
@@ -602,6 +457,7 @@ static const struct dcn31_hpo_dp_stream_encoder_registers hpo_dp_stream_enc_regs
 	hpo_dp_stream_encoder_reg_list(0),
 	hpo_dp_stream_encoder_reg_list(1),
 	hpo_dp_stream_encoder_reg_list(2),
+	hpo_dp_stream_encoder_reg_list(3)
 };
 
 static const struct dcn31_hpo_dp_stream_encoder_shift hpo_dp_se_shift = {
@@ -726,7 +582,7 @@ static const struct dcn30_mmhubbub_mask mcif_wb30_mask = {
 
 #define dsc_regsDCN314(id)\
 [id] = {\
-	DSC_REG_LIST_DCN314(id)\
+	DSC_REG_LIST_DCN20(id)\
 }
 
 static const struct dcn20_dsc_registers dsc_regs[] = {
@@ -737,11 +593,11 @@ static const struct dcn20_dsc_registers dsc_regs[] = {
 };
 
 static const struct dcn20_dsc_shift dsc_shift = {
-	DSC_REG_LIST_SH_MASK_DCN314(__SHIFT)
+	DSC_REG_LIST_SH_MASK_DCN20(__SHIFT)
 };
 
 static const struct dcn20_dsc_mask dsc_mask = {
-	DSC_REG_LIST_SH_MASK_DCN314(_MASK)
+	DSC_REG_LIST_SH_MASK_DCN20(_MASK)
 };
 
 static const struct dcn30_mpc_registers mpc_regs = {
@@ -991,7 +847,7 @@ static const struct resource_caps res_cap_dcn314 = {
 	.num_ddc = 5,
 	.num_vmid = 16,
 	.num_mpc_3dlut = 2,
-	.num_dsc = 4,
+	.num_dsc = 3,
 };
 
 static const struct dc_plane_cap plane_cap = {
@@ -1402,7 +1258,7 @@ static struct stream_encoder *dcn314_stream_encoder_create(
 	int afmt_inst;
 
 	/* Mapping of VPG, AFMT, DME register blocks to DIO block instance */
-	if (eng_id <= ENGINE_ID_DIGF) {
+	if (eng_id < ENGINE_ID_DIGF) {
 		vpg_inst = eng_id;
 		afmt_inst = eng_id;
 	} else
@@ -1447,7 +1303,8 @@ static struct hpo_dp_stream_encoder *dcn31_hpo_dp_stream_encoder_create(
 	 * VPG[8] -> HPO_DP[2]
 	 * VPG[9] -> HPO_DP[3]
 	 */
-	vpg_inst = hpo_dp_inst + 6;
+	//Uses offset index 5-8, but actually maps to vpg_inst 6-9
+	vpg_inst = hpo_dp_inst + 5;
 
 	/* Mapping of APG register blocks to HPO DP block instance:
 	 * APG[0] -> HPO_DP[0]
@@ -1793,109 +1650,16 @@ static struct clock_source *dcn31_clock_source_create(
 	return NULL;
 }
 
-static bool is_dual_plane(enum surface_pixel_format format)
-{
-	return format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN || format == SURFACE_PIXEL_FORMAT_GRPH_RGBE_ALPHA;
-}
-
 static int dcn314_populate_dml_pipes_from_context(
 	struct dc *dc, struct dc_state *context,
 	display_e2e_pipe_params_st *pipes,
 	bool fast_validate)
 {
-	int i, pipe_cnt;
-	struct resource_context *res_ctx = &context->res_ctx;
-	struct pipe_ctx *pipe;
-	bool upscaled = false;
-
-	dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate);
-
-	for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
-		struct dc_crtc_timing *timing;
-
-		if (!res_ctx->pipe_ctx[i].stream)
-			continue;
-		pipe = &res_ctx->pipe_ctx[i];
-		timing = &pipe->stream->timing;
-
-		if (dc_extended_blank_supported(dc) && pipe->stream->adjust.v_total_max == pipe->stream->adjust.v_total_min
-			&& pipe->stream->adjust.v_total_min > timing->v_total)
-			pipes[pipe_cnt].pipe.dest.vtotal = pipe->stream->adjust.v_total_min;
-
-		if (pipe->plane_state &&
-				(pipe->plane_state->src_rect.height < pipe->plane_state->dst_rect.height ||
-				pipe->plane_state->src_rect.width < pipe->plane_state->dst_rect.width))
-			upscaled = true;
-
-		/*
-		 * Immediate flip can be set dynamically after enabling the plane.
-		 * We need to require support for immediate flip or underflow can be
-		 * intermittently experienced depending on peak b/w requirements.
-		 */
-		pipes[pipe_cnt].pipe.src.immediate_flip = true;
-
-		pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
-		pipes[pipe_cnt].pipe.src.hostvm = dc->res_pool->hubbub->riommu_active;
-		pipes[pipe_cnt].pipe.src.gpuvm = true;
-		pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_luma = 0;
-		pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_chroma = 0;
-		pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
-		pipes[pipe_cnt].pipe.src.dcc_rate = 3;
-		pipes[pipe_cnt].dout.dsc_input_bpc = 0;
-
-		if (pipes[pipe_cnt].dout.dsc_enable) {
-			switch (timing->display_color_depth) {
-			case COLOR_DEPTH_888:
-				pipes[pipe_cnt].dout.dsc_input_bpc = 8;
-				break;
-			case COLOR_DEPTH_101010:
-				pipes[pipe_cnt].dout.dsc_input_bpc = 10;
-				break;
-			case COLOR_DEPTH_121212:
-				pipes[pipe_cnt].dout.dsc_input_bpc = 12;
-				break;
-			default:
-				ASSERT(0);
-				break;
-			}
-		}
-
-		pipe_cnt++;
-	}
-	context->bw_ctx.dml.ip.det_buffer_size_kbytes = DCN3_14_DEFAULT_DET_SIZE;
-
-	dc->config.enable_4to1MPC = false;
-	if (pipe_cnt == 1 && pipe->plane_state && !dc->debug.disable_z9_mpc) {
-		if (is_dual_plane(pipe->plane_state->format)
-				&& pipe->plane_state->src_rect.width <= 1920 && pipe->plane_state->src_rect.height <= 1080) {
-			dc->config.enable_4to1MPC = true;
-		} else if (!is_dual_plane(pipe->plane_state->format) && pipe->plane_state->src_rect.width <= 5120) {
-			/* Limit to 5k max to avoid forced pipe split when there is not enough detile for swath */
-			context->bw_ctx.dml.ip.det_buffer_size_kbytes = 192;
-			pipes[0].pipe.src.unbounded_req_mode = true;
-		}
-	} else if (context->stream_count >= dc->debug.crb_alloc_policy_min_disp_count
-			&& dc->debug.crb_alloc_policy > DET_SIZE_DEFAULT) {
-		context->bw_ctx.dml.ip.det_buffer_size_kbytes = dc->debug.crb_alloc_policy * 64;
-	} else if (context->stream_count >= 3 && upscaled) {
-		context->bw_ctx.dml.ip.det_buffer_size_kbytes = 192;
-	}
-
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
-
-		if (!pipe->stream)
-			continue;
+	int pipe_cnt;
 
-		if (pipe->stream->signal == SIGNAL_TYPE_EDP && dc->debug.seamless_boot_odm_combine &&
-				pipe->stream->apply_seamless_boot_optimization) {
-
-			if (pipe->stream->apply_boot_odm_mode == dm_odm_combine_policy_2to1) {
-				context->bw_ctx.dml.vba.ODMCombinePolicy = dm_odm_combine_policy_2to1;
-				break;
-			}
-		}
-	}
+	DC_FP_START();
+	pipe_cnt = dcn314_populate_dml_pipes_from_context_fpu(dc, context, pipes, fast_validate);
+	DC_FP_END();
 
 	return pipe_cnt;
 }
@@ -1906,88 +1670,9 @@ static struct dc_cap_funcs cap_funcs = {
 
 static void dcn314_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
 {
-	struct clk_limit_table *clk_table = &bw_params->clk_table;
-	struct _vcs_dpi_voltage_scaling_st *clock_tmp = dcn3_14_soc._clock_tmp;
-	unsigned int i, closest_clk_lvl;
-	int max_dispclk_mhz = 0, max_dppclk_mhz = 0;
-	int j;
-
-	// Default clock levels are used for diags, which may lead to overclocking.
-	if (!IS_DIAG_DC(dc->ctx->dce_environment)) {
-
-		dcn3_14_ip.max_num_otg = dc->res_pool->res_cap->num_timing_generator;
-		dcn3_14_ip.max_num_dpp = dc->res_pool->pipe_count;
-
-		if (bw_params->num_channels > 0)
-			dcn3_14_soc.num_chans = bw_params->num_channels;
-
-		ASSERT(dcn3_14_soc.num_chans);
-		ASSERT(clk_table->num_entries);
-
-		/* Prepass to find max clocks independent of voltage level. */
-		for (i = 0; i < clk_table->num_entries; ++i) {
-			if (clk_table->entries[i].dispclk_mhz > max_dispclk_mhz)
-				max_dispclk_mhz = clk_table->entries[i].dispclk_mhz;
-			if (clk_table->entries[i].dppclk_mhz > max_dppclk_mhz)
-				max_dppclk_mhz = clk_table->entries[i].dppclk_mhz;
-		}
-
-		for (i = 0; i < clk_table->num_entries; i++) {
-			/* loop backwards*/
-			for (closest_clk_lvl = 0, j = dcn3_14_soc.num_states - 1; j >= 0; j--) {
-				if ((unsigned int) dcn3_14_soc.clock_limits[j].dcfclk_mhz <= clk_table->entries[i].dcfclk_mhz) {
-					closest_clk_lvl = j;
-					break;
-				}
-			}
-			if (clk_table->num_entries == 1) {
-				/*smu gives one DPM level, let's take the highest one*/
-				closest_clk_lvl = dcn3_14_soc.num_states - 1;
-			}
-
-			clock_tmp[i].state = i;
-
-			/* Clocks dependent on voltage level. */
-			clock_tmp[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz;
-			if (clk_table->num_entries == 1 &&
-				clock_tmp[i].dcfclk_mhz < dcn3_14_soc.clock_limits[closest_clk_lvl].dcfclk_mhz) {
-				/*SMU fix not released yet*/
-				clock_tmp[i].dcfclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].dcfclk_mhz;
-			}
-			clock_tmp[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz;
-			clock_tmp[i].socclk_mhz = clk_table->entries[i].socclk_mhz;
-
-			if (clk_table->entries[i].memclk_mhz && clk_table->entries[i].wck_ratio)
-				clock_tmp[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2 * clk_table->entries[i].wck_ratio;
-
-			/* Clocks independent of voltage level. */
-			clock_tmp[i].dispclk_mhz = max_dispclk_mhz ? max_dispclk_mhz :
-				dcn3_14_soc.clock_limits[closest_clk_lvl].dispclk_mhz;
-
-			clock_tmp[i].dppclk_mhz = max_dppclk_mhz ? max_dppclk_mhz :
-				dcn3_14_soc.clock_limits[closest_clk_lvl].dppclk_mhz;
-
-			clock_tmp[i].dram_bw_per_chan_gbps = dcn3_14_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps;
-			clock_tmp[i].dscclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].dscclk_mhz;
-			clock_tmp[i].dtbclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].dtbclk_mhz;
-			clock_tmp[i].phyclk_d18_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz;
-			clock_tmp[i].phyclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].phyclk_mhz;
-		}
-		for (i = 0; i < clk_table->num_entries; i++)
-			dcn3_14_soc.clock_limits[i] = clock_tmp[i];
-		if (clk_table->num_entries)
-			dcn3_14_soc.num_states = clk_table->num_entries;
-	}
-
-	if (max_dispclk_mhz) {
-		dcn3_14_soc.dispclk_dppclk_vco_speed_mhz = max_dispclk_mhz * 2;
-		dc->dml.soc.dispclk_dppclk_vco_speed_mhz = max_dispclk_mhz * 2;
-	}
-
-	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
-		dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN31);
-	else
-		dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN31_FPGA);
+	DC_FP_START();
+	dcn314_update_bw_bounding_box_fpu(dc, bw_params);
+	DC_FP_END();
 }
 
 static struct resource_funcs dcn314_res_pool_funcs = {
@@ -2069,6 +1754,7 @@ static bool dcn314_resource_construct(
 	dc->caps.post_blend_color_processing = true;
 	dc->caps.force_dp_tps4_for_cp2520 = true;
 	dc->caps.dp_hpo = true;
+	dc->caps.dp_hdmi21_pcon_support = true;
 	dc->caps.edp_dsc_support = true;
 	dc->caps.extended_aux_timeout_support = true;
 	dc->caps.dmcub_support = true;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.h b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.h
index c41108847ce0..0dd3153aa5c1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.h
@@ -29,6 +29,9 @@
 
 #include "core_types.h"
 
+extern struct _vcs_dpi_ip_params_st dcn3_14_ip;
+extern struct _vcs_dpi_soc_bounding_box_st dcn3_14_soc;
+
 #define TO_DCN314_RES_POOL(pool)\
 	container_of(pool, struct dcn314_resource_pool, base)
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.h b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.h
index 39929fa67a51..22849eaa6f24 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.h
@@ -32,7 +32,6 @@
 	container_of(pool, struct dcn315_resource_pool, base)
 
 extern struct _vcs_dpi_ip_params_st dcn3_15_ip;
-extern struct _vcs_dpi_ip_params_st dcn3_15_soc;
 
 struct dcn315_resource_pool {
 	struct resource_pool base;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.h b/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.h
index 0dc5a6c13ae7..aba6d634131b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.h
@@ -32,7 +32,6 @@
 	container_of(pool, struct dcn316_resource_pool, base)
 
 extern struct _vcs_dpi_ip_params_st dcn3_16_ip;
-extern struct _vcs_dpi_ip_params_st dcn3_16_soc;
 
 struct dcn316_resource_pool {
 	struct resource_pool base;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c
index a31c64b50410..6640d0ac4304 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c
@@ -42,6 +42,48 @@
 #define DC_LOGGER \
 	dccg->ctx->logger
 
+static void dccg32_get_pixel_rate_div(
+		struct dccg *dccg,
+		uint32_t otg_inst,
+		enum pixel_rate_div *k1,
+		enum pixel_rate_div *k2)
+{
+	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
+	uint32_t val_k1 = PIXEL_RATE_DIV_NA, val_k2 = PIXEL_RATE_DIV_NA;
+
+	*k1 = PIXEL_RATE_DIV_NA;
+	*k2 = PIXEL_RATE_DIV_NA;
+
+	switch (otg_inst) {
+	case 0:
+		REG_GET_2(OTG_PIXEL_RATE_DIV,
+			OTG0_PIXEL_RATE_DIVK1, &val_k1,
+			OTG0_PIXEL_RATE_DIVK2, &val_k2);
+		break;
+	case 1:
+		REG_GET_2(OTG_PIXEL_RATE_DIV,
+			OTG1_PIXEL_RATE_DIVK1, &val_k1,
+			OTG1_PIXEL_RATE_DIVK2, &val_k2);
+		break;
+	case 2:
+		REG_GET_2(OTG_PIXEL_RATE_DIV,
+			OTG2_PIXEL_RATE_DIVK1, &val_k1,
+			OTG2_PIXEL_RATE_DIVK2, &val_k2);
+		break;
+	case 3:
+		REG_GET_2(OTG_PIXEL_RATE_DIV,
+			OTG3_PIXEL_RATE_DIVK1, &val_k1,
+			OTG3_PIXEL_RATE_DIVK2, &val_k2);
+		break;
+	default:
+		BREAK_TO_DEBUGGER();
+		return;
+	}
+
+	*k1 = (enum pixel_rate_div)val_k1;
+	*k2 = (enum pixel_rate_div)val_k2;
+}
+
 static void dccg32_set_pixel_rate_div(
 		struct dccg *dccg,
 		uint32_t otg_inst,
@@ -50,6 +92,17 @@ static void dccg32_set_pixel_rate_div(
 {
 	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
 
+	enum pixel_rate_div cur_k1 = PIXEL_RATE_DIV_NA, cur_k2 = PIXEL_RATE_DIV_NA;
+
+	// Don't program 0xF into the register field. Not valid since
+	// K1 / K2 field is only 1 / 2 bits wide
+	if (k1 == PIXEL_RATE_DIV_NA || k2 == PIXEL_RATE_DIV_NA)
+		return;
+
+	dccg32_get_pixel_rate_div(dccg, otg_inst, &cur_k1, &cur_k2);
+	if (k1 == cur_k1 && k2 == cur_k2)
+		return;
+
 	switch (otg_inst) {
 	case 0:
 		REG_UPDATE_2(OTG_PIXEL_RATE_DIV,
@@ -225,19 +278,19 @@ void dccg32_set_dpstreamclk(
 	case 0:
 		REG_UPDATE_2(DPSTREAMCLK_CNTL,
 			     DPSTREAMCLK0_EN,
-			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK0_SRC_SEL, 0);
+			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK0_SRC_SEL, otg_inst);
 		break;
 	case 1:
 		REG_UPDATE_2(DPSTREAMCLK_CNTL, DPSTREAMCLK1_EN,
-			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK1_SRC_SEL, 1);
+			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK1_SRC_SEL, otg_inst);
 		break;
 	case 2:
 		REG_UPDATE_2(DPSTREAMCLK_CNTL, DPSTREAMCLK2_EN,
-			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK2_SRC_SEL, 2);
+			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK2_SRC_SEL, otg_inst);
 		break;
 	case 3:
 		REG_UPDATE_2(DPSTREAMCLK_CNTL, DPSTREAMCLK3_EN,
-			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK3_SRC_SEL, 3);
+			     (src == REFCLK) ? 0 : 1, DPSTREAMCLK3_SRC_SEL, otg_inst);
 		break;
 	default:
 		BREAK_TO_DEBUGGER();
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c
index 26648ce772da..38a48983f663 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c
@@ -310,6 +310,11 @@ static void enc32_stream_encoder_dp_unblank(
 	// TODO: Confirm if we need to wait for DIG_SYMCLK_FE_ON
 	REG_WAIT(DIG_FE_CNTL, DIG_SYMCLK_FE_ON, 1, 10, 5000);
 
+	/* read start level = 0 will bring underflow / overflow and DIG_FIFO_ERROR = 1
+	 * so set it to 1/2 full = 7 before reset as suggested by hardware team.
+	 */
+	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_READ_START_LEVEL, 0x7);
+
 	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 1);
 
 	REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 1, 10, 5000);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c
index 99eb239bbc7b..9aebc1be2f59 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c
@@ -98,9 +98,13 @@ static void dcn32_program_det_size(struct hubbub *hubbub, int hubp_inst, unsigne
 	default:
 		break;
 	}
-	/* Should never be hit, if it is we have an erroneous hw config*/
-	ASSERT(hubbub2->det0_size + hubbub2->det1_size + hubbub2->det2_size
-			+ hubbub2->det3_size + hubbub2->compbuf_size_segments <= hubbub2->crb_size_segs);
+	if (hubbub2->det0_size + hubbub2->det1_size + hubbub2->det2_size
+			+ hubbub2->det3_size + hubbub2->compbuf_size_segments > hubbub2->crb_size_segs) {
+		/* This may happen during seamless transition from ODM 2:1 to ODM4:1 */
+		DC_LOG_WARNING("CRB Config Warning: DET size (%d,%d,%d,%d) + Compbuf size (%d) >  CRB segments (%d)\n",
+						hubbub2->det0_size, hubbub2->det1_size, hubbub2->det2_size, hubbub2->det3_size,
+						hubbub2->compbuf_size_segments, hubbub2->crb_size_segs);
+	}
 }
 
 static void dcn32_program_compbuf_size(struct hubbub *hubbub, unsigned int compbuf_size_kb, bool safe_to_increase)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c
index 6ec1c52535b9..2038cbda33f7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c
@@ -103,6 +103,11 @@ void hubp32_cursor_set_attributes(
 	enum cursor_lines_per_chunk lpc = hubp2_get_lines_per_chunk(
 			attr->width, attr->color_format);
 
+	//Round cursor width up to next multiple of 64
+	uint32_t cursor_width = ((attr->width + 63) / 64) * 64;
+	uint32_t cursor_height = attr->height;
+	uint32_t cursor_size = cursor_width * cursor_height;
+
 	hubp->curs_attr = *attr;
 
 	REG_UPDATE(CURSOR_SURFACE_ADDRESS_HIGH,
@@ -126,7 +131,24 @@ void hubp32_cursor_set_attributes(
 			 /* used to shift the cursor chunk request deadline */
 			CURSOR0_CHUNK_HDL_ADJUST, 3);
 
-	if (attr->width * attr->height * 4 > 16384)
+	switch (attr->color_format) {
+	case CURSOR_MODE_MONO:
+		cursor_size /= 2;
+		break;
+	case CURSOR_MODE_COLOR_1BIT_AND:
+	case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA:
+	case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA:
+		cursor_size *= 4;
+		break;
+
+	case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED:
+	case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED:
+	default:
+		cursor_size *= 8;
+		break;
+	}
+
+	if (cursor_size > 16384)
 		REG_UPDATE(DCHUBP_MALL_CONFIG, USE_MALL_FOR_CURSOR, true);
 	else
 		REG_UPDATE(DCHUBP_MALL_CONFIG, USE_MALL_FOR_CURSOR, false);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
index d38341f68b17..344fe7535df5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
@@ -250,6 +250,7 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c
 	uint32_t total_lines = 0;
 	uint32_t lines_per_way = 0;
 	uint32_t num_ways = 0;
+	uint32_t prev_addr_low = 0;
 
 	for (i = 0; i < ctx->stream_count; i++) {
 		stream = ctx->streams[i];
@@ -267,10 +268,20 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c
 			plane = ctx->stream_status[i].plane_states[j];
 
 			// Calculate total surface size
-			surface_size = plane->plane_size.surface_pitch *
+			if (prev_addr_low != plane->address.grph.addr.u.low_part) {
+				/* if plane address are different from prev FB, then userspace allocated separate FBs*/
+				surface_size += plane->plane_size.surface_pitch *
 					plane->plane_size.surface_size.height *
 					(plane->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4);
 
+				prev_addr_low = plane->address.grph.addr.u.low_part;
+			} else {
+				/* We have the same fb for all the planes.
+				 * Xorg always creates one giant fb that holds all surfaces,
+				 * so allocating it once is sufficient.
+				 * */
+				continue;
+			}
 			// Convert surface size + starting address to number of cache lines required
 			// (alignment accounted for)
 			cache_lines_used += dcn32_cache_lines_for_surface(dc, surface_size,
@@ -284,24 +295,38 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c
 		}
 
 		// Include cursor size for CAB allocation
-		if (stream->cursor_position.enable && plane->address.grph.cursor_cache_addr.quad_part) {
-			cursor_size = dc->caps.max_cursor_size * dc->caps.max_cursor_size;
-			switch (stream->cursor_attributes.color_format) {
-			case CURSOR_MODE_MONO:
-				cursor_size /= 2;
-				break;
-			case CURSOR_MODE_COLOR_1BIT_AND:
-			case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA:
-			case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA:
-				cursor_size *= 4;
-				break;
+		for (j = 0; j < dc->res_pool->pipe_count; j++) {
+			struct pipe_ctx *pipe = &ctx->res_ctx.pipe_ctx[j];
+			struct hubp *hubp = pipe->plane_res.hubp;
 
-			case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED:
-			case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED:
-				cursor_size *= 8;
-				break;
-			}
-			cache_lines_used += dcn32_cache_lines_for_surface(dc, surface_size,
+			if (pipe->stream && pipe->plane_state && hubp)
+				/* Find the cursor plane and use the exact size instead of
+				 * using the max for calculation
+				 */
+				if (hubp->curs_attr.width > 0) {
+					cursor_size = hubp->curs_attr.width * hubp->curs_attr.height;
+					break;
+				}
+		}
+
+		switch (stream->cursor_attributes.color_format) {
+		case CURSOR_MODE_MONO:
+			cursor_size /= 2;
+			break;
+		case CURSOR_MODE_COLOR_1BIT_AND:
+		case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA:
+		case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA:
+			cursor_size *= 4;
+			break;
+
+		case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED:
+		case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED:
+			cursor_size *= 8;
+			break;
+		}
+
+		if (stream->cursor_position.enable && plane->address.grph.cursor_cache_addr.quad_part) {
+			cache_lines_used += dcn32_cache_lines_for_surface(dc, cursor_size,
 					plane->address.grph.cursor_cache_addr.quad_part);
 		}
 	}
@@ -314,13 +339,36 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c
 	if (cache_lines_used % lines_per_way > 0)
 		num_ways++;
 
+	for (i = 0; i < ctx->stream_count; i++) {
+		stream = ctx->streams[i];
+		for (j = 0; j < ctx->stream_status[i].plane_count; j++) {
+			plane = ctx->stream_status[i].plane_states[j];
+
+			if (stream->cursor_position.enable && plane &&
+				!plane->address.grph.cursor_cache_addr.quad_part &&
+				cursor_size > 16384) {
+				/* Cursor caching is not supported since it won't be on the same line.
+				 * So we need an extra line to accommodate it. With large cursors and a single 4k monitor
+				 * this case triggers corruption. If we're at the edge, then dont trigger display refresh
+				 * from MALL. We only need to cache cursor if its greater that 64x64 at 4 bpp.
+				 */
+				num_ways++;
+				/* We only expect one cursor plane */
+				break;
+			}
+		}
+	}
+
 	return num_ways;
 }
 
 bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable)
 {
 	union dmub_rb_cmd cmd;
-	uint8_t ways;
+	uint8_t ways, i;
+	int j;
+	bool stereo_in_use = false;
+	struct dc_plane_state *plane = NULL;
 
 	if (!dc->ctx->dmub_srv)
 		return false;
@@ -349,7 +397,23 @@ bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable)
 			 * and configure HUBP's to fetch from MALL
 			 */
 			ways = dcn32_calculate_cab_allocation(dc, dc->current_state);
-			if (ways <= dc->caps.cache_num_ways) {
+
+			/* MALL not supported with Stereo3D. If any plane is using stereo,
+			 * don't try to enter MALL.
+			 */
+			for (i = 0; i < dc->current_state->stream_count; i++) {
+				for (j = 0; j < dc->current_state->stream_status[i].plane_count; j++) {
+					plane = dc->current_state->stream_status[i].plane_states[j];
+
+					if (plane->address.type == PLN_ADDR_TYPE_GRPH_STEREO) {
+						stereo_in_use = true;
+						break;
+					}
+				}
+				if (stereo_in_use)
+					break;
+			}
+			if (ways <= dc->caps.cache_num_ways && !stereo_in_use) {
 				memset(&cmd, 0, sizeof(cmd));
 				cmd.cab.header.type = DMUB_CMD__CAB_FOR_SS;
 				cmd.cab.header.sub_type = DMUB_CMD__CAB_DCN_SS_FIT_IN_CAB;
@@ -677,15 +741,39 @@ void dcn32_update_mall_sel(struct dc *dc, struct dc_state *context)
 		struct hubp *hubp = pipe->plane_res.hubp;
 
 		if (pipe->stream && pipe->plane_state && hubp && hubp->funcs->hubp_update_mall_sel) {
-			if (hubp->curs_attr.width * hubp->curs_attr.height * 4 > 16384)
+			//Round cursor width up to next multiple of 64
+			int cursor_width = ((hubp->curs_attr.width + 63) / 64) * 64;
+			int cursor_height = hubp->curs_attr.height;
+			int cursor_size = cursor_width * cursor_height;
+
+			switch (hubp->curs_attr.color_format) {
+			case CURSOR_MODE_MONO:
+				cursor_size /= 2;
+				break;
+			case CURSOR_MODE_COLOR_1BIT_AND:
+			case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA:
+			case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA:
+				cursor_size *= 4;
+				break;
+
+			case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED:
+			case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED:
+			default:
+				cursor_size *= 8;
+				break;
+			}
+
+			if (cursor_size > 16384)
 				cache_cursor = true;
 
 			if (pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) {
 					hubp->funcs->hubp_update_mall_sel(hubp, 1, false);
 			} else {
+				// MALL not supported with Stereo3D
 				hubp->funcs->hubp_update_mall_sel(hubp,
 					num_ways <= dc->caps.cache_num_ways &&
-					pipe->stream->link->psr_settings.psr_version == DC_PSR_VERSION_UNSUPPORTED ? 2 : 0,
+					pipe->stream->link->psr_settings.psr_version == DC_PSR_VERSION_UNSUPPORTED &&
+					pipe->plane_state->address.type !=  PLN_ADDR_TYPE_GRPH_STEREO ? 2 : 0,
 							cache_cursor);
 			}
 		}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c
index eff1f4e17689..1fad7b48bd5b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c
@@ -281,7 +281,7 @@ static struct timing_generator_funcs dcn32_tg_funcs = {
 		.lock_doublebuffer_enable = optc3_lock_doublebuffer_enable,
 		.lock_doublebuffer_disable = optc3_lock_doublebuffer_disable,
 		.enable_optc_clock = optc1_enable_optc_clock,
-		.set_drr = optc31_set_drr, // TODO: Update to optc32_set_drr once FW headers are promoted
+		.set_drr = optc32_set_drr,
 		.get_last_used_drr_vtotal = optc2_get_last_used_drr_vtotal,
 		.set_vtotal_min_max = optc3_set_vtotal_min_max,
 		.set_static_screen_control = optc1_set_static_screen_control,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
index 9a26d24b579f..c3b783cea8a0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
@@ -867,10 +867,11 @@ static const struct dc_debug_options debug_defaults_drv = {
 		}
 	},
 	.use_max_lb = true,
-	.force_disable_subvp = true,
+	.force_disable_subvp = false,
 	.exit_idle_opt_for_cursor_updates = true,
 	.enable_single_display_2to1_odm_policy = true,
 	.enable_dp_dig_pixel_rate_div_policy = 1,
+	.allow_sw_cursor_fallback = false,
 };
 
 static const struct dc_debug_options debug_defaults_diags = {
@@ -2039,7 +2040,8 @@ static bool dcn32_resource_construct(
 	dc->caps.max_downscale_ratio = 600;
 	dc->caps.i2c_speed_in_khz = 100;
 	dc->caps.i2c_speed_in_khz_hdcp = 100; /*1.4 w/a applied by default*/
-	dc->caps.max_cursor_size = 256;
+	/* TODO: Bring max_cursor_size back to 256 after subvp cursor corruption is fixed*/
+	dc->caps.max_cursor_size = 64;
 	dc->caps.min_horizontal_blanking_period = 80;
 	dc->caps.dmdata_alloc_size = 2048;
 	dc->caps.mall_size_per_mem_channel = 0;
@@ -2051,6 +2053,7 @@ static bool dcn32_resource_construct(
 	dc->caps.max_cab_allocation_bytes = 67108864; // 64MB = 1024 * 1024 * 64
 	dc->caps.subvp_fw_processing_delay_us = 15;
 	dc->caps.subvp_prefetch_end_to_mall_start_us = 15;
+	dc->caps.subvp_swath_height_margin_lines = 16;
 	dc->caps.subvp_pstate_allow_width_us = 20;
 	dc->caps.subvp_vertical_int_margin_us = 30;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h
index 1e7e6201c880..cf15d0e5e9b4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h
@@ -30,6 +30,9 @@
 
 #define DCN3_2_DET_SEG_SIZE 64
 #define DCN3_2_MALL_MBLK_SIZE_BYTES 65536 // 64 * 1024
+#define DCN3_2_MBLK_WIDTH 128
+#define DCN3_2_MBLK_HEIGHT_4BPE 128
+#define DCN3_2_MBLK_HEIGHT_8BPE 64
 
 #define TO_DCN32_RES_POOL(pool)\
 	container_of(pool, struct dcn32_resource_pool, base)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
index b3f8503cea9c..1f195c5b3377 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
@@ -46,7 +46,6 @@
 uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_state *context)
 {
 	uint32_t num_ways = 0;
-	uint32_t mall_region_pixels = 0;
 	uint32_t bytes_per_pixel = 0;
 	uint32_t cache_lines_used = 0;
 	uint32_t lines_per_way = 0;
@@ -54,20 +53,64 @@ uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_stat
 	uint32_t bytes_in_mall = 0;
 	uint32_t num_mblks = 0;
 	uint32_t cache_lines_per_plane = 0;
-	uint32_t i = 0;
+	uint32_t i = 0, j = 0;
+	uint32_t mblk_width = 0;
+	uint32_t mblk_height = 0;
+	uint32_t full_vp_width_blk_aligned = 0;
+	uint32_t full_vp_height_blk_aligned = 0;
+	uint32_t mall_alloc_width_blk_aligned = 0;
+	uint32_t mall_alloc_height_blk_aligned = 0;
+	uint32_t full_vp_height = 0;
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
 
 		// Find the phantom pipes
-		if (pipe->stream && pipe->plane_state && !pipe->top_pipe &&
+		if (pipe->stream && pipe->plane_state && !pipe->top_pipe && !pipe->prev_odm_pipe &&
 				pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) {
-			bytes_per_pixel = pipe->plane_state->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4;
-			mall_region_pixels = pipe->stream->timing.h_addressable * pipe->stream->timing.v_addressable;
+			struct pipe_ctx *main_pipe = NULL;
 
-			// For bytes required in MALL, calculate based on number of MBlks required
-			num_mblks = (mall_region_pixels * bytes_per_pixel +
-					DCN3_2_MALL_MBLK_SIZE_BYTES - 1) / DCN3_2_MALL_MBLK_SIZE_BYTES;
+			/* Get full viewport height from main pipe (required for MBLK calculation) */
+			for (j = 0; j < dc->res_pool->pipe_count; j++) {
+				main_pipe = &context->res_ctx.pipe_ctx[j];
+				if (main_pipe->stream == pipe->stream->mall_stream_config.paired_stream) {
+					full_vp_height = main_pipe->plane_res.scl_data.viewport.height;
+					break;
+				}
+			}
+
+			bytes_per_pixel = pipe->plane_state->format >= SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 ? 8 : 4;
+			mblk_width = DCN3_2_MBLK_WIDTH;
+			mblk_height = bytes_per_pixel == 4 ? DCN3_2_MBLK_HEIGHT_4BPE : DCN3_2_MBLK_HEIGHT_8BPE;
+
+			/* full_vp_width_blk_aligned = FLOOR(vp_x_start + full_vp_width + blk_width - 1, blk_width) -
+			 * FLOOR(vp_x_start, blk_width)
+			 */
+			full_vp_width_blk_aligned = ((pipe->plane_res.scl_data.viewport.x +
+					pipe->plane_res.scl_data.viewport.width + mblk_width - 1) / mblk_width * mblk_width) +
+					(pipe->plane_res.scl_data.viewport.x / mblk_width * mblk_width);
+
+			/* full_vp_height_blk_aligned = FLOOR(vp_y_start + full_vp_height + blk_height - 1, blk_height) -
+			 * FLOOR(vp_y_start, blk_height)
+			 */
+			full_vp_height_blk_aligned = ((pipe->plane_res.scl_data.viewport.y +
+					full_vp_height + mblk_height - 1) / mblk_height * mblk_height) +
+					(pipe->plane_res.scl_data.viewport.y / mblk_height * mblk_height);
+
+			/* mall_alloc_width_blk_aligned_l/c = full_vp_width_blk_aligned_l/c */
+			mall_alloc_width_blk_aligned = full_vp_width_blk_aligned;
+
+			/* mall_alloc_height_blk_aligned_l/c = CEILING(sub_vp_height_l/c - 1, blk_height_l/c) + blk_height_l/c */
+			mall_alloc_height_blk_aligned = (pipe->stream->timing.v_addressable - 1 + mblk_height - 1) /
+					mblk_height * mblk_height + mblk_height;
+
+			/* full_mblk_width_ub_l/c = mall_alloc_width_blk_aligned_l/c;
+			 * full_mblk_height_ub_l/c = mall_alloc_height_blk_aligned_l/c;
+			 * num_mblk_l/c = (full_mblk_width_ub_l/c / mblk_width_l/c) * (full_mblk_height_ub_l/c / mblk_height_l/c);
+			 * (Should be divisible, but round up if not)
+			 */
+			num_mblks = ((mall_alloc_width_blk_aligned + mblk_width - 1) / mblk_width) *
+					((mall_alloc_height_blk_aligned + mblk_height - 1) / mblk_height);
 			bytes_in_mall = num_mblks * DCN3_2_MALL_MBLK_SIZE_BYTES;
 			// cache lines used is total bytes / cache_line size. Add +2 for worst case alignment
 			// (MALL is 64-byte aligned)
@@ -144,7 +187,7 @@ bool dcn32_all_pipes_have_stream_and_plane(struct dc *dc,
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
 
 		if (!pipe->stream)
-			continue;
+			return false;
 
 		if (!pipe->plane_state)
 			return false;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
index 8157e40d2c7e..7309eed33a61 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
@@ -868,10 +868,11 @@ static const struct dc_debug_options debug_defaults_drv = {
 		}
 	},
 	.use_max_lb = true,
-	.force_disable_subvp = true,
+	.force_disable_subvp = false,
 	.exit_idle_opt_for_cursor_updates = true,
 	.enable_single_display_2to1_odm_policy = true,
 	.enable_dp_dig_pixel_rate_div_policy = 1,
+	.allow_sw_cursor_fallback = false,
 };
 
 static const struct dc_debug_options debug_defaults_diags = {
@@ -1651,7 +1652,8 @@ static bool dcn321_resource_construct(
 	dc->caps.max_downscale_ratio = 600;
 	dc->caps.i2c_speed_in_khz = 100;
 	dc->caps.i2c_speed_in_khz_hdcp = 100; /*1.4 w/a applied by default*/
-	dc->caps.max_cursor_size = 256;
+	/* TODO: Bring max cursor size back to 256 after subvp cursor corruption is fixed*/
+	dc->caps.max_cursor_size = 64;
 	dc->caps.min_horizontal_blanking_period = 80;
 	dc->caps.dmdata_alloc_size = 2048;
 	dc->caps.mall_size_per_mem_channel = 0;
@@ -1662,8 +1664,9 @@ static bool dcn321_resource_construct(
 	dc->caps.max_cab_allocation_bytes = 33554432; // 32MB = 1024 * 1024 * 32
 	dc->caps.subvp_fw_processing_delay_us = 15;
 	dc->caps.subvp_prefetch_end_to_mall_start_us = 15;
+	dc->caps.subvp_swath_height_margin_lines = 16;
 	dc->caps.subvp_pstate_allow_width_us = 20;
-
+	dc->caps.subvp_vertical_int_margin_us = 30;
 	dc->caps.max_slave_planes = 1;
 	dc->caps.max_slave_yuv_planes = 1;
 	dc->caps.max_slave_rgb_planes = 1;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 359f6e9a1da0..cb81ed2fbd53 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -61,7 +61,6 @@ CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags)
@@ -71,6 +70,9 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(fram
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/display_mode_vba_314.o := $(dml_ccflags) $(frame_warn_flag)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/display_rq_dlg_calc_314.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/dcn314_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/dcn30_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn32/dcn32_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn32/display_mode_vba_32.o := $(dml_ccflags) $(frame_warn_flag)
@@ -82,7 +84,6 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn301/dcn301_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn302/dcn302_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn303/dcn303_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dsc/rc_calc_fpu.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/calcs/dcn_calcs.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/calcs/dcn_calc_auto.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/calcs/dcn_calc_math.o := $(dml_ccflags) -Wno-tautological-compare
@@ -124,6 +125,7 @@ DML += dcn20/display_rq_dlg_calc_20v2.o dcn20/display_mode_vba_20v2.o
 DML += dcn21/display_rq_dlg_calc_21.o dcn21/display_mode_vba_21.o
 DML += dcn30/dcn30_fpu.o dcn30/display_mode_vba_30.o dcn30/display_rq_dlg_calc_30.o
 DML += dcn31/display_mode_vba_31.o dcn31/display_rq_dlg_calc_31.o
+DML += dcn314/display_mode_vba_314.o dcn314/display_rq_dlg_calc_314.o
 DML += dcn32/display_mode_vba_32.o dcn32/display_rq_dlg_calc_32.o dcn32/display_mode_vba_util_32.o
 DML += dcn31/dcn31_fpu.o
 DML += dcn32/dcn32_fpu.o
@@ -131,6 +133,7 @@ DML += dcn321/dcn321_fpu.o
 DML += dcn301/dcn301_fpu.o
 DML += dcn302/dcn302_fpu.o
 DML += dcn303/dcn303_fpu.o
+DML += dcn314/dcn314_fpu.o
 DML += dsc/rc_calc_fpu.o
 DML += calcs/dcn_calcs.o calcs/dcn_calc_math.o calcs/dcn_calc_auto.o
 endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index ca44df4fca74..d34e0f1314d9 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -30,6 +30,7 @@
 #include "dchubbub.h"
 #include "dcn20/dcn20_resource.h"
 #include "dcn21/dcn21_resource.h"
+#include "clk_mgr/dcn21/rn_clk_mgr.h"
 
 #include "dcn20_fpu.h"
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
index 876b321b30ca..1cb858dd6ea0 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
@@ -6610,8 +6610,7 @@ static double CalculateUrgentLatency(
 	return ret;
 }
 
-
-static void UseMinimumDCFCLK(
+static noinline_for_stack void UseMinimumDCFCLK(
 		struct display_mode_lib *mode_lib,
 		int MaxInterDCNTileRepeaters,
 		int MaxPrefetchMode,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c
index 7ef66e511ec8..d211cf6d234c 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c
@@ -26,6 +26,7 @@
 #include "clk_mgr.h"
 #include "dcn20/dcn20_resource.h"
 #include "dcn301/dcn301_resource.h"
+#include "clk_mgr/dcn301/vg_clk_mgr.h"
 
 #include "dml/dcn20/dcn20_fpu.h"
 #include "dcn301_fpu.h"
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
index e36cfa5985ea..fa7b0291ce4d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
@@ -25,6 +25,9 @@
 
 #include "resource.h"
 #include "clk_mgr.h"
+#include "dcn31/dcn31_resource.h"
+#include "dcn315/dcn315_resource.h"
+#include "dcn316/dcn316_resource.h"
 
 #include "dml/dcn20/dcn20_fpu.h"
 #include "dcn31_fpu.h"
@@ -114,7 +117,7 @@ struct _vcs_dpi_ip_params_st dcn3_1_ip = {
 	.dcc_supported = true,
 };
 
-struct _vcs_dpi_soc_bounding_box_st dcn3_1_soc = {
+static struct _vcs_dpi_soc_bounding_box_st dcn3_1_soc = {
 		/*TODO: correct dispclk/dppclk voltage level determination*/
 	.clock_limits = {
 		{
@@ -259,7 +262,7 @@ struct _vcs_dpi_ip_params_st dcn3_15_ip = {
 	.dcc_supported = true,
 };
 
-struct _vcs_dpi_soc_bounding_box_st dcn3_15_soc = {
+static struct _vcs_dpi_soc_bounding_box_st dcn3_15_soc = {
 	.sr_exit_time_us = 9.0,
 	.sr_enter_plus_exit_time_us = 11.0,
 	.sr_exit_z8_time_us = 50.0,
@@ -288,6 +291,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_15_soc = {
 	.do_urgent_latency_adjustment = false,
 	.urgent_latency_adjustment_fabric_clock_component_us = 0,
 	.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
+	.num_chans = 4,
 };
 
 struct _vcs_dpi_ip_params_st dcn3_16_ip = {
@@ -355,7 +359,7 @@ struct _vcs_dpi_ip_params_st dcn3_16_ip = {
 	.dcc_supported = true,
 };
 
-struct _vcs_dpi_soc_bounding_box_st dcn3_16_soc = {
+static struct _vcs_dpi_soc_bounding_box_st dcn3_16_soc = {
 		/*TODO: correct dispclk/dppclk voltage level determination*/
 	.clock_limits = {
 		{
@@ -677,7 +681,11 @@ void dcn315_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
 
 	dcn3_15_ip.max_num_otg = dc->res_pool->res_cap->num_timing_generator;
 	dcn3_15_ip.max_num_dpp = dc->res_pool->pipe_count;
-	dcn3_15_soc.num_chans = bw_params->num_channels;
+
+	if (bw_params->num_channels > 0)
+		dcn3_15_soc.num_chans = bw_params->num_channels;
+	if (bw_params->dram_channel_width_bytes > 0)
+		dcn3_15_soc.dram_channel_width_bytes = bw_params->dram_channel_width_bytes;
 
 	ASSERT(clk_table->num_entries);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
index 3fab19134480..8ca66f1644dc 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
@@ -26,7 +26,7 @@
 #include "dc.h"
 #include "dc_link.h"
 #include "../display_mode_lib.h"
-#include "dml/dcn30/display_mode_vba_30.h"
+#include "../dcn30/display_mode_vba_30.h"
 #include "display_mode_vba_31.h"
 #include "../dml_inline_defs.h"
 
@@ -251,33 +251,13 @@ static void CalculateRowBandwidth(
 
 static void CalculateFlipSchedule(
 		struct display_mode_lib *mode_lib,
+		unsigned int k,
 		double HostVMInefficiencyFactor,
 		double UrgentExtraLatency,
 		double UrgentLatency,
-		unsigned int GPUVMMaxPageTableLevels,
-		bool HostVMEnable,
-		unsigned int HostVMMaxNonCachedPageTableLevels,
-		bool GPUVMEnable,
-		double HostVMMinPageSize,
 		double PDEAndMetaPTEBytesPerFrame,
 		double MetaRowBytes,
-		double DPTEBytesPerRow,
-		double BandwidthAvailableForImmediateFlip,
-		unsigned int TotImmediateFlipBytes,
-		enum source_format_class SourcePixelFormat,
-		double LineTime,
-		double VRatio,
-		double VRatioChroma,
-		double Tno_bw,
-		bool DCCEnable,
-		unsigned int dpte_row_height,
-		unsigned int meta_row_height,
-		unsigned int dpte_row_height_chroma,
-		unsigned int meta_row_height_chroma,
-		double *DestinationLinesToRequestVMInImmediateFlip,
-		double *DestinationLinesToRequestRowInImmediateFlip,
-		double *final_flip_bw,
-		bool *ImmediateFlipSupportedForPipe);
+		double DPTEBytesPerRow);
 static double CalculateWriteBackDelay(
 		enum source_format_class WritebackPixelFormat,
 		double WritebackHRatio,
@@ -311,64 +291,28 @@ static void CalculateVupdateAndDynamicMetadataParameters(
 static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 		struct display_mode_lib *mode_lib,
 		unsigned int PrefetchMode,
-		unsigned int NumberOfActivePlanes,
-		unsigned int MaxLineBufferLines,
-		unsigned int LineBufferSize,
-		unsigned int WritebackInterfaceBufferSize,
 		double DCFCLK,
 		double ReturnBW,
-		bool SynchronizedVBlank,
-		unsigned int dpte_group_bytes[],
-		unsigned int MetaChunkSize,
 		double UrgentLatency,
 		double ExtraLatency,
-		double WritebackLatency,
-		double WritebackChunkSize,
 		double SOCCLK,
-		double DRAMClockChangeLatency,
-		double SRExitTime,
-		double SREnterPlusExitTime,
-		double SRExitZ8Time,
-		double SREnterPlusExitZ8Time,
 		double DCFCLKDeepSleep,
 		unsigned int DETBufferSizeY[],
 		unsigned int DETBufferSizeC[],
 		unsigned int SwathHeightY[],
 		unsigned int SwathHeightC[],
-		unsigned int LBBitPerPixel[],
 		double SwathWidthY[],
 		double SwathWidthC[],
-		double HRatio[],
-		double HRatioChroma[],
-		unsigned int vtaps[],
-		unsigned int VTAPsChroma[],
-		double VRatio[],
-		double VRatioChroma[],
-		unsigned int HTotal[],
-		double PixelClock[],
-		unsigned int BlendingAndTiming[],
 		unsigned int DPPPerPlane[],
 		double BytePerPixelDETY[],
 		double BytePerPixelDETC[],
-		double DSTXAfterScaler[],
-		double DSTYAfterScaler[],
-		bool WritebackEnable[],
-		enum source_format_class WritebackPixelFormat[],
-		double WritebackDestinationWidth[],
-		double WritebackDestinationHeight[],
-		double WritebackSourceHeight[],
 		bool UnboundedRequestEnabled,
 		int unsigned CompressedBufferSizeInkByte,
 		enum clock_change_support *DRAMClockChangeSupport,
-		double *UrgentWatermark,
-		double *WritebackUrgentWatermark,
-		double *DRAMClockChangeWatermark,
-		double *WritebackDRAMClockChangeWatermark,
 		double *StutterExitWatermark,
 		double *StutterEnterPlusExitWatermark,
 		double *Z8StutterExitWatermark,
-		double *Z8StutterEnterPlusExitWatermark,
-		double *MinActiveDRAMClockChangeLatencySupported);
+		double *Z8StutterEnterPlusExitWatermark);
 
 static void CalculateDCFCLKDeepSleep(
 		struct display_mode_lib *mode_lib,
@@ -2904,33 +2848,13 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 			for (k = 0; k < v->NumberOfActivePlanes; ++k) {
 				CalculateFlipSchedule(
 						mode_lib,
+						k,
 						HostVMInefficiencyFactor,
 						v->UrgentExtraLatency,
 						v->UrgentLatency,
-						v->GPUVMMaxPageTableLevels,
-						v->HostVMEnable,
-						v->HostVMMaxNonCachedPageTableLevels,
-						v->GPUVMEnable,
-						v->HostVMMinPageSize,
 						v->PDEAndMetaPTEBytesFrame[k],
 						v->MetaRowByte[k],
-						v->PixelPTEBytesPerRow[k],
-						v->BandwidthAvailableForImmediateFlip,
-						v->TotImmediateFlipBytes,
-						v->SourcePixelFormat[k],
-						v->HTotal[k] / v->PixelClock[k],
-						v->VRatio[k],
-						v->VRatioChroma[k],
-						v->Tno_bw[k],
-						v->DCCEnable[k],
-						v->dpte_row_height[k],
-						v->meta_row_height[k],
-						v->dpte_row_height_chroma[k],
-						v->meta_row_height_chroma[k],
-						&v->DestinationLinesToRequestVMInImmediateFlip[k],
-						&v->DestinationLinesToRequestRowInImmediateFlip[k],
-						&v->final_flip_bw[k],
-						&v->ImmediateFlipSupportedForPipe[k]);
+						v->PixelPTEBytesPerRow[k]);
 			}
 
 			v->total_dcn_read_bw_with_flip = 0.0;
@@ -3017,64 +2941,28 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 		CalculateWatermarksAndDRAMSpeedChangeSupport(
 				mode_lib,
 				PrefetchMode,
-				v->NumberOfActivePlanes,
-				v->MaxLineBufferLines,
-				v->LineBufferSize,
-				v->WritebackInterfaceBufferSize,
 				v->DCFCLK,
 				v->ReturnBW,
-				v->SynchronizedVBlank,
-				v->dpte_group_bytes,
-				v->MetaChunkSize,
 				v->UrgentLatency,
 				v->UrgentExtraLatency,
-				v->WritebackLatency,
-				v->WritebackChunkSize,
 				v->SOCCLK,
-				v->DRAMClockChangeLatency,
-				v->SRExitTime,
-				v->SREnterPlusExitTime,
-				v->SRExitZ8Time,
-				v->SREnterPlusExitZ8Time,
 				v->DCFCLKDeepSleep,
 				v->DETBufferSizeY,
 				v->DETBufferSizeC,
 				v->SwathHeightY,
 				v->SwathHeightC,
-				v->LBBitPerPixel,
 				v->SwathWidthY,
 				v->SwathWidthC,
-				v->HRatio,
-				v->HRatioChroma,
-				v->vtaps,
-				v->VTAPsChroma,
-				v->VRatio,
-				v->VRatioChroma,
-				v->HTotal,
-				v->PixelClock,
-				v->BlendingAndTiming,
 				v->DPPPerPlane,
 				v->BytePerPixelDETY,
 				v->BytePerPixelDETC,
-				v->DSTXAfterScaler,
-				v->DSTYAfterScaler,
-				v->WritebackEnable,
-				v->WritebackPixelFormat,
-				v->WritebackDestinationWidth,
-				v->WritebackDestinationHeight,
-				v->WritebackSourceHeight,
 				v->UnboundedRequestEnabled,
 				v->CompressedBufferSizeInkByte,
 				&DRAMClockChangeSupport,
-				&v->UrgentWatermark,
-				&v->WritebackUrgentWatermark,
-				&v->DRAMClockChangeWatermark,
-				&v->WritebackDRAMClockChangeWatermark,
 				&v->StutterExitWatermark,
 				&v->StutterEnterPlusExitWatermark,
 				&v->Z8StutterExitWatermark,
-				&v->Z8StutterEnterPlusExitWatermark,
-				&v->MinActiveDRAMClockChangeLatencySupported);
+				&v->Z8StutterEnterPlusExitWatermark);
 
 		for (k = 0; k < v->NumberOfActivePlanes; ++k) {
 			if (v->WritebackEnable[k] == true) {
@@ -3598,61 +3486,43 @@ static void CalculateRowBandwidth(
 
 static void CalculateFlipSchedule(
 		struct display_mode_lib *mode_lib,
+		unsigned int k,
 		double HostVMInefficiencyFactor,
 		double UrgentExtraLatency,
 		double UrgentLatency,
-		unsigned int GPUVMMaxPageTableLevels,
-		bool HostVMEnable,
-		unsigned int HostVMMaxNonCachedPageTableLevels,
-		bool GPUVMEnable,
-		double HostVMMinPageSize,
 		double PDEAndMetaPTEBytesPerFrame,
 		double MetaRowBytes,
-		double DPTEBytesPerRow,
-		double BandwidthAvailableForImmediateFlip,
-		unsigned int TotImmediateFlipBytes,
-		enum source_format_class SourcePixelFormat,
-		double LineTime,
-		double VRatio,
-		double VRatioChroma,
-		double Tno_bw,
-		bool DCCEnable,
-		unsigned int dpte_row_height,
-		unsigned int meta_row_height,
-		unsigned int dpte_row_height_chroma,
-		unsigned int meta_row_height_chroma,
-		double *DestinationLinesToRequestVMInImmediateFlip,
-		double *DestinationLinesToRequestRowInImmediateFlip,
-		double *final_flip_bw,
-		bool *ImmediateFlipSupportedForPipe)
+		double DPTEBytesPerRow)
 {
+	struct vba_vars_st *v = &mode_lib->vba;
 	double min_row_time = 0.0;
 	unsigned int HostVMDynamicLevelsTrips;
 	double TimeForFetchingMetaPTEImmediateFlip;
 	double TimeForFetchingRowInVBlankImmediateFlip;
 	double ImmediateFlipBW;
+	double LineTime = v->HTotal[k] / v->PixelClock[k];
 
-	if (GPUVMEnable == true && HostVMEnable == true) {
-		HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels;
+	if (v->GPUVMEnable == true && v->HostVMEnable == true) {
+		HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels;
 	} else {
 		HostVMDynamicLevelsTrips = 0;
 	}
 
-	if (GPUVMEnable == true || DCCEnable == true) {
-		ImmediateFlipBW = (PDEAndMetaPTEBytesPerFrame + MetaRowBytes + DPTEBytesPerRow) * BandwidthAvailableForImmediateFlip / TotImmediateFlipBytes;
+	if (v->GPUVMEnable == true || v->DCCEnable[k] == true) {
+		ImmediateFlipBW = (PDEAndMetaPTEBytesPerFrame + MetaRowBytes + DPTEBytesPerRow) * v->BandwidthAvailableForImmediateFlip / v->TotImmediateFlipBytes;
 	}
 
-	if (GPUVMEnable == true) {
+	if (v->GPUVMEnable == true) {
 		TimeForFetchingMetaPTEImmediateFlip = dml_max3(
-				Tno_bw + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / ImmediateFlipBW,
-				UrgentExtraLatency + UrgentLatency * (GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1),
+				v->Tno_bw[k] + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / ImmediateFlipBW,
+				UrgentExtraLatency + UrgentLatency * (v->GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1),
 				LineTime / 4.0);
 	} else {
 		TimeForFetchingMetaPTEImmediateFlip = 0;
 	}
 
-	*DestinationLinesToRequestVMInImmediateFlip = dml_ceil(4.0 * (TimeForFetchingMetaPTEImmediateFlip / LineTime), 1) / 4.0;
-	if ((GPUVMEnable == true || DCCEnable == true)) {
+	v->DestinationLinesToRequestVMInImmediateFlip[k] = dml_ceil(4.0 * (TimeForFetchingMetaPTEImmediateFlip / LineTime), 1) / 4.0;
+	if ((v->GPUVMEnable == true || v->DCCEnable[k] == true)) {
 		TimeForFetchingRowInVBlankImmediateFlip = dml_max3(
 				(MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / ImmediateFlipBW,
 				UrgentLatency * (HostVMDynamicLevelsTrips + 1),
@@ -3661,54 +3531,54 @@ static void CalculateFlipSchedule(
 		TimeForFetchingRowInVBlankImmediateFlip = 0;
 	}
 
-	*DestinationLinesToRequestRowInImmediateFlip = dml_ceil(4.0 * (TimeForFetchingRowInVBlankImmediateFlip / LineTime), 1) / 4.0;
+	v->DestinationLinesToRequestRowInImmediateFlip[k] = dml_ceil(4.0 * (TimeForFetchingRowInVBlankImmediateFlip / LineTime), 1) / 4.0;
 
-	if (GPUVMEnable == true) {
-		*final_flip_bw = dml_max(
-				PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / (*DestinationLinesToRequestVMInImmediateFlip * LineTime),
-				(MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (*DestinationLinesToRequestRowInImmediateFlip * LineTime));
-	} else if ((GPUVMEnable == true || DCCEnable == true)) {
-		*final_flip_bw = (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (*DestinationLinesToRequestRowInImmediateFlip * LineTime);
+	if (v->GPUVMEnable == true) {
+		v->final_flip_bw[k] = dml_max(
+				PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / (v->DestinationLinesToRequestVMInImmediateFlip[k] * LineTime),
+				(MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (v->DestinationLinesToRequestRowInImmediateFlip[k] * LineTime));
+	} else if ((v->GPUVMEnable == true || v->DCCEnable[k] == true)) {
+		v->final_flip_bw[k] = (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (v->DestinationLinesToRequestRowInImmediateFlip[k] * LineTime);
 	} else {
-		*final_flip_bw = 0;
+		v->final_flip_bw[k] = 0;
 	}
 
-	if (SourcePixelFormat == dm_420_8 || SourcePixelFormat == dm_420_10 || SourcePixelFormat == dm_rgbe_alpha) {
-		if (GPUVMEnable == true && DCCEnable != true) {
-			min_row_time = dml_min(dpte_row_height * LineTime / VRatio, dpte_row_height_chroma * LineTime / VRatioChroma);
-		} else if (GPUVMEnable != true && DCCEnable == true) {
-			min_row_time = dml_min(meta_row_height * LineTime / VRatio, meta_row_height_chroma * LineTime / VRatioChroma);
+	if (v->SourcePixelFormat[k] == dm_420_8 || v->SourcePixelFormat[k] == dm_420_10 || v->SourcePixelFormat[k] == dm_rgbe_alpha) {
+		if (v->GPUVMEnable == true && v->DCCEnable[k] != true) {
+			min_row_time = dml_min(v->dpte_row_height[k] * LineTime / v->VRatio[k], v->dpte_row_height_chroma[k] * LineTime / v->VRatioChroma[k]);
+		} else if (v->GPUVMEnable != true && v->DCCEnable[k] == true) {
+			min_row_time = dml_min(v->meta_row_height[k] * LineTime / v->VRatio[k], v->meta_row_height_chroma[k] * LineTime / v->VRatioChroma[k]);
 		} else {
 			min_row_time = dml_min4(
-					dpte_row_height * LineTime / VRatio,
-					meta_row_height * LineTime / VRatio,
-					dpte_row_height_chroma * LineTime / VRatioChroma,
-					meta_row_height_chroma * LineTime / VRatioChroma);
+					v->dpte_row_height[k] * LineTime / v->VRatio[k],
+					v->meta_row_height[k] * LineTime / v->VRatio[k],
+					v->dpte_row_height_chroma[k] * LineTime / v->VRatioChroma[k],
+					v->meta_row_height_chroma[k] * LineTime / v->VRatioChroma[k]);
 		}
 	} else {
-		if (GPUVMEnable == true && DCCEnable != true) {
-			min_row_time = dpte_row_height * LineTime / VRatio;
-		} else if (GPUVMEnable != true && DCCEnable == true) {
-			min_row_time = meta_row_height * LineTime / VRatio;
+		if (v->GPUVMEnable == true && v->DCCEnable[k] != true) {
+			min_row_time = v->dpte_row_height[k] * LineTime / v->VRatio[k];
+		} else if (v->GPUVMEnable != true && v->DCCEnable[k] == true) {
+			min_row_time = v->meta_row_height[k] * LineTime / v->VRatio[k];
 		} else {
-			min_row_time = dml_min(dpte_row_height * LineTime / VRatio, meta_row_height * LineTime / VRatio);
+			min_row_time = dml_min(v->dpte_row_height[k] * LineTime / v->VRatio[k], v->meta_row_height[k] * LineTime / v->VRatio[k]);
 		}
 	}
 
-	if (*DestinationLinesToRequestVMInImmediateFlip >= 32 || *DestinationLinesToRequestRowInImmediateFlip >= 16
+	if (v->DestinationLinesToRequestVMInImmediateFlip[k] >= 32 || v->DestinationLinesToRequestRowInImmediateFlip[k] >= 16
 			|| TimeForFetchingMetaPTEImmediateFlip + 2 * TimeForFetchingRowInVBlankImmediateFlip > min_row_time) {
-		*ImmediateFlipSupportedForPipe = false;
+		v->ImmediateFlipSupportedForPipe[k] = false;
 	} else {
-		*ImmediateFlipSupportedForPipe = true;
+		v->ImmediateFlipSupportedForPipe[k] = true;
 	}
 
 #ifdef __DML_VBA_DEBUG__
-	dml_print("DML::%s: DestinationLinesToRequestVMInImmediateFlip = %f\n", __func__, *DestinationLinesToRequestVMInImmediateFlip);
-	dml_print("DML::%s: DestinationLinesToRequestRowInImmediateFlip = %f\n", __func__, *DestinationLinesToRequestRowInImmediateFlip);
+	dml_print("DML::%s: DestinationLinesToRequestVMInImmediateFlip = %f\n", __func__, v->DestinationLinesToRequestVMInImmediateFlip[k]);
+	dml_print("DML::%s: DestinationLinesToRequestRowInImmediateFlip = %f\n", __func__, v->DestinationLinesToRequestRowInImmediateFlip[k]);
 	dml_print("DML::%s: TimeForFetchingMetaPTEImmediateFlip = %f\n", __func__, TimeForFetchingMetaPTEImmediateFlip);
 	dml_print("DML::%s: TimeForFetchingRowInVBlankImmediateFlip = %f\n", __func__, TimeForFetchingRowInVBlankImmediateFlip);
 	dml_print("DML::%s: min_row_time = %f\n", __func__, min_row_time);
-	dml_print("DML::%s: ImmediateFlipSupportedForPipe = %d\n", __func__, *ImmediateFlipSupportedForPipe);
+	dml_print("DML::%s: ImmediateFlipSupportedForPipe = %d\n", __func__, v->ImmediateFlipSupportedForPipe[k]);
 #endif
 
 }
@@ -5300,33 +5170,13 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					for (k = 0; k < v->NumberOfActivePlanes; k++) {
 						CalculateFlipSchedule(
 								mode_lib,
+								k,
 								HostVMInefficiencyFactor,
 								v->ExtraLatency,
 								v->UrgLatency[i],
-								v->GPUVMMaxPageTableLevels,
-								v->HostVMEnable,
-								v->HostVMMaxNonCachedPageTableLevels,
-								v->GPUVMEnable,
-								v->HostVMMinPageSize,
 								v->PDEAndMetaPTEBytesPerFrame[i][j][k],
 								v->MetaRowBytes[i][j][k],
-								v->DPTEBytesPerRow[i][j][k],
-								v->BandwidthAvailableForImmediateFlip,
-								v->TotImmediateFlipBytes,
-								v->SourcePixelFormat[k],
-								v->HTotal[k] / v->PixelClock[k],
-								v->VRatio[k],
-								v->VRatioChroma[k],
-								v->Tno_bw[k],
-								v->DCCEnable[k],
-								v->dpte_row_height[k],
-								v->meta_row_height[k],
-								v->dpte_row_height_chroma[k],
-								v->meta_row_height_chroma[k],
-								&v->DestinationLinesToRequestVMInImmediateFlip[k],
-								&v->DestinationLinesToRequestRowInImmediateFlip[k],
-								&v->final_flip_bw[k],
-								&v->ImmediateFlipSupportedForPipe[k]);
+								v->DPTEBytesPerRow[i][j][k]);
 					}
 					v->total_dcn_read_bw_with_flip = 0.0;
 					for (k = 0; k < v->NumberOfActivePlanes; k++) {
@@ -5384,64 +5234,28 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 			CalculateWatermarksAndDRAMSpeedChangeSupport(
 					mode_lib,
 					v->PrefetchModePerState[i][j],
-					v->NumberOfActivePlanes,
-					v->MaxLineBufferLines,
-					v->LineBufferSize,
-					v->WritebackInterfaceBufferSize,
 					v->DCFCLKState[i][j],
 					v->ReturnBWPerState[i][j],
-					v->SynchronizedVBlank,
-					v->dpte_group_bytes,
-					v->MetaChunkSize,
 					v->UrgLatency[i],
 					v->ExtraLatency,
-					v->WritebackLatency,
-					v->WritebackChunkSize,
 					v->SOCCLKPerState[i],
-					v->DRAMClockChangeLatency,
-					v->SRExitTime,
-					v->SREnterPlusExitTime,
-					v->SRExitZ8Time,
-					v->SREnterPlusExitZ8Time,
 					v->ProjectedDCFCLKDeepSleep[i][j],
 					v->DETBufferSizeYThisState,
 					v->DETBufferSizeCThisState,
 					v->SwathHeightYThisState,
 					v->SwathHeightCThisState,
-					v->LBBitPerPixel,
 					v->SwathWidthYThisState,
 					v->SwathWidthCThisState,
-					v->HRatio,
-					v->HRatioChroma,
-					v->vtaps,
-					v->VTAPsChroma,
-					v->VRatio,
-					v->VRatioChroma,
-					v->HTotal,
-					v->PixelClock,
-					v->BlendingAndTiming,
 					v->NoOfDPPThisState,
 					v->BytePerPixelInDETY,
 					v->BytePerPixelInDETC,
-					v->DSTXAfterScaler,
-					v->DSTYAfterScaler,
-					v->WritebackEnable,
-					v->WritebackPixelFormat,
-					v->WritebackDestinationWidth,
-					v->WritebackDestinationHeight,
-					v->WritebackSourceHeight,
 					UnboundedRequestEnabledThisState,
 					CompressedBufferSizeInkByteThisState,
 					&v->DRAMClockChangeSupport[i][j],
-					&v->UrgentWatermark,
-					&v->WritebackUrgentWatermark,
-					&v->DRAMClockChangeWatermark,
-					&v->WritebackDRAMClockChangeWatermark,
-					&dummy,
 					&dummy,
 					&dummy,
 					&dummy,
-					&v->MinActiveDRAMClockChangeLatencySupported);
+					&dummy);
 		}
 	}
 
@@ -5566,64 +5380,28 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 		struct display_mode_lib *mode_lib,
 		unsigned int PrefetchMode,
-		unsigned int NumberOfActivePlanes,
-		unsigned int MaxLineBufferLines,
-		unsigned int LineBufferSize,
-		unsigned int WritebackInterfaceBufferSize,
 		double DCFCLK,
 		double ReturnBW,
-		bool SynchronizedVBlank,
-		unsigned int dpte_group_bytes[],
-		unsigned int MetaChunkSize,
 		double UrgentLatency,
 		double ExtraLatency,
-		double WritebackLatency,
-		double WritebackChunkSize,
 		double SOCCLK,
-		double DRAMClockChangeLatency,
-		double SRExitTime,
-		double SREnterPlusExitTime,
-		double SRExitZ8Time,
-		double SREnterPlusExitZ8Time,
 		double DCFCLKDeepSleep,
 		unsigned int DETBufferSizeY[],
 		unsigned int DETBufferSizeC[],
 		unsigned int SwathHeightY[],
 		unsigned int SwathHeightC[],
-		unsigned int LBBitPerPixel[],
 		double SwathWidthY[],
 		double SwathWidthC[],
-		double HRatio[],
-		double HRatioChroma[],
-		unsigned int vtaps[],
-		unsigned int VTAPsChroma[],
-		double VRatio[],
-		double VRatioChroma[],
-		unsigned int HTotal[],
-		double PixelClock[],
-		unsigned int BlendingAndTiming[],
 		unsigned int DPPPerPlane[],
 		double BytePerPixelDETY[],
 		double BytePerPixelDETC[],
-		double DSTXAfterScaler[],
-		double DSTYAfterScaler[],
-		bool WritebackEnable[],
-		enum source_format_class WritebackPixelFormat[],
-		double WritebackDestinationWidth[],
-		double WritebackDestinationHeight[],
-		double WritebackSourceHeight[],
 		bool UnboundedRequestEnabled,
 		int unsigned CompressedBufferSizeInkByte,
 		enum clock_change_support *DRAMClockChangeSupport,
-		double *UrgentWatermark,
-		double *WritebackUrgentWatermark,
-		double *DRAMClockChangeWatermark,
-		double *WritebackDRAMClockChangeWatermark,
 		double *StutterExitWatermark,
 		double *StutterEnterPlusExitWatermark,
 		double *Z8StutterExitWatermark,
-		double *Z8StutterEnterPlusExitWatermark,
-		double *MinActiveDRAMClockChangeLatencySupported)
+		double *Z8StutterEnterPlusExitWatermark)
 {
 	struct vba_vars_st *v = &mode_lib->vba;
 	double EffectiveLBLatencyHidingY;
@@ -5643,103 +5421,103 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 	double TotalPixelBW = 0.0;
 	int k, j;
 
-	*UrgentWatermark = UrgentLatency + ExtraLatency;
+	v->UrgentWatermark = UrgentLatency + ExtraLatency;
 
 #ifdef __DML_VBA_DEBUG__
 	dml_print("DML::%s: UrgentLatency = %f\n", __func__, UrgentLatency);
 	dml_print("DML::%s: ExtraLatency = %f\n", __func__, ExtraLatency);
-	dml_print("DML::%s: UrgentWatermark = %f\n", __func__, *UrgentWatermark);
+	dml_print("DML::%s: UrgentWatermark = %f\n", __func__, v->UrgentWatermark);
 #endif
 
-	*DRAMClockChangeWatermark = DRAMClockChangeLatency + *UrgentWatermark;
+	v->DRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->UrgentWatermark;
 
 #ifdef __DML_VBA_DEBUG__
-	dml_print("DML::%s: DRAMClockChangeLatency = %f\n", __func__, DRAMClockChangeLatency);
-	dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, *DRAMClockChangeWatermark);
+	dml_print("DML::%s: v->DRAMClockChangeLatency = %f\n", __func__, v->DRAMClockChangeLatency);
+	dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, v->DRAMClockChangeWatermark);
 #endif
 
 	v->TotalActiveWriteback = 0;
-	for (k = 0; k < NumberOfActivePlanes; ++k) {
-		if (WritebackEnable[k] == true) {
+	for (k = 0; k < v->NumberOfActivePlanes; ++k) {
+		if (v->WritebackEnable[k] == true) {
 			v->TotalActiveWriteback = v->TotalActiveWriteback + 1;
 		}
 	}
 
 	if (v->TotalActiveWriteback <= 1) {
-		*WritebackUrgentWatermark = WritebackLatency;
+		v->WritebackUrgentWatermark = v->WritebackLatency;
 	} else {
-		*WritebackUrgentWatermark = WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK;
+		v->WritebackUrgentWatermark = v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK;
 	}
 
 	if (v->TotalActiveWriteback <= 1) {
-		*WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency;
+		v->WritebackDRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->WritebackLatency;
 	} else {
-		*WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK;
+		v->WritebackDRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK;
 	}
 
-	for (k = 0; k < NumberOfActivePlanes; ++k) {
+	for (k = 0; k < v->NumberOfActivePlanes; ++k) {
 		TotalPixelBW = TotalPixelBW
-				+ DPPPerPlane[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] + SwathWidthC[k] * BytePerPixelDETC[k] * VRatioChroma[k])
-						/ (HTotal[k] / PixelClock[k]);
+				+ DPPPerPlane[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] + SwathWidthC[k] * BytePerPixelDETC[k] * v->VRatioChroma[k])
+						/ (v->HTotal[k] / v->PixelClock[k]);
 	}
 
-	for (k = 0; k < NumberOfActivePlanes; ++k) {
+	for (k = 0; k < v->NumberOfActivePlanes; ++k) {
 		double EffectiveDETBufferSizeY = DETBufferSizeY[k];
 
 		v->LBLatencyHidingSourceLinesY = dml_min(
-				(double) MaxLineBufferLines,
-				dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (vtaps[k] - 1);
+				(double) v->MaxLineBufferLines,
+				dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(v->HRatio[k], 1.0)), 1)) - (v->vtaps[k] - 1);
 
 		v->LBLatencyHidingSourceLinesC = dml_min(
-				(double) MaxLineBufferLines,
-				dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTAPsChroma[k] - 1);
+				(double) v->MaxLineBufferLines,
+				dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(v->HRatioChroma[k], 1.0)), 1)) - (v->VTAPsChroma[k] - 1);
 
-		EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / VRatio[k] * (HTotal[k] / PixelClock[k]);
+		EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / v->VRatio[k] * (v->HTotal[k] / v->PixelClock[k]);
 
-		EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / VRatioChroma[k] * (HTotal[k] / PixelClock[k]);
+		EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / v->VRatioChroma[k] * (v->HTotal[k] / v->PixelClock[k]);
 
 		if (UnboundedRequestEnabled) {
 			EffectiveDETBufferSizeY = EffectiveDETBufferSizeY
-					+ CompressedBufferSizeInkByte * 1024 * SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] / (HTotal[k] / PixelClock[k]) / TotalPixelBW;
+					+ CompressedBufferSizeInkByte * 1024 * SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] / (v->HTotal[k] / v->PixelClock[k]) / TotalPixelBW;
 		}
 
 		LinesInDETY[k] = (double) EffectiveDETBufferSizeY / BytePerPixelDETY[k] / SwathWidthY[k];
 		LinesInDETYRoundedDownToSwath[k] = dml_floor(LinesInDETY[k], SwathHeightY[k]);
-		FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k];
+		FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k];
 		if (BytePerPixelDETC[k] > 0) {
 			LinesInDETC = v->DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k];
 			LinesInDETCRoundedDownToSwath = dml_floor(LinesInDETC, SwathHeightC[k]);
-			FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (HTotal[k] / PixelClock[k]) / VRatioChroma[k];
+			FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (v->HTotal[k] / v->PixelClock[k]) / v->VRatioChroma[k];
 		} else {
 			LinesInDETC = 0;
 			FullDETBufferingTimeC = 999999;
 		}
 
 		ActiveDRAMClockChangeLatencyMarginY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY
-				- ((double) DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k] - *UrgentWatermark - *DRAMClockChangeWatermark;
+				- ((double) v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k] - v->UrgentWatermark - v->DRAMClockChangeWatermark;
 
-		if (NumberOfActivePlanes > 1) {
+		if (v->NumberOfActivePlanes > 1) {
 			ActiveDRAMClockChangeLatencyMarginY = ActiveDRAMClockChangeLatencyMarginY
-					- (1 - 1.0 / NumberOfActivePlanes) * SwathHeightY[k] * HTotal[k] / PixelClock[k] / VRatio[k];
+					- (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightY[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatio[k];
 		}
 
 		if (BytePerPixelDETC[k] > 0) {
 			ActiveDRAMClockChangeLatencyMarginC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC
-					- ((double) DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k] - *UrgentWatermark - *DRAMClockChangeWatermark;
+					- ((double) v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k] - v->UrgentWatermark - v->DRAMClockChangeWatermark;
 
-			if (NumberOfActivePlanes > 1) {
+			if (v->NumberOfActivePlanes > 1) {
 				ActiveDRAMClockChangeLatencyMarginC = ActiveDRAMClockChangeLatencyMarginC
-						- (1 - 1.0 / NumberOfActivePlanes) * SwathHeightC[k] * HTotal[k] / PixelClock[k] / VRatioChroma[k];
+						- (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightC[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatioChroma[k];
 			}
 			v->ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMarginY, ActiveDRAMClockChangeLatencyMarginC);
 		} else {
 			v->ActiveDRAMClockChangeLatencyMargin[k] = ActiveDRAMClockChangeLatencyMarginY;
 		}
 
-		if (WritebackEnable[k] == true) {
-			WritebackDRAMClockChangeLatencyHiding = WritebackInterfaceBufferSize * 1024
-					/ (WritebackDestinationWidth[k] * WritebackDestinationHeight[k] / (WritebackSourceHeight[k] * HTotal[k] / PixelClock[k]) * 4);
-			if (WritebackPixelFormat[k] == dm_444_64) {
+		if (v->WritebackEnable[k] == true) {
+			WritebackDRAMClockChangeLatencyHiding = v->WritebackInterfaceBufferSize * 1024
+					/ (v->WritebackDestinationWidth[k] * v->WritebackDestinationHeight[k] / (v->WritebackSourceHeight[k] * v->HTotal[k] / v->PixelClock[k]) * 4);
+			if (v->WritebackPixelFormat[k] == dm_444_64) {
 				WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding / 2;
 			}
 			WritebackDRAMClockChangeLatencyMargin = WritebackDRAMClockChangeLatencyHiding - v->WritebackDRAMClockChangeWatermark;
@@ -5749,14 +5527,14 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 
 	v->MinActiveDRAMClockChangeMargin = 999999;
 	PlaneWithMinActiveDRAMClockChangeMargin = 0;
-	for (k = 0; k < NumberOfActivePlanes; ++k) {
+	for (k = 0; k < v->NumberOfActivePlanes; ++k) {
 		if (v->ActiveDRAMClockChangeLatencyMargin[k] < v->MinActiveDRAMClockChangeMargin) {
 			v->MinActiveDRAMClockChangeMargin = v->ActiveDRAMClockChangeLatencyMargin[k];
-			if (BlendingAndTiming[k] == k) {
+			if (v->BlendingAndTiming[k] == k) {
 				PlaneWithMinActiveDRAMClockChangeMargin = k;
 			} else {
-				for (j = 0; j < NumberOfActivePlanes; ++j) {
-					if (BlendingAndTiming[k] == j) {
+				for (j = 0; j < v->NumberOfActivePlanes; ++j) {
+					if (v->BlendingAndTiming[k] == j) {
 						PlaneWithMinActiveDRAMClockChangeMargin = j;
 					}
 				}
@@ -5764,11 +5542,11 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 		}
 	}
 
-	*MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + DRAMClockChangeLatency;
+	v->MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + v->DRAMClockChangeLatency ;
 
 	SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = 999999;
-	for (k = 0; k < NumberOfActivePlanes; ++k) {
-		if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (BlendingAndTiming[k] == k)) && !(BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin)
+	for (k = 0; k < v->NumberOfActivePlanes; ++k) {
+		if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (v->BlendingAndTiming[k] == k)) && !(v->BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin)
 				&& v->ActiveDRAMClockChangeLatencyMargin[k] < SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank) {
 			SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = v->ActiveDRAMClockChangeLatencyMargin[k];
 		}
@@ -5776,25 +5554,25 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 
 	v->TotalNumberOfActiveOTG = 0;
 
-	for (k = 0; k < NumberOfActivePlanes; ++k) {
-		if (BlendingAndTiming[k] == k) {
+	for (k = 0; k < v->NumberOfActivePlanes; ++k) {
+		if (v->BlendingAndTiming[k] == k) {
 			v->TotalNumberOfActiveOTG = v->TotalNumberOfActiveOTG + 1;
 		}
 	}
 
 	if (v->MinActiveDRAMClockChangeMargin > 0 && PrefetchMode == 0) {
 		*DRAMClockChangeSupport = dm_dram_clock_change_vactive;
-	} else if ((SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1
+	} else if ((v->SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1
 			|| SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank > 0) && PrefetchMode == 0) {
 		*DRAMClockChangeSupport = dm_dram_clock_change_vblank;
 	} else {
 		*DRAMClockChangeSupport = dm_dram_clock_change_unsupported;
 	}
 
-	*StutterExitWatermark = SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep;
-	*StutterEnterPlusExitWatermark = (SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep);
-	*Z8StutterExitWatermark = SRExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep;
-	*Z8StutterEnterPlusExitWatermark = SREnterPlusExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep;
+	*StutterExitWatermark = v->SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep;
+	*StutterEnterPlusExitWatermark = (v->SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep);
+	*Z8StutterExitWatermark = v->SRExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep;
+	*Z8StutterEnterPlusExitWatermark = v->SREnterPlusExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep;
 
 #ifdef __DML_VBA_DEBUG__
 	dml_print("DML::%s: StutterExitWatermark = %f\n", __func__, *StutterExitWatermark);
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
index 66b82e4f05c6..35d10b4d018b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
@@ -27,7 +27,7 @@
 #include "../display_mode_vba.h"
 #include "../dml_inline_defs.h"
 #include "display_rq_dlg_calc_31.h"
-#include "dml/dcn30/display_mode_vba_30.h"
+#include "../dcn30/display_mode_vba_30.h"
 
 static bool is_dual_plane(enum source_format_class source_format)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
new file mode 100644
index 000000000000..4bb3b31ea7e0
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
@@ -0,0 +1,379 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright 2022 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "clk_mgr.h"
+#include "resource.h"
+#include "dcn31/dcn31_hubbub.h"
+#include "dcn314_fpu.h"
+#include "dml/dcn20/dcn20_fpu.h"
+#include "dml/display_mode_vba.h"
+
+struct _vcs_dpi_ip_params_st dcn3_14_ip = {
+	.VBlankNomDefaultUS = 668,
+	.gpuvm_enable = 1,
+	.gpuvm_max_page_table_levels = 1,
+	.hostvm_enable = 1,
+	.hostvm_max_page_table_levels = 2,
+	.rob_buffer_size_kbytes = 64,
+	.det_buffer_size_kbytes = DCN3_14_DEFAULT_DET_SIZE,
+	.config_return_buffer_size_in_kbytes = 1792,
+	.compressed_buffer_segment_size_in_kbytes = 64,
+	.meta_fifo_size_in_kentries = 32,
+	.zero_size_buffer_entries = 512,
+	.compbuf_reserved_space_64b = 256,
+	.compbuf_reserved_space_zs = 64,
+	.dpp_output_buffer_pixels = 2560,
+	.opp_output_buffer_lines = 1,
+	.pixel_chunk_size_kbytes = 8,
+	.meta_chunk_size_kbytes = 2,
+	.min_meta_chunk_size_bytes = 256,
+	.writeback_chunk_size_kbytes = 8,
+	.ptoi_supported = false,
+	.num_dsc = 4,
+	.maximum_dsc_bits_per_component = 10,
+	.dsc422_native_support = false,
+	.is_line_buffer_bpp_fixed = true,
+	.line_buffer_fixed_bpp = 48,
+	.line_buffer_size_bits = 789504,
+	.max_line_buffer_lines = 12,
+	.writeback_interface_buffer_size_kbytes = 90,
+	.max_num_dpp = 4,
+	.max_num_otg = 4,
+	.max_num_hdmi_frl_outputs = 1,
+	.max_num_wb = 1,
+	.max_dchub_pscl_bw_pix_per_clk = 4,
+	.max_pscl_lb_bw_pix_per_clk = 2,
+	.max_lb_vscl_bw_pix_per_clk = 4,
+	.max_vscl_hscl_bw_pix_per_clk = 4,
+	.max_hscl_ratio = 6,
+	.max_vscl_ratio = 6,
+	.max_hscl_taps = 8,
+	.max_vscl_taps = 8,
+	.dpte_buffer_size_in_pte_reqs_luma = 64,
+	.dpte_buffer_size_in_pte_reqs_chroma = 34,
+	.dispclk_ramp_margin_percent = 1,
+	.max_inter_dcn_tile_repeaters = 8,
+	.cursor_buffer_size = 16,
+	.cursor_chunk_size = 2,
+	.writeback_line_buffer_buffer_size = 0,
+	.writeback_min_hscl_ratio = 1,
+	.writeback_min_vscl_ratio = 1,
+	.writeback_max_hscl_ratio = 1,
+	.writeback_max_vscl_ratio = 1,
+	.writeback_max_hscl_taps = 1,
+	.writeback_max_vscl_taps = 1,
+	.dppclk_delay_subtotal = 46,
+	.dppclk_delay_scl = 50,
+	.dppclk_delay_scl_lb_only = 16,
+	.dppclk_delay_cnvc_formatter = 27,
+	.dppclk_delay_cnvc_cursor = 6,
+	.dispclk_delay_subtotal = 119,
+	.dynamic_metadata_vm_enabled = false,
+	.odm_combine_4to1_supported = false,
+	.dcc_supported = true,
+};
+
+struct _vcs_dpi_soc_bounding_box_st dcn3_14_soc = {
+		/*TODO: correct dispclk/dppclk voltage level determination*/
+	.clock_limits = {
+		{
+			.state = 0,
+			.dispclk_mhz = 1200.0,
+			.dppclk_mhz = 1200.0,
+			.phyclk_mhz = 600.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 186.0,
+			.dtbclk_mhz = 600.0,
+		},
+		{
+			.state = 1,
+			.dispclk_mhz = 1200.0,
+			.dppclk_mhz = 1200.0,
+			.phyclk_mhz = 810.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 209.0,
+			.dtbclk_mhz = 600.0,
+		},
+		{
+			.state = 2,
+			.dispclk_mhz = 1200.0,
+			.dppclk_mhz = 1200.0,
+			.phyclk_mhz = 810.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 209.0,
+			.dtbclk_mhz = 600.0,
+		},
+		{
+			.state = 3,
+			.dispclk_mhz = 1200.0,
+			.dppclk_mhz = 1200.0,
+			.phyclk_mhz = 810.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 371.0,
+			.dtbclk_mhz = 600.0,
+		},
+		{
+			.state = 4,
+			.dispclk_mhz = 1200.0,
+			.dppclk_mhz = 1200.0,
+			.phyclk_mhz = 810.0,
+			.phyclk_d18_mhz = 667.0,
+			.dscclk_mhz = 417.0,
+			.dtbclk_mhz = 600.0,
+		},
+	},
+	.num_states = 5,
+	.sr_exit_time_us = 9.0,
+	.sr_enter_plus_exit_time_us = 11.0,
+	.sr_exit_z8_time_us = 442.0,
+	.sr_enter_plus_exit_z8_time_us = 560.0,
+	.writeback_latency_us = 12.0,
+	.dram_channel_width_bytes = 4,
+	.round_trip_ping_latency_dcfclk_cycles = 106,
+	.urgent_latency_pixel_data_only_us = 4.0,
+	.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
+	.urgent_latency_vm_data_only_us = 4.0,
+	.urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096,
+	.urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096,
+	.urgent_out_of_order_return_per_channel_vm_only_bytes = 4096,
+	.pct_ideal_sdp_bw_after_urgent = 80.0,
+	.pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 65.0,
+	.pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 60.0,
+	.pct_ideal_dram_sdp_bw_after_urgent_vm_only = 30.0,
+	.max_avg_sdp_bw_use_normal_percent = 60.0,
+	.max_avg_dram_bw_use_normal_percent = 60.0,
+	.fabric_datapath_to_dcn_data_return_bytes = 32,
+	.return_bus_width_bytes = 64,
+	.downspread_percent = 0.38,
+	.dcn_downspread_percent = 0.5,
+	.gpuvm_min_page_size_bytes = 4096,
+	.hostvm_min_page_size_bytes = 4096,
+	.do_urgent_latency_adjustment = false,
+	.urgent_latency_adjustment_fabric_clock_component_us = 0,
+	.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
+};
+
+
+void dcn314_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_params)
+{
+	struct clk_limit_table *clk_table = &bw_params->clk_table;
+	struct _vcs_dpi_voltage_scaling_st *clock_limits =
+		dcn3_14_soc.clock_limits;
+	unsigned int i, closest_clk_lvl;
+	int max_dispclk_mhz = 0, max_dppclk_mhz = 0;
+	int j;
+
+	dc_assert_fp_enabled();
+
+	// Default clock levels are used for diags, which may lead to overclocking.
+	if (!IS_DIAG_DC(dc->ctx->dce_environment) && dc->config.use_default_clock_table == false) {
+
+		dcn3_14_ip.max_num_otg = dc->res_pool->res_cap->num_timing_generator;
+		dcn3_14_ip.max_num_dpp = dc->res_pool->pipe_count;
+
+		if (bw_params->dram_channel_width_bytes > 0)
+			dcn3_14_soc.dram_channel_width_bytes = bw_params->dram_channel_width_bytes;
+
+		if (bw_params->num_channels > 0)
+			dcn3_14_soc.num_chans = bw_params->num_channels;
+
+		ASSERT(dcn3_14_soc.num_chans);
+		ASSERT(clk_table->num_entries);
+
+		/* Prepass to find max clocks independent of voltage level. */
+		for (i = 0; i < clk_table->num_entries; ++i) {
+			if (clk_table->entries[i].dispclk_mhz > max_dispclk_mhz)
+				max_dispclk_mhz = clk_table->entries[i].dispclk_mhz;
+			if (clk_table->entries[i].dppclk_mhz > max_dppclk_mhz)
+				max_dppclk_mhz = clk_table->entries[i].dppclk_mhz;
+		}
+
+		for (i = 0; i < clk_table->num_entries; i++) {
+			/* loop backwards*/
+			for (closest_clk_lvl = 0, j = dcn3_14_soc.num_states - 1; j >= 0; j--) {
+				if ((unsigned int) dcn3_14_soc.clock_limits[j].dcfclk_mhz <= clk_table->entries[i].dcfclk_mhz) {
+					closest_clk_lvl = j;
+					break;
+				}
+			}
+			if (clk_table->num_entries == 1) {
+				/*smu gives one DPM level, let's take the highest one*/
+				closest_clk_lvl = dcn3_14_soc.num_states - 1;
+			}
+
+			clock_limits[i].state = i;
+
+			/* Clocks dependent on voltage level. */
+			clock_limits[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz;
+			if (clk_table->num_entries == 1 &&
+				clock_limits[i].dcfclk_mhz < dcn3_14_soc.clock_limits[closest_clk_lvl].dcfclk_mhz) {
+				/*SMU fix not released yet*/
+				clock_limits[i].dcfclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].dcfclk_mhz;
+			}
+			clock_limits[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz;
+			clock_limits[i].socclk_mhz = clk_table->entries[i].socclk_mhz;
+
+			if (clk_table->entries[i].memclk_mhz && clk_table->entries[i].wck_ratio)
+				clock_limits[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2 * clk_table->entries[i].wck_ratio;
+
+			/* Clocks independent of voltage level. */
+			clock_limits[i].dispclk_mhz = max_dispclk_mhz ? max_dispclk_mhz :
+				dcn3_14_soc.clock_limits[closest_clk_lvl].dispclk_mhz;
+
+			clock_limits[i].dppclk_mhz = max_dppclk_mhz ? max_dppclk_mhz :
+				dcn3_14_soc.clock_limits[closest_clk_lvl].dppclk_mhz;
+
+			clock_limits[i].dram_bw_per_chan_gbps = dcn3_14_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps;
+			clock_limits[i].dscclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].dscclk_mhz;
+			clock_limits[i].dtbclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].dtbclk_mhz;
+			clock_limits[i].phyclk_d18_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz;
+			clock_limits[i].phyclk_mhz = dcn3_14_soc.clock_limits[closest_clk_lvl].phyclk_mhz;
+		}
+		for (i = 0; i < clk_table->num_entries; i++)
+			dcn3_14_soc.clock_limits[i] = clock_limits[i];
+		if (clk_table->num_entries) {
+			dcn3_14_soc.num_states = clk_table->num_entries;
+		}
+	}
+
+	if (max_dispclk_mhz) {
+		dcn3_14_soc.dispclk_dppclk_vco_speed_mhz = max_dispclk_mhz * 2;
+		dc->dml.soc.dispclk_dppclk_vco_speed_mhz = max_dispclk_mhz * 2;
+	}
+
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
+		dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN314);
+	else
+		dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN31_FPGA);
+}
+
+static bool is_dual_plane(enum surface_pixel_format format)
+{
+	return format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN || format == SURFACE_PIXEL_FORMAT_GRPH_RGBE_ALPHA;
+}
+
+int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *context,
+					       display_e2e_pipe_params_st *pipes,
+					       bool fast_validate)
+{
+	int i, pipe_cnt;
+	struct resource_context *res_ctx = &context->res_ctx;
+	struct pipe_ctx *pipe;
+	bool upscaled = false;
+
+	dc_assert_fp_enabled();
+
+	dcn20_populate_dml_pipes_from_context(dc, context, pipes, fast_validate);
+
+	for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
+		struct dc_crtc_timing *timing;
+
+		if (!res_ctx->pipe_ctx[i].stream)
+			continue;
+		pipe = &res_ctx->pipe_ctx[i];
+		timing = &pipe->stream->timing;
+
+		if (dc_extended_blank_supported(dc) && pipe->stream->adjust.v_total_max == pipe->stream->adjust.v_total_min
+			&& pipe->stream->adjust.v_total_min > timing->v_total)
+			pipes[pipe_cnt].pipe.dest.vtotal = pipe->stream->adjust.v_total_min;
+
+		if (pipe->plane_state &&
+				(pipe->plane_state->src_rect.height < pipe->plane_state->dst_rect.height ||
+				pipe->plane_state->src_rect.width < pipe->plane_state->dst_rect.width))
+			upscaled = true;
+
+		/*
+		 * Immediate flip can be set dynamically after enabling the plane.
+		 * We need to require support for immediate flip or underflow can be
+		 * intermittently experienced depending on peak b/w requirements.
+		 */
+		pipes[pipe_cnt].pipe.src.immediate_flip = true;
+
+		pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
+		pipes[pipe_cnt].pipe.src.hostvm = dc->res_pool->hubbub->riommu_active;
+		pipes[pipe_cnt].pipe.src.gpuvm = true;
+		pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_luma = 0;
+		pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_chroma = 0;
+		pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
+		pipes[pipe_cnt].pipe.src.dcc_rate = 3;
+		pipes[pipe_cnt].dout.dsc_input_bpc = 0;
+
+		if (pipes[pipe_cnt].dout.dsc_enable) {
+			switch (timing->display_color_depth) {
+			case COLOR_DEPTH_888:
+				pipes[pipe_cnt].dout.dsc_input_bpc = 8;
+				break;
+			case COLOR_DEPTH_101010:
+				pipes[pipe_cnt].dout.dsc_input_bpc = 10;
+				break;
+			case COLOR_DEPTH_121212:
+				pipes[pipe_cnt].dout.dsc_input_bpc = 12;
+				break;
+			default:
+				ASSERT(0);
+				break;
+			}
+		}
+
+		pipe_cnt++;
+	}
+	context->bw_ctx.dml.ip.det_buffer_size_kbytes = DCN3_14_DEFAULT_DET_SIZE;
+
+	dc->config.enable_4to1MPC = false;
+	if (pipe_cnt == 1 && pipe->plane_state && !dc->debug.disable_z9_mpc) {
+		if (is_dual_plane(pipe->plane_state->format)
+				&& pipe->plane_state->src_rect.width <= 1920 && pipe->plane_state->src_rect.height <= 1080) {
+			dc->config.enable_4to1MPC = true;
+		} else if (!is_dual_plane(pipe->plane_state->format) && pipe->plane_state->src_rect.width <= 5120) {
+			/* Limit to 5k max to avoid forced pipe split when there is not enough detile for swath */
+			context->bw_ctx.dml.ip.det_buffer_size_kbytes = 192;
+			pipes[0].pipe.src.unbounded_req_mode = true;
+		}
+	} else if (context->stream_count >= dc->debug.crb_alloc_policy_min_disp_count
+			&& dc->debug.crb_alloc_policy > DET_SIZE_DEFAULT) {
+		context->bw_ctx.dml.ip.det_buffer_size_kbytes = dc->debug.crb_alloc_policy * 64;
+	} else if (context->stream_count >= 3 && upscaled) {
+		context->bw_ctx.dml.ip.det_buffer_size_kbytes = 192;
+	}
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
+
+		if (!pipe->stream)
+			continue;
+
+		if (pipe->stream->signal == SIGNAL_TYPE_EDP && dc->debug.seamless_boot_odm_combine &&
+				pipe->stream->apply_seamless_boot_optimization) {
+
+			if (pipe->stream->apply_boot_odm_mode == dm_odm_combine_policy_2to1) {
+				context->bw_ctx.dml.vba.ODMCombinePolicy = dm_odm_combine_policy_2to1;
+				break;
+			}
+		}
+	}
+
+	return pipe_cnt;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.h
new file mode 100644
index 000000000000..d32c5bb99f4c
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright 2022 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DCN314_FPU_H__
+#define __DCN314_FPU_H__
+
+#define DCN3_14_DEFAULT_DET_SIZE 384
+#define DCN3_14_MAX_DET_SIZE 384
+#define DCN3_14_MIN_COMPBUF_SIZE_KB 128
+#define DCN3_14_CRB_SEGMENT_SIZE_KB 64
+
+void dcn314_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_params);
+int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *context,
+					       display_e2e_pipe_params_st *pipes,
+					       bool fast_validate);
+
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c
index fc4d7474c111..ee821c4fb5dd 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c
@@ -61,7 +61,7 @@
 // fudge factor for min dcfclk calclation
 #define __DML_MIN_DCFCLK_FACTOR__   1.15
 
-struct {
+typedef struct {
 	double DPPCLK;
 	double DISPCLK;
 	double PixelClock;
@@ -265,33 +265,13 @@ static void CalculateRowBandwidth(
 
 static void CalculateFlipSchedule(
 		struct display_mode_lib *mode_lib,
+		unsigned int k,
 		double HostVMInefficiencyFactor,
 		double UrgentExtraLatency,
 		double UrgentLatency,
-		unsigned int GPUVMMaxPageTableLevels,
-		bool HostVMEnable,
-		unsigned int HostVMMaxNonCachedPageTableLevels,
-		bool GPUVMEnable,
-		double HostVMMinPageSize,
 		double PDEAndMetaPTEBytesPerFrame,
 		double MetaRowBytes,
-		double DPTEBytesPerRow,
-		double BandwidthAvailableForImmediateFlip,
-		unsigned int TotImmediateFlipBytes,
-		enum source_format_class SourcePixelFormat,
-		double LineTime,
-		double VRatio,
-		double VRatioChroma,
-		double Tno_bw,
-		bool DCCEnable,
-		unsigned int dpte_row_height,
-		unsigned int meta_row_height,
-		unsigned int dpte_row_height_chroma,
-		unsigned int meta_row_height_chroma,
-		double *DestinationLinesToRequestVMInImmediateFlip,
-		double *DestinationLinesToRequestRowInImmediateFlip,
-		double *final_flip_bw,
-		bool *ImmediateFlipSupportedForPipe);
+		double DPTEBytesPerRow);
 static double CalculateWriteBackDelay(
 		enum source_format_class WritebackPixelFormat,
 		double WritebackHRatio,
@@ -325,64 +305,28 @@ static void CalculateVupdateAndDynamicMetadataParameters(
 static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 		struct display_mode_lib *mode_lib,
 		unsigned int PrefetchMode,
-		unsigned int NumberOfActivePlanes,
-		unsigned int MaxLineBufferLines,
-		unsigned int LineBufferSize,
-		unsigned int WritebackInterfaceBufferSize,
 		double DCFCLK,
 		double ReturnBW,
-		bool SynchronizedVBlank,
-		unsigned int dpte_group_bytes[],
-		unsigned int MetaChunkSize,
 		double UrgentLatency,
 		double ExtraLatency,
-		double WritebackLatency,
-		double WritebackChunkSize,
 		double SOCCLK,
-		double DRAMClockChangeLatency,
-		double SRExitTime,
-		double SREnterPlusExitTime,
-		double SRExitZ8Time,
-		double SREnterPlusExitZ8Time,
 		double DCFCLKDeepSleep,
 		unsigned int DETBufferSizeY[],
 		unsigned int DETBufferSizeC[],
 		unsigned int SwathHeightY[],
 		unsigned int SwathHeightC[],
-		unsigned int LBBitPerPixel[],
 		double SwathWidthY[],
 		double SwathWidthC[],
-		double HRatio[],
-		double HRatioChroma[],
-		unsigned int vtaps[],
-		unsigned int VTAPsChroma[],
-		double VRatio[],
-		double VRatioChroma[],
-		unsigned int HTotal[],
-		double PixelClock[],
-		unsigned int BlendingAndTiming[],
 		unsigned int DPPPerPlane[],
 		double BytePerPixelDETY[],
 		double BytePerPixelDETC[],
-		double DSTXAfterScaler[],
-		double DSTYAfterScaler[],
-		bool WritebackEnable[],
-		enum source_format_class WritebackPixelFormat[],
-		double WritebackDestinationWidth[],
-		double WritebackDestinationHeight[],
-		double WritebackSourceHeight[],
 		bool UnboundedRequestEnabled,
 		unsigned int CompressedBufferSizeInkByte,
 		enum clock_change_support *DRAMClockChangeSupport,
-		double *UrgentWatermark,
-		double *WritebackUrgentWatermark,
-		double *DRAMClockChangeWatermark,
-		double *WritebackDRAMClockChangeWatermark,
 		double *StutterExitWatermark,
 		double *StutterEnterPlusExitWatermark,
 		double *Z8StutterExitWatermark,
-		double *Z8StutterEnterPlusExitWatermark,
-		double *MinActiveDRAMClockChangeLatencySupported);
+		double *Z8StutterEnterPlusExitWatermark);
 
 static void CalculateDCFCLKDeepSleep(
 		struct display_mode_lib *mode_lib,
@@ -1599,7 +1543,7 @@ static void CalculateDCCConfiguration(
 	int segment_order_vert_contiguous_luma;
 	int segment_order_vert_contiguous_chroma;
 
-	enum {
+	typedef enum {
 		REQ_256Bytes, REQ_128BytesNonContiguous, REQ_128BytesContiguous, REQ_NA
 	} RequestType;
 	RequestType RequestLuma;
@@ -2928,33 +2872,13 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 			for (k = 0; k < v->NumberOfActivePlanes; ++k) {
 				CalculateFlipSchedule(
 						mode_lib,
+						k,
 						HostVMInefficiencyFactor,
 						v->UrgentExtraLatency,
 						v->UrgentLatency,
-						v->GPUVMMaxPageTableLevels,
-						v->HostVMEnable,
-						v->HostVMMaxNonCachedPageTableLevels,
-						v->GPUVMEnable,
-						v->HostVMMinPageSize,
 						v->PDEAndMetaPTEBytesFrame[k],
 						v->MetaRowByte[k],
-						v->PixelPTEBytesPerRow[k],
-						v->BandwidthAvailableForImmediateFlip,
-						v->TotImmediateFlipBytes,
-						v->SourcePixelFormat[k],
-						v->HTotal[k] / v->PixelClock[k],
-						v->VRatio[k],
-						v->VRatioChroma[k],
-						v->Tno_bw[k],
-						v->DCCEnable[k],
-						v->dpte_row_height[k],
-						v->meta_row_height[k],
-						v->dpte_row_height_chroma[k],
-						v->meta_row_height_chroma[k],
-						&v->DestinationLinesToRequestVMInImmediateFlip[k],
-						&v->DestinationLinesToRequestRowInImmediateFlip[k],
-						&v->final_flip_bw[k],
-						&v->ImmediateFlipSupportedForPipe[k]);
+						v->PixelPTEBytesPerRow[k]);
 			}
 
 			v->total_dcn_read_bw_with_flip = 0.0;
@@ -3041,64 +2965,28 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 		CalculateWatermarksAndDRAMSpeedChangeSupport(
 				mode_lib,
 				PrefetchMode,
-				v->NumberOfActivePlanes,
-				v->MaxLineBufferLines,
-				v->LineBufferSize,
-				v->WritebackInterfaceBufferSize,
 				v->DCFCLK,
 				v->ReturnBW,
-				v->SynchronizedVBlank,
-				v->dpte_group_bytes,
-				v->MetaChunkSize,
 				v->UrgentLatency,
 				v->UrgentExtraLatency,
-				v->WritebackLatency,
-				v->WritebackChunkSize,
 				v->SOCCLK,
-				v->DRAMClockChangeLatency,
-				v->SRExitTime,
-				v->SREnterPlusExitTime,
-				v->SRExitZ8Time,
-				v->SREnterPlusExitZ8Time,
 				v->DCFCLKDeepSleep,
 				v->DETBufferSizeY,
 				v->DETBufferSizeC,
 				v->SwathHeightY,
 				v->SwathHeightC,
-				v->LBBitPerPixel,
 				v->SwathWidthY,
 				v->SwathWidthC,
-				v->HRatio,
-				v->HRatioChroma,
-				v->vtaps,
-				v->VTAPsChroma,
-				v->VRatio,
-				v->VRatioChroma,
-				v->HTotal,
-				v->PixelClock,
-				v->BlendingAndTiming,
 				v->DPPPerPlane,
 				v->BytePerPixelDETY,
 				v->BytePerPixelDETC,
-				v->DSTXAfterScaler,
-				v->DSTYAfterScaler,
-				v->WritebackEnable,
-				v->WritebackPixelFormat,
-				v->WritebackDestinationWidth,
-				v->WritebackDestinationHeight,
-				v->WritebackSourceHeight,
 				v->UnboundedRequestEnabled,
 				v->CompressedBufferSizeInkByte,
 				&DRAMClockChangeSupport,
-				&v->UrgentWatermark,
-				&v->WritebackUrgentWatermark,
-				&v->DRAMClockChangeWatermark,
-				&v->WritebackDRAMClockChangeWatermark,
 				&v->StutterExitWatermark,
 				&v->StutterEnterPlusExitWatermark,
 				&v->Z8StutterExitWatermark,
-				&v->Z8StutterEnterPlusExitWatermark,
-				&v->MinActiveDRAMClockChangeLatencySupported);
+				&v->Z8StutterEnterPlusExitWatermark);
 
 		for (k = 0; k < v->NumberOfActivePlanes; ++k) {
 			if (v->WritebackEnable[k] == true) {
@@ -3710,61 +3598,43 @@ static void CalculateRowBandwidth(
 
 static void CalculateFlipSchedule(
 		struct display_mode_lib *mode_lib,
+		unsigned int k,
 		double HostVMInefficiencyFactor,
 		double UrgentExtraLatency,
 		double UrgentLatency,
-		unsigned int GPUVMMaxPageTableLevels,
-		bool HostVMEnable,
-		unsigned int HostVMMaxNonCachedPageTableLevels,
-		bool GPUVMEnable,
-		double HostVMMinPageSize,
 		double PDEAndMetaPTEBytesPerFrame,
 		double MetaRowBytes,
-		double DPTEBytesPerRow,
-		double BandwidthAvailableForImmediateFlip,
-		unsigned int TotImmediateFlipBytes,
-		enum source_format_class SourcePixelFormat,
-		double LineTime,
-		double VRatio,
-		double VRatioChroma,
-		double Tno_bw,
-		bool DCCEnable,
-		unsigned int dpte_row_height,
-		unsigned int meta_row_height,
-		unsigned int dpte_row_height_chroma,
-		unsigned int meta_row_height_chroma,
-		double *DestinationLinesToRequestVMInImmediateFlip,
-		double *DestinationLinesToRequestRowInImmediateFlip,
-		double *final_flip_bw,
-		bool *ImmediateFlipSupportedForPipe)
+		double DPTEBytesPerRow)
 {
+	struct vba_vars_st *v = &mode_lib->vba;
 	double min_row_time = 0.0;
 	unsigned int HostVMDynamicLevelsTrips;
 	double TimeForFetchingMetaPTEImmediateFlip;
 	double TimeForFetchingRowInVBlankImmediateFlip;
 	double ImmediateFlipBW;
+	double LineTime = v->HTotal[k] / v->PixelClock[k];
 
-	if (GPUVMEnable == true && HostVMEnable == true) {
-		HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels;
+	if (v->GPUVMEnable == true && v->HostVMEnable == true) {
+		HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels;
 	} else {
 		HostVMDynamicLevelsTrips = 0;
 	}
 
-	if (GPUVMEnable == true || DCCEnable == true) {
-		ImmediateFlipBW = (PDEAndMetaPTEBytesPerFrame + MetaRowBytes + DPTEBytesPerRow) * BandwidthAvailableForImmediateFlip / TotImmediateFlipBytes;
+	if (v->GPUVMEnable == true || v->DCCEnable[k] == true) {
+		ImmediateFlipBW = (PDEAndMetaPTEBytesPerFrame + MetaRowBytes + DPTEBytesPerRow) * v->BandwidthAvailableForImmediateFlip / v->TotImmediateFlipBytes;
 	}
 
-	if (GPUVMEnable == true) {
+	if (v->GPUVMEnable == true) {
 		TimeForFetchingMetaPTEImmediateFlip = dml_max3(
-				Tno_bw + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / ImmediateFlipBW,
-				UrgentExtraLatency + UrgentLatency * (GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1),
+				v->Tno_bw[k] + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / ImmediateFlipBW,
+				UrgentExtraLatency + UrgentLatency * (v->GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1),
 				LineTime / 4.0);
 	} else {
 		TimeForFetchingMetaPTEImmediateFlip = 0;
 	}
 
-	*DestinationLinesToRequestVMInImmediateFlip = dml_ceil(4.0 * (TimeForFetchingMetaPTEImmediateFlip / LineTime), 1) / 4.0;
-	if ((GPUVMEnable == true || DCCEnable == true)) {
+	v->DestinationLinesToRequestVMInImmediateFlip[k] = dml_ceil(4.0 * (TimeForFetchingMetaPTEImmediateFlip / LineTime), 1) / 4.0;
+	if ((v->GPUVMEnable == true || v->DCCEnable[k] == true)) {
 		TimeForFetchingRowInVBlankImmediateFlip = dml_max3(
 				(MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / ImmediateFlipBW,
 				UrgentLatency * (HostVMDynamicLevelsTrips + 1),
@@ -3773,54 +3643,54 @@ static void CalculateFlipSchedule(
 		TimeForFetchingRowInVBlankImmediateFlip = 0;
 	}
 
-	*DestinationLinesToRequestRowInImmediateFlip = dml_ceil(4.0 * (TimeForFetchingRowInVBlankImmediateFlip / LineTime), 1) / 4.0;
+	v->DestinationLinesToRequestRowInImmediateFlip[k] = dml_ceil(4.0 * (TimeForFetchingRowInVBlankImmediateFlip / LineTime), 1) / 4.0;
 
-	if (GPUVMEnable == true) {
-		*final_flip_bw = dml_max(
-				PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / (*DestinationLinesToRequestVMInImmediateFlip * LineTime),
-				(MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (*DestinationLinesToRequestRowInImmediateFlip * LineTime));
-	} else if ((GPUVMEnable == true || DCCEnable == true)) {
-		*final_flip_bw = (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (*DestinationLinesToRequestRowInImmediateFlip * LineTime);
+	if (v->GPUVMEnable == true) {
+		v->final_flip_bw[k] = dml_max(
+				PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / (v->DestinationLinesToRequestVMInImmediateFlip[k] * LineTime),
+				(MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (v->DestinationLinesToRequestRowInImmediateFlip[k] * LineTime));
+	} else if ((v->GPUVMEnable == true || v->DCCEnable[k] == true)) {
+		v->final_flip_bw[k] = (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (v->DestinationLinesToRequestRowInImmediateFlip[k] * LineTime);
 	} else {
-		*final_flip_bw = 0;
+		v->final_flip_bw[k] = 0;
 	}
 
-	if (SourcePixelFormat == dm_420_8 || SourcePixelFormat == dm_420_10 || SourcePixelFormat == dm_rgbe_alpha) {
-		if (GPUVMEnable == true && DCCEnable != true) {
-			min_row_time = dml_min(dpte_row_height * LineTime / VRatio, dpte_row_height_chroma * LineTime / VRatioChroma);
-		} else if (GPUVMEnable != true && DCCEnable == true) {
-			min_row_time = dml_min(meta_row_height * LineTime / VRatio, meta_row_height_chroma * LineTime / VRatioChroma);
+	if (v->SourcePixelFormat[k] == dm_420_8 || v->SourcePixelFormat[k] == dm_420_10 || v->SourcePixelFormat[k] == dm_rgbe_alpha) {
+		if (v->GPUVMEnable == true && v->DCCEnable[k] != true) {
+			min_row_time = dml_min(v->dpte_row_height[k] * LineTime / v->VRatio[k], v->dpte_row_height_chroma[k] * LineTime / v->VRatioChroma[k]);
+		} else if (v->GPUVMEnable != true && v->DCCEnable[k] == true) {
+			min_row_time = dml_min(v->meta_row_height[k] * LineTime / v->VRatio[k], v->meta_row_height_chroma[k] * LineTime / v->VRatioChroma[k]);
 		} else {
 			min_row_time = dml_min4(
-					dpte_row_height * LineTime / VRatio,
-					meta_row_height * LineTime / VRatio,
-					dpte_row_height_chroma * LineTime / VRatioChroma,
-					meta_row_height_chroma * LineTime / VRatioChroma);
+					v->dpte_row_height[k] * LineTime / v->VRatio[k],
+					v->meta_row_height[k] * LineTime / v->VRatio[k],
+					v->dpte_row_height_chroma[k] * LineTime / v->VRatioChroma[k],
+					v->meta_row_height_chroma[k] * LineTime / v->VRatioChroma[k]);
 		}
 	} else {
-		if (GPUVMEnable == true && DCCEnable != true) {
-			min_row_time = dpte_row_height * LineTime / VRatio;
-		} else if (GPUVMEnable != true && DCCEnable == true) {
-			min_row_time = meta_row_height * LineTime / VRatio;
+		if (v->GPUVMEnable == true && v->DCCEnable[k] != true) {
+			min_row_time = v->dpte_row_height[k] * LineTime / v->VRatio[k];
+		} else if (v->GPUVMEnable != true && v->DCCEnable[k] == true) {
+			min_row_time = v->meta_row_height[k] * LineTime / v->VRatio[k];
 		} else {
-			min_row_time = dml_min(dpte_row_height * LineTime / VRatio, meta_row_height * LineTime / VRatio);
+			min_row_time = dml_min(v->dpte_row_height[k] * LineTime / v->VRatio[k], v->meta_row_height[k] * LineTime / v->VRatio[k]);
 		}
 	}
 
-	if (*DestinationLinesToRequestVMInImmediateFlip >= 32 || *DestinationLinesToRequestRowInImmediateFlip >= 16
+	if (v->DestinationLinesToRequestVMInImmediateFlip[k] >= 32 || v->DestinationLinesToRequestRowInImmediateFlip[k] >= 16
 			|| TimeForFetchingMetaPTEImmediateFlip + 2 * TimeForFetchingRowInVBlankImmediateFlip > min_row_time) {
-		*ImmediateFlipSupportedForPipe = false;
+		v->ImmediateFlipSupportedForPipe[k] = false;
 	} else {
-		*ImmediateFlipSupportedForPipe = true;
+		v->ImmediateFlipSupportedForPipe[k] = true;
 	}
 
 #ifdef __DML_VBA_DEBUG__
-	dml_print("DML::%s: DestinationLinesToRequestVMInImmediateFlip = %f\n", __func__, *DestinationLinesToRequestVMInImmediateFlip);
-	dml_print("DML::%s: DestinationLinesToRequestRowInImmediateFlip = %f\n", __func__, *DestinationLinesToRequestRowInImmediateFlip);
+	dml_print("DML::%s: DestinationLinesToRequestVMInImmediateFlip = %f\n", __func__, v->DestinationLinesToRequestVMInImmediateFlip[k]);
+	dml_print("DML::%s: DestinationLinesToRequestRowInImmediateFlip = %f\n", __func__, v->DestinationLinesToRequestRowInImmediateFlip[k]);
 	dml_print("DML::%s: TimeForFetchingMetaPTEImmediateFlip = %f\n", __func__, TimeForFetchingMetaPTEImmediateFlip);
 	dml_print("DML::%s: TimeForFetchingRowInVBlankImmediateFlip = %f\n", __func__, TimeForFetchingRowInVBlankImmediateFlip);
 	dml_print("DML::%s: min_row_time = %f\n", __func__, min_row_time);
-	dml_print("DML::%s: ImmediateFlipSupportedForPipe = %d\n", __func__, *ImmediateFlipSupportedForPipe);
+	dml_print("DML::%s: ImmediateFlipSupportedForPipe = %d\n", __func__, v->ImmediateFlipSupportedForPipe[k]);
 #endif
 
 }
@@ -4071,9 +3941,7 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_
 
 	v->SourceFormatPixelAndScanSupport = true;
 	for (k = 0; k < v->NumberOfActivePlanes; k++) {
-		if ((v->SurfaceTiling[k] == dm_sw_linear && (!(v->SourceScan[k] != dm_vert) || v->DCCEnable[k] == true))
-				|| ((v->SurfaceTiling[k] == dm_sw_64kb_d || v->SurfaceTiling[k] == dm_sw_64kb_d_t
-						|| v->SurfaceTiling[k] == dm_sw_64kb_d_x) && !(v->SourcePixelFormat[k] == dm_444_64))) {
+		if (v->SurfaceTiling[k] == dm_sw_linear && (!(v->SourceScan[k] != dm_vert) || v->DCCEnable[k] == true)) {
 			v->SourceFormatPixelAndScanSupport = false;
 		}
 	}
@@ -5414,33 +5282,13 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_
 					for (k = 0; k < v->NumberOfActivePlanes; k++) {
 						CalculateFlipSchedule(
 								mode_lib,
+								k,
 								HostVMInefficiencyFactor,
 								v->ExtraLatency,
 								v->UrgLatency[i],
-								v->GPUVMMaxPageTableLevels,
-								v->HostVMEnable,
-								v->HostVMMaxNonCachedPageTableLevels,
-								v->GPUVMEnable,
-								v->HostVMMinPageSize,
 								v->PDEAndMetaPTEBytesPerFrame[i][j][k],
 								v->MetaRowBytes[i][j][k],
-								v->DPTEBytesPerRow[i][j][k],
-								v->BandwidthAvailableForImmediateFlip,
-								v->TotImmediateFlipBytes,
-								v->SourcePixelFormat[k],
-								v->HTotal[k] / v->PixelClock[k],
-								v->VRatio[k],
-								v->VRatioChroma[k],
-								v->Tno_bw[k],
-								v->DCCEnable[k],
-								v->dpte_row_height[k],
-								v->meta_row_height[k],
-								v->dpte_row_height_chroma[k],
-								v->meta_row_height_chroma[k],
-								&v->DestinationLinesToRequestVMInImmediateFlip[k],
-								&v->DestinationLinesToRequestRowInImmediateFlip[k],
-								&v->final_flip_bw[k],
-								&v->ImmediateFlipSupportedForPipe[k]);
+								v->DPTEBytesPerRow[i][j][k]);
 					}
 					v->total_dcn_read_bw_with_flip = 0.0;
 					for (k = 0; k < v->NumberOfActivePlanes; k++) {
@@ -5498,64 +5346,28 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_
 			CalculateWatermarksAndDRAMSpeedChangeSupport(
 					mode_lib,
 					v->PrefetchModePerState[i][j],
-					v->NumberOfActivePlanes,
-					v->MaxLineBufferLines,
-					v->LineBufferSize,
-					v->WritebackInterfaceBufferSize,
 					v->DCFCLKState[i][j],
 					v->ReturnBWPerState[i][j],
-					v->SynchronizedVBlank,
-					v->dpte_group_bytes,
-					v->MetaChunkSize,
 					v->UrgLatency[i],
 					v->ExtraLatency,
-					v->WritebackLatency,
-					v->WritebackChunkSize,
 					v->SOCCLKPerState[i],
-					v->DRAMClockChangeLatency,
-					v->SRExitTime,
-					v->SREnterPlusExitTime,
-					v->SRExitZ8Time,
-					v->SREnterPlusExitZ8Time,
 					v->ProjectedDCFCLKDeepSleep[i][j],
 					v->DETBufferSizeYThisState,
 					v->DETBufferSizeCThisState,
 					v->SwathHeightYThisState,
 					v->SwathHeightCThisState,
-					v->LBBitPerPixel,
 					v->SwathWidthYThisState,
 					v->SwathWidthCThisState,
-					v->HRatio,
-					v->HRatioChroma,
-					v->vtaps,
-					v->VTAPsChroma,
-					v->VRatio,
-					v->VRatioChroma,
-					v->HTotal,
-					v->PixelClock,
-					v->BlendingAndTiming,
 					v->NoOfDPPThisState,
 					v->BytePerPixelInDETY,
 					v->BytePerPixelInDETC,
-					v->DSTXAfterScaler,
-					v->DSTYAfterScaler,
-					v->WritebackEnable,
-					v->WritebackPixelFormat,
-					v->WritebackDestinationWidth,
-					v->WritebackDestinationHeight,
-					v->WritebackSourceHeight,
 					UnboundedRequestEnabledThisState,
 					CompressedBufferSizeInkByteThisState,
 					&v->DRAMClockChangeSupport[i][j],
-					&v->UrgentWatermark,
-					&v->WritebackUrgentWatermark,
-					&v->DRAMClockChangeWatermark,
-					&v->WritebackDRAMClockChangeWatermark,
-					&dummy,
 					&dummy,
 					&dummy,
 					&dummy,
-					&v->MinActiveDRAMClockChangeLatencySupported);
+					&dummy);
 		}
 	}
 
@@ -5681,64 +5493,28 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_
 static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 		struct display_mode_lib *mode_lib,
 		unsigned int PrefetchMode,
-		unsigned int NumberOfActivePlanes,
-		unsigned int MaxLineBufferLines,
-		unsigned int LineBufferSize,
-		unsigned int WritebackInterfaceBufferSize,
 		double DCFCLK,
 		double ReturnBW,
-		bool SynchronizedVBlank,
-		unsigned int dpte_group_bytes[],
-		unsigned int MetaChunkSize,
 		double UrgentLatency,
 		double ExtraLatency,
-		double WritebackLatency,
-		double WritebackChunkSize,
 		double SOCCLK,
-		double DRAMClockChangeLatency,
-		double SRExitTime,
-		double SREnterPlusExitTime,
-		double SRExitZ8Time,
-		double SREnterPlusExitZ8Time,
 		double DCFCLKDeepSleep,
 		unsigned int DETBufferSizeY[],
 		unsigned int DETBufferSizeC[],
 		unsigned int SwathHeightY[],
 		unsigned int SwathHeightC[],
-		unsigned int LBBitPerPixel[],
 		double SwathWidthY[],
 		double SwathWidthC[],
-		double HRatio[],
-		double HRatioChroma[],
-		unsigned int vtaps[],
-		unsigned int VTAPsChroma[],
-		double VRatio[],
-		double VRatioChroma[],
-		unsigned int HTotal[],
-		double PixelClock[],
-		unsigned int BlendingAndTiming[],
 		unsigned int DPPPerPlane[],
 		double BytePerPixelDETY[],
 		double BytePerPixelDETC[],
-		double DSTXAfterScaler[],
-		double DSTYAfterScaler[],
-		bool WritebackEnable[],
-		enum source_format_class WritebackPixelFormat[],
-		double WritebackDestinationWidth[],
-		double WritebackDestinationHeight[],
-		double WritebackSourceHeight[],
 		bool UnboundedRequestEnabled,
 		unsigned int CompressedBufferSizeInkByte,
 		enum clock_change_support *DRAMClockChangeSupport,
-		double *UrgentWatermark,
-		double *WritebackUrgentWatermark,
-		double *DRAMClockChangeWatermark,
-		double *WritebackDRAMClockChangeWatermark,
 		double *StutterExitWatermark,
 		double *StutterEnterPlusExitWatermark,
 		double *Z8StutterExitWatermark,
-		double *Z8StutterEnterPlusExitWatermark,
-		double *MinActiveDRAMClockChangeLatencySupported)
+		double *Z8StutterEnterPlusExitWatermark)
 {
 	struct vba_vars_st *v = &mode_lib->vba;
 	double EffectiveLBLatencyHidingY;
@@ -5758,103 +5534,103 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 	double TotalPixelBW = 0.0;
 	int k, j;
 
-	*UrgentWatermark = UrgentLatency + ExtraLatency;
+	v->UrgentWatermark = UrgentLatency + ExtraLatency;
 
 #ifdef __DML_VBA_DEBUG__
 	dml_print("DML::%s: UrgentLatency = %f\n", __func__, UrgentLatency);
 	dml_print("DML::%s: ExtraLatency = %f\n", __func__, ExtraLatency);
-	dml_print("DML::%s: UrgentWatermark = %f\n", __func__, *UrgentWatermark);
+	dml_print("DML::%s: UrgentWatermark = %f\n", __func__, v->UrgentWatermark);
 #endif
 
-	*DRAMClockChangeWatermark = DRAMClockChangeLatency + *UrgentWatermark;
+	v->DRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->UrgentWatermark;
 
 #ifdef __DML_VBA_DEBUG__
-	dml_print("DML::%s: DRAMClockChangeLatency = %f\n", __func__, DRAMClockChangeLatency);
-	dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, *DRAMClockChangeWatermark);
+	dml_print("DML::%s: v->DRAMClockChangeLatency = %f\n", __func__, v->DRAMClockChangeLatency);
+	dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, v->DRAMClockChangeWatermark);
 #endif
 
 	v->TotalActiveWriteback = 0;
-	for (k = 0; k < NumberOfActivePlanes; ++k) {
-		if (WritebackEnable[k] == true) {
+	for (k = 0; k < v->NumberOfActivePlanes; ++k) {
+		if (v->WritebackEnable[k] == true) {
 			v->TotalActiveWriteback = v->TotalActiveWriteback + 1;
 		}
 	}
 
 	if (v->TotalActiveWriteback <= 1) {
-		*WritebackUrgentWatermark = WritebackLatency;
+		v->WritebackUrgentWatermark = v->WritebackLatency;
 	} else {
-		*WritebackUrgentWatermark = WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK;
+		v->WritebackUrgentWatermark = v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK;
 	}
 
 	if (v->TotalActiveWriteback <= 1) {
-		*WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency;
+		v->WritebackDRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->WritebackLatency;
 	} else {
-		*WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK;
+		v->WritebackDRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK;
 	}
 
-	for (k = 0; k < NumberOfActivePlanes; ++k) {
+	for (k = 0; k < v->NumberOfActivePlanes; ++k) {
 		TotalPixelBW = TotalPixelBW
-				+ DPPPerPlane[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] + SwathWidthC[k] * BytePerPixelDETC[k] * VRatioChroma[k])
-						/ (HTotal[k] / PixelClock[k]);
+				+ DPPPerPlane[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] + SwathWidthC[k] * BytePerPixelDETC[k] * v->VRatioChroma[k])
+						/ (v->HTotal[k] / v->PixelClock[k]);
 	}
 
-	for (k = 0; k < NumberOfActivePlanes; ++k) {
+	for (k = 0; k < v->NumberOfActivePlanes; ++k) {
 		double EffectiveDETBufferSizeY = DETBufferSizeY[k];
 
 		v->LBLatencyHidingSourceLinesY = dml_min(
-				(double) MaxLineBufferLines,
-				dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (vtaps[k] - 1);
+				(double) v->MaxLineBufferLines,
+				dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(v->HRatio[k], 1.0)), 1)) - (v->vtaps[k] - 1);
 
 		v->LBLatencyHidingSourceLinesC = dml_min(
-				(double) MaxLineBufferLines,
-				dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTAPsChroma[k] - 1);
+				(double) v->MaxLineBufferLines,
+				dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(v->HRatioChroma[k], 1.0)), 1)) - (v->VTAPsChroma[k] - 1);
 
-		EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / VRatio[k] * (HTotal[k] / PixelClock[k]);
+		EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / v->VRatio[k] * (v->HTotal[k] / v->PixelClock[k]);
 
-		EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / VRatioChroma[k] * (HTotal[k] / PixelClock[k]);
+		EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / v->VRatioChroma[k] * (v->HTotal[k] / v->PixelClock[k]);
 
 		if (UnboundedRequestEnabled) {
 			EffectiveDETBufferSizeY = EffectiveDETBufferSizeY
-					+ CompressedBufferSizeInkByte * 1024 * SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] / (HTotal[k] / PixelClock[k]) / TotalPixelBW;
+					+ CompressedBufferSizeInkByte * 1024 * SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] / (v->HTotal[k] / v->PixelClock[k]) / TotalPixelBW;
 		}
 
 		LinesInDETY[k] = (double) EffectiveDETBufferSizeY / BytePerPixelDETY[k] / SwathWidthY[k];
 		LinesInDETYRoundedDownToSwath[k] = dml_floor(LinesInDETY[k], SwathHeightY[k]);
-		FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k];
+		FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k];
 		if (BytePerPixelDETC[k] > 0) {
 			LinesInDETC = v->DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k];
 			LinesInDETCRoundedDownToSwath = dml_floor(LinesInDETC, SwathHeightC[k]);
-			FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (HTotal[k] / PixelClock[k]) / VRatioChroma[k];
+			FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (v->HTotal[k] / v->PixelClock[k]) / v->VRatioChroma[k];
 		} else {
 			LinesInDETC = 0;
 			FullDETBufferingTimeC = 999999;
 		}
 
 		ActiveDRAMClockChangeLatencyMarginY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY
-				- ((double) DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k] - *UrgentWatermark - *DRAMClockChangeWatermark;
+				- ((double) v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k] - v->UrgentWatermark - v->DRAMClockChangeWatermark;
 
-		if (NumberOfActivePlanes > 1) {
+		if (v->NumberOfActivePlanes > 1) {
 			ActiveDRAMClockChangeLatencyMarginY = ActiveDRAMClockChangeLatencyMarginY
-					- (1 - 1.0 / NumberOfActivePlanes) * SwathHeightY[k] * HTotal[k] / PixelClock[k] / VRatio[k];
+					- (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightY[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatio[k];
 		}
 
 		if (BytePerPixelDETC[k] > 0) {
 			ActiveDRAMClockChangeLatencyMarginC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC
-					- ((double) DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k] - *UrgentWatermark - *DRAMClockChangeWatermark;
+					- ((double) v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k] - v->UrgentWatermark - v->DRAMClockChangeWatermark;
 
-			if (NumberOfActivePlanes > 1) {
+			if (v->NumberOfActivePlanes > 1) {
 				ActiveDRAMClockChangeLatencyMarginC = ActiveDRAMClockChangeLatencyMarginC
-						- (1 - 1.0 / NumberOfActivePlanes) * SwathHeightC[k] * HTotal[k] / PixelClock[k] / VRatioChroma[k];
+						- (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightC[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatioChroma[k];
 			}
 			v->ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMarginY, ActiveDRAMClockChangeLatencyMarginC);
 		} else {
 			v->ActiveDRAMClockChangeLatencyMargin[k] = ActiveDRAMClockChangeLatencyMarginY;
 		}
 
-		if (WritebackEnable[k] == true) {
-			WritebackDRAMClockChangeLatencyHiding = WritebackInterfaceBufferSize * 1024
-					/ (WritebackDestinationWidth[k] * WritebackDestinationHeight[k] / (WritebackSourceHeight[k] * HTotal[k] / PixelClock[k]) * 4);
-			if (WritebackPixelFormat[k] == dm_444_64) {
+		if (v->WritebackEnable[k] == true) {
+			WritebackDRAMClockChangeLatencyHiding = v->WritebackInterfaceBufferSize * 1024
+					/ (v->WritebackDestinationWidth[k] * v->WritebackDestinationHeight[k] / (v->WritebackSourceHeight[k] * v->HTotal[k] / v->PixelClock[k]) * 4);
+			if (v->WritebackPixelFormat[k] == dm_444_64) {
 				WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding / 2;
 			}
 			WritebackDRAMClockChangeLatencyMargin = WritebackDRAMClockChangeLatencyHiding - v->WritebackDRAMClockChangeWatermark;
@@ -5864,14 +5640,14 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 
 	v->MinActiveDRAMClockChangeMargin = 999999;
 	PlaneWithMinActiveDRAMClockChangeMargin = 0;
-	for (k = 0; k < NumberOfActivePlanes; ++k) {
+	for (k = 0; k < v->NumberOfActivePlanes; ++k) {
 		if (v->ActiveDRAMClockChangeLatencyMargin[k] < v->MinActiveDRAMClockChangeMargin) {
 			v->MinActiveDRAMClockChangeMargin = v->ActiveDRAMClockChangeLatencyMargin[k];
-			if (BlendingAndTiming[k] == k) {
+			if (v->BlendingAndTiming[k] == k) {
 				PlaneWithMinActiveDRAMClockChangeMargin = k;
 			} else {
-				for (j = 0; j < NumberOfActivePlanes; ++j) {
-					if (BlendingAndTiming[k] == j) {
+				for (j = 0; j < v->NumberOfActivePlanes; ++j) {
+					if (v->BlendingAndTiming[k] == j) {
 						PlaneWithMinActiveDRAMClockChangeMargin = j;
 					}
 				}
@@ -5879,11 +5655,11 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 		}
 	}
 
-	*MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + DRAMClockChangeLatency;
+	v->MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + v->DRAMClockChangeLatency ;
 
 	SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = 999999;
-	for (k = 0; k < NumberOfActivePlanes; ++k) {
-		if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (BlendingAndTiming[k] == k)) && !(BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin)
+	for (k = 0; k < v->NumberOfActivePlanes; ++k) {
+		if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (v->BlendingAndTiming[k] == k)) && !(v->BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin)
 				&& v->ActiveDRAMClockChangeLatencyMargin[k] < SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank) {
 			SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = v->ActiveDRAMClockChangeLatencyMargin[k];
 		}
@@ -5891,25 +5667,25 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 
 	v->TotalNumberOfActiveOTG = 0;
 
-	for (k = 0; k < NumberOfActivePlanes; ++k) {
-		if (BlendingAndTiming[k] == k) {
+	for (k = 0; k < v->NumberOfActivePlanes; ++k) {
+		if (v->BlendingAndTiming[k] == k) {
 			v->TotalNumberOfActiveOTG = v->TotalNumberOfActiveOTG + 1;
 		}
 	}
 
 	if (v->MinActiveDRAMClockChangeMargin > 0 && PrefetchMode == 0) {
 		*DRAMClockChangeSupport = dm_dram_clock_change_vactive;
-	} else if ((SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1
+	} else if ((v->SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1
 			|| SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank > 0) && PrefetchMode == 0) {
 		*DRAMClockChangeSupport = dm_dram_clock_change_vblank;
 	} else {
 		*DRAMClockChangeSupport = dm_dram_clock_change_unsupported;
 	}
 
-	*StutterExitWatermark = SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep;
-	*StutterEnterPlusExitWatermark = (SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep);
-	*Z8StutterExitWatermark = SRExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep;
-	*Z8StutterEnterPlusExitWatermark = SREnterPlusExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep;
+	*StutterExitWatermark = v->SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep;
+	*StutterEnterPlusExitWatermark = (v->SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep);
+	*Z8StutterExitWatermark = v->SRExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep;
+	*Z8StutterEnterPlusExitWatermark = v->SREnterPlusExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep;
 
 #ifdef __DML_VBA_DEBUG__
 	dml_print("DML::%s: StutterExitWatermark = %f\n", __func__, *StutterExitWatermark);
@@ -7157,12 +6933,13 @@ static double CalculateExtraLatencyBytes(
 			HostVMDynamicLevels = dml_max(0, (int) HostVMMaxNonCachedPageTableLevels - 1);
 		else
 			HostVMDynamicLevels = dml_max(0, (int) HostVMMaxNonCachedPageTableLevels - 2);
-	else
+	} else {
 		HostVMDynamicLevels = 0;
+	}
 
 	ret = ReorderingBytes + (TotalNumberOfActiveDPP * PixelChunkSizeInKByte + TotalNumberOfDCCActiveDPP * MetaChunkSize) * 1024.0;
 
-	if (GPUVMEnable == true)
+	if (GPUVMEnable == true) {
 		for (k = 0; k < NumberOfActivePlanes; ++k)
 			ret = ret + NumberOfDPP[k] * dpte_group_bytes[k] * (1 + 8 * HostVMDynamicLevels) * HostVMInefficiencyFactor;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index 66453546e24f..e573e706430d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -121,8 +121,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc = {
 		},
 	},
 	.num_states = 1,
-	.sr_exit_time_us = 20.16,
-	.sr_enter_plus_exit_time_us = 27.13,
+	.sr_exit_time_us = 42.97,
+	.sr_enter_plus_exit_time_us = 49.94,
 	.sr_exit_z8_time_us = 285.0,
 	.sr_enter_plus_exit_z8_time_us = 320,
 	.writeback_latency_us = 12.0,
@@ -244,6 +244,50 @@ void dcn32_build_wm_range_table_fpu(struct clk_mgr_internal *clk_mgr)
 }
 
 /**
+ * Finds dummy_latency_index when MCLK switching using firmware based
+ * vblank stretch is enabled. This function will iterate through the
+ * table of dummy pstate latencies until the lowest value that allows
+ * dm_allow_self_refresh_and_mclk_switch to happen is found
+ */
+int dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(struct dc *dc,
+							    struct dc_state *context,
+							    display_e2e_pipe_params_st *pipes,
+							    int pipe_cnt,
+							    int vlevel)
+{
+	const int max_latency_table_entries = 4;
+	const struct vba_vars_st *vba = &context->bw_ctx.dml.vba;
+	int dummy_latency_index = 0;
+
+	dc_assert_fp_enabled();
+
+	while (dummy_latency_index < max_latency_table_entries) {
+		context->bw_ctx.dml.soc.dram_clock_change_latency_us =
+				dc->clk_mgr->bw_params->dummy_pstate_table[dummy_latency_index].dummy_pstate_latency_us;
+		dcn32_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, false);
+
+		if (vlevel < context->bw_ctx.dml.vba.soc.num_states &&
+				vba->DRAMClockChangeSupport[vlevel][vba->maxMpcComb] != dm_dram_clock_change_unsupported)
+			break;
+
+		dummy_latency_index++;
+	}
+
+	if (dummy_latency_index == max_latency_table_entries) {
+		ASSERT(dummy_latency_index != max_latency_table_entries);
+		/* If the execution gets here, it means dummy p_states are
+		 * not possible. This should never happen and would mean
+		 * something is severely wrong.
+		 * Here we reset dummy_latency_index to 3, because it is
+		 * better to have underflows than system crashes.
+		 */
+		dummy_latency_index = max_latency_table_entries - 1;
+	}
+
+	return dummy_latency_index;
+}
+
+/**
  * dcn32_helper_populate_phantom_dlg_params - Get DLG params for phantom pipes
  * and populate pipe_ctx with those params.
  *
@@ -473,8 +517,11 @@ void dcn32_set_phantom_stream_timing(struct dc *dc,
 
 	// DML calculation for MALL region doesn't take into account FW delay
 	// and required pstate allow width for multi-display cases
+	/* Add 16 lines margin to the MALL REGION because SUB_VP_START_LINE must be aligned
+	 * to 2 swaths (i.e. 16 lines)
+	 */
 	phantom_vactive = get_subviewport_lines_needed_in_mall(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx) +
-				pstate_width_fw_delay_lines;
+				pstate_width_fw_delay_lines + dc->caps.subvp_swath_height_margin_lines;
 
 	// For backporch of phantom pipe, use vstartup of the main pipe
 	phantom_bp = get_vstartup(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
@@ -490,6 +537,7 @@ void dcn32_set_phantom_stream_timing(struct dc *dc,
 						phantom_stream->timing.v_front_porch +
 						phantom_stream->timing.v_sync_width +
 						phantom_bp;
+	phantom_stream->timing.flags.DSC = 0; // Don't need DSC for phantom timing
 }
 
 /**
@@ -983,9 +1031,15 @@ static void dcn32_full_validate_bw_helper(struct dc *dc,
 	 * DML favors voltage over p-state, but we're more interested in
 	 * supporting p-state over voltage. We can't support p-state in
 	 * prefetch mode > 0 so try capping the prefetch mode to start.
+	 * Override present for testing.
 	 */
-	context->bw_ctx.dml.soc.allow_for_pstate_or_stutter_in_vblank_final =
+	if (dc->debug.dml_disallow_alternate_prefetch_modes)
+		context->bw_ctx.dml.soc.allow_for_pstate_or_stutter_in_vblank_final =
 			dm_prefetch_support_uclk_fclk_and_stutter;
+	else
+		context->bw_ctx.dml.soc.allow_for_pstate_or_stutter_in_vblank_final =
+			dm_prefetch_support_uclk_fclk_and_stutter_if_possible;
+
 	*vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, *pipe_cnt);
 	/* This may adjust vlevel and maxMpcComb */
 	if (*vlevel < context->bw_ctx.dml.soc.num_states)
@@ -1004,6 +1058,15 @@ static void dcn32_full_validate_bw_helper(struct dc *dc,
 	    dc->debug.force_subvp_mclk_switch)) {
 
 		dcn32_merge_pipes_for_subvp(dc, context);
+		// to re-initialize viewport after the pipe merge
+		for (int i = 0; i < dc->res_pool->pipe_count; i++) {
+			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+			if (!pipe_ctx->plane_state || !pipe_ctx->stream)
+				continue;
+
+			resource_build_scaling_params(pipe_ctx);
+		}
 
 		while (!found_supported_config && dcn32_enough_pipes_for_subvp(dc, context) &&
 			dcn32_assign_subvp_pipe(dc, context, &dc_pipe_idx)) {
@@ -1014,7 +1077,9 @@ static void dcn32_full_validate_bw_helper(struct dc *dc,
 			 * will not allow for switch in VBLANK. The DRR display must have it's VBLANK stretched
 			 * enough to support MCLK switching.
 			 */
-			if (*vlevel == context->bw_ctx.dml.soc.num_states) {
+			if (*vlevel == context->bw_ctx.dml.soc.num_states &&
+				context->bw_ctx.dml.soc.allow_for_pstate_or_stutter_in_vblank_final ==
+					dm_prefetch_support_uclk_fclk_and_stutter) {
 				context->bw_ctx.dml.soc.allow_for_pstate_or_stutter_in_vblank_final =
 								dm_prefetch_support_stutter;
 				/* There are params (such as FabricClock) that need to be recalculated
@@ -1344,7 +1409,8 @@ bool dcn32_internal_validate_bw(struct dc *dc,
 	int split[MAX_PIPES] = { 0 };
 	bool merge[MAX_PIPES] = { false };
 	bool newly_split[MAX_PIPES] = { false };
-	int pipe_cnt, i, pipe_idx, vlevel;
+	int pipe_cnt, i, pipe_idx;
+	int vlevel = context->bw_ctx.dml.soc.num_states;
 	struct vba_vars_st *vba = &context->bw_ctx.dml.vba;
 
 	dc_assert_fp_enabled();
@@ -1373,17 +1439,22 @@ bool dcn32_internal_validate_bw(struct dc *dc,
 		DC_FP_END();
 	}
 
-	if (fast_validate || vlevel == context->bw_ctx.dml.soc.num_states ||
-			vba->DRAMClockChangeSupport[vlevel][vba->maxMpcComb] == dm_dram_clock_change_unsupported) {
+	if (fast_validate ||
+			(dc->debug.dml_disallow_alternate_prefetch_modes &&
+			(vlevel == context->bw_ctx.dml.soc.num_states ||
+				vba->DRAMClockChangeSupport[vlevel][vba->maxMpcComb] == dm_dram_clock_change_unsupported))) {
 		/*
-		 * If mode is unsupported or there's still no p-state support then
-		 * fall back to favoring voltage.
+		 * If dml_disallow_alternate_prefetch_modes is false, then we have already
+		 * tried alternate prefetch modes during full validation.
+		 *
+		 * If mode is unsupported or there is no p-state support, then
+		 * fall back to favouring voltage.
 		 *
-		 * If Prefetch mode 0 failed for this config, or passed with Max UCLK, try if
-		 * supported with Prefetch mode 1 (dm_prefetch_support_fclk_and_stutter == 2)
+		 * If Prefetch mode 0 failed for this config, or passed with Max UCLK, then try
+		 * to support with Prefetch mode 1 (dm_prefetch_support_fclk_and_stutter == 2)
 		 */
 		context->bw_ctx.dml.soc.allow_for_pstate_or_stutter_in_vblank_final =
-				dm_prefetch_support_fclk_and_stutter;
+			dm_prefetch_support_fclk_and_stutter;
 
 		vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, pipe_cnt);
 
@@ -1619,7 +1690,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
 			dcn30_can_support_mclk_switch_using_fw_based_vblank_stretch(dc, context);
 
 		if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) {
-			dummy_latency_index = dcn30_find_dummy_latency_index_for_fw_based_mclk_switch(dc,
+			dummy_latency_index = dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(dc,
 				context, pipes, pipe_cnt, vlevel);
 
 			/* After calling dcn30_find_dummy_latency_index_for_fw_based_mclk_switch
@@ -1855,6 +1926,45 @@ static void remove_entry_from_table_at_index(struct _vcs_dpi_voltage_scaling_st
 	memset(&table[--(*num_entries)], 0, sizeof(struct _vcs_dpi_voltage_scaling_st));
 }
 
+void dcn32_patch_dpm_table(struct clk_bw_params *bw_params)
+{
+	int i;
+	unsigned int max_dcfclk_mhz = 0, max_dispclk_mhz = 0, max_dppclk_mhz = 0,
+			max_phyclk_mhz = 0, max_dtbclk_mhz = 0, max_fclk_mhz = 0, max_uclk_mhz = 0;
+
+	for (i = 0; i < MAX_NUM_DPM_LVL; i++) {
+		if (bw_params->clk_table.entries[i].dcfclk_mhz > max_dcfclk_mhz)
+			max_dcfclk_mhz = bw_params->clk_table.entries[i].dcfclk_mhz;
+		if (bw_params->clk_table.entries[i].fclk_mhz > max_fclk_mhz)
+			max_fclk_mhz = bw_params->clk_table.entries[i].fclk_mhz;
+		if (bw_params->clk_table.entries[i].memclk_mhz > max_uclk_mhz)
+			max_uclk_mhz = bw_params->clk_table.entries[i].memclk_mhz;
+		if (bw_params->clk_table.entries[i].dispclk_mhz > max_dispclk_mhz)
+			max_dispclk_mhz = bw_params->clk_table.entries[i].dispclk_mhz;
+		if (bw_params->clk_table.entries[i].dppclk_mhz > max_dppclk_mhz)
+			max_dppclk_mhz = bw_params->clk_table.entries[i].dppclk_mhz;
+		if (bw_params->clk_table.entries[i].phyclk_mhz > max_phyclk_mhz)
+			max_phyclk_mhz = bw_params->clk_table.entries[i].phyclk_mhz;
+		if (bw_params->clk_table.entries[i].dtbclk_mhz > max_dtbclk_mhz)
+			max_dtbclk_mhz = bw_params->clk_table.entries[i].dtbclk_mhz;
+	}
+
+	/* Scan through clock values we currently have and if they are 0,
+	 *  then populate it with dcn3_2_soc.clock_limits[] value.
+	 *
+	 * Do it for DCFCLK, DISPCLK, DTBCLK and UCLK as any of those being
+	 *  0, will cause it to skip building the clock table.
+	 */
+	if (max_dcfclk_mhz == 0)
+		bw_params->clk_table.entries[0].dcfclk_mhz = dcn3_2_soc.clock_limits[0].dcfclk_mhz;
+	if (max_dispclk_mhz == 0)
+		bw_params->clk_table.entries[0].dispclk_mhz = dcn3_2_soc.clock_limits[0].dispclk_mhz;
+	if (max_dtbclk_mhz == 0)
+		bw_params->clk_table.entries[0].dtbclk_mhz = dcn3_2_soc.clock_limits[0].dtbclk_mhz;
+	if (max_uclk_mhz == 0)
+		bw_params->clk_table.entries[0].memclk_mhz = dcn3_2_soc.clock_limits[0].dram_speed_mts / 16;
+}
+
 static int build_synthetic_soc_states(struct clk_bw_params *bw_params,
 		struct _vcs_dpi_voltage_scaling_st *table, unsigned int *num_entries)
 {
@@ -2098,6 +2208,13 @@ void dcn32_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_pa
 				dc->bb_overrides.dram_clock_change_latency_ns / 1000.0;
 		}
 
+		if ((int)(dcn3_2_soc.fclk_change_latency_us * 1000)
+				!= dc->bb_overrides.fclk_clock_change_latency_ns
+				&& dc->bb_overrides.fclk_clock_change_latency_ns) {
+			dcn3_2_soc.fclk_change_latency_us =
+				dc->bb_overrides.fclk_clock_change_latency_ns / 1000;
+		}
+
 		if ((int)(dcn3_2_soc.dummy_pstate_latency_us * 1000)
 				!= dc->bb_overrides.dummy_clock_change_latency_ns
 				&& dc->bb_overrides.dummy_clock_change_latency_ns) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
index 3ed06ab855be..e1b79e2aab8c 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
@@ -71,4 +71,12 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
 
 void dcn32_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_params);
 
+int dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(struct dc *dc,
+							    struct dc_state *context,
+							    display_e2e_pipe_params_st *pipes,
+							    int pipe_cnt,
+							    int vlevel);
+
+void dcn32_patch_dpm_table(struct clk_bw_params *bw_params);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c
index 890612db08dc..6980f698eb23 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c
@@ -221,7 +221,6 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 		// VBA_DELTA
 		// Calculate DET size, swath height
 		dml32_CalculateSwathAndDETConfiguration(
-				&v->dummy_vars.dml32_CalculateSwathAndDETConfiguration,
 				mode_lib->vba.DETSizeOverride,
 				mode_lib->vba.UsesMALLForPStateChange,
 				mode_lib->vba.ConfigReturnBufferSizeInKByte,
@@ -461,7 +460,6 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 	{
 
 		dml32_CalculateVMRowAndSwath(
-				&v->dummy_vars.dml32_CalculateVMRowAndSwath,
 				mode_lib->vba.NumberOfActiveSurfaces,
 				v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.SurfaceParameters,
 				v->SurfaceSizeInMALL,
@@ -758,31 +756,17 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 			v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.BytePerPixelC = v->BytePerPixelC[k];
 			v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.ProgressiveToInterlaceUnitInOPP = mode_lib->vba.ProgressiveToInterlaceUnitInOPP;
 			v->ErrorResult[k] = dml32_CalculatePrefetchSchedule(
-					&v->dummy_vars.dml32_CalculatePrefetchSchedule,
+					v,
+					k,
 					v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.HostVMInefficiencyFactor,
-					&v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe, v->DSCDelay[k],
-					mode_lib->vba.DPPCLKDelaySubtotal + mode_lib->vba.DPPCLKDelayCNVCFormater,
-					mode_lib->vba.DPPCLKDelaySCL,
-					mode_lib->vba.DPPCLKDelaySCLLBOnly,
-					mode_lib->vba.DPPCLKDelayCNVCCursor,
-					mode_lib->vba.DISPCLKDelaySubtotal,
-					(unsigned int) (v->SwathWidthY[k] / mode_lib->vba.HRatio[k]),
-					mode_lib->vba.OutputFormat[k],
-					mode_lib->vba.MaxInterDCNTileRepeaters,
+					&v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe,
+					v->DSCDelay[k],
+					(unsigned int) (v->SwathWidthY[k] / v->HRatio[k]),
 					dml_min(v->VStartupLines, v->MaxVStartupLines[k]),
 					v->MaxVStartupLines[k],
-					mode_lib->vba.GPUVMMaxPageTableLevels,
-					mode_lib->vba.GPUVMEnable,
-					mode_lib->vba.HostVMEnable,
-					mode_lib->vba.HostVMMaxNonCachedPageTableLevels,
-					mode_lib->vba.HostVMMinPageSize,
-					mode_lib->vba.DynamicMetadataEnable[k],
-					mode_lib->vba.DynamicMetadataVMEnabled,
-					mode_lib->vba.DynamicMetadataLinesBeforeActiveRequired[k],
-					mode_lib->vba.DynamicMetadataTransmittedBytes[k],
 					v->UrgentLatency,
 					v->UrgentExtraLatency,
-					mode_lib->vba.TCalc,
+					v->TCalc,
 					v->PDEAndMetaPTEBytesFrame[k],
 					v->MetaRowByte[k],
 					v->PixelPTEBytesPerRow[k],
@@ -796,8 +780,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 					v->MaxNumSwathC[k],
 					v->swath_width_luma_ub[k],
 					v->swath_width_chroma_ub[k],
-					mode_lib->vba.SwathHeightY[k],
-					mode_lib->vba.SwathHeightC[k],
+					v->SwathHeightY[k],
+					v->SwathHeightC[k],
 					TWait,
 					/* Output */
 					&v->DSTXAfterScaler[k],
@@ -1167,59 +1151,28 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 		v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.mmSOCParameters.SMNLatency = mode_lib->vba.SMNLatency;
 
 		dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
-			&v->dummy_vars.dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport,
-			mode_lib->vba.USRRetrainingRequiredFinal,
-			mode_lib->vba.UsesMALLForPStateChange,
-			mode_lib->vba.PrefetchModePerState[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb],
-			mode_lib->vba.NumberOfActiveSurfaces,
-			mode_lib->vba.MaxLineBufferLines,
-			mode_lib->vba.LineBufferSizeFinal,
-			mode_lib->vba.WritebackInterfaceBufferSize,
-			mode_lib->vba.DCFCLK,
-			mode_lib->vba.ReturnBW,
-			mode_lib->vba.SynchronizeTimingsFinal,
-			mode_lib->vba.SynchronizeDRRDisplaysForUCLKPStateChangeFinal,
-			mode_lib->vba.DRRDisplay,
-			v->dpte_group_bytes,
-			v->meta_row_height,
-			v->meta_row_height_chroma,
+			v,
+			v->PrefetchModePerState[v->VoltageLevel][v->maxMpcComb],
+			v->DCFCLK,
+			v->ReturnBW,
 			v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.mmSOCParameters,
-			mode_lib->vba.WritebackChunkSize,
-			mode_lib->vba.SOCCLK,
+			v->SOCCLK,
 			v->DCFCLKDeepSleep,
-			mode_lib->vba.DETBufferSizeY,
-			mode_lib->vba.DETBufferSizeC,
-			mode_lib->vba.SwathHeightY,
-			mode_lib->vba.SwathHeightC,
-			mode_lib->vba.LBBitPerPixel,
+			v->DETBufferSizeY,
+			v->DETBufferSizeC,
+			v->SwathHeightY,
+			v->SwathHeightC,
 			v->SwathWidthY,
 			v->SwathWidthC,
-			mode_lib->vba.HRatio,
-			mode_lib->vba.HRatioChroma,
-			mode_lib->vba.vtaps,
-			mode_lib->vba.VTAPsChroma,
-			mode_lib->vba.VRatio,
-			mode_lib->vba.VRatioChroma,
-			mode_lib->vba.HTotal,
-			mode_lib->vba.VTotal,
-			mode_lib->vba.VActive,
-			mode_lib->vba.PixelClock,
-			mode_lib->vba.BlendingAndTiming,
-			mode_lib->vba.DPPPerPlane,
+			v->DPPPerPlane,
 			v->BytePerPixelDETY,
 			v->BytePerPixelDETC,
 			v->DSTXAfterScaler,
 			v->DSTYAfterScaler,
-			mode_lib->vba.WritebackEnable,
-			mode_lib->vba.WritebackPixelFormat,
-			mode_lib->vba.WritebackDestinationWidth,
-			mode_lib->vba.WritebackDestinationHeight,
-			mode_lib->vba.WritebackSourceHeight,
 			v->UnboundedRequestEnabled,
 			v->CompressedBufferSizeInkByte,
 
 			/* Output */
-			&v->Watermark,
 			&v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.dummy_dramchange_support,
 			v->MaxActiveDRAMClockChangeLatencySupported,
 			v->SubViewportLinesNeededInMALL,
@@ -1811,10 +1764,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				&mode_lib->vba.Read256BlockHeightC[k],
 				&mode_lib->vba.Read256BlockWidthY[k],
 				&mode_lib->vba.Read256BlockWidthC[k],
-				&mode_lib->vba.MicroTileHeightY[k],
-				&mode_lib->vba.MicroTileHeightC[k],
-				&mode_lib->vba.MicroTileWidthY[k],
-				&mode_lib->vba.MicroTileWidthC[k]);
+				&mode_lib->vba.MacroTileHeightY[k],
+				&mode_lib->vba.MacroTileHeightC[k],
+				&mode_lib->vba.MacroTileWidthY[k],
+				&mode_lib->vba.MacroTileWidthC[k]);
 	}
 
 	/*Bandwidth Support Check*/
@@ -1952,7 +1905,6 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	}
 
 	dml32_CalculateSwathAndDETConfiguration(
-			&v->dummy_vars.dml32_CalculateSwathAndDETConfiguration,
 			mode_lib->vba.DETSizeOverride,
 			mode_lib->vba.UsesMALLForPStateChange,
 			mode_lib->vba.ConfigReturnBufferSizeInKByte,
@@ -2040,6 +1992,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				dml32_CalculateODMMode(
 						mode_lib->vba.MaximumPixelsPerLinePerDSCUnit,
 						mode_lib->vba.HActive[k],
+						mode_lib->vba.OutputFormat[k],
 						mode_lib->vba.Output[k],
 						mode_lib->vba.ODMUse[k],
 						mode_lib->vba.MaxDispclk[i],
@@ -2061,6 +2014,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				dml32_CalculateODMMode(
 						mode_lib->vba.MaximumPixelsPerLinePerDSCUnit,
 						mode_lib->vba.HActive[k],
+						mode_lib->vba.OutputFormat[k],
 						mode_lib->vba.Output[k],
 						mode_lib->vba.ODMUse[k],
 						mode_lib->vba.MaxDispclk[i],
@@ -2549,7 +2503,6 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 			}
 
 			dml32_CalculateSwathAndDETConfiguration(
-					&v->dummy_vars.dml32_CalculateSwathAndDETConfiguration,
 					mode_lib->vba.DETSizeOverride,
 					mode_lib->vba.UsesMALLForPStateChange,
 					mode_lib->vba.ConfigReturnBufferSizeInKByte,
@@ -2666,10 +2619,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 			mode_lib->vba.Read256BlockWidthC,
 			mode_lib->vba.Read256BlockHeightY,
 			mode_lib->vba.Read256BlockHeightC,
-			mode_lib->vba.MicroTileWidthY,
-			mode_lib->vba.MicroTileWidthC,
-			mode_lib->vba.MicroTileHeightY,
-			mode_lib->vba.MicroTileHeightC,
+			mode_lib->vba.MacroTileWidthY,
+			mode_lib->vba.MacroTileWidthC,
+			mode_lib->vba.MacroTileHeightY,
+			mode_lib->vba.MacroTileHeightC,
 
 			/* Output */
 			mode_lib->vba.SurfaceSizeInMALL,
@@ -2716,10 +2669,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeight256BytesY = mode_lib->vba.Read256BlockHeightY[k];
 				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidth256BytesC = mode_lib->vba.Read256BlockWidthC[k];
 				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeight256BytesC = mode_lib->vba.Read256BlockHeightC[k];
-				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthY = mode_lib->vba.MicroTileWidthY[k];
-				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightY = mode_lib->vba.MicroTileHeightY[k];
-				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthC = mode_lib->vba.MicroTileWidthC[k];
-				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightC = mode_lib->vba.MicroTileHeightC[k];
+				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthY = mode_lib->vba.MacroTileWidthY[k];
+				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightY = mode_lib->vba.MacroTileHeightY[k];
+				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthC = mode_lib->vba.MacroTileWidthC[k];
+				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightC = mode_lib->vba.MacroTileHeightC[k];
 				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].InterlaceEnable = mode_lib->vba.Interlace[k];
 				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].HTotal = mode_lib->vba.HTotal[k];
 				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].DCCEnable = mode_lib->vba.DCCEnable[k];
@@ -2749,7 +2702,6 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 
 			{
 				dml32_CalculateVMRowAndSwath(
-						&v->dummy_vars.dml32_CalculateVMRowAndSwath,
 						mode_lib->vba.NumberOfActiveSurfaces,
 						v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters,
 						mode_lib->vba.SurfaceSizeInMALL,
@@ -3266,64 +3218,47 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 
 					mode_lib->vba.NoTimeForPrefetch[i][j][k] =
 						dml32_CalculatePrefetchSchedule(
-							&v->dummy_vars.dml32_CalculatePrefetchSchedule,
+							v,
+							k,
 							v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.HostVMInefficiencyFactor,
 							&v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.myPipe,
-							mode_lib->vba.DSCDelayPerState[i][k],
-							mode_lib->vba.DPPCLKDelaySubtotal +
-								mode_lib->vba.DPPCLKDelayCNVCFormater,
-							mode_lib->vba.DPPCLKDelaySCL,
-							mode_lib->vba.DPPCLKDelaySCLLBOnly,
-							mode_lib->vba.DPPCLKDelayCNVCCursor,
-							mode_lib->vba.DISPCLKDelaySubtotal,
-							mode_lib->vba.SwathWidthYThisState[k] /
-								mode_lib->vba.HRatio[k],
-							mode_lib->vba.OutputFormat[k],
-							mode_lib->vba.MaxInterDCNTileRepeaters,
-							dml_min(mode_lib->vba.MaxVStartup,
-									mode_lib->vba.MaximumVStartup[i][j][k]),
-							mode_lib->vba.MaximumVStartup[i][j][k],
-							mode_lib->vba.GPUVMMaxPageTableLevels,
-							mode_lib->vba.GPUVMEnable, mode_lib->vba.HostVMEnable,
-							mode_lib->vba.HostVMMaxNonCachedPageTableLevels,
-							mode_lib->vba.HostVMMinPageSize,
-							mode_lib->vba.DynamicMetadataEnable[k],
-							mode_lib->vba.DynamicMetadataVMEnabled,
-							mode_lib->vba.DynamicMetadataLinesBeforeActiveRequired[k],
-							mode_lib->vba.DynamicMetadataTransmittedBytes[k],
-							mode_lib->vba.UrgLatency[i],
-							mode_lib->vba.ExtraLatency,
-							mode_lib->vba.TimeCalc,
-							mode_lib->vba.PDEAndMetaPTEBytesPerFrame[i][j][k],
-							mode_lib->vba.MetaRowBytes[i][j][k],
-							mode_lib->vba.DPTEBytesPerRow[i][j][k],
-							mode_lib->vba.PrefetchLinesY[i][j][k],
-							mode_lib->vba.SwathWidthYThisState[k],
-							mode_lib->vba.PrefillY[k],
-							mode_lib->vba.MaxNumSwY[k],
-							mode_lib->vba.PrefetchLinesC[i][j][k],
-							mode_lib->vba.SwathWidthCThisState[k],
-							mode_lib->vba.PrefillC[k],
-							mode_lib->vba.MaxNumSwC[k],
-							mode_lib->vba.swath_width_luma_ub_this_state[k],
-							mode_lib->vba.swath_width_chroma_ub_this_state[k],
-							mode_lib->vba.SwathHeightYThisState[k],
-							mode_lib->vba.SwathHeightCThisState[k], mode_lib->vba.TWait,
+							v->DSCDelayPerState[i][k],
+							v->SwathWidthYThisState[k] / v->HRatio[k],
+							dml_min(v->MaxVStartup, v->MaximumVStartup[i][j][k]),
+							v->MaximumVStartup[i][j][k],
+							v->UrgLatency[i],
+							v->ExtraLatency,
+							v->TimeCalc,
+							v->PDEAndMetaPTEBytesPerFrame[i][j][k],
+							v->MetaRowBytes[i][j][k],
+							v->DPTEBytesPerRow[i][j][k],
+							v->PrefetchLinesY[i][j][k],
+							v->SwathWidthYThisState[k],
+							v->PrefillY[k],
+							v->MaxNumSwY[k],
+							v->PrefetchLinesC[i][j][k],
+							v->SwathWidthCThisState[k],
+							v->PrefillC[k],
+							v->MaxNumSwC[k],
+							v->swath_width_luma_ub_this_state[k],
+							v->swath_width_chroma_ub_this_state[k],
+							v->SwathHeightYThisState[k],
+							v->SwathHeightCThisState[k], v->TWait,
 
 							/* Output */
 							&v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTXAfterScaler[k],
 							&v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTYAfterScaler[k],
-							&mode_lib->vba.LineTimesForPrefetch[k],
-							&mode_lib->vba.PrefetchBW[k],
-							&mode_lib->vba.LinesForMetaPTE[k],
-							&mode_lib->vba.LinesForMetaAndDPTERow[k],
-							&mode_lib->vba.VRatioPreY[i][j][k],
-							&mode_lib->vba.VRatioPreC[i][j][k],
-							&mode_lib->vba.RequiredPrefetchPixelDataBWLuma[0][0][k],
-							&mode_lib->vba.RequiredPrefetchPixelDataBWChroma[0][0][k],
-							&mode_lib->vba.NoTimeForDynamicMetadata[i][j][k],
-							&mode_lib->vba.Tno_bw[k],
-							&mode_lib->vba.prefetch_vmrow_bw[k],
+							&v->LineTimesForPrefetch[k],
+							&v->PrefetchBW[k],
+							&v->LinesForMetaPTE[k],
+							&v->LinesForMetaAndDPTERow[k],
+							&v->VRatioPreY[i][j][k],
+							&v->VRatioPreC[i][j][k],
+							&v->RequiredPrefetchPixelDataBWLuma[0][0][k],
+							&v->RequiredPrefetchPixelDataBWChroma[0][0][k],
+							&v->NoTimeForDynamicMetadata[i][j][k],
+							&v->Tno_bw[k],
+							&v->prefetch_vmrow_bw[k],
 							&v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single[0],         // double *Tdmdl_vm
 							&v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single[1],         // double *Tdmdl
 							&v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single[2],         // double *TSetup
@@ -3566,63 +3501,32 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 
 			{
 				dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
-						&v->dummy_vars.dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport,
-						mode_lib->vba.USRRetrainingRequiredFinal,
-						mode_lib->vba.UsesMALLForPStateChange,
-						mode_lib->vba.PrefetchModePerState[i][j],
-						mode_lib->vba.NumberOfActiveSurfaces,
-						mode_lib->vba.MaxLineBufferLines,
-						mode_lib->vba.LineBufferSizeFinal,
-						mode_lib->vba.WritebackInterfaceBufferSize,
-						mode_lib->vba.DCFCLKState[i][j],
-						mode_lib->vba.ReturnBWPerState[i][j],
-						mode_lib->vba.SynchronizeTimingsFinal,
-						mode_lib->vba.SynchronizeDRRDisplaysForUCLKPStateChangeFinal,
-						mode_lib->vba.DRRDisplay,
-						mode_lib->vba.dpte_group_bytes,
-						mode_lib->vba.meta_row_height,
-						mode_lib->vba.meta_row_height_chroma,
+						v,
+						v->PrefetchModePerState[i][j],
+						v->DCFCLKState[i][j],
+						v->ReturnBWPerState[i][j],
 						v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.mSOCParameters,
-						mode_lib->vba.WritebackChunkSize,
-						mode_lib->vba.SOCCLKPerState[i],
-						mode_lib->vba.ProjectedDCFCLKDeepSleep[i][j],
-						mode_lib->vba.DETBufferSizeYThisState,
-						mode_lib->vba.DETBufferSizeCThisState,
-						mode_lib->vba.SwathHeightYThisState,
-						mode_lib->vba.SwathHeightCThisState,
-						mode_lib->vba.LBBitPerPixel,
-						mode_lib->vba.SwathWidthYThisState, // 24
-						mode_lib->vba.SwathWidthCThisState,
-						mode_lib->vba.HRatio,
-						mode_lib->vba.HRatioChroma,
-						mode_lib->vba.vtaps,
-						mode_lib->vba.VTAPsChroma,
-						mode_lib->vba.VRatio,
-						mode_lib->vba.VRatioChroma,
-						mode_lib->vba.HTotal,
-						mode_lib->vba.VTotal,
-						mode_lib->vba.VActive,
-						mode_lib->vba.PixelClock,
-						mode_lib->vba.BlendingAndTiming,
-						mode_lib->vba.NoOfDPPThisState,
-						mode_lib->vba.BytePerPixelInDETY,
-						mode_lib->vba.BytePerPixelInDETC,
+						v->SOCCLKPerState[i],
+						v->ProjectedDCFCLKDeepSleep[i][j],
+						v->DETBufferSizeYThisState,
+						v->DETBufferSizeCThisState,
+						v->SwathHeightYThisState,
+						v->SwathHeightCThisState,
+						v->SwathWidthYThisState, // 24
+						v->SwathWidthCThisState,
+						v->NoOfDPPThisState,
+						v->BytePerPixelInDETY,
+						v->BytePerPixelInDETC,
 						v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTXAfterScaler,
 						v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTYAfterScaler,
-						mode_lib->vba.WritebackEnable,
-						mode_lib->vba.WritebackPixelFormat,
-						mode_lib->vba.WritebackDestinationWidth,
-						mode_lib->vba.WritebackDestinationHeight,
-						mode_lib->vba.WritebackSourceHeight,
-						mode_lib->vba.UnboundedRequestEnabledThisState,
-						mode_lib->vba.CompressedBufferSizeInkByteThisState,
+						v->UnboundedRequestEnabledThisState,
+						v->CompressedBufferSizeInkByteThisState,
 
 						/* Output */
-						&mode_lib->vba.Watermark, // Store the values in vba
-						&mode_lib->vba.DRAMClockChangeSupport[i][j],
+						&v->DRAMClockChangeSupport[i][j],
 						&v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single2[0], // double *MaxActiveDRAMClockChangeLatencySupported
 						&v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_integer[0], // Long SubViewportLinesNeededInMALL[]
-						&mode_lib->vba.FCLKChangeSupport[i][j],
+						&v->FCLKChangeSupport[i][j],
 						&v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.dummy_single2[1], // double *MinActiveFCLKChangeLatencySupported
 						&mode_lib->vba.USRRetrainingSupport[i][j],
 						mode_lib->vba.ActiveDRAMClockChangeLatencyMargin);
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
index 07f8f3b8626b..365d290bba99 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
@@ -27,6 +27,8 @@
 #include "display_mode_vba_32.h"
 #include "../display_mode_lib.h"
 
+#define DCN32_MAX_FMT_420_BUFFER_WIDTH 4096
+
 unsigned int dml32_dscceComputeDelay(
 		unsigned int bpc,
 		double BPP,
@@ -391,7 +393,6 @@ void dml32_CalculateBytePerPixelAndBlockSizes(
 } // CalculateBytePerPixelAndBlockSizes
 
 void dml32_CalculateSwathAndDETConfiguration(
-		struct dml32_CalculateSwathAndDETConfiguration *st_vars,
 		unsigned int DETSizeOverride[],
 		enum dm_use_mall_for_pstate_change_mode UseMALLForPStateChange[],
 		unsigned int ConfigReturnBufferSizeInKByte,
@@ -456,10 +457,18 @@ void dml32_CalculateSwathAndDETConfiguration(
 		bool ViewportSizeSupportPerSurface[],
 		bool *ViewportSizeSupport)
 {
+	unsigned int MaximumSwathHeightY[DC__NUM_DPP__MAX];
+	unsigned int MaximumSwathHeightC[DC__NUM_DPP__MAX];
+	unsigned int RoundedUpMaxSwathSizeBytesY[DC__NUM_DPP__MAX];
+	unsigned int RoundedUpMaxSwathSizeBytesC[DC__NUM_DPP__MAX];
+	unsigned int RoundedUpSwathSizeBytesY;
+	unsigned int RoundedUpSwathSizeBytesC;
+	double SwathWidthdoubleDPP[DC__NUM_DPP__MAX];
+	double SwathWidthdoubleDPPChroma[DC__NUM_DPP__MAX];
 	unsigned int k;
-
-	st_vars->TotalActiveDPP = 0;
-	st_vars->NoChromaSurfaces = true;
+	unsigned int TotalActiveDPP = 0;
+	bool NoChromaSurfaces = true;
+	unsigned int DETBufferSizeInKByteForSwathCalculation;
 
 #ifdef __DML_VBA_DEBUG__
 	dml_print("DML::%s: ForceSingleDPP = %d\n", __func__, ForceSingleDPP);
@@ -494,43 +503,43 @@ void dml32_CalculateSwathAndDETConfiguration(
 			DPPPerSurface,
 
 			/* Output */
-			st_vars->SwathWidthdoubleDPP,
-			st_vars->SwathWidthdoubleDPPChroma,
+			SwathWidthdoubleDPP,
+			SwathWidthdoubleDPPChroma,
 			SwathWidth,
 			SwathWidthChroma,
-			st_vars->MaximumSwathHeightY,
-			st_vars->MaximumSwathHeightC,
+			MaximumSwathHeightY,
+			MaximumSwathHeightC,
 			swath_width_luma_ub,
 			swath_width_chroma_ub);
 
 	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
-		st_vars->RoundedUpMaxSwathSizeBytesY[k] = swath_width_luma_ub[k] * BytePerPixDETY[k] * st_vars->MaximumSwathHeightY[k];
-		st_vars->RoundedUpMaxSwathSizeBytesC[k] = swath_width_chroma_ub[k] * BytePerPixDETC[k] * st_vars->MaximumSwathHeightC[k];
+		RoundedUpMaxSwathSizeBytesY[k] = swath_width_luma_ub[k] * BytePerPixDETY[k] * MaximumSwathHeightY[k];
+		RoundedUpMaxSwathSizeBytesC[k] = swath_width_chroma_ub[k] * BytePerPixDETC[k] * MaximumSwathHeightC[k];
 #ifdef __DML_VBA_DEBUG__
 		dml_print("DML::%s: k=%0d DPPPerSurface = %d\n", __func__, k, DPPPerSurface[k]);
 		dml_print("DML::%s: k=%0d swath_width_luma_ub = %d\n", __func__, k, swath_width_luma_ub[k]);
 		dml_print("DML::%s: k=%0d BytePerPixDETY = %f\n", __func__, k, BytePerPixDETY[k]);
-		dml_print("DML::%s: k=%0d MaximumSwathHeightY = %d\n", __func__, k, st_vars->MaximumSwathHeightY[k]);
+		dml_print("DML::%s: k=%0d MaximumSwathHeightY = %d\n", __func__, k, MaximumSwathHeightY[k]);
 		dml_print("DML::%s: k=%0d RoundedUpMaxSwathSizeBytesY = %d\n", __func__, k,
-				st_vars->RoundedUpMaxSwathSizeBytesY[k]);
+				RoundedUpMaxSwathSizeBytesY[k]);
 		dml_print("DML::%s: k=%0d swath_width_chroma_ub = %d\n", __func__, k, swath_width_chroma_ub[k]);
 		dml_print("DML::%s: k=%0d BytePerPixDETC = %f\n", __func__, k, BytePerPixDETC[k]);
-		dml_print("DML::%s: k=%0d MaximumSwathHeightC = %d\n", __func__, k, st_vars->MaximumSwathHeightC[k]);
+		dml_print("DML::%s: k=%0d MaximumSwathHeightC = %d\n", __func__, k, MaximumSwathHeightC[k]);
 		dml_print("DML::%s: k=%0d RoundedUpMaxSwathSizeBytesC = %d\n", __func__, k,
-				st_vars->RoundedUpMaxSwathSizeBytesC[k]);
+				RoundedUpMaxSwathSizeBytesC[k]);
 #endif
 
 		if (SourcePixelFormat[k] == dm_420_10) {
-			st_vars->RoundedUpMaxSwathSizeBytesY[k] = dml_ceil((unsigned int) st_vars->RoundedUpMaxSwathSizeBytesY[k], 256);
-			st_vars->RoundedUpMaxSwathSizeBytesC[k] = dml_ceil((unsigned int) st_vars->RoundedUpMaxSwathSizeBytesC[k], 256);
+			RoundedUpMaxSwathSizeBytesY[k] = dml_ceil((unsigned int) RoundedUpMaxSwathSizeBytesY[k], 256);
+			RoundedUpMaxSwathSizeBytesC[k] = dml_ceil((unsigned int) RoundedUpMaxSwathSizeBytesC[k], 256);
 		}
 	}
 
 	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
-		st_vars->TotalActiveDPP = st_vars->TotalActiveDPP + (ForceSingleDPP ? 1 : DPPPerSurface[k]);
+		TotalActiveDPP = TotalActiveDPP + (ForceSingleDPP ? 1 : DPPPerSurface[k]);
 		if (SourcePixelFormat[k] == dm_420_8 || SourcePixelFormat[k] == dm_420_10 ||
 				SourcePixelFormat[k] == dm_420_12 || SourcePixelFormat[k] == dm_rgbe_alpha) {
-			st_vars->NoChromaSurfaces = false;
+			NoChromaSurfaces = false;
 		}
 	}
 
@@ -540,10 +549,10 @@ void dml32_CalculateSwathAndDETConfiguration(
 	// if unbounded req is enabled, program reserved space such that the ROB will not hold more than 8 swaths worth of data
 	// - assume worst-case compression rate of 4. [ROB size - 8 * swath_size / max_compression ratio]
 	// - assume for "narrow" vp case in which the ROB can fit 8 swaths, the DET should be big enough to do full size req
-	*CompBufReservedSpaceNeedAdjustment = ((int) ROBSizeKBytes - (int) *CompBufReservedSpaceKBytes) > (int) (st_vars->RoundedUpMaxSwathSizeBytesY[0]/512);
+	*CompBufReservedSpaceNeedAdjustment = ((int) ROBSizeKBytes - (int) *CompBufReservedSpaceKBytes) > (int) (RoundedUpMaxSwathSizeBytesY[0]/512);
 
 	if (*CompBufReservedSpaceNeedAdjustment == 1) {
-		*CompBufReservedSpaceKBytes = ROBSizeKBytes - st_vars->RoundedUpMaxSwathSizeBytesY[0]/512;
+		*CompBufReservedSpaceKBytes = ROBSizeKBytes - RoundedUpMaxSwathSizeBytesY[0]/512;
 	}
 
 	#ifdef __DML_VBA_DEBUG__
@@ -551,7 +560,7 @@ void dml32_CalculateSwathAndDETConfiguration(
 		dml_print("DML::%s: CompBufReservedSpaceNeedAdjustment  = %d\n",  __func__, *CompBufReservedSpaceNeedAdjustment);
 	#endif
 
-	*UnboundedRequestEnabled = dml32_UnboundedRequest(UseUnboundedRequestingFinal, st_vars->TotalActiveDPP, st_vars->NoChromaSurfaces, Output[0], SurfaceTiling[0], *CompBufReservedSpaceNeedAdjustment, DisableUnboundRequestIfCompBufReservedSpaceNeedAdjustment);
+	*UnboundedRequestEnabled = dml32_UnboundedRequest(UseUnboundedRequestingFinal, TotalActiveDPP, NoChromaSurfaces, Output[0], SurfaceTiling[0], *CompBufReservedSpaceNeedAdjustment, DisableUnboundRequestIfCompBufReservedSpaceNeedAdjustment);
 
 	dml32_CalculateDETBufferSize(DETSizeOverride,
 			UseMALLForPStateChange,
@@ -566,8 +575,8 @@ void dml32_CalculateSwathAndDETConfiguration(
 			SourcePixelFormat,
 			ReadBandwidthLuma,
 			ReadBandwidthChroma,
-			st_vars->RoundedUpMaxSwathSizeBytesY,
-			st_vars->RoundedUpMaxSwathSizeBytesC,
+			RoundedUpMaxSwathSizeBytesY,
+			RoundedUpMaxSwathSizeBytesC,
 			DPPPerSurface,
 
 			/* Output */
@@ -575,7 +584,7 @@ void dml32_CalculateSwathAndDETConfiguration(
 			CompressedBufferSizeInkByte);
 
 #ifdef __DML_VBA_DEBUG__
-	dml_print("DML::%s: TotalActiveDPP = %d\n", __func__, st_vars->TotalActiveDPP);
+	dml_print("DML::%s: TotalActiveDPP = %d\n", __func__, TotalActiveDPP);
 	dml_print("DML::%s: nomDETInKByte = %d\n", __func__, nomDETInKByte);
 	dml_print("DML::%s: ConfigReturnBufferSizeInKByte = %d\n", __func__, ConfigReturnBufferSizeInKByte);
 	dml_print("DML::%s: UseUnboundedRequestingFinal = %d\n", __func__, UseUnboundedRequestingFinal);
@@ -586,42 +595,42 @@ void dml32_CalculateSwathAndDETConfiguration(
 	*ViewportSizeSupport = true;
 	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
 
-		st_vars->DETBufferSizeInKByteForSwathCalculation = (UseMALLForPStateChange[k] ==
+		DETBufferSizeInKByteForSwathCalculation = (UseMALLForPStateChange[k] ==
 				dm_use_mall_pstate_change_phantom_pipe ? 1024 : DETBufferSizeInKByte[k]);
 #ifdef __DML_VBA_DEBUG__
 		dml_print("DML::%s: k=%0d DETBufferSizeInKByteForSwathCalculation = %d\n", __func__, k,
-				st_vars->DETBufferSizeInKByteForSwathCalculation);
+				DETBufferSizeInKByteForSwathCalculation);
 #endif
 
-		if (st_vars->RoundedUpMaxSwathSizeBytesY[k] + st_vars->RoundedUpMaxSwathSizeBytesC[k] <=
-				st_vars->DETBufferSizeInKByteForSwathCalculation * 1024 / 2) {
-			SwathHeightY[k] = st_vars->MaximumSwathHeightY[k];
-			SwathHeightC[k] = st_vars->MaximumSwathHeightC[k];
-			st_vars->RoundedUpSwathSizeBytesY = st_vars->RoundedUpMaxSwathSizeBytesY[k];
-			st_vars->RoundedUpSwathSizeBytesC = st_vars->RoundedUpMaxSwathSizeBytesC[k];
-		} else if (st_vars->RoundedUpMaxSwathSizeBytesY[k] >= 1.5 * st_vars->RoundedUpMaxSwathSizeBytesC[k] &&
-				st_vars->RoundedUpMaxSwathSizeBytesY[k] / 2 + st_vars->RoundedUpMaxSwathSizeBytesC[k] <=
-				st_vars->DETBufferSizeInKByteForSwathCalculation * 1024 / 2) {
-			SwathHeightY[k] = st_vars->MaximumSwathHeightY[k] / 2;
-			SwathHeightC[k] = st_vars->MaximumSwathHeightC[k];
-			st_vars->RoundedUpSwathSizeBytesY = st_vars->RoundedUpMaxSwathSizeBytesY[k] / 2;
-			st_vars->RoundedUpSwathSizeBytesC = st_vars->RoundedUpMaxSwathSizeBytesC[k];
-		} else if (st_vars->RoundedUpMaxSwathSizeBytesY[k] < 1.5 * st_vars->RoundedUpMaxSwathSizeBytesC[k] &&
-				st_vars->RoundedUpMaxSwathSizeBytesY[k] + st_vars->RoundedUpMaxSwathSizeBytesC[k] / 2 <=
-				st_vars->DETBufferSizeInKByteForSwathCalculation * 1024 / 2) {
-			SwathHeightY[k] = st_vars->MaximumSwathHeightY[k];
-			SwathHeightC[k] = st_vars->MaximumSwathHeightC[k] / 2;
-			st_vars->RoundedUpSwathSizeBytesY = st_vars->RoundedUpMaxSwathSizeBytesY[k];
-			st_vars->RoundedUpSwathSizeBytesC = st_vars->RoundedUpMaxSwathSizeBytesC[k] / 2;
+		if (RoundedUpMaxSwathSizeBytesY[k] + RoundedUpMaxSwathSizeBytesC[k] <=
+				DETBufferSizeInKByteForSwathCalculation * 1024 / 2) {
+			SwathHeightY[k] = MaximumSwathHeightY[k];
+			SwathHeightC[k] = MaximumSwathHeightC[k];
+			RoundedUpSwathSizeBytesY = RoundedUpMaxSwathSizeBytesY[k];
+			RoundedUpSwathSizeBytesC = RoundedUpMaxSwathSizeBytesC[k];
+		} else if (RoundedUpMaxSwathSizeBytesY[k] >= 1.5 * RoundedUpMaxSwathSizeBytesC[k] &&
+				RoundedUpMaxSwathSizeBytesY[k] / 2 + RoundedUpMaxSwathSizeBytesC[k] <=
+				DETBufferSizeInKByteForSwathCalculation * 1024 / 2) {
+			SwathHeightY[k] = MaximumSwathHeightY[k] / 2;
+			SwathHeightC[k] = MaximumSwathHeightC[k];
+			RoundedUpSwathSizeBytesY = RoundedUpMaxSwathSizeBytesY[k] / 2;
+			RoundedUpSwathSizeBytesC = RoundedUpMaxSwathSizeBytesC[k];
+		} else if (RoundedUpMaxSwathSizeBytesY[k] < 1.5 * RoundedUpMaxSwathSizeBytesC[k] &&
+				RoundedUpMaxSwathSizeBytesY[k] + RoundedUpMaxSwathSizeBytesC[k] / 2 <=
+				DETBufferSizeInKByteForSwathCalculation * 1024 / 2) {
+			SwathHeightY[k] = MaximumSwathHeightY[k];
+			SwathHeightC[k] = MaximumSwathHeightC[k] / 2;
+			RoundedUpSwathSizeBytesY = RoundedUpMaxSwathSizeBytesY[k];
+			RoundedUpSwathSizeBytesC = RoundedUpMaxSwathSizeBytesC[k] / 2;
 		} else {
-			SwathHeightY[k] = st_vars->MaximumSwathHeightY[k] / 2;
-			SwathHeightC[k] = st_vars->MaximumSwathHeightC[k] / 2;
-			st_vars->RoundedUpSwathSizeBytesY = st_vars->RoundedUpMaxSwathSizeBytesY[k] / 2;
-			st_vars->RoundedUpSwathSizeBytesC = st_vars->RoundedUpMaxSwathSizeBytesC[k] / 2;
+			SwathHeightY[k] = MaximumSwathHeightY[k] / 2;
+			SwathHeightC[k] = MaximumSwathHeightC[k] / 2;
+			RoundedUpSwathSizeBytesY = RoundedUpMaxSwathSizeBytesY[k] / 2;
+			RoundedUpSwathSizeBytesC = RoundedUpMaxSwathSizeBytesC[k] / 2;
 		}
 
-		if ((st_vars->RoundedUpMaxSwathSizeBytesY[k] / 2 + st_vars->RoundedUpMaxSwathSizeBytesC[k] / 2 >
-				st_vars->DETBufferSizeInKByteForSwathCalculation * 1024 / 2)
+		if ((RoundedUpMaxSwathSizeBytesY[k] / 2 + RoundedUpMaxSwathSizeBytesC[k] / 2 >
+				DETBufferSizeInKByteForSwathCalculation * 1024 / 2)
 				|| SwathWidth[k] > MaximumSwathWidthLuma[k] || (SwathHeightC[k] > 0 &&
 						SwathWidthChroma[k] > MaximumSwathWidthChroma[k])) {
 			*ViewportSizeSupport = false;
@@ -636,7 +645,7 @@ void dml32_CalculateSwathAndDETConfiguration(
 #endif
 			DETBufferSizeY[k] = DETBufferSizeInKByte[k] * 1024;
 			DETBufferSizeC[k] = 0;
-		} else if (st_vars->RoundedUpSwathSizeBytesY <= 1.5 * st_vars->RoundedUpSwathSizeBytesC) {
+		} else if (RoundedUpSwathSizeBytesY <= 1.5 * RoundedUpSwathSizeBytesC) {
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML::%s: k=%0d Half DET for plane0, half for plane1\n", __func__, k);
 #endif
@@ -654,11 +663,11 @@ void dml32_CalculateSwathAndDETConfiguration(
 		dml_print("DML::%s: k=%0d SwathHeightY = %d\n", __func__, k, SwathHeightY[k]);
 		dml_print("DML::%s: k=%0d SwathHeightC = %d\n", __func__, k, SwathHeightC[k]);
 		dml_print("DML::%s: k=%0d RoundedUpMaxSwathSizeBytesY = %d\n", __func__,
-				k, st_vars->RoundedUpMaxSwathSizeBytesY[k]);
+				k, RoundedUpMaxSwathSizeBytesY[k]);
 		dml_print("DML::%s: k=%0d RoundedUpMaxSwathSizeBytesC = %d\n", __func__,
-				k, st_vars->RoundedUpMaxSwathSizeBytesC[k]);
-		dml_print("DML::%s: k=%0d RoundedUpSwathSizeBytesY = %d\n", __func__, k, st_vars->RoundedUpSwathSizeBytesY);
-		dml_print("DML::%s: k=%0d RoundedUpSwathSizeBytesC = %d\n", __func__, k, st_vars->RoundedUpSwathSizeBytesC);
+				k, RoundedUpMaxSwathSizeBytesC[k]);
+		dml_print("DML::%s: k=%0d RoundedUpSwathSizeBytesY = %d\n", __func__, k, RoundedUpSwathSizeBytesY);
+		dml_print("DML::%s: k=%0d RoundedUpSwathSizeBytesC = %d\n", __func__, k, RoundedUpSwathSizeBytesC);
 		dml_print("DML::%s: k=%0d DETBufferSizeInKByte = %d\n", __func__, k, DETBufferSizeInKByte[k]);
 		dml_print("DML::%s: k=%0d DETBufferSizeY = %d\n", __func__, k, DETBufferSizeY[k]);
 		dml_print("DML::%s: k=%0d DETBufferSizeC = %d\n", __func__, k, DETBufferSizeC[k]);
@@ -1175,6 +1184,7 @@ void dml32_CalculateDETBufferSize(
 void dml32_CalculateODMMode(
 		unsigned int MaximumPixelsPerLinePerDSCUnit,
 		unsigned int HActive,
+		enum output_format_class OutFormat,
 		enum output_encoder_class Output,
 		enum odm_combine_policy ODMUse,
 		double StateDispclk,
@@ -1246,6 +1256,29 @@ void dml32_CalculateODMMode(
 		else
 			*TotalAvailablePipesSupport = false;
 	}
+	if (OutFormat == dm_420 && HActive > DCN32_MAX_FMT_420_BUFFER_WIDTH &&
+			ODMUse != dm_odm_combine_policy_4to1) {
+		if (HActive > DCN32_MAX_FMT_420_BUFFER_WIDTH * 4) {
+			*ODMMode = dm_odm_combine_mode_disabled;
+			*NumberOfDPP = 0;
+			*TotalAvailablePipesSupport = false;
+		} else if (HActive > DCN32_MAX_FMT_420_BUFFER_WIDTH * 2 ||
+				*ODMMode == dm_odm_combine_mode_4to1) {
+			*ODMMode = dm_odm_combine_mode_4to1;
+			*RequiredDISPCLKPerSurface = SurfaceRequiredDISPCLKWithODMCombineFourToOne;
+			*NumberOfDPP = 4;
+		} else {
+			*ODMMode = dm_odm_combine_mode_2to1;
+			*RequiredDISPCLKPerSurface = SurfaceRequiredDISPCLKWithODMCombineTwoToOne;
+			*NumberOfDPP = 2;
+		}
+	}
+	if (Output == dm_hdmi && OutFormat == dm_420 &&
+			HActive > DCN32_MAX_FMT_420_BUFFER_WIDTH) {
+		*ODMMode = dm_odm_combine_mode_disabled;
+		*NumberOfDPP = 0;
+		*TotalAvailablePipesSupport = false;
+	}
 }
 
 double dml32_CalculateRequiredDispclk(
@@ -1867,7 +1900,6 @@ void dml32_CalculateSurfaceSizeInMall(
 } // CalculateSurfaceSizeInMall
 
 void dml32_CalculateVMRowAndSwath(
-		struct dml32_CalculateVMRowAndSwath *st_vars,
 		unsigned int NumberOfActiveSurfaces,
 		DmlPipe myPipe[],
 		unsigned int SurfaceSizeInMALL[],
@@ -1933,6 +1965,21 @@ void dml32_CalculateVMRowAndSwath(
 		unsigned int BIGK_FRAGMENT_SIZE[])
 {
 	unsigned int k;
+	unsigned int PTEBufferSizeInRequestsForLuma[DC__NUM_DPP__MAX];
+	unsigned int PTEBufferSizeInRequestsForChroma[DC__NUM_DPP__MAX];
+	unsigned int PDEAndMetaPTEBytesFrameY;
+	unsigned int PDEAndMetaPTEBytesFrameC;
+	unsigned int MetaRowByteY[DC__NUM_DPP__MAX];
+	unsigned int MetaRowByteC[DC__NUM_DPP__MAX];
+	unsigned int PixelPTEBytesPerRowY[DC__NUM_DPP__MAX];
+	unsigned int PixelPTEBytesPerRowC[DC__NUM_DPP__MAX];
+	unsigned int PixelPTEBytesPerRowY_one_row_per_frame[DC__NUM_DPP__MAX];
+	unsigned int PixelPTEBytesPerRowC_one_row_per_frame[DC__NUM_DPP__MAX];
+	unsigned int dpte_row_width_luma_ub_one_row_per_frame[DC__NUM_DPP__MAX];
+	unsigned int dpte_row_height_luma_one_row_per_frame[DC__NUM_DPP__MAX];
+	unsigned int dpte_row_width_chroma_ub_one_row_per_frame[DC__NUM_DPP__MAX];
+	unsigned int dpte_row_height_chroma_one_row_per_frame[DC__NUM_DPP__MAX];
+	bool one_row_per_frame_fits_in_buffer[DC__NUM_DPP__MAX];
 
 	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
 		if (HostVMEnable == true) {
@@ -1954,15 +2001,15 @@ void dml32_CalculateVMRowAndSwath(
 				myPipe[k].SourcePixelFormat == dm_rgbe_alpha) {
 			if ((myPipe[k].SourcePixelFormat == dm_420_10 || myPipe[k].SourcePixelFormat == dm_420_12) &&
 					!IsVertical(myPipe[k].SourceRotation)) {
-				st_vars->PTEBufferSizeInRequestsForLuma[k] =
+				PTEBufferSizeInRequestsForLuma[k] =
 						(PTEBufferSizeInRequestsLuma + PTEBufferSizeInRequestsChroma) / 2;
-				st_vars->PTEBufferSizeInRequestsForChroma[k] = st_vars->PTEBufferSizeInRequestsForLuma[k];
+				PTEBufferSizeInRequestsForChroma[k] = PTEBufferSizeInRequestsForLuma[k];
 			} else {
-				st_vars->PTEBufferSizeInRequestsForLuma[k] = PTEBufferSizeInRequestsLuma;
-				st_vars->PTEBufferSizeInRequestsForChroma[k] = PTEBufferSizeInRequestsChroma;
+				PTEBufferSizeInRequestsForLuma[k] = PTEBufferSizeInRequestsLuma;
+				PTEBufferSizeInRequestsForChroma[k] = PTEBufferSizeInRequestsChroma;
 			}
 
-			st_vars->PDEAndMetaPTEBytesFrameC = dml32_CalculateVMAndRowBytes(
+			PDEAndMetaPTEBytesFrameC = dml32_CalculateVMAndRowBytes(
 					myPipe[k].ViewportStationary,
 					myPipe[k].DCCEnable,
 					myPipe[k].DPPPerSurface,
@@ -1982,21 +2029,21 @@ void dml32_CalculateVMRowAndSwath(
 					GPUVMMaxPageTableLevels,
 					GPUVMMinPageSizeKBytes[k],
 					HostVMMinPageSize,
-					st_vars->PTEBufferSizeInRequestsForChroma[k],
+					PTEBufferSizeInRequestsForChroma[k],
 					myPipe[k].PitchC,
 					myPipe[k].DCCMetaPitchC,
 					myPipe[k].BlockWidthC,
 					myPipe[k].BlockHeightC,
 
 					/* Output */
-					&st_vars->MetaRowByteC[k],
-					&st_vars->PixelPTEBytesPerRowC[k],
+					&MetaRowByteC[k],
+					&PixelPTEBytesPerRowC[k],
 					&dpte_row_width_chroma_ub[k],
 					&dpte_row_height_chroma[k],
 					&dpte_row_height_linear_chroma[k],
-					&st_vars->PixelPTEBytesPerRowC_one_row_per_frame[k],
-					&st_vars->dpte_row_width_chroma_ub_one_row_per_frame[k],
-					&st_vars->dpte_row_height_chroma_one_row_per_frame[k],
+					&PixelPTEBytesPerRowC_one_row_per_frame[k],
+					&dpte_row_width_chroma_ub_one_row_per_frame[k],
+					&dpte_row_height_chroma_one_row_per_frame[k],
 					&meta_req_width_chroma[k],
 					&meta_req_height_chroma[k],
 					&meta_row_width_chroma[k],
@@ -2024,19 +2071,19 @@ void dml32_CalculateVMRowAndSwath(
 					&VInitPreFillC[k],
 					&MaxNumSwathC[k]);
 		} else {
-			st_vars->PTEBufferSizeInRequestsForLuma[k] = PTEBufferSizeInRequestsLuma + PTEBufferSizeInRequestsChroma;
-			st_vars->PTEBufferSizeInRequestsForChroma[k] = 0;
-			st_vars->PixelPTEBytesPerRowC[k] = 0;
-			st_vars->PDEAndMetaPTEBytesFrameC = 0;
-			st_vars->MetaRowByteC[k] = 0;
+			PTEBufferSizeInRequestsForLuma[k] = PTEBufferSizeInRequestsLuma + PTEBufferSizeInRequestsChroma;
+			PTEBufferSizeInRequestsForChroma[k] = 0;
+			PixelPTEBytesPerRowC[k] = 0;
+			PDEAndMetaPTEBytesFrameC = 0;
+			MetaRowByteC[k] = 0;
 			MaxNumSwathC[k] = 0;
 			PrefetchSourceLinesC[k] = 0;
-			st_vars->dpte_row_height_chroma_one_row_per_frame[k] = 0;
-			st_vars->dpte_row_width_chroma_ub_one_row_per_frame[k] = 0;
-			st_vars->PixelPTEBytesPerRowC_one_row_per_frame[k] = 0;
+			dpte_row_height_chroma_one_row_per_frame[k] = 0;
+			dpte_row_width_chroma_ub_one_row_per_frame[k] = 0;
+			PixelPTEBytesPerRowC_one_row_per_frame[k] = 0;
 		}
 
-		st_vars->PDEAndMetaPTEBytesFrameY = dml32_CalculateVMAndRowBytes(
+		PDEAndMetaPTEBytesFrameY = dml32_CalculateVMAndRowBytes(
 				myPipe[k].ViewportStationary,
 				myPipe[k].DCCEnable,
 				myPipe[k].DPPPerSurface,
@@ -2056,21 +2103,21 @@ void dml32_CalculateVMRowAndSwath(
 				GPUVMMaxPageTableLevels,
 				GPUVMMinPageSizeKBytes[k],
 				HostVMMinPageSize,
-				st_vars->PTEBufferSizeInRequestsForLuma[k],
+				PTEBufferSizeInRequestsForLuma[k],
 				myPipe[k].PitchY,
 				myPipe[k].DCCMetaPitchY,
 				myPipe[k].BlockWidthY,
 				myPipe[k].BlockHeightY,
 
 				/* Output */
-				&st_vars->MetaRowByteY[k],
-				&st_vars->PixelPTEBytesPerRowY[k],
+				&MetaRowByteY[k],
+				&PixelPTEBytesPerRowY[k],
 				&dpte_row_width_luma_ub[k],
 				&dpte_row_height_luma[k],
 				&dpte_row_height_linear_luma[k],
-				&st_vars->PixelPTEBytesPerRowY_one_row_per_frame[k],
-				&st_vars->dpte_row_width_luma_ub_one_row_per_frame[k],
-				&st_vars->dpte_row_height_luma_one_row_per_frame[k],
+				&PixelPTEBytesPerRowY_one_row_per_frame[k],
+				&dpte_row_width_luma_ub_one_row_per_frame[k],
+				&dpte_row_height_luma_one_row_per_frame[k],
 				&meta_req_width[k],
 				&meta_req_height[k],
 				&meta_row_width[k],
@@ -2098,19 +2145,19 @@ void dml32_CalculateVMRowAndSwath(
 				&VInitPreFillY[k],
 				&MaxNumSwathY[k]);
 
-		PDEAndMetaPTEBytesFrame[k] = st_vars->PDEAndMetaPTEBytesFrameY + st_vars->PDEAndMetaPTEBytesFrameC;
-		MetaRowByte[k] = st_vars->MetaRowByteY[k] + st_vars->MetaRowByteC[k];
+		PDEAndMetaPTEBytesFrame[k] = PDEAndMetaPTEBytesFrameY + PDEAndMetaPTEBytesFrameC;
+		MetaRowByte[k] = MetaRowByteY[k] + MetaRowByteC[k];
 
-		if (st_vars->PixelPTEBytesPerRowY[k] <= 64 * st_vars->PTEBufferSizeInRequestsForLuma[k] &&
-				st_vars->PixelPTEBytesPerRowC[k] <= 64 * st_vars->PTEBufferSizeInRequestsForChroma[k]) {
+		if (PixelPTEBytesPerRowY[k] <= 64 * PTEBufferSizeInRequestsForLuma[k] &&
+				PixelPTEBytesPerRowC[k] <= 64 * PTEBufferSizeInRequestsForChroma[k]) {
 			PTEBufferSizeNotExceeded[k] = true;
 		} else {
 			PTEBufferSizeNotExceeded[k] = false;
 		}
 
-		st_vars->one_row_per_frame_fits_in_buffer[k] = (st_vars->PixelPTEBytesPerRowY_one_row_per_frame[k] <= 64 * 2 *
-			st_vars->PTEBufferSizeInRequestsForLuma[k] &&
-			st_vars->PixelPTEBytesPerRowC_one_row_per_frame[k] <= 64 * 2 * st_vars->PTEBufferSizeInRequestsForChroma[k]);
+		one_row_per_frame_fits_in_buffer[k] = (PixelPTEBytesPerRowY_one_row_per_frame[k] <= 64 * 2 *
+			PTEBufferSizeInRequestsForLuma[k] &&
+			PixelPTEBytesPerRowC_one_row_per_frame[k] <= 64 * 2 * PTEBufferSizeInRequestsForChroma[k]);
 	}
 
 	dml32_CalculateMALLUseForStaticScreen(
@@ -2118,7 +2165,7 @@ void dml32_CalculateVMRowAndSwath(
 			MALLAllocatedForDCN,
 			UseMALLForStaticScreen,   // mode
 			SurfaceSizeInMALL,
-			st_vars->one_row_per_frame_fits_in_buffer,
+			one_row_per_frame_fits_in_buffer,
 			/* Output */
 			UsesMALLForStaticScreen); // boolen
 
@@ -2144,13 +2191,13 @@ void dml32_CalculateVMRowAndSwath(
 				!(UseMALLForPStateChange[k] == dm_use_mall_pstate_change_full_frame);
 
 		if (use_one_row_for_frame[k]) {
-			dpte_row_height_luma[k] = st_vars->dpte_row_height_luma_one_row_per_frame[k];
-			dpte_row_width_luma_ub[k] = st_vars->dpte_row_width_luma_ub_one_row_per_frame[k];
-			st_vars->PixelPTEBytesPerRowY[k] = st_vars->PixelPTEBytesPerRowY_one_row_per_frame[k];
-			dpte_row_height_chroma[k] = st_vars->dpte_row_height_chroma_one_row_per_frame[k];
-			dpte_row_width_chroma_ub[k] = st_vars->dpte_row_width_chroma_ub_one_row_per_frame[k];
-			st_vars->PixelPTEBytesPerRowC[k] = st_vars->PixelPTEBytesPerRowC_one_row_per_frame[k];
-			PTEBufferSizeNotExceeded[k] = st_vars->one_row_per_frame_fits_in_buffer[k];
+			dpte_row_height_luma[k] = dpte_row_height_luma_one_row_per_frame[k];
+			dpte_row_width_luma_ub[k] = dpte_row_width_luma_ub_one_row_per_frame[k];
+			PixelPTEBytesPerRowY[k] = PixelPTEBytesPerRowY_one_row_per_frame[k];
+			dpte_row_height_chroma[k] = dpte_row_height_chroma_one_row_per_frame[k];
+			dpte_row_width_chroma_ub[k] = dpte_row_width_chroma_ub_one_row_per_frame[k];
+			PixelPTEBytesPerRowC[k] = PixelPTEBytesPerRowC_one_row_per_frame[k];
+			PTEBufferSizeNotExceeded[k] = one_row_per_frame_fits_in_buffer[k];
 		}
 
 		if (MetaRowByte[k] <= DCCMetaBufferSizeBytes)
@@ -2158,7 +2205,7 @@ void dml32_CalculateVMRowAndSwath(
 		else
 			DCCMetaBufferSizeNotExceeded[k] = false;
 
-		PixelPTEBytesPerRow[k] = st_vars->PixelPTEBytesPerRowY[k] + st_vars->PixelPTEBytesPerRowC[k];
+		PixelPTEBytesPerRow[k] = PixelPTEBytesPerRowY[k] + PixelPTEBytesPerRowC[k];
 		if (use_one_row_for_frame[k])
 			PixelPTEBytesPerRow[k] = PixelPTEBytesPerRow[k] / 2;
 
@@ -2169,11 +2216,11 @@ void dml32_CalculateVMRowAndSwath(
 				myPipe[k].VRatioChroma,
 				myPipe[k].DCCEnable,
 				myPipe[k].HTotal / myPipe[k].PixelClock,
-				st_vars->MetaRowByteY[k], st_vars->MetaRowByteC[k],
+				MetaRowByteY[k], MetaRowByteC[k],
 				meta_row_height[k],
 				meta_row_height_chroma[k],
-				st_vars->PixelPTEBytesPerRowY[k],
-				st_vars->PixelPTEBytesPerRowC[k],
+				PixelPTEBytesPerRowY[k],
+				PixelPTEBytesPerRowC[k],
 				dpte_row_height_luma[k],
 				dpte_row_height_chroma[k],
 
@@ -2189,12 +2236,12 @@ void dml32_CalculateVMRowAndSwath(
 		dml_print("DML::%s: k=%d, dpte_row_height_luma         = %d\n",  __func__, k, dpte_row_height_luma[k]);
 		dml_print("DML::%s: k=%d, dpte_row_width_luma_ub       = %d\n",
 				__func__, k, dpte_row_width_luma_ub[k]);
-		dml_print("DML::%s: k=%d, PixelPTEBytesPerRowY         = %d\n",  __func__, k, st_vars->PixelPTEBytesPerRowY[k]);
+		dml_print("DML::%s: k=%d, PixelPTEBytesPerRowY         = %d\n",  __func__, k, PixelPTEBytesPerRowY[k]);
 		dml_print("DML::%s: k=%d, dpte_row_height_chroma       = %d\n",
 				__func__, k, dpte_row_height_chroma[k]);
 		dml_print("DML::%s: k=%d, dpte_row_width_chroma_ub     = %d\n",
 				__func__, k, dpte_row_width_chroma_ub[k]);
-		dml_print("DML::%s: k=%d, PixelPTEBytesPerRowC         = %d\n",  __func__, k, st_vars->PixelPTEBytesPerRowC[k]);
+		dml_print("DML::%s: k=%d, PixelPTEBytesPerRowC         = %d\n",  __func__, k, PixelPTEBytesPerRowC[k]);
 		dml_print("DML::%s: k=%d, PixelPTEBytesPerRow          = %d\n",  __func__, k, PixelPTEBytesPerRow[k]);
 		dml_print("DML::%s: k=%d, PTEBufferSizeNotExceeded     = %d\n",
 				__func__, k, PTEBufferSizeNotExceeded[k]);
@@ -3342,29 +3389,14 @@ double dml32_CalculateExtraLatency(
 } // CalculateExtraLatency
 
 bool dml32_CalculatePrefetchSchedule(
-		struct dml32_CalculatePrefetchSchedule *st_vars,
+		struct vba_vars_st *v,
+		unsigned int k,
 		double HostVMInefficiencyFactor,
 		DmlPipe *myPipe,
 		unsigned int DSCDelay,
-		double DPPCLKDelaySubtotalPlusCNVCFormater,
-		double DPPCLKDelaySCL,
-		double DPPCLKDelaySCLLBOnly,
-		double DPPCLKDelayCNVCCursor,
-		double DISPCLKDelaySubtotal,
 		unsigned int DPP_RECOUT_WIDTH,
-		enum output_format_class OutputFormat,
-		unsigned int MaxInterDCNTileRepeaters,
 		unsigned int VStartup,
 		unsigned int MaxVStartup,
-		unsigned int GPUVMPageTableLevels,
-		bool GPUVMEnable,
-		bool HostVMEnable,
-		unsigned int HostVMMaxNonCachedPageTableLevels,
-		double HostVMMinPageSize,
-		bool DynamicMetadataEnable,
-		bool DynamicMetadataVMEnabled,
-		int DynamicMetadataLinesBeforeActiveRequired,
-		unsigned int DynamicMetadataTransmittedBytes,
 		double UrgentLatency,
 		double UrgentExtraLatency,
 		double TCalc,
@@ -3405,72 +3437,100 @@ bool dml32_CalculatePrefetchSchedule(
 		double   *VUpdateWidthPix,
 		double   *VReadyOffsetPix)
 {
+	double DPPCLKDelaySubtotalPlusCNVCFormater = v->DPPCLKDelaySubtotal + v->DPPCLKDelayCNVCFormater;
 	bool MyError = false;
-
-	st_vars->TimeForFetchingMetaPTE = 0;
-	st_vars->TimeForFetchingRowInVBlank = 0;
-	st_vars->LinesToRequestPrefetchPixelData = 0;
-	st_vars->max_vratio_pre = __DML_MAX_VRATIO_PRE__;
-	st_vars->Tsw_est1 = 0;
-	st_vars->Tsw_est3 = 0;
-
-	if (GPUVMEnable == true && HostVMEnable == true)
-		st_vars->HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels;
+	unsigned int DPPCycles, DISPCLKCycles;
+	double DSTTotalPixelsAfterScaler;
+	double LineTime;
+	double dst_y_prefetch_equ;
+	double prefetch_bw_oto;
+	double Tvm_oto;
+	double Tr0_oto;
+	double Tvm_oto_lines;
+	double Tr0_oto_lines;
+	double dst_y_prefetch_oto;
+	double TimeForFetchingMetaPTE = 0;
+	double TimeForFetchingRowInVBlank = 0;
+	double LinesToRequestPrefetchPixelData = 0;
+	unsigned int HostVMDynamicLevelsTrips;
+	double  trip_to_mem;
+	double  Tvm_trips;
+	double  Tr0_trips;
+	double  Tvm_trips_rounded;
+	double  Tr0_trips_rounded;
+	double  Lsw_oto;
+	double  Tpre_rounded;
+	double  prefetch_bw_equ;
+	double  Tvm_equ;
+	double  Tr0_equ;
+	double  Tdmbf;
+	double  Tdmec;
+	double  Tdmsks;
+	double  prefetch_sw_bytes;
+	double  bytes_pp;
+	double  dep_bytes;
+	unsigned int max_vratio_pre = __DML_MAX_VRATIO_PRE__;
+	double  min_Lsw;
+	double  Tsw_est1 = 0;
+	double  Tsw_est3 = 0;
+
+	if (v->GPUVMEnable == true && v->HostVMEnable == true)
+		HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels;
 	else
-		st_vars->HostVMDynamicLevelsTrips = 0;
+		HostVMDynamicLevelsTrips = 0;
 #ifdef __DML_VBA_DEBUG__
-	dml_print("DML::%s: GPUVMEnable = %d\n", __func__, GPUVMEnable);
-	dml_print("DML::%s: GPUVMPageTableLevels = %d\n", __func__, GPUVMPageTableLevels);
+	dml_print("DML::%s: v->GPUVMEnable = %d\n", __func__, v->GPUVMEnable);
+	dml_print("DML::%s: v->GPUVMMaxPageTableLevels = %d\n", __func__, v->GPUVMMaxPageTableLevels);
 	dml_print("DML::%s: DCCEnable = %d\n", __func__, myPipe->DCCEnable);
-	dml_print("DML::%s: HostVMEnable=%d HostVMInefficiencyFactor=%f\n",
-			__func__, HostVMEnable, HostVMInefficiencyFactor);
+	dml_print("DML::%s: v->HostVMEnable=%d HostVMInefficiencyFactor=%f\n",
+			__func__, v->HostVMEnable, HostVMInefficiencyFactor);
 #endif
 	dml32_CalculateVUpdateAndDynamicMetadataParameters(
-			MaxInterDCNTileRepeaters,
+			v->MaxInterDCNTileRepeaters,
 			myPipe->Dppclk,
 			myPipe->Dispclk,
 			myPipe->DCFClkDeepSleep,
 			myPipe->PixelClock,
 			myPipe->HTotal,
 			myPipe->VBlank,
-			DynamicMetadataTransmittedBytes,
-			DynamicMetadataLinesBeforeActiveRequired,
+			v->DynamicMetadataTransmittedBytes[k],
+			v->DynamicMetadataLinesBeforeActiveRequired[k],
 			myPipe->InterlaceEnable,
 			myPipe->ProgressiveToInterlaceUnitInOPP,
 			TSetup,
 
 			/* output */
-			&st_vars->Tdmbf,
-			&st_vars->Tdmec,
-			&st_vars->Tdmsks,
+			&Tdmbf,
+			&Tdmec,
+			&Tdmsks,
 			VUpdateOffsetPix,
 			VUpdateWidthPix,
 			VReadyOffsetPix);
 
-	st_vars->LineTime = myPipe->HTotal / myPipe->PixelClock;
-	st_vars->trip_to_mem = UrgentLatency;
-	st_vars->Tvm_trips = UrgentExtraLatency + st_vars->trip_to_mem * (GPUVMPageTableLevels * (st_vars->HostVMDynamicLevelsTrips + 1) - 1);
+	LineTime = myPipe->HTotal / myPipe->PixelClock;
+	trip_to_mem = UrgentLatency;
+	Tvm_trips = UrgentExtraLatency + trip_to_mem * (v->GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1);
 
-	if (DynamicMetadataVMEnabled == true)
-		*Tdmdl = TWait + st_vars->Tvm_trips + st_vars->trip_to_mem;
+	if (v->DynamicMetadataVMEnabled == true)
+		*Tdmdl = TWait + Tvm_trips + trip_to_mem;
 	else
 		*Tdmdl = TWait + UrgentExtraLatency;
 
 #ifdef __DML_VBA_ALLOW_DELTA__
-	if (DynamicMetadataEnable == false)
+	if (v->DynamicMetadataEnable[k] == false)
 		*Tdmdl = 0.0;
 #endif
 
-	if (DynamicMetadataEnable == true) {
-		if (VStartup * st_vars->LineTime < *TSetup + *Tdmdl + st_vars->Tdmbf + st_vars->Tdmec + st_vars->Tdmsks) {
+	if (v->DynamicMetadataEnable[k] == true) {
+		if (VStartup * LineTime < *TSetup + *Tdmdl + Tdmbf + Tdmec + Tdmsks) {
 			*NotEnoughTimeForDynamicMetadata = true;
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML::%s: Not Enough Time for Dynamic Meta!\n", __func__);
 			dml_print("DML::%s: Tdmbf: %fus - time for dmd transfer from dchub to dio output buffer\n",
-					__func__, st_vars->Tdmbf);
-			dml_print("DML::%s: Tdmec: %fus - time dio takes to transfer dmd\n", __func__, st_vars->Tdmec);
+					__func__, Tdmbf);
+			dml_print("DML::%s: Tdmec: %fus - time dio takes to transfer dmd\n", __func__, Tdmec);
 			dml_print("DML::%s: Tdmsks: %fus - time before active dmd must complete transmission at dio\n",
-					__func__, st_vars->Tdmsks);
+					__func__, Tdmsks);
 			dml_print("DML::%s: Tdmdl: %fus - time for fabric to become ready and fetch dmd\n",
 					__func__, *Tdmdl);
 #endif
@@ -3481,22 +3541,22 @@ bool dml32_CalculatePrefetchSchedule(
 		*NotEnoughTimeForDynamicMetadata = false;
 	}
 
-	*Tdmdl_vm =  (DynamicMetadataEnable == true && DynamicMetadataVMEnabled == true &&
-			GPUVMEnable == true ? TWait + st_vars->Tvm_trips : 0);
+	*Tdmdl_vm =  (v->DynamicMetadataEnable[k] == true && v->DynamicMetadataVMEnabled == true &&
+			v->GPUVMEnable == true ? TWait + Tvm_trips : 0);
 
 	if (myPipe->ScalerEnabled)
-		st_vars->DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCL;
+		DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + v->DPPCLKDelaySCL;
 	else
-		st_vars->DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + DPPCLKDelaySCLLBOnly;
+		DPPCycles = DPPCLKDelaySubtotalPlusCNVCFormater + v->DPPCLKDelaySCLLBOnly;
 
-	st_vars->DPPCycles = st_vars->DPPCycles + myPipe->NumberOfCursors * DPPCLKDelayCNVCCursor;
+	DPPCycles = DPPCycles + myPipe->NumberOfCursors * v->DPPCLKDelayCNVCCursor;
 
-	st_vars->DISPCLKCycles = DISPCLKDelaySubtotal;
+	DISPCLKCycles = v->DISPCLKDelaySubtotal;
 
 	if (myPipe->Dppclk == 0.0 || myPipe->Dispclk == 0.0)
 		return true;
 
-	*DSTXAfterScaler = st_vars->DPPCycles * myPipe->PixelClock / myPipe->Dppclk + st_vars->DISPCLKCycles *
+	*DSTXAfterScaler = DPPCycles * myPipe->PixelClock / myPipe->Dppclk + DISPCLKCycles *
 			myPipe->PixelClock / myPipe->Dispclk + DSCDelay;
 
 	*DSTXAfterScaler = *DSTXAfterScaler + (myPipe->ODMMode != dm_odm_combine_mode_disabled ? 18 : 0)
@@ -3506,10 +3566,10 @@ bool dml32_CalculatePrefetchSchedule(
 			+ ((myPipe->ODMMode == dm_odm_mode_mso_1to4) ? myPipe->HActive * 3 / 4 : 0);
 
 #ifdef __DML_VBA_DEBUG__
-	dml_print("DML::%s: DPPCycles: %d\n", __func__, st_vars->DPPCycles);
+	dml_print("DML::%s: DPPCycles: %d\n", __func__, DPPCycles);
 	dml_print("DML::%s: PixelClock: %f\n", __func__, myPipe->PixelClock);
 	dml_print("DML::%s: Dppclk: %f\n", __func__, myPipe->Dppclk);
-	dml_print("DML::%s: DISPCLKCycles: %d\n", __func__, st_vars->DISPCLKCycles);
+	dml_print("DML::%s: DISPCLKCycles: %d\n", __func__, DISPCLKCycles);
 	dml_print("DML::%s: DISPCLK: %f\n", __func__,  myPipe->Dispclk);
 	dml_print("DML::%s: DSCDelay: %d\n", __func__,  DSCDelay);
 	dml_print("DML::%s: ODMMode: %d\n", __func__,  myPipe->ODMMode);
@@ -3517,14 +3577,14 @@ bool dml32_CalculatePrefetchSchedule(
 	dml_print("DML::%s: DSTXAfterScaler: %d\n", __func__,  *DSTXAfterScaler);
 #endif
 
-	if (OutputFormat == dm_420 || (myPipe->InterlaceEnable && myPipe->ProgressiveToInterlaceUnitInOPP))
+	if (v->OutputFormat[k] == dm_420 || (myPipe->InterlaceEnable && myPipe->ProgressiveToInterlaceUnitInOPP))
 		*DSTYAfterScaler = 1;
 	else
 		*DSTYAfterScaler = 0;
 
-	st_vars->DSTTotalPixelsAfterScaler = *DSTYAfterScaler * myPipe->HTotal + *DSTXAfterScaler;
-	*DSTYAfterScaler = dml_floor(st_vars->DSTTotalPixelsAfterScaler / myPipe->HTotal, 1);
-	*DSTXAfterScaler = st_vars->DSTTotalPixelsAfterScaler - ((double) (*DSTYAfterScaler * myPipe->HTotal));
+	DSTTotalPixelsAfterScaler = *DSTYAfterScaler * myPipe->HTotal + *DSTXAfterScaler;
+	*DSTYAfterScaler = dml_floor(DSTTotalPixelsAfterScaler / myPipe->HTotal, 1);
+	*DSTXAfterScaler = DSTTotalPixelsAfterScaler - ((double) (*DSTYAfterScaler * myPipe->HTotal));
 #ifdef __DML_VBA_DEBUG__
 	dml_print("DML::%s: DSTXAfterScaler: %d (final)\n", __func__,  *DSTXAfterScaler);
 	dml_print("DML::%s: DSTYAfterScaler: %d (final)\n", __func__, *DSTYAfterScaler);
@@ -3532,132 +3592,132 @@ bool dml32_CalculatePrefetchSchedule(
 
 	MyError = false;
 
-	st_vars->Tr0_trips = st_vars->trip_to_mem * (st_vars->HostVMDynamicLevelsTrips + 1);
-
-	if (GPUVMEnable == true) {
-		st_vars->Tvm_trips_rounded = dml_ceil(4.0 * st_vars->Tvm_trips / st_vars->LineTime, 1.0) / 4.0 * st_vars->LineTime;
-		st_vars->Tr0_trips_rounded = dml_ceil(4.0 * st_vars->Tr0_trips / st_vars->LineTime, 1.0) / 4.0 * st_vars->LineTime;
-		if (GPUVMPageTableLevels >= 3) {
-			*Tno_bw = UrgentExtraLatency + st_vars->trip_to_mem *
-					(double) ((GPUVMPageTableLevels - 2) * (st_vars->HostVMDynamicLevelsTrips + 1) - 1);
-		} else if (GPUVMPageTableLevels == 1 && myPipe->DCCEnable != true) {
-			st_vars->Tr0_trips_rounded = dml_ceil(4.0 * UrgentExtraLatency / st_vars->LineTime, 1.0) /
-					4.0 * st_vars->LineTime; // VBA_ERROR
+	Tr0_trips = trip_to_mem * (HostVMDynamicLevelsTrips + 1);
+
+	if (v->GPUVMEnable == true) {
+		Tvm_trips_rounded = dml_ceil(4.0 * Tvm_trips / LineTime, 1.0) / 4.0 * LineTime;
+		Tr0_trips_rounded = dml_ceil(4.0 * Tr0_trips / LineTime, 1.0) / 4.0 * LineTime;
+		if (v->GPUVMMaxPageTableLevels >= 3) {
+			*Tno_bw = UrgentExtraLatency + trip_to_mem *
+					(double) ((v->GPUVMMaxPageTableLevels - 2) * (HostVMDynamicLevelsTrips + 1) - 1);
+		} else if (v->GPUVMMaxPageTableLevels == 1 && myPipe->DCCEnable != true) {
+			Tr0_trips_rounded = dml_ceil(4.0 * UrgentExtraLatency / LineTime, 1.0) /
+					4.0 * LineTime; // VBA_ERROR
 			*Tno_bw = UrgentExtraLatency;
 		} else {
 			*Tno_bw = 0;
 		}
 	} else if (myPipe->DCCEnable == true) {
-		st_vars->Tvm_trips_rounded = st_vars->LineTime / 4.0;
-		st_vars->Tr0_trips_rounded = dml_ceil(4.0 * st_vars->Tr0_trips / st_vars->LineTime, 1.0) / 4.0 * st_vars->LineTime;
+		Tvm_trips_rounded = LineTime / 4.0;
+		Tr0_trips_rounded = dml_ceil(4.0 * Tr0_trips / LineTime, 1.0) / 4.0 * LineTime;
 		*Tno_bw = 0;
 	} else {
-		st_vars->Tvm_trips_rounded = st_vars->LineTime / 4.0;
-		st_vars->Tr0_trips_rounded = st_vars->LineTime / 2.0;
+		Tvm_trips_rounded = LineTime / 4.0;
+		Tr0_trips_rounded = LineTime / 2.0;
 		*Tno_bw = 0;
 	}
-	st_vars->Tvm_trips_rounded = dml_max(st_vars->Tvm_trips_rounded, st_vars->LineTime / 4.0);
-	st_vars->Tr0_trips_rounded = dml_max(st_vars->Tr0_trips_rounded, st_vars->LineTime / 4.0);
+	Tvm_trips_rounded = dml_max(Tvm_trips_rounded, LineTime / 4.0);
+	Tr0_trips_rounded = dml_max(Tr0_trips_rounded, LineTime / 4.0);
 
 	if (myPipe->SourcePixelFormat == dm_420_8 || myPipe->SourcePixelFormat == dm_420_10
 			|| myPipe->SourcePixelFormat == dm_420_12) {
-		st_vars->bytes_pp = myPipe->BytePerPixelY + myPipe->BytePerPixelC / 4;
+		bytes_pp = myPipe->BytePerPixelY + myPipe->BytePerPixelC / 4;
 	} else {
-		st_vars->bytes_pp = myPipe->BytePerPixelY + myPipe->BytePerPixelC;
+		bytes_pp = myPipe->BytePerPixelY + myPipe->BytePerPixelC;
 	}
 
-	st_vars->prefetch_sw_bytes = PrefetchSourceLinesY * swath_width_luma_ub * myPipe->BytePerPixelY
+	prefetch_sw_bytes = PrefetchSourceLinesY * swath_width_luma_ub * myPipe->BytePerPixelY
 			+ PrefetchSourceLinesC * swath_width_chroma_ub * myPipe->BytePerPixelC;
-	st_vars->prefetch_bw_oto = dml_max(st_vars->bytes_pp * myPipe->PixelClock / myPipe->DPPPerSurface,
-			st_vars->prefetch_sw_bytes / (dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) * st_vars->LineTime));
-
-	st_vars->min_Lsw = dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) / st_vars->max_vratio_pre;
-	st_vars->min_Lsw = dml_max(st_vars->min_Lsw, 1.0);
-	st_vars->Lsw_oto = dml_ceil(4.0 * dml_max(st_vars->prefetch_sw_bytes / st_vars->prefetch_bw_oto / st_vars->LineTime, st_vars->min_Lsw), 1.0) / 4.0;
-
-	if (GPUVMEnable == true) {
-		st_vars->Tvm_oto = dml_max3(
-				st_vars->Tvm_trips,
-				*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / st_vars->prefetch_bw_oto,
-				st_vars->LineTime / 4.0);
+	prefetch_bw_oto = dml_max(bytes_pp * myPipe->PixelClock / myPipe->DPPPerSurface,
+			prefetch_sw_bytes / (dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) * LineTime));
+
+	min_Lsw = dml_max(PrefetchSourceLinesY, PrefetchSourceLinesC) / max_vratio_pre;
+	min_Lsw = dml_max(min_Lsw, 1.0);
+	Lsw_oto = dml_ceil(4.0 * dml_max(prefetch_sw_bytes / prefetch_bw_oto / LineTime, min_Lsw), 1.0) / 4.0;
+
+	if (v->GPUVMEnable == true) {
+		Tvm_oto = dml_max3(
+				Tvm_trips,
+				*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / prefetch_bw_oto,
+				LineTime / 4.0);
 	} else
-		st_vars->Tvm_oto = st_vars->LineTime / 4.0;
-
-	if ((GPUVMEnable == true || myPipe->DCCEnable == true)) {
-		st_vars->Tr0_oto = dml_max4(
-				st_vars->Tr0_trips,
-				(MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / st_vars->prefetch_bw_oto,
-				(st_vars->LineTime - st_vars->Tvm_oto)/2.0,
-				st_vars->LineTime / 4.0);
+		Tvm_oto = LineTime / 4.0;
+
+	if ((v->GPUVMEnable == true || myPipe->DCCEnable == true)) {
+		Tr0_oto = dml_max4(
+				Tr0_trips,
+				(MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_oto,
+				(LineTime - Tvm_oto)/2.0,
+				LineTime / 4.0);
 #ifdef __DML_VBA_DEBUG__
 		dml_print("DML::%s: Tr0_oto max0 = %f\n", __func__,
-				(MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / st_vars->prefetch_bw_oto);
-		dml_print("DML::%s: Tr0_oto max1 = %f\n", __func__, st_vars->Tr0_trips);
-		dml_print("DML::%s: Tr0_oto max2 = %f\n", __func__, st_vars->LineTime - st_vars->Tvm_oto);
-		dml_print("DML::%s: Tr0_oto max3 = %f\n", __func__, st_vars->LineTime / 4);
+				(MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) / prefetch_bw_oto);
+		dml_print("DML::%s: Tr0_oto max1 = %f\n", __func__, Tr0_trips);
+		dml_print("DML::%s: Tr0_oto max2 = %f\n", __func__, LineTime - Tvm_oto);
+		dml_print("DML::%s: Tr0_oto max3 = %f\n", __func__, LineTime / 4);
 #endif
 	} else
-		st_vars->Tr0_oto = (st_vars->LineTime - st_vars->Tvm_oto) / 2.0;
+		Tr0_oto = (LineTime - Tvm_oto) / 2.0;
 
-	st_vars->Tvm_oto_lines = dml_ceil(4.0 * st_vars->Tvm_oto / st_vars->LineTime, 1) / 4.0;
-	st_vars->Tr0_oto_lines = dml_ceil(4.0 * st_vars->Tr0_oto / st_vars->LineTime, 1) / 4.0;
-	st_vars->dst_y_prefetch_oto = st_vars->Tvm_oto_lines + 2 * st_vars->Tr0_oto_lines + st_vars->Lsw_oto;
+	Tvm_oto_lines = dml_ceil(4.0 * Tvm_oto / LineTime, 1) / 4.0;
+	Tr0_oto_lines = dml_ceil(4.0 * Tr0_oto / LineTime, 1) / 4.0;
+	dst_y_prefetch_oto = Tvm_oto_lines + 2 * Tr0_oto_lines + Lsw_oto;
 
-	st_vars->dst_y_prefetch_equ = VStartup - (*TSetup + dml_max(TWait + TCalc, *Tdmdl)) / st_vars->LineTime -
+	dst_y_prefetch_equ = VStartup - (*TSetup + dml_max(TWait + TCalc, *Tdmdl)) / LineTime -
 			(*DSTYAfterScaler + (double) *DSTXAfterScaler / (double) myPipe->HTotal);
 
 #ifdef __DML_VBA_DEBUG__
 	dml_print("DML::%s: HTotal = %d\n", __func__, myPipe->HTotal);
-	dml_print("DML::%s: min_Lsw = %f\n", __func__, st_vars->min_Lsw);
+	dml_print("DML::%s: min_Lsw = %f\n", __func__, min_Lsw);
 	dml_print("DML::%s: *Tno_bw = %f\n", __func__, *Tno_bw);
 	dml_print("DML::%s: UrgentExtraLatency = %f\n", __func__, UrgentExtraLatency);
-	dml_print("DML::%s: trip_to_mem = %f\n", __func__, st_vars->trip_to_mem);
+	dml_print("DML::%s: trip_to_mem = %f\n", __func__, trip_to_mem);
 	dml_print("DML::%s: BytePerPixelY = %d\n", __func__, myPipe->BytePerPixelY);
 	dml_print("DML::%s: PrefetchSourceLinesY = %f\n", __func__, PrefetchSourceLinesY);
 	dml_print("DML::%s: swath_width_luma_ub = %d\n", __func__, swath_width_luma_ub);
 	dml_print("DML::%s: BytePerPixelC = %d\n", __func__, myPipe->BytePerPixelC);
 	dml_print("DML::%s: PrefetchSourceLinesC = %f\n", __func__, PrefetchSourceLinesC);
 	dml_print("DML::%s: swath_width_chroma_ub = %d\n", __func__, swath_width_chroma_ub);
-	dml_print("DML::%s: prefetch_sw_bytes = %f\n", __func__, st_vars->prefetch_sw_bytes);
-	dml_print("DML::%s: bytes_pp = %f\n", __func__, st_vars->bytes_pp);
+	dml_print("DML::%s: prefetch_sw_bytes = %f\n", __func__, prefetch_sw_bytes);
+	dml_print("DML::%s: bytes_pp = %f\n", __func__, bytes_pp);
 	dml_print("DML::%s: PDEAndMetaPTEBytesFrame = %d\n", __func__, PDEAndMetaPTEBytesFrame);
 	dml_print("DML::%s: MetaRowByte = %d\n", __func__, MetaRowByte);
 	dml_print("DML::%s: PixelPTEBytesPerRow = %d\n", __func__, PixelPTEBytesPerRow);
 	dml_print("DML::%s: HostVMInefficiencyFactor = %f\n", __func__, HostVMInefficiencyFactor);
-	dml_print("DML::%s: Tvm_trips = %f\n", __func__, st_vars->Tvm_trips);
-	dml_print("DML::%s: Tr0_trips = %f\n", __func__, st_vars->Tr0_trips);
-	dml_print("DML::%s: prefetch_bw_oto = %f\n", __func__, st_vars->prefetch_bw_oto);
-	dml_print("DML::%s: Tr0_oto = %f\n", __func__, st_vars->Tr0_oto);
-	dml_print("DML::%s: Tvm_oto = %f\n", __func__, st_vars->Tvm_oto);
-	dml_print("DML::%s: Tvm_oto_lines = %f\n", __func__, st_vars->Tvm_oto_lines);
-	dml_print("DML::%s: Tr0_oto_lines = %f\n", __func__, st_vars->Tr0_oto_lines);
-	dml_print("DML::%s: Lsw_oto = %f\n", __func__, st_vars->Lsw_oto);
-	dml_print("DML::%s: dst_y_prefetch_oto = %f\n", __func__, st_vars->dst_y_prefetch_oto);
-	dml_print("DML::%s: dst_y_prefetch_equ = %f\n", __func__, st_vars->dst_y_prefetch_equ);
+	dml_print("DML::%s: Tvm_trips = %f\n", __func__, Tvm_trips);
+	dml_print("DML::%s: Tr0_trips = %f\n", __func__, Tr0_trips);
+	dml_print("DML::%s: prefetch_bw_oto = %f\n", __func__, prefetch_bw_oto);
+	dml_print("DML::%s: Tr0_oto = %f\n", __func__, Tr0_oto);
+	dml_print("DML::%s: Tvm_oto = %f\n", __func__, Tvm_oto);
+	dml_print("DML::%s: Tvm_oto_lines = %f\n", __func__, Tvm_oto_lines);
+	dml_print("DML::%s: Tr0_oto_lines = %f\n", __func__, Tr0_oto_lines);
+	dml_print("DML::%s: Lsw_oto = %f\n", __func__, Lsw_oto);
+	dml_print("DML::%s: dst_y_prefetch_oto = %f\n", __func__, dst_y_prefetch_oto);
+	dml_print("DML::%s: dst_y_prefetch_equ = %f\n", __func__, dst_y_prefetch_equ);
 #endif
 
-	st_vars->dst_y_prefetch_equ = dml_floor(4.0 * (st_vars->dst_y_prefetch_equ + 0.125), 1) / 4.0;
-	st_vars->Tpre_rounded = st_vars->dst_y_prefetch_equ * st_vars->LineTime;
+	dst_y_prefetch_equ = dml_floor(4.0 * (dst_y_prefetch_equ + 0.125), 1) / 4.0;
+	Tpre_rounded = dst_y_prefetch_equ * LineTime;
 #ifdef __DML_VBA_DEBUG__
-	dml_print("DML::%s: dst_y_prefetch_equ: %f (after round)\n", __func__, st_vars->dst_y_prefetch_equ);
-	dml_print("DML::%s: LineTime: %f\n", __func__, st_vars->LineTime);
+	dml_print("DML::%s: dst_y_prefetch_equ: %f (after round)\n", __func__, dst_y_prefetch_equ);
+	dml_print("DML::%s: LineTime: %f\n", __func__, LineTime);
 	dml_print("DML::%s: VStartup: %d\n", __func__, VStartup);
 	dml_print("DML::%s: Tvstartup: %fus - time between vstartup and first pixel of active\n",
-			__func__, VStartup * st_vars->LineTime);
+			__func__, VStartup * LineTime);
 	dml_print("DML::%s: TSetup: %fus - time from vstartup to vready\n", __func__, *TSetup);
 	dml_print("DML::%s: TCalc: %fus - time for calculations in dchub starting at vready\n", __func__, TCalc);
-	dml_print("DML::%s: Tdmbf: %fus - time for dmd transfer from dchub to dio output buffer\n", __func__, st_vars->Tdmbf);
-	dml_print("DML::%s: Tdmec: %fus - time dio takes to transfer dmd\n", __func__, st_vars->Tdmec);
+	dml_print("DML::%s: Tdmbf: %fus - time for dmd transfer from dchub to dio output buffer\n", __func__, Tdmbf);
+	dml_print("DML::%s: Tdmec: %fus - time dio takes to transfer dmd\n", __func__, Tdmec);
 	dml_print("DML::%s: Tdmdl_vm: %fus - time for vm stages of dmd\n", __func__, *Tdmdl_vm);
 	dml_print("DML::%s: Tdmdl: %fus - time for fabric to become ready and fetch dmd\n", __func__, *Tdmdl);
 	dml_print("DML::%s: DSTYAfterScaler: %d lines - number of lines of pipeline and buffer delay after scaler\n",
 			__func__, *DSTYAfterScaler);
 #endif
-	st_vars->dep_bytes = dml_max(PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor,
+	dep_bytes = dml_max(PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor,
 			MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor);
 
-	if (st_vars->prefetch_sw_bytes < st_vars->dep_bytes)
-		st_vars->prefetch_sw_bytes = 2 * st_vars->dep_bytes;
+	if (prefetch_sw_bytes < dep_bytes)
+		prefetch_sw_bytes = 2 * dep_bytes;
 
 	*PrefetchBandwidth = 0;
 	*DestinationLinesToRequestVMInVBlank = 0;
@@ -3665,61 +3725,61 @@ bool dml32_CalculatePrefetchSchedule(
 	*VRatioPrefetchY = 0;
 	*VRatioPrefetchC = 0;
 	*RequiredPrefetchPixDataBWLuma = 0;
-	if (st_vars->dst_y_prefetch_equ > 1) {
+	if (dst_y_prefetch_equ > 1) {
 		double PrefetchBandwidth1;
 		double PrefetchBandwidth2;
 		double PrefetchBandwidth3;
 		double PrefetchBandwidth4;
 
-		if (st_vars->Tpre_rounded - *Tno_bw > 0) {
+		if (Tpre_rounded - *Tno_bw > 0) {
 			PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte
 					+ 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor
-					+ st_vars->prefetch_sw_bytes) / (st_vars->Tpre_rounded - *Tno_bw);
-			st_vars->Tsw_est1 = st_vars->prefetch_sw_bytes / PrefetchBandwidth1;
+					+ prefetch_sw_bytes) / (Tpre_rounded - *Tno_bw);
+			Tsw_est1 = prefetch_sw_bytes / PrefetchBandwidth1;
 		} else
 			PrefetchBandwidth1 = 0;
 
-		if (VStartup == MaxVStartup && (st_vars->Tsw_est1 / st_vars->LineTime < st_vars->min_Lsw)
-				&& st_vars->Tpre_rounded - st_vars->min_Lsw * st_vars->LineTime - 0.75 * st_vars->LineTime - *Tno_bw > 0) {
+		if (VStartup == MaxVStartup && (Tsw_est1 / LineTime < min_Lsw)
+				&& Tpre_rounded - min_Lsw * LineTime - 0.75 * LineTime - *Tno_bw > 0) {
 			PrefetchBandwidth1 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + 2 * MetaRowByte
 					+ 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor)
-					/ (st_vars->Tpre_rounded - st_vars->min_Lsw * st_vars->LineTime - 0.75 * st_vars->LineTime - *Tno_bw);
+					/ (Tpre_rounded - min_Lsw * LineTime - 0.75 * LineTime - *Tno_bw);
 		}
 
-		if (st_vars->Tpre_rounded - *Tno_bw - 2 * st_vars->Tr0_trips_rounded > 0)
-			PrefetchBandwidth2 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + st_vars->prefetch_sw_bytes) /
-			(st_vars->Tpre_rounded - *Tno_bw - 2 * st_vars->Tr0_trips_rounded);
+		if (Tpre_rounded - *Tno_bw - 2 * Tr0_trips_rounded > 0)
+			PrefetchBandwidth2 = (PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor + prefetch_sw_bytes) /
+			(Tpre_rounded - *Tno_bw - 2 * Tr0_trips_rounded);
 		else
 			PrefetchBandwidth2 = 0;
 
-		if (st_vars->Tpre_rounded - st_vars->Tvm_trips_rounded > 0) {
+		if (Tpre_rounded - Tvm_trips_rounded > 0) {
 			PrefetchBandwidth3 = (2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor
-					+ st_vars->prefetch_sw_bytes) / (st_vars->Tpre_rounded - st_vars->Tvm_trips_rounded);
-			st_vars->Tsw_est3 = st_vars->prefetch_sw_bytes / PrefetchBandwidth3;
+					+ prefetch_sw_bytes) / (Tpre_rounded - Tvm_trips_rounded);
+			Tsw_est3 = prefetch_sw_bytes / PrefetchBandwidth3;
 		} else
 			PrefetchBandwidth3 = 0;
 
 
 		if (VStartup == MaxVStartup &&
-				(st_vars->Tsw_est3 / st_vars->LineTime < st_vars->min_Lsw) && st_vars->Tpre_rounded - st_vars->min_Lsw * st_vars->LineTime - 0.75 *
-				st_vars->LineTime - st_vars->Tvm_trips_rounded > 0) {
+				(Tsw_est3 / LineTime < min_Lsw) && Tpre_rounded - min_Lsw * LineTime - 0.75 *
+				LineTime - Tvm_trips_rounded > 0) {
 			PrefetchBandwidth3 = (2 * MetaRowByte + 2 * PixelPTEBytesPerRow * HostVMInefficiencyFactor)
-					/ (st_vars->Tpre_rounded - st_vars->min_Lsw * st_vars->LineTime - 0.75 * st_vars->LineTime - st_vars->Tvm_trips_rounded);
+					/ (Tpre_rounded - min_Lsw * LineTime - 0.75 * LineTime - Tvm_trips_rounded);
 		}
 
-		if (st_vars->Tpre_rounded - st_vars->Tvm_trips_rounded - 2 * st_vars->Tr0_trips_rounded > 0) {
-			PrefetchBandwidth4 = st_vars->prefetch_sw_bytes /
-					(st_vars->Tpre_rounded - st_vars->Tvm_trips_rounded - 2 * st_vars->Tr0_trips_rounded);
+		if (Tpre_rounded - Tvm_trips_rounded - 2 * Tr0_trips_rounded > 0) {
+			PrefetchBandwidth4 = prefetch_sw_bytes /
+					(Tpre_rounded - Tvm_trips_rounded - 2 * Tr0_trips_rounded);
 		} else {
 			PrefetchBandwidth4 = 0;
 		}
 
 #ifdef __DML_VBA_DEBUG__
-		dml_print("DML::%s: Tpre_rounded: %f\n", __func__, st_vars->Tpre_rounded);
+		dml_print("DML::%s: Tpre_rounded: %f\n", __func__, Tpre_rounded);
 		dml_print("DML::%s: Tno_bw: %f\n", __func__, *Tno_bw);
-		dml_print("DML::%s: Tvm_trips_rounded: %f\n", __func__, st_vars->Tvm_trips_rounded);
-		dml_print("DML::%s: Tsw_est1: %f\n", __func__, st_vars->Tsw_est1);
-		dml_print("DML::%s: Tsw_est3: %f\n", __func__, st_vars->Tsw_est3);
+		dml_print("DML::%s: Tvm_trips_rounded: %f\n", __func__, Tvm_trips_rounded);
+		dml_print("DML::%s: Tsw_est1: %f\n", __func__, Tsw_est1);
+		dml_print("DML::%s: Tsw_est3: %f\n", __func__, Tsw_est3);
 		dml_print("DML::%s: PrefetchBandwidth1: %f\n", __func__, PrefetchBandwidth1);
 		dml_print("DML::%s: PrefetchBandwidth2: %f\n", __func__, PrefetchBandwidth2);
 		dml_print("DML::%s: PrefetchBandwidth3: %f\n", __func__, PrefetchBandwidth3);
@@ -3732,9 +3792,9 @@ bool dml32_CalculatePrefetchSchedule(
 
 			if (PrefetchBandwidth1 > 0) {
 				if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth1
-						>= st_vars->Tvm_trips_rounded
+						>= Tvm_trips_rounded
 						&& (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor)
-								/ PrefetchBandwidth1 >= st_vars->Tr0_trips_rounded) {
+								/ PrefetchBandwidth1 >= Tr0_trips_rounded) {
 					Case1OK = true;
 				} else {
 					Case1OK = false;
@@ -3745,9 +3805,9 @@ bool dml32_CalculatePrefetchSchedule(
 
 			if (PrefetchBandwidth2 > 0) {
 				if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth2
-						>= st_vars->Tvm_trips_rounded
+						>= Tvm_trips_rounded
 						&& (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor)
-						/ PrefetchBandwidth2 < st_vars->Tr0_trips_rounded) {
+						/ PrefetchBandwidth2 < Tr0_trips_rounded) {
 					Case2OK = true;
 				} else {
 					Case2OK = false;
@@ -3758,9 +3818,9 @@ bool dml32_CalculatePrefetchSchedule(
 
 			if (PrefetchBandwidth3 > 0) {
 				if (*Tno_bw + PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor / PrefetchBandwidth3 <
-						st_vars->Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow *
+						Tvm_trips_rounded && (MetaRowByte + PixelPTEBytesPerRow *
 								HostVMInefficiencyFactor) / PrefetchBandwidth3 >=
-								st_vars->Tr0_trips_rounded) {
+								Tr0_trips_rounded) {
 					Case3OK = true;
 				} else {
 					Case3OK = false;
@@ -3770,80 +3830,80 @@ bool dml32_CalculatePrefetchSchedule(
 			}
 
 			if (Case1OK)
-				st_vars->prefetch_bw_equ = PrefetchBandwidth1;
+				prefetch_bw_equ = PrefetchBandwidth1;
 			else if (Case2OK)
-				st_vars->prefetch_bw_equ = PrefetchBandwidth2;
+				prefetch_bw_equ = PrefetchBandwidth2;
 			else if (Case3OK)
-				st_vars->prefetch_bw_equ = PrefetchBandwidth3;
+				prefetch_bw_equ = PrefetchBandwidth3;
 			else
-				st_vars->prefetch_bw_equ = PrefetchBandwidth4;
+				prefetch_bw_equ = PrefetchBandwidth4;
 
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML::%s: Case1OK: %d\n", __func__, Case1OK);
 			dml_print("DML::%s: Case2OK: %d\n", __func__, Case2OK);
 			dml_print("DML::%s: Case3OK: %d\n", __func__, Case3OK);
-			dml_print("DML::%s: prefetch_bw_equ: %f\n", __func__, st_vars->prefetch_bw_equ);
+			dml_print("DML::%s: prefetch_bw_equ: %f\n", __func__, prefetch_bw_equ);
 #endif
 
-			if (st_vars->prefetch_bw_equ > 0) {
-				if (GPUVMEnable == true) {
-					st_vars->Tvm_equ = dml_max3(*Tno_bw + PDEAndMetaPTEBytesFrame *
-							HostVMInefficiencyFactor / st_vars->prefetch_bw_equ,
-							st_vars->Tvm_trips, st_vars->LineTime / 4);
+			if (prefetch_bw_equ > 0) {
+				if (v->GPUVMEnable == true) {
+					Tvm_equ = dml_max3(*Tno_bw + PDEAndMetaPTEBytesFrame *
+							HostVMInefficiencyFactor / prefetch_bw_equ,
+							Tvm_trips, LineTime / 4);
 				} else {
-					st_vars->Tvm_equ = st_vars->LineTime / 4;
+					Tvm_equ = LineTime / 4;
 				}
 
-				if ((GPUVMEnable == true || myPipe->DCCEnable == true)) {
-					st_vars->Tr0_equ = dml_max4((MetaRowByte + PixelPTEBytesPerRow *
-							HostVMInefficiencyFactor) / st_vars->prefetch_bw_equ, st_vars->Tr0_trips,
-							(st_vars->LineTime - st_vars->Tvm_equ) / 2, st_vars->LineTime / 4);
+				if ((v->GPUVMEnable == true || myPipe->DCCEnable == true)) {
+					Tr0_equ = dml_max4((MetaRowByte + PixelPTEBytesPerRow *
+							HostVMInefficiencyFactor) / prefetch_bw_equ, Tr0_trips,
+							(LineTime - Tvm_equ) / 2, LineTime / 4);
 				} else {
-					st_vars->Tr0_equ = (st_vars->LineTime - st_vars->Tvm_equ) / 2;
+					Tr0_equ = (LineTime - Tvm_equ) / 2;
 				}
 			} else {
-				st_vars->Tvm_equ = 0;
-				st_vars->Tr0_equ = 0;
+				Tvm_equ = 0;
+				Tr0_equ = 0;
 #ifdef __DML_VBA_DEBUG__
 				dml_print("DML: prefetch_bw_equ equals 0! %s:%d\n", __FILE__, __LINE__);
 #endif
 			}
 		}
 
-		if (st_vars->dst_y_prefetch_oto < st_vars->dst_y_prefetch_equ) {
-			*DestinationLinesForPrefetch = st_vars->dst_y_prefetch_oto;
-			st_vars->TimeForFetchingMetaPTE = st_vars->Tvm_oto;
-			st_vars->TimeForFetchingRowInVBlank = st_vars->Tr0_oto;
-			*PrefetchBandwidth = st_vars->prefetch_bw_oto;
+		if (dst_y_prefetch_oto < dst_y_prefetch_equ) {
+			*DestinationLinesForPrefetch = dst_y_prefetch_oto;
+			TimeForFetchingMetaPTE = Tvm_oto;
+			TimeForFetchingRowInVBlank = Tr0_oto;
+			*PrefetchBandwidth = prefetch_bw_oto;
 		} else {
-			*DestinationLinesForPrefetch = st_vars->dst_y_prefetch_equ;
-			st_vars->TimeForFetchingMetaPTE = st_vars->Tvm_equ;
-			st_vars->TimeForFetchingRowInVBlank = st_vars->Tr0_equ;
-			*PrefetchBandwidth = st_vars->prefetch_bw_equ;
+			*DestinationLinesForPrefetch = dst_y_prefetch_equ;
+			TimeForFetchingMetaPTE = Tvm_equ;
+			TimeForFetchingRowInVBlank = Tr0_equ;
+			*PrefetchBandwidth = prefetch_bw_equ;
 		}
 
-		*DestinationLinesToRequestVMInVBlank = dml_ceil(4.0 * st_vars->TimeForFetchingMetaPTE / st_vars->LineTime, 1.0) / 4.0;
+		*DestinationLinesToRequestVMInVBlank = dml_ceil(4.0 * TimeForFetchingMetaPTE / LineTime, 1.0) / 4.0;
 
 		*DestinationLinesToRequestRowInVBlank =
-				dml_ceil(4.0 * st_vars->TimeForFetchingRowInVBlank / st_vars->LineTime, 1.0) / 4.0;
+				dml_ceil(4.0 * TimeForFetchingRowInVBlank / LineTime, 1.0) / 4.0;
 
-		st_vars->LinesToRequestPrefetchPixelData = *DestinationLinesForPrefetch -
+		LinesToRequestPrefetchPixelData = *DestinationLinesForPrefetch -
 				*DestinationLinesToRequestVMInVBlank - 2 * *DestinationLinesToRequestRowInVBlank;
 
 #ifdef __DML_VBA_DEBUG__
 		dml_print("DML::%s: DestinationLinesForPrefetch = %f\n", __func__, *DestinationLinesForPrefetch);
 		dml_print("DML::%s: DestinationLinesToRequestVMInVBlank = %f\n",
 				__func__, *DestinationLinesToRequestVMInVBlank);
-		dml_print("DML::%s: TimeForFetchingRowInVBlank = %f\n", __func__, st_vars->TimeForFetchingRowInVBlank);
-		dml_print("DML::%s: LineTime = %f\n", __func__, st_vars->LineTime);
+		dml_print("DML::%s: TimeForFetchingRowInVBlank = %f\n", __func__, TimeForFetchingRowInVBlank);
+		dml_print("DML::%s: LineTime = %f\n", __func__, LineTime);
 		dml_print("DML::%s: DestinationLinesToRequestRowInVBlank = %f\n",
 				__func__, *DestinationLinesToRequestRowInVBlank);
 		dml_print("DML::%s: PrefetchSourceLinesY = %f\n", __func__, PrefetchSourceLinesY);
-		dml_print("DML::%s: LinesToRequestPrefetchPixelData = %f\n", __func__, st_vars->LinesToRequestPrefetchPixelData);
+		dml_print("DML::%s: LinesToRequestPrefetchPixelData = %f\n", __func__, LinesToRequestPrefetchPixelData);
 #endif
 
-		if (st_vars->LinesToRequestPrefetchPixelData >= 1 && st_vars->prefetch_bw_equ > 0) {
-			*VRatioPrefetchY = (double) PrefetchSourceLinesY / st_vars->LinesToRequestPrefetchPixelData;
+		if (LinesToRequestPrefetchPixelData >= 1 && prefetch_bw_equ > 0) {
+			*VRatioPrefetchY = (double) PrefetchSourceLinesY / LinesToRequestPrefetchPixelData;
 			*VRatioPrefetchY = dml_max(*VRatioPrefetchY, 1.0);
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML::%s: VRatioPrefetchY = %f\n", __func__, *VRatioPrefetchY);
@@ -3851,12 +3911,12 @@ bool dml32_CalculatePrefetchSchedule(
 			dml_print("DML::%s: VInitPreFillY = %d\n", __func__, VInitPreFillY);
 #endif
 			if ((SwathHeightY > 4) && (VInitPreFillY > 3)) {
-				if (st_vars->LinesToRequestPrefetchPixelData > (VInitPreFillY - 3.0) / 2.0) {
+				if (LinesToRequestPrefetchPixelData > (VInitPreFillY - 3.0) / 2.0) {
 					*VRatioPrefetchY =
 							dml_max((double) PrefetchSourceLinesY /
-									st_vars->LinesToRequestPrefetchPixelData,
+									LinesToRequestPrefetchPixelData,
 									(double) MaxNumSwathY * SwathHeightY /
-									(st_vars->LinesToRequestPrefetchPixelData -
+									(LinesToRequestPrefetchPixelData -
 									(VInitPreFillY - 3.0) / 2.0));
 					*VRatioPrefetchY = dml_max(*VRatioPrefetchY, 1.0);
 				} else {
@@ -3870,7 +3930,7 @@ bool dml32_CalculatePrefetchSchedule(
 #endif
 			}
 
-			*VRatioPrefetchC = (double) PrefetchSourceLinesC / st_vars->LinesToRequestPrefetchPixelData;
+			*VRatioPrefetchC = (double) PrefetchSourceLinesC / LinesToRequestPrefetchPixelData;
 			*VRatioPrefetchC = dml_max(*VRatioPrefetchC, 1.0);
 
 #ifdef __DML_VBA_DEBUG__
@@ -3879,11 +3939,11 @@ bool dml32_CalculatePrefetchSchedule(
 			dml_print("DML::%s: VInitPreFillC = %d\n", __func__, VInitPreFillC);
 #endif
 			if ((SwathHeightC > 4)) {
-				if (st_vars->LinesToRequestPrefetchPixelData > (VInitPreFillC - 3.0) / 2.0) {
+				if (LinesToRequestPrefetchPixelData > (VInitPreFillC - 3.0) / 2.0) {
 					*VRatioPrefetchC =
 						dml_max(*VRatioPrefetchC,
 							(double) MaxNumSwathC * SwathHeightC /
-							(st_vars->LinesToRequestPrefetchPixelData -
+							(LinesToRequestPrefetchPixelData -
 							(VInitPreFillC - 3.0) / 2.0));
 					*VRatioPrefetchC = dml_max(*VRatioPrefetchC, 1.0);
 				} else {
@@ -3898,25 +3958,25 @@ bool dml32_CalculatePrefetchSchedule(
 			}
 
 			*RequiredPrefetchPixDataBWLuma = (double) PrefetchSourceLinesY
-					/ st_vars->LinesToRequestPrefetchPixelData * myPipe->BytePerPixelY * swath_width_luma_ub
-					/ st_vars->LineTime;
+					/ LinesToRequestPrefetchPixelData * myPipe->BytePerPixelY * swath_width_luma_ub
+					/ LineTime;
 
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML::%s: BytePerPixelY = %d\n", __func__, myPipe->BytePerPixelY);
 			dml_print("DML::%s: swath_width_luma_ub = %d\n", __func__, swath_width_luma_ub);
-			dml_print("DML::%s: LineTime = %f\n", __func__, st_vars->LineTime);
+			dml_print("DML::%s: LineTime = %f\n", __func__, LineTime);
 			dml_print("DML::%s: RequiredPrefetchPixDataBWLuma = %f\n",
 					__func__, *RequiredPrefetchPixDataBWLuma);
 #endif
 			*RequiredPrefetchPixDataBWChroma = (double) PrefetchSourceLinesC /
-					st_vars->LinesToRequestPrefetchPixelData
+					LinesToRequestPrefetchPixelData
 					* myPipe->BytePerPixelC
-					* swath_width_chroma_ub / st_vars->LineTime;
+					* swath_width_chroma_ub / LineTime;
 		} else {
 			MyError = true;
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML:%s: MyErr set. LinesToRequestPrefetchPixelData: %f, should be > 0\n",
-					__func__, st_vars->LinesToRequestPrefetchPixelData);
+					__func__, LinesToRequestPrefetchPixelData);
 #endif
 			*VRatioPrefetchY = 0;
 			*VRatioPrefetchC = 0;
@@ -3925,15 +3985,15 @@ bool dml32_CalculatePrefetchSchedule(
 		}
 #ifdef __DML_VBA_DEBUG__
 		dml_print("DML: Tpre: %fus - sum of time to request meta pte, 2 x data pte + meta data, swaths\n",
-			(double)st_vars->LinesToRequestPrefetchPixelData * st_vars->LineTime +
-			2.0*st_vars->TimeForFetchingRowInVBlank + st_vars->TimeForFetchingMetaPTE);
-		dml_print("DML:  Tvm: %fus - time to fetch page tables for meta surface\n", st_vars->TimeForFetchingMetaPTE);
+			(double)LinesToRequestPrefetchPixelData * LineTime +
+			2.0*TimeForFetchingRowInVBlank + TimeForFetchingMetaPTE);
+		dml_print("DML:  Tvm: %fus - time to fetch page tables for meta surface\n", TimeForFetchingMetaPTE);
 		dml_print("DML: To: %fus - time for propagation from scaler to optc\n",
-			(*DSTYAfterScaler + ((double) (*DSTXAfterScaler) / (double) myPipe->HTotal)) * st_vars->LineTime);
+			(*DSTYAfterScaler + ((double) (*DSTXAfterScaler) / (double) myPipe->HTotal)) * LineTime);
 		dml_print("DML: Tvstartup - TSetup - Tcalc - Twait - Tpre - To > 0\n");
-		dml_print("DML: Tslack(pre): %fus - time left over in schedule\n", VStartup * st_vars->LineTime -
-			st_vars->TimeForFetchingMetaPTE - 2*st_vars->TimeForFetchingRowInVBlank - (*DSTYAfterScaler +
-			((double) (*DSTXAfterScaler) / (double) myPipe->HTotal)) * st_vars->LineTime - TWait - TCalc - *TSetup);
+		dml_print("DML: Tslack(pre): %fus - time left over in schedule\n", VStartup * LineTime -
+			TimeForFetchingMetaPTE - 2*TimeForFetchingRowInVBlank - (*DSTYAfterScaler +
+			((double) (*DSTXAfterScaler) / (double) myPipe->HTotal)) * LineTime - TWait - TCalc - *TSetup);
 		dml_print("DML: row_bytes = dpte_row_bytes (per_pipe) = PixelPTEBytesPerRow = : %d\n",
 				PixelPTEBytesPerRow);
 #endif
@@ -3941,7 +4001,7 @@ bool dml32_CalculatePrefetchSchedule(
 		MyError = true;
 #ifdef __DML_VBA_DEBUG__
 		dml_print("DML::%s: MyErr set, dst_y_prefetch_equ = %f (should be > 1)\n",
-				__func__, st_vars->dst_y_prefetch_equ);
+				__func__, dst_y_prefetch_equ);
 #endif
 	}
 
@@ -3957,10 +4017,10 @@ bool dml32_CalculatePrefetchSchedule(
 			dml_print("DML::%s: HostVMInefficiencyFactor = %f\n", __func__, HostVMInefficiencyFactor);
 			dml_print("DML::%s: DestinationLinesToRequestVMInVBlank = %f\n",
 					__func__, *DestinationLinesToRequestVMInVBlank);
-			dml_print("DML::%s: LineTime = %f\n", __func__, st_vars->LineTime);
+			dml_print("DML::%s: LineTime = %f\n", __func__, LineTime);
 #endif
 			prefetch_vm_bw = PDEAndMetaPTEBytesFrame * HostVMInefficiencyFactor /
-					(*DestinationLinesToRequestVMInVBlank * st_vars->LineTime);
+					(*DestinationLinesToRequestVMInVBlank * LineTime);
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML::%s: prefetch_vm_bw = %f\n", __func__, prefetch_vm_bw);
 #endif
@@ -3977,7 +4037,7 @@ bool dml32_CalculatePrefetchSchedule(
 			prefetch_row_bw = 0;
 		} else if (*DestinationLinesToRequestRowInVBlank > 0) {
 			prefetch_row_bw = (MetaRowByte + PixelPTEBytesPerRow * HostVMInefficiencyFactor) /
-					(*DestinationLinesToRequestRowInVBlank * st_vars->LineTime);
+					(*DestinationLinesToRequestRowInVBlank * LineTime);
 
 #ifdef __DML_VBA_DEBUG__
 			dml_print("DML::%s: MetaRowByte = %d\n", __func__, MetaRowByte);
@@ -4000,12 +4060,12 @@ bool dml32_CalculatePrefetchSchedule(
 
 	if (MyError) {
 		*PrefetchBandwidth = 0;
-		st_vars->TimeForFetchingMetaPTE = 0;
-		st_vars->TimeForFetchingRowInVBlank = 0;
+		TimeForFetchingMetaPTE = 0;
+		TimeForFetchingRowInVBlank = 0;
 		*DestinationLinesToRequestVMInVBlank = 0;
 		*DestinationLinesToRequestRowInVBlank = 0;
 		*DestinationLinesForPrefetch = 0;
-		st_vars->LinesToRequestPrefetchPixelData = 0;
+		LinesToRequestPrefetchPixelData = 0;
 		*VRatioPrefetchY = 0;
 		*VRatioPrefetchC = 0;
 		*RequiredPrefetchPixDataBWLuma = 0;
@@ -4159,59 +4219,28 @@ void dml32_CalculateFlipSchedule(
 } // CalculateFlipSchedule
 
 void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
-		struct dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport *st_vars,
-		bool USRRetrainingRequiredFinal,
-		enum dm_use_mall_for_pstate_change_mode UseMALLForPStateChange[],
+		struct vba_vars_st *v,
 		unsigned int PrefetchMode,
-		unsigned int NumberOfActiveSurfaces,
-		unsigned int MaxLineBufferLines,
-		unsigned int LineBufferSize,
-		unsigned int WritebackInterfaceBufferSize,
 		double DCFCLK,
 		double ReturnBW,
-		bool SynchronizeTimingsFinal,
-		bool SynchronizeDRRDisplaysForUCLKPStateChangeFinal,
-		bool DRRDisplay[],
-		unsigned int dpte_group_bytes[],
-		unsigned int meta_row_height[],
-		unsigned int meta_row_height_chroma[],
 		SOCParametersList mmSOCParameters,
-		unsigned int WritebackChunkSize,
 		double SOCCLK,
 		double DCFClkDeepSleep,
 		unsigned int DETBufferSizeY[],
 		unsigned int DETBufferSizeC[],
 		unsigned int SwathHeightY[],
 		unsigned int SwathHeightC[],
-		unsigned int LBBitPerPixel[],
 		double SwathWidthY[],
 		double SwathWidthC[],
-		double HRatio[],
-		double HRatioChroma[],
-		unsigned int VTaps[],
-		unsigned int VTapsChroma[],
-		double VRatio[],
-		double VRatioChroma[],
-		unsigned int HTotal[],
-		unsigned int VTotal[],
-		unsigned int VActive[],
-		double PixelClock[],
-		unsigned int BlendingAndTiming[],
 		unsigned int DPPPerSurface[],
 		double BytePerPixelDETY[],
 		double BytePerPixelDETC[],
 		double DSTXAfterScaler[],
 		double DSTYAfterScaler[],
-		bool WritebackEnable[],
-		enum source_format_class WritebackPixelFormat[],
-		double WritebackDestinationWidth[],
-		double WritebackDestinationHeight[],
-		double WritebackSourceHeight[],
 		bool UnboundedRequestEnabled,
 		unsigned int CompressedBufferSizeInkByte,
 
 		/* Output */
-		Watermarks *Watermark,
 		enum clock_change_support *DRAMClockChangeSupport,
 		double MaxActiveDRAMClockChangeLatencySupported[],
 		unsigned int SubViewportLinesNeededInMALL[],
@@ -4221,229 +4250,251 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 		double ActiveDRAMClockChangeLatencyMargin[])
 {
 	unsigned int i, j, k;
-
-	st_vars->SurfaceWithMinActiveFCLKChangeMargin = 0;
-	st_vars->DRAMClockChangeSupportNumber = 0;
-	st_vars->DRAMClockChangeMethod = 0;
-	st_vars->FoundFirstSurfaceWithMinActiveFCLKChangeMargin = false;
-	st_vars->MinActiveFCLKChangeMargin = 0.;
-	st_vars->SecondMinActiveFCLKChangeMarginOneDisplayInVBLank = 0.;
-	st_vars->TotalPixelBW = 0.0;
-	st_vars->TotalActiveWriteback = 0;
-
-	Watermark->UrgentWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency;
-	Watermark->USRRetrainingWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency
+	unsigned int SurfaceWithMinActiveFCLKChangeMargin = 0;
+	unsigned int DRAMClockChangeSupportNumber = 0;
+	unsigned int LastSurfaceWithoutMargin;
+	unsigned int DRAMClockChangeMethod = 0;
+	bool FoundFirstSurfaceWithMinActiveFCLKChangeMargin = false;
+	double MinActiveFCLKChangeMargin = 0.;
+	double SecondMinActiveFCLKChangeMarginOneDisplayInVBLank = 0.;
+	double ActiveClockChangeLatencyHidingY;
+	double ActiveClockChangeLatencyHidingC;
+	double ActiveClockChangeLatencyHiding;
+    double EffectiveDETBufferSizeY;
+	double     ActiveFCLKChangeLatencyMargin[DC__NUM_DPP__MAX];
+	double     USRRetrainingLatencyMargin[DC__NUM_DPP__MAX];
+	double TotalPixelBW = 0.0;
+	bool    SynchronizedSurfaces[DC__NUM_DPP__MAX][DC__NUM_DPP__MAX];
+	double     EffectiveLBLatencyHidingY;
+	double     EffectiveLBLatencyHidingC;
+	double     LinesInDETY[DC__NUM_DPP__MAX];
+	double     LinesInDETC[DC__NUM_DPP__MAX];
+	unsigned int    LinesInDETYRoundedDownToSwath[DC__NUM_DPP__MAX];
+	unsigned int    LinesInDETCRoundedDownToSwath[DC__NUM_DPP__MAX];
+	double     FullDETBufferingTimeY;
+	double     FullDETBufferingTimeC;
+	double     WritebackDRAMClockChangeLatencyMargin;
+	double     WritebackFCLKChangeLatencyMargin;
+	double     WritebackLatencyHiding;
+	bool    SameTimingForFCLKChange;
+
+	unsigned int    TotalActiveWriteback = 0;
+	unsigned int LBLatencyHidingSourceLinesY[DC__NUM_DPP__MAX];
+	unsigned int LBLatencyHidingSourceLinesC[DC__NUM_DPP__MAX];
+
+	v->Watermark.UrgentWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency;
+	v->Watermark.USRRetrainingWatermark = mmSOCParameters.UrgentLatency + mmSOCParameters.ExtraLatency
 			+ mmSOCParameters.USRRetrainingLatency + mmSOCParameters.SMNLatency;
-	Watermark->DRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + Watermark->UrgentWatermark;
-	Watermark->FCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + Watermark->UrgentWatermark;
-	Watermark->StutterExitWatermark = mmSOCParameters.SRExitTime + mmSOCParameters.ExtraLatency
+	v->Watermark.DRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency + v->Watermark.UrgentWatermark;
+	v->Watermark.FCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency + v->Watermark.UrgentWatermark;
+	v->Watermark.StutterExitWatermark = mmSOCParameters.SRExitTime + mmSOCParameters.ExtraLatency
 			+ 10 / DCFClkDeepSleep;
-	Watermark->StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitTime + mmSOCParameters.ExtraLatency
+	v->Watermark.StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitTime + mmSOCParameters.ExtraLatency
 			+ 10 / DCFClkDeepSleep;
-	Watermark->Z8StutterExitWatermark = mmSOCParameters.SRExitZ8Time + mmSOCParameters.ExtraLatency
+	v->Watermark.Z8StutterExitWatermark = mmSOCParameters.SRExitZ8Time + mmSOCParameters.ExtraLatency
 			+ 10 / DCFClkDeepSleep;
-	Watermark->Z8StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitZ8Time
+	v->Watermark.Z8StutterEnterPlusExitWatermark = mmSOCParameters.SREnterPlusExitZ8Time
 			+ mmSOCParameters.ExtraLatency + 10 / DCFClkDeepSleep;
 
 #ifdef __DML_VBA_DEBUG__
 	dml_print("DML::%s: UrgentLatency = %f\n", __func__, mmSOCParameters.UrgentLatency);
 	dml_print("DML::%s: ExtraLatency = %f\n", __func__, mmSOCParameters.ExtraLatency);
 	dml_print("DML::%s: DRAMClockChangeLatency = %f\n", __func__, mmSOCParameters.DRAMClockChangeLatency);
-	dml_print("DML::%s: UrgentWatermark = %f\n", __func__, Watermark->UrgentWatermark);
-	dml_print("DML::%s: USRRetrainingWatermark = %f\n", __func__, Watermark->USRRetrainingWatermark);
-	dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, Watermark->DRAMClockChangeWatermark);
-	dml_print("DML::%s: FCLKChangeWatermark = %f\n", __func__, Watermark->FCLKChangeWatermark);
-	dml_print("DML::%s: StutterExitWatermark = %f\n", __func__, Watermark->StutterExitWatermark);
-	dml_print("DML::%s: StutterEnterPlusExitWatermark = %f\n", __func__, Watermark->StutterEnterPlusExitWatermark);
-	dml_print("DML::%s: Z8StutterExitWatermark = %f\n", __func__, Watermark->Z8StutterExitWatermark);
+	dml_print("DML::%s: UrgentWatermark = %f\n", __func__, v->Watermark.UrgentWatermark);
+	dml_print("DML::%s: USRRetrainingWatermark = %f\n", __func__, v->Watermark.USRRetrainingWatermark);
+	dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, v->Watermark.DRAMClockChangeWatermark);
+	dml_print("DML::%s: FCLKChangeWatermark = %f\n", __func__, v->Watermark.FCLKChangeWatermark);
+	dml_print("DML::%s: StutterExitWatermark = %f\n", __func__, v->Watermark.StutterExitWatermark);
+	dml_print("DML::%s: StutterEnterPlusExitWatermark = %f\n", __func__, v->Watermark.StutterEnterPlusExitWatermark);
+	dml_print("DML::%s: Z8StutterExitWatermark = %f\n", __func__, v->Watermark.Z8StutterExitWatermark);
 	dml_print("DML::%s: Z8StutterEnterPlusExitWatermark = %f\n",
-			__func__, Watermark->Z8StutterEnterPlusExitWatermark);
+			__func__, v->Watermark.Z8StutterEnterPlusExitWatermark);
 #endif
 
 
-	st_vars->TotalActiveWriteback = 0;
-	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
-		if (WritebackEnable[k] == true)
-			st_vars->TotalActiveWriteback = st_vars->TotalActiveWriteback + 1;
+	TotalActiveWriteback = 0;
+	for (k = 0; k < v->NumberOfActiveSurfaces; ++k) {
+		if (v->WritebackEnable[k] == true)
+			TotalActiveWriteback = TotalActiveWriteback + 1;
 	}
 
-	if (st_vars->TotalActiveWriteback <= 1) {
-		Watermark->WritebackUrgentWatermark = mmSOCParameters.WritebackLatency;
+	if (TotalActiveWriteback <= 1) {
+		v->Watermark.WritebackUrgentWatermark = mmSOCParameters.WritebackLatency;
 	} else {
-		Watermark->WritebackUrgentWatermark = mmSOCParameters.WritebackLatency
-				+ WritebackChunkSize * 1024.0 / 32.0 / SOCCLK;
+		v->Watermark.WritebackUrgentWatermark = mmSOCParameters.WritebackLatency
+				+ v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK;
 	}
-	if (USRRetrainingRequiredFinal)
-		Watermark->WritebackUrgentWatermark = Watermark->WritebackUrgentWatermark
+	if (v->USRRetrainingRequiredFinal)
+		v->Watermark.WritebackUrgentWatermark = v->Watermark.WritebackUrgentWatermark
 				+ mmSOCParameters.USRRetrainingLatency;
 
-	if (st_vars->TotalActiveWriteback <= 1) {
-		Watermark->WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency
+	if (TotalActiveWriteback <= 1) {
+		v->Watermark.WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency
 				+ mmSOCParameters.WritebackLatency;
-		Watermark->WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency
+		v->Watermark.WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency
 				+ mmSOCParameters.WritebackLatency;
 	} else {
-		Watermark->WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency
-				+ mmSOCParameters.WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK;
-		Watermark->WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency
-				+ mmSOCParameters.WritebackLatency + WritebackChunkSize * 1024 / 32 / SOCCLK;
+		v->Watermark.WritebackDRAMClockChangeWatermark = mmSOCParameters.DRAMClockChangeLatency
+				+ mmSOCParameters.WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK;
+		v->Watermark.WritebackFCLKChangeWatermark = mmSOCParameters.FCLKChangeLatency
+				+ mmSOCParameters.WritebackLatency + v->WritebackChunkSize * 1024 / 32 / SOCCLK;
 	}
 
-	if (USRRetrainingRequiredFinal)
-		Watermark->WritebackDRAMClockChangeWatermark = Watermark->WritebackDRAMClockChangeWatermark
+	if (v->USRRetrainingRequiredFinal)
+		v->Watermark.WritebackDRAMClockChangeWatermark = v->Watermark.WritebackDRAMClockChangeWatermark
 				+ mmSOCParameters.USRRetrainingLatency;
 
-	if (USRRetrainingRequiredFinal)
-		Watermark->WritebackFCLKChangeWatermark = Watermark->WritebackFCLKChangeWatermark
+	if (v->USRRetrainingRequiredFinal)
+		v->Watermark.WritebackFCLKChangeWatermark = v->Watermark.WritebackFCLKChangeWatermark
 				+ mmSOCParameters.USRRetrainingLatency;
 
 #ifdef __DML_VBA_DEBUG__
 	dml_print("DML::%s: WritebackDRAMClockChangeWatermark = %f\n",
-			__func__, Watermark->WritebackDRAMClockChangeWatermark);
-	dml_print("DML::%s: WritebackFCLKChangeWatermark = %f\n", __func__, Watermark->WritebackFCLKChangeWatermark);
-	dml_print("DML::%s: WritebackUrgentWatermark = %f\n", __func__, Watermark->WritebackUrgentWatermark);
-	dml_print("DML::%s: USRRetrainingRequiredFinal = %d\n", __func__, USRRetrainingRequiredFinal);
+			__func__, v->Watermark.WritebackDRAMClockChangeWatermark);
+	dml_print("DML::%s: WritebackFCLKChangeWatermark = %f\n", __func__, v->Watermark.WritebackFCLKChangeWatermark);
+	dml_print("DML::%s: WritebackUrgentWatermark = %f\n", __func__, v->Watermark.WritebackUrgentWatermark);
+	dml_print("DML::%s: v->USRRetrainingRequiredFinal = %d\n", __func__, v->USRRetrainingRequiredFinal);
 	dml_print("DML::%s: USRRetrainingLatency = %f\n", __func__, mmSOCParameters.USRRetrainingLatency);
 #endif
 
-	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
-		st_vars->TotalPixelBW = st_vars->TotalPixelBW + DPPPerSurface[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] +
-				SwathWidthC[k] * BytePerPixelDETC[k] * VRatioChroma[k]) / (HTotal[k] / PixelClock[k]);
+	for (k = 0; k < v->NumberOfActiveSurfaces; ++k) {
+		TotalPixelBW = TotalPixelBW + DPPPerSurface[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] +
+				SwathWidthC[k] * BytePerPixelDETC[k] * v->VRatioChroma[k]) / (v->HTotal[k] / v->PixelClock[k]);
 	}
 
-	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
+	for (k = 0; k < v->NumberOfActiveSurfaces; ++k) {
 
-		st_vars->LBLatencyHidingSourceLinesY[k] = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (VTaps[k] - 1);
-		st_vars->LBLatencyHidingSourceLinesC[k] = dml_min((double) MaxLineBufferLines, dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTapsChroma[k] - 1);
+		LBLatencyHidingSourceLinesY[k] = dml_min((double) v->MaxLineBufferLines, dml_floor(v->LineBufferSizeFinal / v->LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(v->HRatio[k], 1.0)), 1)) - (v->vtaps[k] - 1);
+		LBLatencyHidingSourceLinesC[k] = dml_min((double) v->MaxLineBufferLines, dml_floor(v->LineBufferSizeFinal / v->LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(v->HRatioChroma[k], 1.0)), 1)) - (v->VTAPsChroma[k] - 1);
 
 
 #ifdef __DML_VBA_DEBUG__
-		dml_print("DML::%s: k=%d, MaxLineBufferLines = %d\n", __func__, k, MaxLineBufferLines);
-		dml_print("DML::%s: k=%d, LineBufferSize     = %d\n", __func__, k, LineBufferSize);
-		dml_print("DML::%s: k=%d, LBBitPerPixel      = %d\n", __func__, k, LBBitPerPixel[k]);
-		dml_print("DML::%s: k=%d, HRatio             = %f\n", __func__, k, HRatio[k]);
-		dml_print("DML::%s: k=%d, VTaps              = %d\n", __func__, k, VTaps[k]);
+		dml_print("DML::%s: k=%d, v->MaxLineBufferLines = %d\n", __func__, k, v->MaxLineBufferLines);
+		dml_print("DML::%s: k=%d, v->LineBufferSizeFinal     = %d\n", __func__, k, v->LineBufferSizeFinal);
+		dml_print("DML::%s: k=%d, v->LBBitPerPixel      = %d\n", __func__, k, v->LBBitPerPixel[k]);
+		dml_print("DML::%s: k=%d, v->HRatio             = %f\n", __func__, k, v->HRatio[k]);
+		dml_print("DML::%s: k=%d, v->vtaps              = %d\n", __func__, k, v->vtaps[k]);
 #endif
 
-		st_vars->EffectiveLBLatencyHidingY = st_vars->LBLatencyHidingSourceLinesY[k] / VRatio[k] * (HTotal[k] / PixelClock[k]);
-		st_vars->EffectiveLBLatencyHidingC = st_vars->LBLatencyHidingSourceLinesC[k] / VRatioChroma[k] * (HTotal[k] / PixelClock[k]);
-		st_vars->EffectiveDETBufferSizeY = DETBufferSizeY[k];
+		EffectiveLBLatencyHidingY = LBLatencyHidingSourceLinesY[k] / v->VRatio[k] * (v->HTotal[k] / v->PixelClock[k]);
+		EffectiveLBLatencyHidingC = LBLatencyHidingSourceLinesC[k] / v->VRatioChroma[k] * (v->HTotal[k] / v->PixelClock[k]);
+		EffectiveDETBufferSizeY = DETBufferSizeY[k];
 
 		if (UnboundedRequestEnabled) {
-			st_vars->EffectiveDETBufferSizeY = st_vars->EffectiveDETBufferSizeY
+			EffectiveDETBufferSizeY = EffectiveDETBufferSizeY
 					+ CompressedBufferSizeInkByte * 1024
-							* (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k])
-							/ (HTotal[k] / PixelClock[k]) / st_vars->TotalPixelBW;
+							* (SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k])
+							/ (v->HTotal[k] / v->PixelClock[k]) / TotalPixelBW;
 		}
 
-		st_vars->LinesInDETY[k] = (double) st_vars->EffectiveDETBufferSizeY / BytePerPixelDETY[k] / SwathWidthY[k];
-		st_vars->LinesInDETYRoundedDownToSwath[k] = dml_floor(st_vars->LinesInDETY[k], SwathHeightY[k]);
-		st_vars->FullDETBufferingTimeY = st_vars->LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k];
+		LinesInDETY[k] = (double) EffectiveDETBufferSizeY / BytePerPixelDETY[k] / SwathWidthY[k];
+		LinesInDETYRoundedDownToSwath[k] = dml_floor(LinesInDETY[k], SwathHeightY[k]);
+		FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k];
 
-		st_vars->ActiveClockChangeLatencyHidingY = st_vars->EffectiveLBLatencyHidingY + st_vars->FullDETBufferingTimeY
-				- (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k];
+		ActiveClockChangeLatencyHidingY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY
+				- (DSTXAfterScaler[k] / v->HTotal[k] + DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k];
 
-		if (NumberOfActiveSurfaces > 1) {
-			st_vars->ActiveClockChangeLatencyHidingY = st_vars->ActiveClockChangeLatencyHidingY
-					- (1 - 1 / NumberOfActiveSurfaces) * SwathHeightY[k] * HTotal[k]
-							/ PixelClock[k] / VRatio[k];
+		if (v->NumberOfActiveSurfaces > 1) {
+			ActiveClockChangeLatencyHidingY = ActiveClockChangeLatencyHidingY
+					- (1 - 1 / v->NumberOfActiveSurfaces) * SwathHeightY[k] * v->HTotal[k]
+							/ v->PixelClock[k] / v->VRatio[k];
 		}
 
 		if (BytePerPixelDETC[k] > 0) {
-			st_vars->LinesInDETC[k] = DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k];
-			st_vars->LinesInDETCRoundedDownToSwath[k] = dml_floor(st_vars->LinesInDETC[k], SwathHeightC[k]);
-			st_vars->FullDETBufferingTimeC = st_vars->LinesInDETCRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k])
-					/ VRatioChroma[k];
-			st_vars->ActiveClockChangeLatencyHidingC = st_vars->EffectiveLBLatencyHidingC + st_vars->FullDETBufferingTimeC
-					- (DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k]
-							/ PixelClock[k];
-			if (NumberOfActiveSurfaces > 1) {
-				st_vars->ActiveClockChangeLatencyHidingC = st_vars->ActiveClockChangeLatencyHidingC
-						- (1 - 1 / NumberOfActiveSurfaces) * SwathHeightC[k] * HTotal[k]
-								/ PixelClock[k] / VRatioChroma[k];
+			LinesInDETC[k] = DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k];
+			LinesInDETCRoundedDownToSwath[k] = dml_floor(LinesInDETC[k], SwathHeightC[k]);
+			FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k])
+					/ v->VRatioChroma[k];
+			ActiveClockChangeLatencyHidingC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC
+					- (DSTXAfterScaler[k] / v->HTotal[k] + DSTYAfterScaler[k]) * v->HTotal[k]
+							/ v->PixelClock[k];
+			if (v->NumberOfActiveSurfaces > 1) {
+				ActiveClockChangeLatencyHidingC = ActiveClockChangeLatencyHidingC
+						- (1 - 1 / v->NumberOfActiveSurfaces) * SwathHeightC[k] * v->HTotal[k]
+								/ v->PixelClock[k] / v->VRatioChroma[k];
 			}
-			st_vars->ActiveClockChangeLatencyHiding = dml_min(st_vars->ActiveClockChangeLatencyHidingY,
-					st_vars->ActiveClockChangeLatencyHidingC);
+			ActiveClockChangeLatencyHiding = dml_min(ActiveClockChangeLatencyHidingY,
+					ActiveClockChangeLatencyHidingC);
 		} else {
-			st_vars->ActiveClockChangeLatencyHiding = st_vars->ActiveClockChangeLatencyHidingY;
+			ActiveClockChangeLatencyHiding = ActiveClockChangeLatencyHidingY;
 		}
 
-		ActiveDRAMClockChangeLatencyMargin[k] = st_vars->ActiveClockChangeLatencyHiding - Watermark->UrgentWatermark
-				- Watermark->DRAMClockChangeWatermark;
-		st_vars->ActiveFCLKChangeLatencyMargin[k] = st_vars->ActiveClockChangeLatencyHiding - Watermark->UrgentWatermark
-				- Watermark->FCLKChangeWatermark;
-		st_vars->USRRetrainingLatencyMargin[k] = st_vars->ActiveClockChangeLatencyHiding - Watermark->USRRetrainingWatermark;
+		ActiveDRAMClockChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - v->Watermark.UrgentWatermark
+				- v->Watermark.DRAMClockChangeWatermark;
+		ActiveFCLKChangeLatencyMargin[k] = ActiveClockChangeLatencyHiding - v->Watermark.UrgentWatermark
+				- v->Watermark.FCLKChangeWatermark;
+		USRRetrainingLatencyMargin[k] = ActiveClockChangeLatencyHiding - v->Watermark.USRRetrainingWatermark;
 
-		if (WritebackEnable[k]) {
-			st_vars->WritebackLatencyHiding = WritebackInterfaceBufferSize * 1024
-					/ (WritebackDestinationWidth[k] * WritebackDestinationHeight[k]
-							/ (WritebackSourceHeight[k] * HTotal[k] / PixelClock[k]) * 4);
-			if (WritebackPixelFormat[k] == dm_444_64)
-				st_vars->WritebackLatencyHiding = st_vars->WritebackLatencyHiding / 2;
+		if (v->WritebackEnable[k]) {
+			WritebackLatencyHiding = v->WritebackInterfaceBufferSize * 1024
+					/ (v->WritebackDestinationWidth[k] * v->WritebackDestinationHeight[k]
+							/ (v->WritebackSourceHeight[k] * v->HTotal[k] / v->PixelClock[k]) * 4);
+			if (v->WritebackPixelFormat[k] == dm_444_64)
+				WritebackLatencyHiding = WritebackLatencyHiding / 2;
 
-			st_vars->WritebackDRAMClockChangeLatencyMargin = st_vars->WritebackLatencyHiding
-					- Watermark->WritebackDRAMClockChangeWatermark;
+			WritebackDRAMClockChangeLatencyMargin = WritebackLatencyHiding
+					- v->Watermark.WritebackDRAMClockChangeWatermark;
 
-			st_vars->WritebackFCLKChangeLatencyMargin = st_vars->WritebackLatencyHiding
-					- Watermark->WritebackFCLKChangeWatermark;
+			WritebackFCLKChangeLatencyMargin = WritebackLatencyHiding
+					- v->Watermark.WritebackFCLKChangeWatermark;
 
 			ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMargin[k],
-					st_vars->WritebackFCLKChangeLatencyMargin);
-			st_vars->ActiveFCLKChangeLatencyMargin[k] = dml_min(st_vars->ActiveFCLKChangeLatencyMargin[k],
-					st_vars->WritebackDRAMClockChangeLatencyMargin);
+					WritebackFCLKChangeLatencyMargin);
+			ActiveFCLKChangeLatencyMargin[k] = dml_min(ActiveFCLKChangeLatencyMargin[k],
+					WritebackDRAMClockChangeLatencyMargin);
 		}
 		MaxActiveDRAMClockChangeLatencySupported[k] =
-				(UseMALLForPStateChange[k] == dm_use_mall_pstate_change_phantom_pipe) ?
+				(v->UsesMALLForPStateChange[k] == dm_use_mall_pstate_change_phantom_pipe) ?
 						0 :
 						(ActiveDRAMClockChangeLatencyMargin[k]
 								+ mmSOCParameters.DRAMClockChangeLatency);
 	}
 
-	for (i = 0; i < NumberOfActiveSurfaces; ++i) {
-		for (j = 0; j < NumberOfActiveSurfaces; ++j) {
+	for (i = 0; i < v->NumberOfActiveSurfaces; ++i) {
+		for (j = 0; j < v->NumberOfActiveSurfaces; ++j) {
 			if (i == j ||
-					(BlendingAndTiming[i] == i && BlendingAndTiming[j] == i) ||
-					(BlendingAndTiming[j] == j && BlendingAndTiming[i] == j) ||
-					(BlendingAndTiming[i] == BlendingAndTiming[j] && BlendingAndTiming[i] != i) ||
-					(SynchronizeTimingsFinal && PixelClock[i] == PixelClock[j] &&
-					HTotal[i] == HTotal[j] && VTotal[i] == VTotal[j] &&
-					VActive[i] == VActive[j]) || (SynchronizeDRRDisplaysForUCLKPStateChangeFinal &&
-					(DRRDisplay[i] || DRRDisplay[j]))) {
-				st_vars->SynchronizedSurfaces[i][j] = true;
+					(v->BlendingAndTiming[i] == i && v->BlendingAndTiming[j] == i) ||
+					(v->BlendingAndTiming[j] == j && v->BlendingAndTiming[i] == j) ||
+					(v->BlendingAndTiming[i] == v->BlendingAndTiming[j] && v->BlendingAndTiming[i] != i) ||
+					(v->SynchronizeTimingsFinal && v->PixelClock[i] == v->PixelClock[j] &&
+					v->HTotal[i] == v->HTotal[j] && v->VTotal[i] == v->VTotal[j] &&
+					v->VActive[i] == v->VActive[j]) || (v->SynchronizeDRRDisplaysForUCLKPStateChangeFinal &&
+					(v->DRRDisplay[i] || v->DRRDisplay[j]))) {
+				SynchronizedSurfaces[i][j] = true;
 			} else {
-				st_vars->SynchronizedSurfaces[i][j] = false;
+				SynchronizedSurfaces[i][j] = false;
 			}
 		}
 	}
 
-	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
-		if ((UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) &&
-				(!st_vars->FoundFirstSurfaceWithMinActiveFCLKChangeMargin ||
-				st_vars->ActiveFCLKChangeLatencyMargin[k] < st_vars->MinActiveFCLKChangeMargin)) {
-			st_vars->FoundFirstSurfaceWithMinActiveFCLKChangeMargin = true;
-			st_vars->MinActiveFCLKChangeMargin = st_vars->ActiveFCLKChangeLatencyMargin[k];
-			st_vars->SurfaceWithMinActiveFCLKChangeMargin = k;
+	for (k = 0; k < v->NumberOfActiveSurfaces; ++k) {
+		if ((v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) &&
+				(!FoundFirstSurfaceWithMinActiveFCLKChangeMargin ||
+				ActiveFCLKChangeLatencyMargin[k] < MinActiveFCLKChangeMargin)) {
+			FoundFirstSurfaceWithMinActiveFCLKChangeMargin = true;
+			MinActiveFCLKChangeMargin = ActiveFCLKChangeLatencyMargin[k];
+			SurfaceWithMinActiveFCLKChangeMargin = k;
 		}
 	}
 
-	*MinActiveFCLKChangeLatencySupported = st_vars->MinActiveFCLKChangeMargin + mmSOCParameters.FCLKChangeLatency;
+	*MinActiveFCLKChangeLatencySupported = MinActiveFCLKChangeMargin + mmSOCParameters.FCLKChangeLatency;
 
-	st_vars->SameTimingForFCLKChange = true;
-	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
-		if (!st_vars->SynchronizedSurfaces[k][st_vars->SurfaceWithMinActiveFCLKChangeMargin]) {
-			if ((UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) &&
-					(st_vars->SameTimingForFCLKChange ||
-					st_vars->ActiveFCLKChangeLatencyMargin[k] <
-					st_vars->SecondMinActiveFCLKChangeMarginOneDisplayInVBLank)) {
-				st_vars->SecondMinActiveFCLKChangeMarginOneDisplayInVBLank = st_vars->ActiveFCLKChangeLatencyMargin[k];
+	SameTimingForFCLKChange = true;
+	for (k = 0; k < v->NumberOfActiveSurfaces; ++k) {
+		if (!SynchronizedSurfaces[k][SurfaceWithMinActiveFCLKChangeMargin]) {
+			if ((v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) &&
+					(SameTimingForFCLKChange ||
+					ActiveFCLKChangeLatencyMargin[k] <
+					SecondMinActiveFCLKChangeMarginOneDisplayInVBLank)) {
+				SecondMinActiveFCLKChangeMarginOneDisplayInVBLank = ActiveFCLKChangeLatencyMargin[k];
 			}
-			st_vars->SameTimingForFCLKChange = false;
+			SameTimingForFCLKChange = false;
 		}
 	}
 
-	if (st_vars->MinActiveFCLKChangeMargin > 0) {
+	if (MinActiveFCLKChangeMargin > 0) {
 		*FCLKChangeSupport = dm_fclock_change_vactive;
-	} else if ((st_vars->SameTimingForFCLKChange || st_vars->SecondMinActiveFCLKChangeMarginOneDisplayInVBLank > 0) &&
+	} else if ((SameTimingForFCLKChange || SecondMinActiveFCLKChangeMarginOneDisplayInVBLank > 0) &&
 			(PrefetchMode <= 1)) {
 		*FCLKChangeSupport = dm_fclock_change_vblank;
 	} else {
@@ -4451,95 +4502,95 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 	}
 
 	*USRRetrainingSupport = true;
-	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
-		if ((UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) &&
-				(st_vars->USRRetrainingLatencyMargin[k] < 0)) {
+	for (k = 0; k < v->NumberOfActiveSurfaces; ++k) {
+		if ((v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe) &&
+				(USRRetrainingLatencyMargin[k] < 0)) {
 			*USRRetrainingSupport = false;
 		}
 	}
 
-	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
-		if (UseMALLForPStateChange[k] != dm_use_mall_pstate_change_full_frame &&
-				UseMALLForPStateChange[k] != dm_use_mall_pstate_change_sub_viewport &&
-				UseMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe &&
+	for (k = 0; k < v->NumberOfActiveSurfaces; ++k) {
+		if (v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_full_frame &&
+				v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_sub_viewport &&
+				v->UsesMALLForPStateChange[k] != dm_use_mall_pstate_change_phantom_pipe &&
 				ActiveDRAMClockChangeLatencyMargin[k] < 0) {
 			if (PrefetchMode > 0) {
-				st_vars->DRAMClockChangeSupportNumber = 2;
-			} else if (st_vars->DRAMClockChangeSupportNumber == 0) {
-				st_vars->DRAMClockChangeSupportNumber = 1;
-				st_vars->LastSurfaceWithoutMargin = k;
-			} else if (st_vars->DRAMClockChangeSupportNumber == 1 &&
-					!st_vars->SynchronizedSurfaces[st_vars->LastSurfaceWithoutMargin][k]) {
-				st_vars->DRAMClockChangeSupportNumber = 2;
+				DRAMClockChangeSupportNumber = 2;
+			} else if (DRAMClockChangeSupportNumber == 0) {
+				DRAMClockChangeSupportNumber = 1;
+				LastSurfaceWithoutMargin = k;
+			} else if (DRAMClockChangeSupportNumber == 1 &&
+					!SynchronizedSurfaces[LastSurfaceWithoutMargin][k]) {
+				DRAMClockChangeSupportNumber = 2;
 			}
 		}
 	}
 
-	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
-		if (UseMALLForPStateChange[k] == dm_use_mall_pstate_change_full_frame)
-			st_vars->DRAMClockChangeMethod = 1;
-		else if (UseMALLForPStateChange[k] == dm_use_mall_pstate_change_sub_viewport)
-			st_vars->DRAMClockChangeMethod = 2;
+	for (k = 0; k < v->NumberOfActiveSurfaces; ++k) {
+		if (v->UsesMALLForPStateChange[k] == dm_use_mall_pstate_change_full_frame)
+			DRAMClockChangeMethod = 1;
+		else if (v->UsesMALLForPStateChange[k] == dm_use_mall_pstate_change_sub_viewport)
+			DRAMClockChangeMethod = 2;
 	}
 
-	if (st_vars->DRAMClockChangeMethod == 0) {
-		if (st_vars->DRAMClockChangeSupportNumber == 0)
+	if (DRAMClockChangeMethod == 0) {
+		if (DRAMClockChangeSupportNumber == 0)
 			*DRAMClockChangeSupport = dm_dram_clock_change_vactive;
-		else if (st_vars->DRAMClockChangeSupportNumber == 1)
+		else if (DRAMClockChangeSupportNumber == 1)
 			*DRAMClockChangeSupport = dm_dram_clock_change_vblank;
 		else
 			*DRAMClockChangeSupport = dm_dram_clock_change_unsupported;
-	} else if (st_vars->DRAMClockChangeMethod == 1) {
-		if (st_vars->DRAMClockChangeSupportNumber == 0)
+	} else if (DRAMClockChangeMethod == 1) {
+		if (DRAMClockChangeSupportNumber == 0)
 			*DRAMClockChangeSupport = dm_dram_clock_change_vactive_w_mall_full_frame;
-		else if (st_vars->DRAMClockChangeSupportNumber == 1)
+		else if (DRAMClockChangeSupportNumber == 1)
 			*DRAMClockChangeSupport = dm_dram_clock_change_vblank_w_mall_full_frame;
 		else
 			*DRAMClockChangeSupport = dm_dram_clock_change_unsupported;
 	} else {
-		if (st_vars->DRAMClockChangeSupportNumber == 0)
+		if (DRAMClockChangeSupportNumber == 0)
 			*DRAMClockChangeSupport = dm_dram_clock_change_vactive_w_mall_sub_vp;
-		else if (st_vars->DRAMClockChangeSupportNumber == 1)
+		else if (DRAMClockChangeSupportNumber == 1)
 			*DRAMClockChangeSupport = dm_dram_clock_change_vblank_w_mall_sub_vp;
 		else
 			*DRAMClockChangeSupport = dm_dram_clock_change_unsupported;
 	}
 
-	for (k = 0; k < NumberOfActiveSurfaces; ++k) {
+	for (k = 0; k < v->NumberOfActiveSurfaces; ++k) {
 		unsigned int dst_y_pstate;
 		unsigned int src_y_pstate_l;
 		unsigned int src_y_pstate_c;
 		unsigned int src_y_ahead_l, src_y_ahead_c, sub_vp_lines_l, sub_vp_lines_c;
 
-		dst_y_pstate = dml_ceil((mmSOCParameters.DRAMClockChangeLatency + mmSOCParameters.UrgentLatency) / (HTotal[k] / PixelClock[k]), 1);
-		src_y_pstate_l = dml_ceil(dst_y_pstate * VRatio[k], SwathHeightY[k]);
-		src_y_ahead_l = dml_floor(DETBufferSizeY[k] / BytePerPixelDETY[k] / SwathWidthY[k], SwathHeightY[k]) + st_vars->LBLatencyHidingSourceLinesY[k];
-		sub_vp_lines_l = src_y_pstate_l + src_y_ahead_l + meta_row_height[k];
+		dst_y_pstate = dml_ceil((mmSOCParameters.DRAMClockChangeLatency + mmSOCParameters.UrgentLatency) / (v->HTotal[k] / v->PixelClock[k]), 1);
+		src_y_pstate_l = dml_ceil(dst_y_pstate * v->VRatio[k], SwathHeightY[k]);
+		src_y_ahead_l = dml_floor(DETBufferSizeY[k] / BytePerPixelDETY[k] / SwathWidthY[k], SwathHeightY[k]) + LBLatencyHidingSourceLinesY[k];
+		sub_vp_lines_l = src_y_pstate_l + src_y_ahead_l + v->meta_row_height[k];
 
 #ifdef __DML_VBA_DEBUG__
 dml_print("DML::%s: k=%d, DETBufferSizeY               = %d\n", __func__, k, DETBufferSizeY[k]);
 dml_print("DML::%s: k=%d, BytePerPixelDETY             = %f\n", __func__, k, BytePerPixelDETY[k]);
 dml_print("DML::%s: k=%d, SwathWidthY                  = %d\n", __func__, k, SwathWidthY[k]);
 dml_print("DML::%s: k=%d, SwathHeightY                 = %d\n", __func__, k, SwathHeightY[k]);
-dml_print("DML::%s: k=%d, LBLatencyHidingSourceLinesY  = %d\n", __func__, k, st_vars->LBLatencyHidingSourceLinesY[k]);
+dml_print("DML::%s: k=%d, LBLatencyHidingSourceLinesY  = %d\n", __func__, k, LBLatencyHidingSourceLinesY[k]);
 dml_print("DML::%s: k=%d, dst_y_pstate      = %d\n", __func__, k, dst_y_pstate);
 dml_print("DML::%s: k=%d, src_y_pstate_l    = %d\n", __func__, k, src_y_pstate_l);
 dml_print("DML::%s: k=%d, src_y_ahead_l     = %d\n", __func__, k, src_y_ahead_l);
-dml_print("DML::%s: k=%d, meta_row_height   = %d\n", __func__, k, meta_row_height[k]);
+dml_print("DML::%s: k=%d, v->meta_row_height   = %d\n", __func__, k, v->meta_row_height[k]);
 dml_print("DML::%s: k=%d, sub_vp_lines_l    = %d\n", __func__, k, sub_vp_lines_l);
 #endif
 		SubViewportLinesNeededInMALL[k] = sub_vp_lines_l;
 
 		if (BytePerPixelDETC[k] > 0) {
-			src_y_pstate_c = dml_ceil(dst_y_pstate * VRatioChroma[k], SwathHeightC[k]);
-			src_y_ahead_c = dml_floor(DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k], SwathHeightC[k]) + st_vars->LBLatencyHidingSourceLinesC[k];
-			sub_vp_lines_c = src_y_pstate_c + src_y_ahead_c + meta_row_height_chroma[k];
+			src_y_pstate_c = dml_ceil(dst_y_pstate * v->VRatioChroma[k], SwathHeightC[k]);
+			src_y_ahead_c = dml_floor(DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k], SwathHeightC[k]) + LBLatencyHidingSourceLinesC[k];
+			sub_vp_lines_c = src_y_pstate_c + src_y_ahead_c + v->meta_row_height_chroma[k];
 			SubViewportLinesNeededInMALL[k] = dml_max(sub_vp_lines_l, sub_vp_lines_c);
 
 #ifdef __DML_VBA_DEBUG__
 dml_print("DML::%s: k=%d, src_y_pstate_c            = %d\n", __func__, k, src_y_pstate_c);
 dml_print("DML::%s: k=%d, src_y_ahead_c             = %d\n", __func__, k, src_y_ahead_c);
-dml_print("DML::%s: k=%d, meta_row_height_chroma    = %d\n", __func__, k, meta_row_height_chroma[k]);
+dml_print("DML::%s: k=%d, v->meta_row_height_chroma    = %d\n", __func__, k, v->meta_row_height_chroma[k]);
 dml_print("DML::%s: k=%d, sub_vp_lines_c            = %d\n", __func__, k, sub_vp_lines_c);
 #endif
 		}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h
index 37a314ce284b..0b427d89b3c5 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h
@@ -82,7 +82,6 @@ void dml32_CalculateSinglePipeDPPCLKAndSCLThroughput(
 		double *DPPCLKUsingSingleDPP);
 
 void dml32_CalculateSwathAndDETConfiguration(
-		struct dml32_CalculateSwathAndDETConfiguration *st_vars,
 		unsigned int DETSizeOverride[],
 		enum dm_use_mall_for_pstate_change_mode UseMALLForPStateChange[],
 		unsigned int ConfigReturnBufferSizeInKByte,
@@ -217,6 +216,7 @@ void dml32_CalculateDETBufferSize(
 void dml32_CalculateODMMode(
 		unsigned int MaximumPixelsPerLinePerDSCUnit,
 		unsigned int HActive,
+		enum output_format_class OutFormat,
 		enum output_encoder_class Output,
 		enum odm_combine_policy ODMUse,
 		double StateDispclk,
@@ -362,7 +362,6 @@ void dml32_CalculateSurfaceSizeInMall(
 		bool *ExceededMALLSize);
 
 void dml32_CalculateVMRowAndSwath(
-		struct dml32_CalculateVMRowAndSwath *st_vars,
 		unsigned int NumberOfActiveSurfaces,
 		DmlPipe myPipe[],
 		unsigned int SurfaceSizeInMALL[],
@@ -715,29 +714,14 @@ double dml32_CalculateExtraLatency(
 		unsigned int HostVMMaxNonCachedPageTableLevels);
 
 bool dml32_CalculatePrefetchSchedule(
-		struct dml32_CalculatePrefetchSchedule *st_vars,
+		struct vba_vars_st *v,
+		unsigned int k,
 		double HostVMInefficiencyFactor,
 		DmlPipe *myPipe,
 		unsigned int DSCDelay,
-		double DPPCLKDelaySubtotalPlusCNVCFormater,
-		double DPPCLKDelaySCL,
-		double DPPCLKDelaySCLLBOnly,
-		double DPPCLKDelayCNVCCursor,
-		double DISPCLKDelaySubtotal,
 		unsigned int DPP_RECOUT_WIDTH,
-		enum output_format_class OutputFormat,
-		unsigned int MaxInterDCNTileRepeaters,
 		unsigned int VStartup,
 		unsigned int MaxVStartup,
-		unsigned int GPUVMPageTableLevels,
-		bool GPUVMEnable,
-		bool HostVMEnable,
-		unsigned int HostVMMaxNonCachedPageTableLevels,
-		double HostVMMinPageSize,
-		bool DynamicMetadataEnable,
-		bool DynamicMetadataVMEnabled,
-		int DynamicMetadataLinesBeforeActiveRequired,
-		unsigned int DynamicMetadataTransmittedBytes,
 		double UrgentLatency,
 		double UrgentExtraLatency,
 		double TCalc,
@@ -811,59 +795,28 @@ void dml32_CalculateFlipSchedule(
 		bool *ImmediateFlipSupportedForPipe);
 
 void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
-		struct dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport *st_vars,
-		bool USRRetrainingRequiredFinal,
-		enum dm_use_mall_for_pstate_change_mode UseMALLForPStateChange[],
+		struct vba_vars_st *v,
 		unsigned int PrefetchMode,
-		unsigned int NumberOfActiveSurfaces,
-		unsigned int MaxLineBufferLines,
-		unsigned int LineBufferSize,
-		unsigned int WritebackInterfaceBufferSize,
 		double DCFCLK,
 		double ReturnBW,
-		bool SynchronizeTimingsFinal,
-		bool SynchronizeDRRDisplaysForUCLKPStateChangeFinal,
-		bool DRRDisplay[],
-		unsigned int dpte_group_bytes[],
-		unsigned int meta_row_height[],
-		unsigned int meta_row_height_chroma[],
 		SOCParametersList mmSOCParameters,
-		unsigned int WritebackChunkSize,
 		double SOCCLK,
 		double DCFClkDeepSleep,
 		unsigned int DETBufferSizeY[],
 		unsigned int DETBufferSizeC[],
 		unsigned int SwathHeightY[],
 		unsigned int SwathHeightC[],
-		unsigned int LBBitPerPixel[],
 		double SwathWidthY[],
 		double SwathWidthC[],
-		double HRatio[],
-		double HRatioChroma[],
-		unsigned int VTaps[],
-		unsigned int VTapsChroma[],
-		double VRatio[],
-		double VRatioChroma[],
-		unsigned int HTotal[],
-		unsigned int VTotal[],
-		unsigned int VActive[],
-		double PixelClock[],
-		unsigned int BlendingAndTiming[],
 		unsigned int DPPPerSurface[],
 		double BytePerPixelDETY[],
 		double BytePerPixelDETC[],
 		double DSTXAfterScaler[],
 		double DSTYAfterScaler[],
-		bool WritebackEnable[],
-		enum source_format_class WritebackPixelFormat[],
-		double WritebackDestinationWidth[],
-		double WritebackDestinationHeight[],
-		double WritebackSourceHeight[],
 		bool UnboundedRequestEnabled,
 		unsigned int CompressedBufferSizeInkByte,
 
 		/* Output */
-		Watermarks *Watermark,
 		enum clock_change_support *DRAMClockChangeSupport,
 		double MaxActiveDRAMClockChangeLatencySupported[],
 		unsigned int SubViewportLinesNeededInMALL[],
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
index 84b4b00f29cb..c87091683b5d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
@@ -498,6 +498,13 @@ void dcn321_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p
 				dc->bb_overrides.dram_clock_change_latency_ns / 1000.0;
 		}
 
+		if ((int)(dcn3_21_soc.fclk_change_latency_us * 1000)
+				!= dc->bb_overrides.fclk_clock_change_latency_ns
+				&& dc->bb_overrides.fclk_clock_change_latency_ns) {
+			dcn3_21_soc.fclk_change_latency_us =
+				dc->bb_overrides.fclk_clock_change_latency_ns / 1000;
+		}
+
 		if ((int)(dcn3_21_soc.dummy_pstate_latency_us * 1000)
 				!= dc->bb_overrides.dummy_clock_change_latency_ns
 				&& dc->bb_overrides.dummy_clock_change_latency_ns) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
index 5d27ff0ebb5f..f5400eda07a5 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
@@ -35,6 +35,8 @@
 #include "dcn30/display_rq_dlg_calc_30.h"
 #include "dcn31/display_mode_vba_31.h"
 #include "dcn31/display_rq_dlg_calc_31.h"
+#include "dcn314/display_mode_vba_314.h"
+#include "dcn314/display_rq_dlg_calc_314.h"
 #include "dcn32/display_mode_vba_32.h"
 #include "dcn32/display_rq_dlg_calc_32.h"
 #include "dml_logger.h"
@@ -74,6 +76,13 @@ const struct dml_funcs dml31_funcs = {
 	.rq_dlg_get_rq_reg = dml31_rq_dlg_get_rq_reg
 };
 
+const struct dml_funcs dml314_funcs = {
+	.validate = dml314_ModeSupportAndSystemConfigurationFull,
+	.recalculate = dml314_recalculate,
+	.rq_dlg_get_dlg_reg = dml314_rq_dlg_get_dlg_reg,
+	.rq_dlg_get_rq_reg = dml314_rq_dlg_get_rq_reg
+};
+
 const struct dml_funcs dml32_funcs = {
 	.validate = dml32_ModeSupportAndSystemConfigurationFull,
     .recalculate = dml32_recalculate,
@@ -107,6 +116,9 @@ void dml_init_instance(struct display_mode_lib *lib,
 	case DML_PROJECT_DCN31_FPGA:
 		lib->funcs = dml31_funcs;
 		break;
+	case DML_PROJECT_DCN314:
+		lib->funcs = dml314_funcs;
+		break;
 	case DML_PROJECT_DCN32:
 		lib->funcs = dml32_funcs;
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
index 2bdd6ed22611..b1878a1440e2 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
@@ -41,6 +41,7 @@ enum dml_project {
 	DML_PROJECT_DCN30,
 	DML_PROJECT_DCN31,
 	DML_PROJECT_DCN31_FPGA,
+	DML_PROJECT_DCN314,
 	DML_PROJECT_DCN32,
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
index 8460aefe7b6d..2051ddaa641a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
@@ -182,108 +182,6 @@ void Calculate256BBlockSizes(
 		unsigned int *BlockWidth256BytesY,
 		unsigned int *BlockWidth256BytesC);
 
-struct dml32_CalculateSwathAndDETConfiguration {
-	unsigned int MaximumSwathHeightY[DC__NUM_DPP__MAX];
-	unsigned int MaximumSwathHeightC[DC__NUM_DPP__MAX];
-	unsigned int RoundedUpMaxSwathSizeBytesY[DC__NUM_DPP__MAX];
-	unsigned int RoundedUpMaxSwathSizeBytesC[DC__NUM_DPP__MAX];
-	unsigned int RoundedUpSwathSizeBytesY;
-	unsigned int RoundedUpSwathSizeBytesC;
-	double SwathWidthdoubleDPP[DC__NUM_DPP__MAX];
-	double SwathWidthdoubleDPPChroma[DC__NUM_DPP__MAX];
-	unsigned int TotalActiveDPP;
-	bool NoChromaSurfaces;
-	unsigned int DETBufferSizeInKByteForSwathCalculation;
-};
-
-struct dml32_CalculateVMRowAndSwath {
-	unsigned int PTEBufferSizeInRequestsForLuma[DC__NUM_DPP__MAX];
-	unsigned int PTEBufferSizeInRequestsForChroma[DC__NUM_DPP__MAX];
-	unsigned int PDEAndMetaPTEBytesFrameY;
-	unsigned int PDEAndMetaPTEBytesFrameC;
-	unsigned int MetaRowByteY[DC__NUM_DPP__MAX];
-	unsigned int MetaRowByteC[DC__NUM_DPP__MAX];
-	unsigned int PixelPTEBytesPerRowY[DC__NUM_DPP__MAX];
-	unsigned int PixelPTEBytesPerRowC[DC__NUM_DPP__MAX];
-	unsigned int PixelPTEBytesPerRowY_one_row_per_frame[DC__NUM_DPP__MAX];
-	unsigned int PixelPTEBytesPerRowC_one_row_per_frame[DC__NUM_DPP__MAX];
-	unsigned int dpte_row_width_luma_ub_one_row_per_frame[DC__NUM_DPP__MAX];
-	unsigned int dpte_row_height_luma_one_row_per_frame[DC__NUM_DPP__MAX];
-	unsigned int dpte_row_width_chroma_ub_one_row_per_frame[DC__NUM_DPP__MAX];
-	unsigned int dpte_row_height_chroma_one_row_per_frame[DC__NUM_DPP__MAX];
-	bool one_row_per_frame_fits_in_buffer[DC__NUM_DPP__MAX];
-};
-
-struct dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport {
-	unsigned int SurfaceWithMinActiveFCLKChangeMargin;
-	unsigned int DRAMClockChangeSupportNumber;
-	unsigned int LastSurfaceWithoutMargin;
-	unsigned int DRAMClockChangeMethod;
-	bool FoundFirstSurfaceWithMinActiveFCLKChangeMargin;
-	double MinActiveFCLKChangeMargin;
-	double SecondMinActiveFCLKChangeMarginOneDisplayInVBLank;
-	double ActiveClockChangeLatencyHidingY;
-	double ActiveClockChangeLatencyHidingC;
-	double ActiveClockChangeLatencyHiding;
-	double EffectiveDETBufferSizeY;
-	double ActiveFCLKChangeLatencyMargin[DC__NUM_DPP__MAX];
-	double USRRetrainingLatencyMargin[DC__NUM_DPP__MAX];
-	double TotalPixelBW;
-	bool SynchronizedSurfaces[DC__NUM_DPP__MAX][DC__NUM_DPP__MAX];
-	double EffectiveLBLatencyHidingY;
-	double EffectiveLBLatencyHidingC;
-	double LinesInDETY[DC__NUM_DPP__MAX];
-	double LinesInDETC[DC__NUM_DPP__MAX];
-	unsigned int LinesInDETYRoundedDownToSwath[DC__NUM_DPP__MAX];
-	unsigned int LinesInDETCRoundedDownToSwath[DC__NUM_DPP__MAX];
-	double FullDETBufferingTimeY;
-	double FullDETBufferingTimeC;
-	double WritebackDRAMClockChangeLatencyMargin;
-	double WritebackFCLKChangeLatencyMargin;
-	double WritebackLatencyHiding;
-	bool SameTimingForFCLKChange;
-	unsigned int TotalActiveWriteback;
-	unsigned int LBLatencyHidingSourceLinesY[DC__NUM_DPP__MAX];
-	unsigned int LBLatencyHidingSourceLinesC[DC__NUM_DPP__MAX];
-};
-
-struct dml32_CalculatePrefetchSchedule {
-	unsigned int DPPCycles, DISPCLKCycles;
-	double DSTTotalPixelsAfterScaler;
-	double LineTime;
-	double dst_y_prefetch_equ;
-	double prefetch_bw_oto;
-	double Tvm_oto;
-	double Tr0_oto;
-	double Tvm_oto_lines;
-	double Tr0_oto_lines;
-	double dst_y_prefetch_oto;
-	double TimeForFetchingMetaPTE;
-	double TimeForFetchingRowInVBlank;
-	double LinesToRequestPrefetchPixelData;
-	unsigned int HostVMDynamicLevelsTrips;
-	double trip_to_mem;
-	double Tvm_trips;
-	double Tr0_trips;
-	double Tvm_trips_rounded;
-	double Tr0_trips_rounded;
-	double Lsw_oto;
-	double Tpre_rounded;
-	double prefetch_bw_equ;
-	double Tvm_equ;
-	double Tr0_equ;
-	double Tdmbf;
-	double Tdmec;
-	double Tdmsks;
-	double prefetch_sw_bytes;
-	double bytes_pp;
-	double dep_bytes;
-	unsigned int max_vratio_pre;
-	double min_Lsw;
-	double Tsw_est1;
-	double Tsw_est3;
-};
-
 struct DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation {
 	unsigned int dummy_integer_array[2][DC__NUM_DPP__MAX];
 	double dummy_single_array[2][DC__NUM_DPP__MAX];
@@ -355,10 +253,6 @@ struct dummy_vars {
 	struct DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation
 	DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation;
 	struct dml32_ModeSupportAndSystemConfigurationFull dml32_ModeSupportAndSystemConfigurationFull;
-	struct dml32_CalculateSwathAndDETConfiguration dml32_CalculateSwathAndDETConfiguration;
-	struct dml32_CalculateVMRowAndSwath dml32_CalculateVMRowAndSwath;
-	struct dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport;
-	struct dml32_CalculatePrefetchSchedule dml32_CalculatePrefetchSchedule;
 };
 
 struct vba_vars_st {
@@ -757,10 +651,10 @@ struct vba_vars_st {
 
 	unsigned int OutputTypeAndRatePerState[DC__VOLTAGE_STATES][DC__NUM_DPP__MAX];
 	double RequiredDISPCLKPerSurface[DC__VOLTAGE_STATES][2][DC__NUM_DPP__MAX];
-	unsigned int MicroTileHeightY[DC__NUM_DPP__MAX];
-	unsigned int MicroTileHeightC[DC__NUM_DPP__MAX];
-	unsigned int MicroTileWidthY[DC__NUM_DPP__MAX];
-	unsigned int MicroTileWidthC[DC__NUM_DPP__MAX];
+	unsigned int MacroTileHeightY[DC__NUM_DPP__MAX];
+	unsigned int MacroTileHeightC[DC__NUM_DPP__MAX];
+	unsigned int MacroTileWidthY[DC__NUM_DPP__MAX];
+	unsigned int MacroTileWidthC[DC__NUM_DPP__MAX];
 	bool ImmediateFlipRequiredFinal;
 	bool DCCProgrammingAssumesScanDirectionUnknownFinal;
 	bool EnoughWritebackUnits;
@@ -906,8 +800,6 @@ struct vba_vars_st {
 	double PSCL_FACTOR[DC__NUM_DPP__MAX];
 	double PSCL_FACTOR_CHROMA[DC__NUM_DPP__MAX];
 	double MaximumVStartup[DC__VOLTAGE_STATES][2][DC__NUM_DPP__MAX];
-	unsigned int MacroTileWidthY[DC__NUM_DPP__MAX];
-	unsigned int MacroTileWidthC[DC__NUM_DPP__MAX];
 	double AlignedDCCMetaPitch[DC__NUM_DPP__MAX];
 	double AlignedYPitch[DC__NUM_DPP__MAX];
 	double AlignedCPitch[DC__NUM_DPP__MAX];
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
index 5d2b028e5dad..d9f1b0a4fbd4 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
@@ -214,6 +214,7 @@ struct dummy_pstate_entry {
 struct clk_bw_params {
 	unsigned int vram_type;
 	unsigned int num_channels;
+	unsigned int dram_channel_width_bytes;
  	unsigned int dispclk_vco_khz;
 	unsigned int dc_mode_softmax_memclk;
 	struct clk_limit_table clk_table;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
index 68c2ed434d2c..cff5fd55a0ad 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
@@ -340,6 +340,8 @@ struct clk_mgr_internal {
 	bool smu_present;
 	void *wm_range_table;
 	long long wm_range_table_addr;
+
+	bool dpm_present;
 };
 
 struct clk_mgr_internal_funcs {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index 58158764adc0..7614125c92c7 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -219,6 +219,10 @@ void check_syncd_pipes_for_disabled_master_pipe(struct dc *dc,
 	struct dc_state *context,
 	uint8_t disabled_master_pipe_idx);
 
+void reset_sync_context_for_pipe(const struct dc *dc,
+	struct dc_state *context,
+	uint8_t pipe_idx);
+
 uint8_t resource_transmitter_to_phy_idx(const struct dc *dc, enum transmitter transmitter);
 
 const struct link_hwss *get_link_hwss(const struct dc_link *link,
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c b/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c
index db7b0b155374..226af06278ce 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c
@@ -116,7 +116,7 @@ static void setup_hpo_dp_stream_encoder(struct pipe_ctx *pipe_ctx)
 	dto_params.timing = &pipe_ctx->stream->timing;
 	dto_params.ref_dtbclk_khz = dc->clk_mgr->funcs->get_dtb_ref_clk_frequency(dc->clk_mgr);
 
-	dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, link_enc->inst);
+	dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, stream_enc->inst);
 	dccg->funcs->enable_symclk32_se(dccg, stream_enc->inst, phyd32clk);
 	dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
 	stream_enc->funcs->enable_stream(stream_enc);
@@ -137,7 +137,7 @@ static void reset_hpo_dp_stream_encoder(struct pipe_ctx *pipe_ctx)
 	stream_enc->funcs->disable(stream_enc);
 	dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
 	dccg->funcs->disable_symclk32_se(dccg, stream_enc->inst);
-	dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst,  pipe_ctx->link_res.hpo_dp_link_enc->inst);
+	dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, stream_enc->inst);
 }
 
 static void setup_hpo_dp_stream_attribute(struct pipe_ctx *pipe_ctx)
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index ab06c7fc7452..9f3558c0ef11 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -244,13 +244,15 @@ enum {
 #define ASICREV_IS_GC_10_3_7(eChipRev) ((eChipRev >= GC_10_3_7_A0) && (eChipRev < GC_10_3_7_UNKNOWN))
 
 #define AMDGPU_FAMILY_GC_11_0_0 145
-#define AMDGPU_FAMILY_GC_11_0_2 148
+#define AMDGPU_FAMILY_GC_11_0_1 148
 #define GC_11_0_0_A0 0x1
 #define GC_11_0_2_A0 0x10
+#define GC_11_0_3_A0 0x20
 #define GC_11_UNKNOWN 0xFF
 
 #define ASICREV_IS_GC_11_0_0(eChipRev) (eChipRev < GC_11_0_2_A0)
-#define ASICREV_IS_GC_11_0_2(eChipRev) (eChipRev >= GC_11_0_2_A0 && eChipRev < GC_11_UNKNOWN)
+#define ASICREV_IS_GC_11_0_2(eChipRev) (eChipRev >= GC_11_0_2_A0 && eChipRev < GC_11_0_3_A0)
+#define ASICREV_IS_GC_11_0_3(eChipRev) (eChipRev >= GC_11_0_3_A0 && eChipRev < GC_11_UNKNOWN)
 
 /*
  * ASIC chip ID
diff --git a/drivers/gpu/drm/amd/display/include/logger_types.h b/drivers/gpu/drm/amd/display/include/logger_types.h
index f093b49c5e6e..3bf08a60c45c 100644
--- a/drivers/gpu/drm/amd/display/include/logger_types.h
+++ b/drivers/gpu/drm/amd/display/include/logger_types.h
@@ -119,13 +119,15 @@ enum dc_log_type {
 	LOG_HDMI_RETIMER_REDRIVER,
 	LOG_DSC,
 	LOG_SMU_MSG,
+	LOG_DC2RESERVED4,
+	LOG_DC2RESERVED5,
 	LOG_DWB,
 	LOG_GAMMA_DEBUG,
 	LOG_MAX_HW_POINTS,
 	LOG_ALL_TF_CHANNELS,
 	LOG_SAMPLE_1DLUT,
 	LOG_DP2,
-	LOG_SECTION_TOTAL_COUNT
+	LOG_DC2RESERVED12,
 };
 
 #define DC_MIN_LOG_MASK ((1 << LOG_ERROR) | \
diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
index 859ffd8725c5..04f7656906ca 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -1600,6 +1600,7 @@ static void interpolate_user_regamma(uint32_t hw_points_num,
 	struct fixed31_32 lut2;
 	struct fixed31_32 delta_lut;
 	struct fixed31_32 delta_index;
+	const struct fixed31_32 one = dc_fixpt_from_int(1);
 
 	i = 0;
 	/* fixed_pt library has problems handling too small values */
@@ -1628,6 +1629,9 @@ static void interpolate_user_regamma(uint32_t hw_points_num,
 			} else
 				hw_x = coordinates_x[i].x;
 
+			if (dc_fixpt_le(one, hw_x))
+				hw_x = one;
+
 			norm_x = dc_fixpt_mul(norm_factor, hw_x);
 			index = dc_fixpt_floor(norm_x);
 			if (index < 0 || index > 255)
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index da09ba7589f7..0f39ab9dc5b4 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -613,10 +613,6 @@ static void build_vrr_infopacket_data_v1(const struct mod_vrr_params *vrr,
 	 * Note: We should never go above the field rate of the mode timing set.
 	 */
 	infopacket->sb[8] = (unsigned char)((vrr->max_refresh_in_uhz + 500000) / 1000000);
-
-	/* FreeSync HDR */
-	infopacket->sb[9] = 0;
-	infopacket->sb[10] = 0;
 }
 
 static void build_vrr_infopacket_data_v3(const struct mod_vrr_params *vrr,
@@ -684,10 +680,6 @@ static void build_vrr_infopacket_data_v3(const struct mod_vrr_params *vrr,
 
 	/* PB16 : Reserved bits 7:1, FixedRate bit 0 */
 	infopacket->sb[16] = (vrr->state == VRR_STATE_ACTIVE_FIXED) ? 1 : 0;
-
-	//FreeSync HDR
-	infopacket->sb[9] = 0;
-	infopacket->sb[10] = 0;
 }
 
 static void build_vrr_infopacket_fs2_data(enum color_transfer_func app_tf,
@@ -772,8 +764,7 @@ static void build_vrr_infopacket_header_v2(enum signal_type signal,
 		/* HB2  = [Bits 7:5 = 0] [Bits 4:0 = Length = 0x09] */
 		infopacket->hb2 = 0x09;
 
-		*payload_size = 0x0A;
-
+		*payload_size = 0x09;
 	} else if (dc_is_dp_signal(signal)) {
 
 		/* HEADER */
@@ -822,9 +813,9 @@ static void build_vrr_infopacket_header_v3(enum signal_type signal,
 		infopacket->hb1 = version;
 
 		/* HB2  = [Bits 7:5 = 0] [Bits 4:0 = Length] */
-		*payload_size = 0x10;
-		infopacket->hb2 = *payload_size - 1; //-1 for checksum
+		infopacket->hb2 = 0x10;
 
+		*payload_size = 0x10;
 	} else if (dc_is_dp_signal(signal)) {
 
 		/* HEADER */
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_offset.h
index 2ed95790a600..cf8d60c4df1b 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_offset.h
@@ -15243,6 +15243,8 @@
 #define regBIF0_PCIE_TX_TRACKING_ADDR_HI_BASE_IDX                                                       5
 #define regBIF0_PCIE_TX_TRACKING_CTRL_STATUS                                                            0x420186
 #define regBIF0_PCIE_TX_TRACKING_CTRL_STATUS_BASE_IDX                                                   5
+#define regBIF0_PCIE_TX_POWER_CTRL_1                                                                    0x420187
+#define regBIF0_PCIE_TX_POWER_CTRL_1_BASE_IDX                                                           5
 #define regBIF0_PCIE_TX_CTRL_4                                                                          0x42018b
 #define regBIF0_PCIE_TX_CTRL_4_BASE_IDX                                                                 5
 #define regBIF0_PCIE_TX_STATUS                                                                          0x420194
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_sh_mask.h
index eb62a18fcc48..3d60c9e92548 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_7_0_sh_mask.h
@@ -85627,6 +85627,19 @@
 #define BIF0_PCIE_TX_TRACKING_CTRL_STATUS__TX_TRACKING_PORT_MASK                                              0x0000000EL
 #define BIF0_PCIE_TX_TRACKING_CTRL_STATUS__TX_TRACKING_UNIT_ID_MASK                                           0x00007F00L
 #define BIF0_PCIE_TX_TRACKING_CTRL_STATUS__TX_TRACKING_STATUS_VALID_MASK                                      0x00008000L
+//BIF0_PCIE_TX_POWER_CTRL_1
+#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_LS_EN__SHIFT                                                       0x0
+#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_DS_EN__SHIFT                                                       0x1
+#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_SD_EN__SHIFT                                                       0x2
+#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_LS_EN__SHIFT                                                    0x3
+#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_DS_EN__SHIFT                                                    0x4
+#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_SD_EN__SHIFT                                                    0x5
+#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_LS_EN_MASK                                                         0x00000001L
+#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_DS_EN_MASK                                                         0x00000002L
+#define BIF0_PCIE_TX_POWER_CTRL_1__MST_MEM_SD_EN_MASK                                                         0x00000004L
+#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_LS_EN_MASK                                                      0x00000008L
+#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_DS_EN_MASK                                                      0x00000010L
+#define BIF0_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_SD_EN_MASK                                                      0x00000020L
 //BIF0_PCIE_TX_CTRL_4
 #define BIF0_PCIE_TX_CTRL_4__TX_PORT_ACCESS_TIMER_SKEW__SHIFT                                                 0x0
 #define BIF0_PCIE_TX_CTRL_4__TX_PORT_ACCESS_TIMER_SKEW_MASK                                                   0x0000000FL
diff --git a/drivers/gpu/drm/amd/include/mes_v11_api_def.h b/drivers/gpu/drm/amd/include/mes_v11_api_def.h
index 80dab1146439..7e85cdc5bd34 100644
--- a/drivers/gpu/drm/amd/include/mes_v11_api_def.h
+++ b/drivers/gpu/drm/amd/include/mes_v11_api_def.h
@@ -268,7 +268,9 @@ union MESAPI__ADD_QUEUE {
 			uint32_t is_tmz_queue		: 1;
 			uint32_t map_kiq_utility_queue  : 1;
 			uint32_t is_kfd_process		: 1;
-			uint32_t reserved		: 22;
+			uint32_t trap_en		: 1;
+			uint32_t is_aql_queue		: 1;
+			uint32_t reserved		: 20;
 		};
 		struct MES_API_STATUS		api_status;
 		uint64_t                        tma_addr;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h
index 78620b0bd279..063f4a737605 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h
@@ -24,12 +24,8 @@
 #ifndef SMU13_DRIVER_IF_V13_0_0_H
 #define SMU13_DRIVER_IF_V13_0_0_H
 
-// *** IMPORTANT ***
-// PMFW TEAM: Always increment the interface version on any change to this file
-#define SMU13_DRIVER_IF_VERSION  0x23
-
 //Increment this version if SkuTable_t or BoardTable_t change
-#define PPTABLE_VERSION 0x1D
+#define PPTABLE_VERSION 0x24
 
 #define NUM_GFXCLK_DPM_LEVELS    16
 #define NUM_SOCCLK_DPM_LEVELS    8
@@ -1193,8 +1189,17 @@ typedef struct {
   // SECTION: Advanced Options
   uint32_t          DebugOverrides;
 
+  // Section: Total Board Power idle vs active coefficients
+  uint8_t     TotalBoardPowerSupport;
+  uint8_t     TotalBoardPowerPadding[3];
+
+  int16_t     TotalIdleBoardPowerM;
+  int16_t     TotalIdleBoardPowerB;
+  int16_t     TotalBoardPowerM;
+  int16_t     TotalBoardPowerB;
+
   // SECTION: Sku Reserved
-  uint32_t         Spare[64];
+  uint32_t         Spare[61];
 
   // Padding for MMHUB - do not modify this
   uint32_t     MmHubPadding[8];
@@ -1259,7 +1264,8 @@ typedef struct {
   // SECTION: Clock Spread Spectrum
 
   // UCLK Spread Spectrum
-  uint16_t     UclkSpreadPadding;
+  uint8_t      UclkTrainingModeSpreadPercent;
+  uint8_t      UclkSpreadPadding;
   uint16_t     UclkSpreadFreq;      // kHz
 
   // UCLK Spread Spectrum
@@ -1272,11 +1278,7 @@ typedef struct {
 
   // Section: Memory Config
   uint8_t      DramWidth; // Width of interface to the channel for each DRAM module. See DRAM_BIT_WIDTH_TYPE_e
-  uint8_t      PaddingMem1[3];
-
-  // Section: Total Board Power
-  uint16_t     TotalBoardPower;     //Only needed for TCP Estimated case, where TCP = TGP+Total Board Power
-  uint16_t     BoardPowerPadding;
+  uint8_t      PaddingMem1[7];
 
   // SECTION: UMC feature flags
   uint8_t      HsrEnabled;
@@ -1375,8 +1377,11 @@ typedef struct {
   uint16_t Vcn1ActivityPercentage  ;
 
   uint32_t EnergyAccumulator;
-  uint16_t AverageSocketPower    ;
+  uint16_t AverageSocketPower;
+  uint16_t AverageTotalBoardPower;
+
   uint16_t AvgTemperature[TEMP_COUNT];
+  uint16_t TempPadding;
 
   uint8_t  PcieRate               ;
   uint8_t  PcieWidth              ;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h
index 76f695a1d065..ae2d337158f3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_4.h
@@ -27,7 +27,7 @@
 // *** IMPORTANT ***
 // SMU TEAM: Always increment the interface version if
 // any structure is changed in this file
-#define PMFW_DRIVER_IF_VERSION 4
+#define PMFW_DRIVER_IF_VERSION 5
 
 typedef struct {
   int32_t value;
@@ -197,6 +197,8 @@ typedef struct {
 
   uint16_t SkinTemp;
   uint16_t DeviceState;
+  uint16_t CurTemp;                     //[centi-Celsius]
+  uint16_t spare2;
 } SmuMetrics_t;
 
 typedef struct {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
index c02e5e576728..f442bf085a31 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
@@ -28,9 +28,9 @@
 #define SMU13_DRIVER_IF_VERSION_INV 0xFFFFFFFF
 #define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x04
 #define SMU13_DRIVER_IF_VERSION_ALDE 0x08
-#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x04
+#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x05
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04
-#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0 0x2C
+#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0 0x30
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x2C
 
 #define SMU13_MODE1_RESET_WAIT_TIME_IN_MS 500  //500ms
@@ -291,5 +291,11 @@ int smu_v13_0_set_default_dpm_tables(struct smu_context *smu);
 void smu_v13_0_set_smu_mailbox_registers(struct smu_context *smu);
 
 int smu_v13_0_mode1_reset(struct smu_context *smu);
+
+int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu,
+					void **table,
+					uint32_t *size,
+					uint32_t pptable_id);
+
 #endif
 #endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index fa520d79ef67..644ea150e075 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -368,6 +368,17 @@ static void sienna_cichlid_check_bxco_support(struct smu_context *smu)
 		smu_baco->platform_support =
 			(val & RCC_BIF_STRAP0__STRAP_PX_CAPABLE_MASK) ? true :
 									false;
+
+		/*
+		 * Disable BACO entry/exit completely on below SKUs to
+		 * avoid hardware intermittent failures.
+		 */
+		if (((adev->pdev->device == 0x73A1) &&
+		    (adev->pdev->revision == 0x00)) ||
+		    ((adev->pdev->device == 0x73BF) &&
+		    (adev->pdev->revision == 0xCF)))
+			smu_baco->platform_support = false;
+
 	}
 }
 
@@ -4283,6 +4294,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.dump_pptable = sienna_cichlid_dump_pptable,
 	.init_microcode = smu_v11_0_init_microcode,
 	.load_microcode = smu_v11_0_load_microcode,
+	.fini_microcode = smu_v11_0_fini_microcode,
 	.init_smc_tables = sienna_cichlid_init_smc_tables,
 	.fini_smc_tables = smu_v11_0_fini_smc_tables,
 	.init_power = smu_v11_0_init_power,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index e8fe84f806d1..93f9b8377539 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -84,9 +84,6 @@ MODULE_FIRMWARE("amdgpu/smu_13_0_7.bin");
 static const int link_width[] = {0, 1, 2, 4, 8, 12, 16};
 static const int link_speed[] = {25, 50, 80, 160};
 
-static int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu, void **table, uint32_t *size,
-					       uint32_t pptable_id);
-
 int smu_v13_0_init_microcode(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
@@ -212,40 +209,16 @@ int smu_v13_0_init_pptable_microcode(struct smu_context *smu)
 	if (!adev->scpm_enabled)
 		return 0;
 
+	if ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 7)) ||
+	    (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0)))
+		return 0;
+
 	/* override pptable_id from driver parameter */
 	if (amdgpu_smu_pptable_id >= 0) {
 		pptable_id = amdgpu_smu_pptable_id;
 		dev_info(adev->dev, "override pptable id %d\n", pptable_id);
 	} else {
 		pptable_id = smu->smu_table.boot_values.pp_table_id;
-
-		if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 7) &&
-			pptable_id == 3667)
-			pptable_id = 36671;
-
-		if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 7) &&
-			pptable_id == 3688)
-			pptable_id = 36881;
-		/*
-		 * Temporary solution for SMU V13.0.0 with SCPM enabled:
-		 *   - use 36831 signed pptable when pp_table_id is 3683
-		 *   - use 36641 signed pptable when pp_table_id is 3664 or 0
-		 * TODO: drop these when the pptable carried in vbios is ready.
-		 */
-		if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0)) {
-			switch (pptable_id) {
-			case 0:
-			case 3664:
-				pptable_id = 36641;
-				break;
-			case 3683:
-				pptable_id = 36831;
-				break;
-			default:
-				dev_err(adev->dev, "Unsupported pptable id %d\n", pptable_id);
-				return -EINVAL;
-			}
-		}
 	}
 
 	/* "pptable_id == 0" means vbios carries the pptable. */
@@ -425,8 +398,10 @@ static int smu_v13_0_get_pptable_from_vbios(struct smu_context *smu, void **tabl
 	return 0;
 }
 
-static int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu, void **table, uint32_t *size,
-					       uint32_t pptable_id)
+int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu,
+					void **table,
+					uint32_t *size,
+					uint32_t pptable_id)
 {
 	const struct smc_firmware_header_v1_0 *hdr;
 	struct amdgpu_device *adev = smu->adev;
@@ -476,25 +451,6 @@ int smu_v13_0_setup_pptable(struct smu_context *smu)
 	} else {
 		pptable_id = smu->smu_table.boot_values.pp_table_id;
 
-		/*
-		 * Temporary solution for SMU V13.0.0 with SCPM disabled:
-		 *   - use 3664 or 3683 on request
-		 *   - use 3664 when pptable_id is 0
-		 * TODO: drop these when the pptable carried in vbios is ready.
-		 */
-		if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0)) {
-			switch (pptable_id) {
-			case 0:
-				pptable_id = 3664;
-				break;
-			case 3664:
-			case 3683:
-				break;
-			default:
-				dev_err(adev->dev, "Unsupported pptable id %d\n", pptable_id);
-				return -EINVAL;
-			}
-		}
 	}
 
 	/* force using vbios pptable in sriov mode */
@@ -2344,8 +2300,8 @@ int smu_v13_0_set_gfx_power_up_by_imu(struct smu_context *smu)
 
 	index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_MSG,
 					       SMU_MSG_EnableGfxImu);
-
-	return smu_cmn_send_msg_without_waiting(smu, index, 0);
+	/* Param 1 to tell PMFW to enable GFXOFF feature */
+	return smu_cmn_send_msg_without_waiting(smu, index, 1);
 }
 
 int smu_v13_0_od_edit_dpm_table(struct smu_context *smu,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 1bbeceeb9e3c..1d454485e0d9 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -239,82 +239,47 @@ smu_v13_0_0_get_allowed_feature_mask(struct smu_context *smu,
 				  uint32_t *feature_mask, uint32_t num)
 {
 	struct amdgpu_device *adev = smu->adev;
+	u32 smu_version;
 
 	if (num > 2)
 		return -EINVAL;
 
-	memset(feature_mask, 0, sizeof(uint32_t) * num);
-
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_FW_DATA_READ_BIT);
+	memset(feature_mask, 0xff, sizeof(uint32_t) * num);
 
-	if (adev->pm.pp_feature & PP_SCLK_DPM_MASK) {
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_GFXCLK_BIT);
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_GFX_IMU_BIT);
+	if (!(adev->pm.pp_feature & PP_SCLK_DPM_MASK)) {
+		*(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DPM_GFXCLK_BIT);
+		*(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_GFX_IMU_BIT);
 	}
 
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_MM_DPM_BIT);
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_VCN_BIT);
-
-	if ((adev->pg_flags & AMD_PG_SUPPORT_ATHUB) &&
-	    (adev->pg_flags & AMD_PG_SUPPORT_MMHUB))
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_ATHUB_MMHUB_PG_BIT);
-
-	if (adev->pm.pp_feature & PP_SOCCLK_DPM_MASK)
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT);
-
-#if 0
-	if (adev->pm.pp_feature & PP_GFXOFF_MASK)
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_GFXOFF_BIT);
-#endif
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_ATHUB) ||
+	    !(adev->pg_flags & AMD_PG_SUPPORT_MMHUB))
+		*(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_ATHUB_MMHUB_PG_BIT);
 
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_THROTTLERS_BIT);
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_FAN_CONTROL_BIT);
+	if (!(adev->pm.pp_feature & PP_SOCCLK_DPM_MASK))
+		*(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT);
 
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DF_CSTATE_BIT);
-
-	if (adev->pm.pp_feature & PP_MCLK_DPM_MASK) {
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_UCLK_BIT);
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_VMEMP_SCALING_BIT);
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_VDDIO_MEM_SCALING_BIT);
+	/* PMFW 78.58 contains a critical fix for gfxoff feature */
+	smu_cmn_get_smc_version(smu, NULL, &smu_version);
+	if ((smu_version < 0x004e3a00) ||
+	     !(adev->pm.pp_feature & PP_GFXOFF_MASK))
+		*(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_GFXOFF_BIT);
+
+	if (!(adev->pm.pp_feature & PP_MCLK_DPM_MASK)) {
+		*(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DPM_UCLK_BIT);
+		*(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_VMEMP_SCALING_BIT);
+		*(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_VDDIO_MEM_SCALING_BIT);
 	}
 
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_MEM_TEMP_READ_BIT);
-
-	if (adev->pm.pp_feature & PP_SCLK_DEEP_SLEEP_MASK)
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_GFXCLK_BIT);
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_SOCCLK_BIT);
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_SOC_MPCLK_DS_BIT);
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_BACO_MPCLK_DS_BIT);
+	if (!(adev->pm.pp_feature & PP_SCLK_DEEP_SLEEP_MASK))
+		*(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DS_GFXCLK_BIT);
 
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_FCLK_BIT);
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_DCN_BIT);
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_DCFCLK_BIT);
-
-	if (adev->pm.pp_feature & PP_PCIE_DPM_MASK) {
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_LINK_BIT);
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_LCLK_BIT);
+	if (!(adev->pm.pp_feature & PP_PCIE_DPM_MASK)) {
+		*(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DPM_LINK_BIT);
+		*(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_DS_LCLK_BIT);
 	}
 
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_BACO_BIT);
-
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_MP0CLK_BIT);
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_FW_DSTATE_BIT);
-
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_OUT_OF_BAND_MONITOR_BIT);
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_SOC_CG_BIT);
-
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_FCLK_BIT);
-
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_FW_CTF_BIT);
-
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_UCLK_BIT);
-
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_VR0HOT_BIT);
-
-	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_GFX_POWER_OPTIMIZER_BIT);
-
-	if (adev->pm.pp_feature & PP_ULV_MASK)
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_GFX_ULV_BIT);
+	if (!(adev->pm.pp_feature & PP_ULV_MASK))
+		*(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_GFX_ULV_BIT);
 
 	return 0;
 }
@@ -388,30 +353,35 @@ static int smu_v13_0_0_append_powerplay_table(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_v13_0_0_setup_pptable(struct smu_context *smu)
+static int smu_v13_0_0_get_pptable_from_pmfw(struct smu_context *smu,
+					     void **table,
+					     uint32_t *size)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	void *combo_pptable = smu_table->combo_pptable;
-	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 
-	/*
-	 * With SCPM enabled, the pptable used will be signed. It cannot
-	 * be used directly by driver. To get the raw pptable, we need to
-	 * rely on the combo pptable(and its revelant SMU message).
-	 */
-	if (adev->scpm_enabled) {
-		ret = smu_cmn_get_combo_pptable(smu);
-		if (ret)
-			return ret;
+	ret = smu_cmn_get_combo_pptable(smu);
+	if (ret)
+		return ret;
 
-		smu->smu_table.power_play_table = combo_pptable;
-		smu->smu_table.power_play_table_size = sizeof(struct smu_13_0_0_powerplay_table);
-	} else {
-		ret = smu_v13_0_setup_pptable(smu);
-		if (ret)
-			return ret;
-	}
+	*table = combo_pptable;
+	*size = sizeof(struct smu_13_0_0_powerplay_table);
+
+	return 0;
+}
+
+static int smu_v13_0_0_setup_pptable(struct smu_context *smu)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct amdgpu_device *adev = smu->adev;
+	int ret = 0;
+
+	ret = smu_v13_0_0_get_pptable_from_pmfw(smu,
+						&smu_table->power_play_table,
+						&smu_table->power_play_table_size);
+	if (ret)
+		return ret;
 
 	ret = smu_v13_0_0_store_powerplay_table(smu);
 	if (ret)
@@ -1792,7 +1762,9 @@ static const struct pptable_funcs smu_v13_0_0_ppt_funcs = {
 	.dump_pptable = smu_v13_0_0_dump_pptable,
 	.init_microcode = smu_v13_0_init_microcode,
 	.load_microcode = smu_v13_0_load_microcode,
+	.fini_microcode = smu_v13_0_fini_microcode,
 	.init_smc_tables = smu_v13_0_0_init_smc_tables,
+	.fini_smc_tables = smu_v13_0_fini_smc_tables,
 	.init_power = smu_v13_0_init_power,
 	.fini_power = smu_v13_0_fini_power,
 	.check_fw_status = smu_v13_0_check_fw_status,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
index 82d3718d8324..97e1d55dcaad 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
@@ -71,7 +71,6 @@ static struct cmn2asic_msg_mapping smu_v13_0_4_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(TestMessage,                    PPSMC_MSG_TestMessage,			1),
 	MSG_MAP(GetSmuVersion,                  PPSMC_MSG_GetPmfwVersion,		1),
 	MSG_MAP(GetDriverIfVersion,             PPSMC_MSG_GetDriverIfVersion,		1),
-	MSG_MAP(EnableGfxOff,                   PPSMC_MSG_EnableGfxOff,			1),
 	MSG_MAP(AllowGfxOff,                    PPSMC_MSG_AllowGfxOff,			1),
 	MSG_MAP(DisallowGfxOff,                 PPSMC_MSG_DisallowGfxOff,		1),
 	MSG_MAP(PowerDownVcn,                   PPSMC_MSG_PowerDownVcn,			1),
@@ -199,6 +198,9 @@ static int smu_v13_0_4_fini_smc_tables(struct smu_context *smu)
 	kfree(smu_table->watermarks_table);
 	smu_table->watermarks_table = NULL;
 
+	kfree(smu_table->gpu_metrics_table);
+	smu_table->gpu_metrics_table = NULL;
+
 	return 0;
 }
 
@@ -226,18 +228,6 @@ static int smu_v13_0_4_system_features_control(struct smu_context *smu, bool en)
 	return ret;
 }
 
-static int smu_v13_0_4_post_smu_init(struct smu_context *smu)
-{
-	struct amdgpu_device *adev = smu->adev;
-	int ret = 0;
-
-	/* allow message will be sent after enable message */
-	ret = smu_cmn_send_smc_msg(smu, SMU_MSG_EnableGfxOff, NULL);
-	if (ret)
-		dev_err(adev->dev, "Failed to Enable GfxOff!\n");
-	return ret;
-}
-
 static ssize_t smu_v13_0_4_get_gpu_metrics(struct smu_context *smu,
 					   void **table)
 {
@@ -1026,7 +1016,6 @@ static const struct pptable_funcs smu_v13_0_4_ppt_funcs = {
 	.get_pp_feature_mask = smu_cmn_get_pp_feature_mask,
 	.set_driver_table_location = smu_v13_0_set_driver_table_location,
 	.gfx_off_control = smu_v13_0_gfx_off_control,
-	.post_init = smu_v13_0_4_post_smu_init,
 	.mode2_reset = smu_v13_0_4_mode2_reset,
 	.get_dpm_ultimate_freq = smu_v13_0_4_get_dpm_ultimate_freq,
 	.od_edit_dpm_table = smu_v13_0_od_edit_dpm_table,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c
index 47360ef5c175..66445964efbd 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c
@@ -176,6 +176,9 @@ static int smu_v13_0_5_fini_smc_tables(struct smu_context *smu)
 	kfree(smu_table->watermarks_table);
 	smu_table->watermarks_table = NULL;
 
+	kfree(smu_table->gpu_metrics_table);
+	smu_table->gpu_metrics_table = NULL;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index 9dd56e73218b..c422bf8a09b1 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -120,6 +120,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_7_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(DisallowGfxOff,			PPSMC_MSG_DisallowGfxOff,              0),
 	MSG_MAP(Mode1Reset,             PPSMC_MSG_Mode1Reset,                  0),
 	MSG_MAP(PrepareMp1ForUnload,		PPSMC_MSG_PrepareMp1ForUnload,         0),
+	MSG_MAP(SetMGpuFanBoostLimitRpm,	PPSMC_MSG_SetMGpuFanBoostLimitRpm,     0),
 };
 
 static struct cmn2asic_mapping smu_v13_0_7_clk_map[SMU_CLK_COUNT] = {
@@ -400,11 +401,27 @@ static int smu_v13_0_7_append_powerplay_table(struct smu_context *smu)
 	return 0;
 }
 
+static int smu_v13_0_7_get_pptable_from_pmfw(struct smu_context *smu,
+					     void **table,
+					     uint32_t *size)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	void *combo_pptable = smu_table->combo_pptable;
+	int ret = 0;
+
+	ret = smu_cmn_get_combo_pptable(smu);
+	if (ret)
+		return ret;
+
+	*table = combo_pptable;
+	*size = sizeof(struct smu_13_0_7_powerplay_table);
+
+	return 0;
+}
 
 static int smu_v13_0_7_setup_pptable(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	void *combo_pptable = smu_table->combo_pptable;
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 
@@ -413,18 +430,11 @@ static int smu_v13_0_7_setup_pptable(struct smu_context *smu)
 	 * be used directly by driver. To get the raw pptable, we need to
 	 * rely on the combo pptable(and its revelant SMU message).
 	 */
-	if (adev->scpm_enabled) {
-		ret = smu_cmn_get_combo_pptable(smu);
-		if (ret)
-			return ret;
-
-		smu->smu_table.power_play_table = combo_pptable;
-		smu->smu_table.power_play_table_size = sizeof(struct smu_13_0_7_powerplay_table);
-	} else {
-		ret = smu_v13_0_setup_pptable(smu);
-		if (ret)
-			return ret;
-	}
+	ret = smu_v13_0_7_get_pptable_from_pmfw(smu,
+						&smu_table->power_play_table,
+						&smu_table->power_play_table_size);
+	if (ret)
+		return ret;
 
 	ret = smu_v13_0_7_store_powerplay_table(smu);
 	if (ret)
@@ -1567,6 +1577,16 @@ static int smu_v13_0_7_set_mp1_state(struct smu_context *smu,
 	return ret;
 }
 
+static bool smu_v13_0_7_is_mode1_reset_supported(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+
+	/* SRIOV does not support SMU mode1 reset */
+	if (amdgpu_sriov_vf(adev))
+		return false;
+
+	return true;
+}
 static const struct pptable_funcs smu_v13_0_7_ppt_funcs = {
 	.get_allowed_feature_mask = smu_v13_0_7_get_allowed_feature_mask,
 	.set_default_dpm_table = smu_v13_0_7_set_default_dpm_table,
@@ -1574,7 +1594,9 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = {
 	.dump_pptable = smu_v13_0_7_dump_pptable,
 	.init_microcode = smu_v13_0_init_microcode,
 	.load_microcode = smu_v13_0_load_microcode,
+	.fini_microcode = smu_v13_0_fini_microcode,
 	.init_smc_tables = smu_v13_0_7_init_smc_tables,
+	.fini_smc_tables = smu_v13_0_fini_smc_tables,
 	.init_power = smu_v13_0_init_power,
 	.fini_power = smu_v13_0_fini_power,
 	.check_fw_status = smu_v13_0_7_check_fw_status,
@@ -1624,6 +1646,8 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = {
 	.baco_set_state = smu_v13_0_baco_set_state,
 	.baco_enter = smu_v13_0_baco_enter,
 	.baco_exit = smu_v13_0_baco_exit,
+	.mode1_reset_is_support = smu_v13_0_7_is_mode1_reset_supported,
+	.mode1_reset = smu_v13_0_mode1_reset,
 	.set_mp1_state = smu_v13_0_7_set_mp1_state,
 };
 
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index 8aadcc0aa90b..df9370e0ff23 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -1864,12 +1864,6 @@ EXPORT_SYMBOL_GPL(analogix_dp_remove);
 int analogix_dp_suspend(struct analogix_dp_device *dp)
 {
 	clk_disable_unprepare(dp->clock);
-
-	if (dp->plat_data->panel) {
-		if (drm_panel_unprepare(dp->plat_data->panel))
-			DRM_ERROR("failed to turnoff the panel\n");
-	}
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(analogix_dp_suspend);
@@ -1884,13 +1878,6 @@ int analogix_dp_resume(struct analogix_dp_device *dp)
 		return ret;
 	}
 
-	if (dp->plat_data->panel) {
-		if (drm_panel_prepare(dp->plat_data->panel)) {
-			DRM_ERROR("failed to setup the panel\n");
-			return -EBUSY;
-		}
-	}
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(analogix_dp_resume);
diff --git a/drivers/gpu/drm/bridge/lontium-lt8912b.c b/drivers/gpu/drm/bridge/lontium-lt8912b.c
index 28bad30dc4e5..5968f4af190b 100644
--- a/drivers/gpu/drm/bridge/lontium-lt8912b.c
+++ b/drivers/gpu/drm/bridge/lontium-lt8912b.c
@@ -188,7 +188,7 @@ static int lt8912_write_lvds_config(struct lt8912 *lt)
 		{0x03, 0xff},
 	};
 
-	return regmap_multi_reg_write(lt->regmap[I2C_CEC_DSI], seq, ARRAY_SIZE(seq));
+	return regmap_multi_reg_write(lt->regmap[I2C_MAIN], seq, ARRAY_SIZE(seq));
 };
 
 static inline struct lt8912 *bridge_to_lt8912(struct drm_bridge *b)
@@ -268,7 +268,7 @@ static int lt8912_video_setup(struct lt8912 *lt)
 	u32 hactive, h_total, hpw, hfp, hbp;
 	u32 vactive, v_total, vpw, vfp, vbp;
 	u8 settle = 0x08;
-	int ret;
+	int ret, hsync_activehigh, vsync_activehigh;
 
 	if (!lt)
 		return -EINVAL;
@@ -278,12 +278,14 @@ static int lt8912_video_setup(struct lt8912 *lt)
 	hpw = lt->mode.hsync_len;
 	hbp = lt->mode.hback_porch;
 	h_total = hactive + hfp + hpw + hbp;
+	hsync_activehigh = lt->mode.flags & DISPLAY_FLAGS_HSYNC_HIGH;
 
 	vactive = lt->mode.vactive;
 	vfp = lt->mode.vfront_porch;
 	vpw = lt->mode.vsync_len;
 	vbp = lt->mode.vback_porch;
 	v_total = vactive + vfp + vpw + vbp;
+	vsync_activehigh = lt->mode.flags & DISPLAY_FLAGS_VSYNC_HIGH;
 
 	if (vactive <= 600)
 		settle = 0x04;
@@ -317,6 +319,13 @@ static int lt8912_video_setup(struct lt8912 *lt)
 	ret |= regmap_write(lt->regmap[I2C_CEC_DSI], 0x3e, hfp & 0xff);
 	ret |= regmap_write(lt->regmap[I2C_CEC_DSI], 0x3f, hfp >> 8);
 
+	ret |= regmap_update_bits(lt->regmap[I2C_MAIN], 0xab, BIT(0),
+				  vsync_activehigh ? BIT(0) : 0);
+	ret |= regmap_update_bits(lt->regmap[I2C_MAIN], 0xab, BIT(1),
+				  hsync_activehigh ? BIT(1) : 0);
+	ret |= regmap_update_bits(lt->regmap[I2C_MAIN], 0xb2, BIT(0),
+				  lt->connector.display_info.is_hdmi ? BIT(0) : 0);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/bridge/lvds-codec.c b/drivers/gpu/drm/bridge/lvds-codec.c
index 702ea803a743..39e7004de720 100644
--- a/drivers/gpu/drm/bridge/lvds-codec.c
+++ b/drivers/gpu/drm/bridge/lvds-codec.c
@@ -180,7 +180,7 @@ static int lvds_codec_probe(struct platform_device *pdev)
 		of_node_put(bus_node);
 		if (ret == -ENODEV) {
 			dev_warn(dev, "missing 'data-mapping' DT property\n");
-		} else if (ret) {
+		} else if (ret < 0) {
 			dev_err(dev, "invalid 'data-mapping' DT property\n");
 			return ret;
 		} else {
diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index 493922069c90..01ee3febb813 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -377,8 +377,8 @@ static int vrr_range_show(struct seq_file *m, void *data)
 	if (connector->status != connector_status_connected)
 		return -ENODEV;
 
-	seq_printf(m, "Min: %u\n", (u8)connector->display_info.monitor_range.min_vfreq);
-	seq_printf(m, "Max: %u\n", (u8)connector->display_info.monitor_range.max_vfreq);
+	seq_printf(m, "Min: %u\n", connector->display_info.monitor_range.min_vfreq);
+	seq_printf(m, "Max: %u\n", connector->display_info.monitor_range.max_vfreq);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index bbc25e3b7220..eaa819381281 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -5971,12 +5971,14 @@ static void drm_parse_cea_ext(struct drm_connector *connector,
 }
 
 static
-void get_monitor_range(const struct detailed_timing *timing,
-		       void *info_monitor_range)
+void get_monitor_range(const struct detailed_timing *timing, void *c)
 {
-	struct drm_monitor_range_info *monitor_range = info_monitor_range;
+	struct detailed_mode_closure *closure = c;
+	struct drm_display_info *info = &closure->connector->display_info;
+	struct drm_monitor_range_info *monitor_range = &info->monitor_range;
 	const struct detailed_non_pixel *data = &timing->data.other_data;
 	const struct detailed_data_monitor_range *range = &data->data.range;
+	const struct edid *edid = closure->drm_edid->edid;
 
 	if (!is_display_descriptor(timing, EDID_DETAIL_MONITOR_RANGE))
 		return;
@@ -5992,18 +5994,28 @@ void get_monitor_range(const struct detailed_timing *timing,
 
 	monitor_range->min_vfreq = range->min_vfreq;
 	monitor_range->max_vfreq = range->max_vfreq;
+
+	if (edid->revision >= 4) {
+		if (data->pad2 & DRM_EDID_RANGE_OFFSET_MIN_VFREQ)
+			monitor_range->min_vfreq += 255;
+		if (data->pad2 & DRM_EDID_RANGE_OFFSET_MAX_VFREQ)
+			monitor_range->max_vfreq += 255;
+	}
 }
 
 static void drm_get_monitor_range(struct drm_connector *connector,
 				  const struct drm_edid *drm_edid)
 {
-	struct drm_display_info *info = &connector->display_info;
+	const struct drm_display_info *info = &connector->display_info;
+	struct detailed_mode_closure closure = {
+		.connector = connector,
+		.drm_edid = drm_edid,
+	};
 
 	if (!version_greater(drm_edid, 1, 1))
 		return;
 
-	drm_for_each_detailed_block(drm_edid, get_monitor_range,
-				    &info->monitor_range);
+	drm_for_each_detailed_block(drm_edid, get_monitor_range, &closure);
 
 	DRM_DEBUG_KMS("Supported Monitor Refresh rate range is %d Hz - %d Hz\n",
 		      info->monitor_range.min_vfreq,
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 86d670c71286..ad068865ba20 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -168,21 +168,6 @@ void drm_gem_private_object_init(struct drm_device *dev,
 }
 EXPORT_SYMBOL(drm_gem_private_object_init);
 
-static void
-drm_gem_remove_prime_handles(struct drm_gem_object *obj, struct drm_file *filp)
-{
-	/*
-	 * Note: obj->dma_buf can't disappear as long as we still hold a
-	 * handle reference in obj->handle_count.
-	 */
-	mutex_lock(&filp->prime.lock);
-	if (obj->dma_buf) {
-		drm_prime_remove_buf_handle_locked(&filp->prime,
-						   obj->dma_buf);
-	}
-	mutex_unlock(&filp->prime.lock);
-}
-
 /**
  * drm_gem_object_handle_free - release resources bound to userspace handles
  * @obj: GEM object to clean up.
@@ -253,7 +238,7 @@ drm_gem_object_release_handle(int id, void *ptr, void *data)
 	if (obj->funcs->close)
 		obj->funcs->close(obj, file_priv);
 
-	drm_gem_remove_prime_handles(obj, file_priv);
+	drm_prime_remove_buf_handle(&file_priv->prime, id);
 	drm_vma_node_revoke(&obj->vma_node, file_priv);
 
 	drm_gem_object_handle_put_unlocked(obj);
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 1fbbc19f1ac0..7bb98e6a446d 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -74,8 +74,8 @@ int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
 
 void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv);
 void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv);
-void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv,
-					struct dma_buf *dma_buf);
+void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv,
+				 uint32_t handle);
 
 /* drm_drv.c */
 struct drm_minor *drm_minor_acquire(unsigned int minor_id);
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index a3f180653b8b..eb09e86044c6 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -190,29 +190,33 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri
 	return -ENOENT;
 }
 
-void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv,
-					struct dma_buf *dma_buf)
+void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv,
+				 uint32_t handle)
 {
 	struct rb_node *rb;
 
-	rb = prime_fpriv->dmabufs.rb_node;
+	mutex_lock(&prime_fpriv->lock);
+
+	rb = prime_fpriv->handles.rb_node;
 	while (rb) {
 		struct drm_prime_member *member;
 
-		member = rb_entry(rb, struct drm_prime_member, dmabuf_rb);
-		if (member->dma_buf == dma_buf) {
+		member = rb_entry(rb, struct drm_prime_member, handle_rb);
+		if (member->handle == handle) {
 			rb_erase(&member->handle_rb, &prime_fpriv->handles);
 			rb_erase(&member->dmabuf_rb, &prime_fpriv->dmabufs);
 
-			dma_buf_put(dma_buf);
+			dma_buf_put(member->dma_buf);
 			kfree(member);
-			return;
-		} else if (member->dma_buf < dma_buf) {
+			break;
+		} else if (member->handle < handle) {
 			rb = rb->rb_right;
 		} else {
 			rb = rb->rb_left;
 		}
 	}
+
+	mutex_unlock(&prime_fpriv->lock);
 }
 
 void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv)
diff --git a/drivers/gpu/drm/gma500/cdv_device.c b/drivers/gpu/drm/gma500/cdv_device.c
index dd32b484dd82..ce96234f3df2 100644
--- a/drivers/gpu/drm/gma500/cdv_device.c
+++ b/drivers/gpu/drm/gma500/cdv_device.c
@@ -581,11 +581,9 @@ static const struct psb_offset cdv_regmap[2] = {
 static int cdv_chip_setup(struct drm_device *dev)
 {
 	struct drm_psb_private *dev_priv = to_drm_psb_private(dev);
-	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	INIT_WORK(&dev_priv->hotplug_work, cdv_hotplug_work_func);
 
-	if (pci_enable_msi(pdev))
-		dev_warn(dev->dev, "Enabling MSI failed!\n");
+	dev_priv->use_msi = true;
 	dev_priv->regmap = cdv_regmap;
 	gma_get_core_freq(dev);
 	psb_intel_opregion_init(dev);
diff --git a/drivers/gpu/drm/gma500/gem.c b/drivers/gpu/drm/gma500/gem.c
index dffe37490206..4b7627a72637 100644
--- a/drivers/gpu/drm/gma500/gem.c
+++ b/drivers/gpu/drm/gma500/gem.c
@@ -112,12 +112,12 @@ static void psb_gem_free_object(struct drm_gem_object *obj)
 {
 	struct psb_gem_object *pobj = to_psb_gem_object(obj);
 
-	drm_gem_object_release(obj);
-
 	/* Undo the mmap pin if we are destroying the object */
 	if (pobj->mmapping)
 		psb_gem_unpin(pobj);
 
+	drm_gem_object_release(obj);
+
 	WARN_ON(pobj->in_gart && !pobj->stolen);
 
 	release_resource(&pobj->resource);
diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c
index bd40c040a2c9..2f52eceda3a1 100644
--- a/drivers/gpu/drm/gma500/gma_display.c
+++ b/drivers/gpu/drm/gma500/gma_display.c
@@ -532,15 +532,18 @@ int gma_crtc_page_flip(struct drm_crtc *crtc,
 		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
 
 		gma_crtc->page_flip_event = event;
+		spin_unlock_irqrestore(&dev->event_lock, flags);
 
 		/* Call this locked if we want an event at vblank interrupt. */
 		ret = crtc_funcs->mode_set_base(crtc, crtc->x, crtc->y, old_fb);
 		if (ret) {
-			gma_crtc->page_flip_event = NULL;
-			drm_crtc_vblank_put(crtc);
+			spin_lock_irqsave(&dev->event_lock, flags);
+			if (gma_crtc->page_flip_event) {
+				gma_crtc->page_flip_event = NULL;
+				drm_crtc_vblank_put(crtc);
+			}
+			spin_unlock_irqrestore(&dev->event_lock, flags);
 		}
-
-		spin_unlock_irqrestore(&dev->event_lock, flags);
 	} else {
 		ret = crtc_funcs->mode_set_base(crtc, crtc->x, crtc->y, old_fb);
 	}
diff --git a/drivers/gpu/drm/gma500/oaktrail_device.c b/drivers/gpu/drm/gma500/oaktrail_device.c
index 5923a9c89312..f90e628cb482 100644
--- a/drivers/gpu/drm/gma500/oaktrail_device.c
+++ b/drivers/gpu/drm/gma500/oaktrail_device.c
@@ -501,12 +501,9 @@ static const struct psb_offset oaktrail_regmap[2] = {
 static int oaktrail_chip_setup(struct drm_device *dev)
 {
 	struct drm_psb_private *dev_priv = to_drm_psb_private(dev);
-	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	int ret;
 
-	if (pci_enable_msi(pdev))
-		dev_warn(dev->dev, "Enabling MSI failed!\n");
-
+	dev_priv->use_msi = true;
 	dev_priv->regmap = oaktrail_regmap;
 
 	ret = mid_chip_setup(dev);
diff --git a/drivers/gpu/drm/gma500/power.c b/drivers/gpu/drm/gma500/power.c
index b91de6d36e41..66873085d450 100644
--- a/drivers/gpu/drm/gma500/power.c
+++ b/drivers/gpu/drm/gma500/power.c
@@ -139,8 +139,6 @@ static void gma_suspend_pci(struct pci_dev *pdev)
 	dev_priv->regs.saveBSM = bsm;
 	pci_read_config_dword(pdev, 0xFC, &vbt);
 	dev_priv->regs.saveVBT = vbt;
-	pci_read_config_dword(pdev, PSB_PCIx_MSI_ADDR_LOC, &dev_priv->msi_addr);
-	pci_read_config_dword(pdev, PSB_PCIx_MSI_DATA_LOC, &dev_priv->msi_data);
 
 	pci_disable_device(pdev);
 	pci_set_power_state(pdev, PCI_D3hot);
@@ -168,9 +166,6 @@ static bool gma_resume_pci(struct pci_dev *pdev)
 	pci_restore_state(pdev);
 	pci_write_config_dword(pdev, 0x5c, dev_priv->regs.saveBSM);
 	pci_write_config_dword(pdev, 0xFC, dev_priv->regs.saveVBT);
-	/* restoring MSI address and data in PCIx space */
-	pci_write_config_dword(pdev, PSB_PCIx_MSI_ADDR_LOC, dev_priv->msi_addr);
-	pci_write_config_dword(pdev, PSB_PCIx_MSI_DATA_LOC, dev_priv->msi_data);
 	ret = pci_enable_device(pdev);
 
 	if (ret != 0)
@@ -223,8 +218,7 @@ int gma_power_resume(struct device *_dev)
 	mutex_lock(&power_mutex);
 	gma_resume_pci(pdev);
 	gma_resume_display(pdev);
-	gma_irq_preinstall(dev);
-	gma_irq_postinstall(dev);
+	gma_irq_install(dev);
 	mutex_unlock(&power_mutex);
 	return 0;
 }
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index 1d8744f3e702..54e756b48606 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -383,7 +383,7 @@ static int psb_driver_load(struct drm_device *dev, unsigned long flags)
 	PSB_WVDC32(0xFFFFFFFF, PSB_INT_MASK_R);
 	spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags);
 
-	gma_irq_install(dev, pdev->irq);
+	gma_irq_install(dev);
 
 	dev->max_vblank_count = 0xffffff; /* only 24 bits of frame count */
 
diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h
index 0ea3d23575f3..731cc356c07a 100644
--- a/drivers/gpu/drm/gma500/psb_drv.h
+++ b/drivers/gpu/drm/gma500/psb_drv.h
@@ -490,6 +490,7 @@ struct drm_psb_private {
 	int rpm_enabled;
 
 	/* MID specific */
+	bool use_msi;
 	bool has_gct;
 	struct oaktrail_gct_data gct_data;
 
@@ -499,10 +500,6 @@ struct drm_psb_private {
 	/* Register state */
 	struct psb_save_area regs;
 
-	/* MSI reg save */
-	uint32_t msi_addr;
-	uint32_t msi_data;
-
 	/* Hotplug handling */
 	struct work_struct hotplug_work;
 
diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c
index e6e6d61bbeab..038f18ed0a95 100644
--- a/drivers/gpu/drm/gma500/psb_irq.c
+++ b/drivers/gpu/drm/gma500/psb_irq.c
@@ -316,17 +316,24 @@ void gma_irq_postinstall(struct drm_device *dev)
 	spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags);
 }
 
-int gma_irq_install(struct drm_device *dev, unsigned int irq)
+int gma_irq_install(struct drm_device *dev)
 {
+	struct drm_psb_private *dev_priv = to_drm_psb_private(dev);
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	int ret;
 
-	if (irq == IRQ_NOTCONNECTED)
+	if (dev_priv->use_msi && pci_enable_msi(pdev)) {
+		dev_warn(dev->dev, "Enabling MSI failed!\n");
+		dev_priv->use_msi = false;
+	}
+
+	if (pdev->irq == IRQ_NOTCONNECTED)
 		return -ENOTCONN;
 
 	gma_irq_preinstall(dev);
 
 	/* PCI devices require shared interrupts. */
-	ret = request_irq(irq, gma_irq_handler, IRQF_SHARED, dev->driver->name, dev);
+	ret = request_irq(pdev->irq, gma_irq_handler, IRQF_SHARED, dev->driver->name, dev);
 	if (ret)
 		return ret;
 
@@ -369,6 +376,8 @@ void gma_irq_uninstall(struct drm_device *dev)
 	spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags);
 
 	free_irq(pdev->irq, dev);
+	if (dev_priv->use_msi)
+		pci_disable_msi(pdev);
 }
 
 int gma_crtc_enable_vblank(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/gma500/psb_irq.h b/drivers/gpu/drm/gma500/psb_irq.h
index b51e395194ff..7648f69824a5 100644
--- a/drivers/gpu/drm/gma500/psb_irq.h
+++ b/drivers/gpu/drm/gma500/psb_irq.h
@@ -17,7 +17,7 @@ struct drm_device;
 
 void gma_irq_preinstall(struct drm_device *dev);
 void gma_irq_postinstall(struct drm_device *dev);
-int  gma_irq_install(struct drm_device *dev, unsigned int irq);
+int  gma_irq_install(struct drm_device *dev);
 void gma_irq_uninstall(struct drm_device *dev);
 
 int  gma_crtc_enable_vblank(struct drm_crtc *crtc);
diff --git a/drivers/gpu/drm/hisilicon/hibmc/Kconfig b/drivers/gpu/drm/hisilicon/hibmc/Kconfig
index 073adfe438dd..4e41c144a290 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/Kconfig
+++ b/drivers/gpu/drm/hisilicon/hibmc/Kconfig
@@ -2,6 +2,7 @@
 config DRM_HISI_HIBMC
 	tristate "DRM Support for Hisilicon Hibmc"
 	depends on DRM && PCI && (ARM64 || COMPILE_TEST)
+	depends on MMU
 	select DRM_KMS_HELPER
 	select DRM_VRAM_HELPER
 	select DRM_TTM
diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
index 6d11e7938c83..f84d39762a72 100644
--- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
+++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
@@ -23,9 +23,6 @@
 #define DRIVER_MAJOR 1
 #define DRIVER_MINOR 0
 
-#define PCI_VENDOR_ID_MICROSOFT 0x1414
-#define PCI_DEVICE_ID_HYPERV_VIDEO 0x5353
-
 DEFINE_DRM_GEM_FOPS(hv_fops);
 
 static struct drm_driver hyperv_driver = {
@@ -133,7 +130,6 @@ static int hyperv_vmbus_probe(struct hv_device *hdev,
 	}
 
 	ret = hyperv_setup_vram(hv, hdev);
-
 	if (ret)
 		goto err_vmbus_close;
 
@@ -150,18 +146,20 @@ static int hyperv_vmbus_probe(struct hv_device *hdev,
 
 	ret = hyperv_mode_config_init(hv);
 	if (ret)
-		goto err_vmbus_close;
+		goto err_free_mmio;
 
 	ret = drm_dev_register(dev, 0);
 	if (ret) {
 		drm_err(dev, "Failed to register drm driver.\n");
-		goto err_vmbus_close;
+		goto err_free_mmio;
 	}
 
 	drm_fbdev_generic_setup(dev, 0);
 
 	return 0;
 
+err_free_mmio:
+	vmbus_free_mmio(hv->mem->start, hv->fb_size);
 err_vmbus_close:
 	vmbus_close(hdev->channel);
 err_hv_set_drv_data:
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index 5dcfa7feffa9..1390729401a0 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -1629,6 +1629,8 @@ static int gen11_dsi_dsc_compute_config(struct intel_encoder *encoder,
 	/* FIXME: initialize from VBT */
 	vdsc_cfg->rc_model_size = DSC_RC_MODEL_SIZE_CONST;
 
+	vdsc_cfg->pic_height = crtc_state->hw.adjusted_mode.crtc_vdisplay;
+
 	ret = intel_dsc_compute_params(crtc_state);
 	if (ret)
 		return ret;
@@ -2070,7 +2072,14 @@ void icl_dsi_init(struct drm_i915_private *dev_priv)
 	else
 		intel_dsi->ports = BIT(port);
 
+	if (drm_WARN_ON(&dev_priv->drm, intel_connector->panel.vbt.dsi.bl_ports & ~intel_dsi->ports))
+		intel_connector->panel.vbt.dsi.bl_ports &= intel_dsi->ports;
+
 	intel_dsi->dcs_backlight_ports = intel_connector->panel.vbt.dsi.bl_ports;
+
+	if (drm_WARN_ON(&dev_priv->drm, intel_connector->panel.vbt.dsi.cabc_ports & ~intel_dsi->ports))
+		intel_connector->panel.vbt.dsi.cabc_ports &= intel_dsi->ports;
+
 	intel_dsi->dcs_cabc_ports = intel_connector->panel.vbt.dsi.cabc_ports;
 
 	for_each_dsi_port(port, intel_dsi->ports) {
diff --git a/drivers/gpu/drm/i915/display/intel_backlight.c b/drivers/gpu/drm/i915/display/intel_backlight.c
index 110fc98ec280..f5e1d692976e 100644
--- a/drivers/gpu/drm/i915/display/intel_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_backlight.c
@@ -16,6 +16,7 @@
 #include "intel_dsi_dcs_backlight.h"
 #include "intel_panel.h"
 #include "intel_pci_config.h"
+#include "intel_pps.h"
 
 /**
  * scale - scale values from one range to another
@@ -971,26 +972,24 @@ int intel_backlight_device_register(struct intel_connector *connector)
 	if (!name)
 		return -ENOMEM;
 
-	bd = backlight_device_register(name, connector->base.kdev, connector,
-				       &intel_backlight_device_ops, &props);
-
-	/*
-	 * Using the same name independent of the drm device or connector
-	 * prevents registration of multiple backlight devices in the
-	 * driver. However, we need to use the default name for backward
-	 * compatibility. Use unique names for subsequent backlight devices as a
-	 * fallback when the default name already exists.
-	 */
-	if (IS_ERR(bd) && PTR_ERR(bd) == -EEXIST) {
+	bd = backlight_device_get_by_name(name);
+	if (bd) {
+		put_device(&bd->dev);
+		/*
+		 * Using the same name independent of the drm device or connector
+		 * prevents registration of multiple backlight devices in the
+		 * driver. However, we need to use the default name for backward
+		 * compatibility. Use unique names for subsequent backlight devices as a
+		 * fallback when the default name already exists.
+		 */
 		kfree(name);
 		name = kasprintf(GFP_KERNEL, "card%d-%s-backlight",
 				 i915->drm.primary->index, connector->base.name);
 		if (!name)
 			return -ENOMEM;
-
-		bd = backlight_device_register(name, connector->base.kdev, connector,
-					       &intel_backlight_device_ops, &props);
 	}
+	bd = backlight_device_register(name, connector->base.kdev, connector,
+				       &intel_backlight_device_ops, &props);
 
 	if (IS_ERR(bd)) {
 		drm_err(&i915->drm,
@@ -1773,9 +1772,13 @@ void intel_backlight_init_funcs(struct intel_panel *panel)
 		panel->backlight.pwm_funcs = &i9xx_pwm_funcs;
 	}
 
-	if (connector->base.connector_type == DRM_MODE_CONNECTOR_eDP &&
-	    intel_dp_aux_init_backlight_funcs(connector) == 0)
-		return;
+	if (connector->base.connector_type == DRM_MODE_CONNECTOR_eDP) {
+		if (intel_dp_aux_init_backlight_funcs(connector) == 0)
+			return;
+
+		if (!(dev_priv->quirks & QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK))
+			connector->panel.backlight.power = intel_pps_backlight_power;
+	}
 
 	/* We're using a standard PWM backlight interface */
 	panel->backlight.funcs = &pwm_bl_funcs;
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index 51dde5bfd956..7d6eb9ad7a02 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -479,6 +479,13 @@ init_bdb_block(struct drm_i915_private *i915,
 
 	block_size = get_blocksize(block);
 
+	/*
+	 * Version number and new block size are considered
+	 * part of the header for MIPI sequenece block v3+.
+	 */
+	if (section_id == BDB_MIPI_SEQUENCE && *(const u8 *)block >= 3)
+		block_size += 5;
+
 	entry = kzalloc(struct_size(entry, data, max(min_size, block_size) + 3),
 			GFP_KERNEL);
 	if (!entry) {
@@ -1596,6 +1603,8 @@ static void parse_dsi_backlight_ports(struct drm_i915_private *i915,
 				      struct intel_panel *panel,
 				      enum port port)
 {
+	enum port port_bc = DISPLAY_VER(i915) >= 11 ? PORT_B : PORT_C;
+
 	if (!panel->vbt.dsi.config->dual_link || i915->vbt.version < 197) {
 		panel->vbt.dsi.bl_ports = BIT(port);
 		if (panel->vbt.dsi.config->cabc_supported)
@@ -1609,11 +1618,11 @@ static void parse_dsi_backlight_ports(struct drm_i915_private *i915,
 		panel->vbt.dsi.bl_ports = BIT(PORT_A);
 		break;
 	case DL_DCS_PORT_C:
-		panel->vbt.dsi.bl_ports = BIT(PORT_C);
+		panel->vbt.dsi.bl_ports = BIT(port_bc);
 		break;
 	default:
 	case DL_DCS_PORT_A_AND_C:
-		panel->vbt.dsi.bl_ports = BIT(PORT_A) | BIT(PORT_C);
+		panel->vbt.dsi.bl_ports = BIT(PORT_A) | BIT(port_bc);
 		break;
 	}
 
@@ -1625,12 +1634,12 @@ static void parse_dsi_backlight_ports(struct drm_i915_private *i915,
 		panel->vbt.dsi.cabc_ports = BIT(PORT_A);
 		break;
 	case DL_DCS_PORT_C:
-		panel->vbt.dsi.cabc_ports = BIT(PORT_C);
+		panel->vbt.dsi.cabc_ports = BIT(port_bc);
 		break;
 	default:
 	case DL_DCS_PORT_A_AND_C:
 		panel->vbt.dsi.cabc_ports =
-					BIT(PORT_A) | BIT(PORT_C);
+					BIT(PORT_A) | BIT(port_bc);
 		break;
 	}
 }
diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c
index 79269d2c476b..3699869ab2db 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.c
+++ b/drivers/gpu/drm/i915/display/intel_bw.c
@@ -404,15 +404,17 @@ static int tgl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel
 		int clpchgroup;
 		int j;
 
-		if (i < num_groups - 1)
-			bi_next = &dev_priv->max_bw[i + 1];
-
 		clpchgroup = (sa->deburst * qi.deinterleave / num_channels) << i;
 
-		if (i < num_groups - 1 && clpchgroup < clperchgroup)
-			bi_next->num_planes = (ipqdepth - clpchgroup) / clpchgroup + 1;
-		else
-			bi_next->num_planes = 0;
+		if (i < num_groups - 1) {
+			bi_next = &dev_priv->max_bw[i + 1];
+
+			if (clpchgroup < clperchgroup)
+				bi_next->num_planes = (ipqdepth - clpchgroup) /
+						       clpchgroup + 1;
+			else
+				bi_next->num_planes = 0;
+		}
 
 		bi->num_qgv_points = qi.num_points;
 		bi->num_psf_gv_points = qi.num_psf_points;
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 32292c0be2bd..3ed7eeacc706 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -389,23 +389,13 @@ static int dg2_max_source_rate(struct intel_dp *intel_dp)
 	return intel_dp_is_edp(intel_dp) ? 810000 : 1350000;
 }
 
-static bool is_low_voltage_sku(struct drm_i915_private *i915, enum phy phy)
-{
-	u32 voltage;
-
-	voltage = intel_de_read(i915, ICL_PORT_COMP_DW3(phy)) & VOLTAGE_INFO_MASK;
-
-	return voltage == VOLTAGE_INFO_0_85V;
-}
-
 static int icl_max_source_rate(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
 	enum phy phy = intel_port_to_phy(dev_priv, dig_port->base.port);
 
-	if (intel_phy_is_combo(dev_priv, phy) &&
-	    (is_low_voltage_sku(dev_priv, phy) || !intel_dp_is_edp(intel_dp)))
+	if (intel_phy_is_combo(dev_priv, phy) && !intel_dp_is_edp(intel_dp))
 		return 540000;
 
 	return 810000;
@@ -413,23 +403,7 @@ static int icl_max_source_rate(struct intel_dp *intel_dp)
 
 static int ehl_max_source_rate(struct intel_dp *intel_dp)
 {
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	enum phy phy = intel_port_to_phy(dev_priv, dig_port->base.port);
-
-	if (intel_dp_is_edp(intel_dp) || is_low_voltage_sku(dev_priv, phy))
-		return 540000;
-
-	return 810000;
-}
-
-static int dg1_max_source_rate(struct intel_dp *intel_dp)
-{
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
-	enum phy phy = intel_port_to_phy(i915, dig_port->base.port);
-
-	if (intel_phy_is_combo(i915, phy) && is_low_voltage_sku(i915, phy))
+	if (intel_dp_is_edp(intel_dp))
 		return 540000;
 
 	return 810000;
@@ -491,7 +465,7 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp)
 			max_rate = dg2_max_source_rate(intel_dp);
 		else if (IS_ALDERLAKE_P(dev_priv) || IS_ALDERLAKE_S(dev_priv) ||
 			 IS_DG1(dev_priv) || IS_ROCKETLAKE(dev_priv))
-			max_rate = dg1_max_source_rate(intel_dp);
+			max_rate = 810000;
 		else if (IS_JSL_EHL(dev_priv))
 			max_rate = ehl_max_source_rate(intel_dp);
 		else
@@ -1395,6 +1369,7 @@ static int intel_dp_dsc_compute_params(struct intel_encoder *encoder,
 	 * DP_DSC_RC_BUF_SIZE for this.
 	 */
 	vdsc_cfg->rc_model_size = DSC_RC_MODEL_SIZE_CONST;
+	vdsc_cfg->pic_height = crtc_state->hw.adjusted_mode.crtc_vdisplay;
 
 	/*
 	 * Slice Height of 8 works for all currently available panels. So start
@@ -5293,8 +5268,6 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 
 	intel_panel_init(intel_connector);
 
-	if (!(dev_priv->quirks & QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK))
-		intel_connector->panel.backlight.power = intel_pps_backlight_power;
 	intel_backlight_setup(intel_connector, pipe);
 
 	intel_edp_add_properties(intel_dp);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 9feaf1a589f3..d213d8ad1ea5 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -671,6 +671,28 @@ intel_dp_prepare_link_train(struct intel_dp *intel_dp,
 	intel_dp_compute_rate(intel_dp, crtc_state->port_clock,
 			      &link_bw, &rate_select);
 
+	/*
+	 * WaEdpLinkRateDataReload
+	 *
+	 * Parade PS8461E MUX (used on varius TGL+ laptops) needs
+	 * to snoop the link rates reported by the sink when we
+	 * use LINK_RATE_SET in order to operate in jitter cleaning
+	 * mode (as opposed to redriver mode). Unfortunately it
+	 * loses track of the snooped link rates when powered down,
+	 * so we need to make it re-snoop often. Without this high
+	 * link rates are not stable.
+	 */
+	if (!link_bw) {
+		struct intel_connector *connector = intel_dp->attached_connector;
+		__le16 sink_rates[DP_MAX_SUPPORTED_RATES];
+
+		drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s] Reloading eDP link rates\n",
+			    connector->base.base.id, connector->base.name);
+
+		drm_dp_dpcd_read(&intel_dp->aux, DP_SUPPORTED_LINK_RATES,
+				 sink_rates, sizeof(sink_rates));
+	}
+
 	if (link_bw)
 		drm_dbg_kms(&i915->drm,
 			    "[ENCODER:%d:%s] Using LINK_BW_SET value %02x\n",
diff --git a/drivers/gpu/drm/i915/display/intel_quirks.c b/drivers/gpu/drm/i915/display/intel_quirks.c
index c8488f5ebd04..e415cd7c0b84 100644
--- a/drivers/gpu/drm/i915/display/intel_quirks.c
+++ b/drivers/gpu/drm/i915/display/intel_quirks.c
@@ -191,6 +191,9 @@ static struct intel_quirk intel_quirks[] = {
 	/* ASRock ITX*/
 	{ 0x3185, 0x1849, 0x2212, quirk_increase_ddi_disabled_time },
 	{ 0x3184, 0x1849, 0x2212, quirk_increase_ddi_disabled_time },
+	/* ECS Liva Q2 */
+	{ 0x3185, 0x1019, 0xa94d, quirk_increase_ddi_disabled_time },
+	{ 0x3184, 0x1019, 0xa94d, quirk_increase_ddi_disabled_time },
 };
 
 void intel_init_quirks(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c
index 43e1bbc1e303..ca530f0733e0 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc.c
+++ b/drivers/gpu/drm/i915/display/intel_vdsc.c
@@ -460,7 +460,6 @@ int intel_dsc_compute_params(struct intel_crtc_state *pipe_config)
 	u8 i = 0;
 
 	vdsc_cfg->pic_width = pipe_config->hw.adjusted_mode.crtc_hdisplay;
-	vdsc_cfg->pic_height = pipe_config->hw.adjusted_mode.crtc_vdisplay;
 	vdsc_cfg->slice_width = DIV_ROUND_UP(vdsc_cfg->pic_width,
 					     pipe_config->dsc.slice_count);
 
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index b9b1fed99874..35136d26e517 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -1933,7 +1933,14 @@ void vlv_dsi_init(struct drm_i915_private *dev_priv)
 	else
 		intel_dsi->ports = BIT(port);
 
+	if (drm_WARN_ON(&dev_priv->drm, intel_connector->panel.vbt.dsi.bl_ports & ~intel_dsi->ports))
+		intel_connector->panel.vbt.dsi.bl_ports &= intel_dsi->ports;
+
 	intel_dsi->dcs_backlight_ports = intel_connector->panel.vbt.dsi.bl_ports;
+
+	if (drm_WARN_ON(&dev_priv->drm, intel_connector->panel.vbt.dsi.cabc_ports & ~intel_dsi->ports))
+		intel_connector->panel.vbt.dsi.cabc_ports &= intel_dsi->ports;
+
 	intel_dsi->dcs_cabc_ports = intel_connector->panel.vbt.dsi.cabc_ports;
 
 	/* Create a DSI host (and a device) for each port. */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index dabdfe09f5e5..0bcde53c50c6 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1269,6 +1269,10 @@ static void i915_gem_context_release_work(struct work_struct *work)
 	trace_i915_context_free(ctx);
 	GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
 
+	spin_lock(&ctx->i915->gem.contexts.lock);
+	list_del(&ctx->link);
+	spin_unlock(&ctx->i915->gem.contexts.lock);
+
 	if (ctx->syncobj)
 		drm_syncobj_put(ctx->syncobj);
 
@@ -1521,10 +1525,6 @@ static void context_close(struct i915_gem_context *ctx)
 
 	ctx->file_priv = ERR_PTR(-EBADF);
 
-	spin_lock(&ctx->i915->gem.contexts.lock);
-	list_del(&ctx->link);
-	spin_unlock(&ctx->i915->gem.contexts.lock);
-
 	client = ctx->client;
 	if (client) {
 		spin_lock(&client->ctx_lock);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index ccec4055fde3..85482a04d158 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -268,7 +268,7 @@ static void __i915_gem_object_free_mmaps(struct drm_i915_gem_object *obj)
  */
 void __i915_gem_object_pages_fini(struct drm_i915_gem_object *obj)
 {
-	assert_object_held(obj);
+	assert_object_held_shared(obj);
 
 	if (!list_empty(&obj->vma.list)) {
 		struct i915_vma *vma;
@@ -331,15 +331,7 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 			continue;
 		}
 
-		if (!i915_gem_object_trylock(obj, NULL)) {
-			/* busy, toss it back to the pile */
-			if (llist_add(&obj->freed, &i915->mm.free_list))
-				queue_delayed_work(i915->wq, &i915->mm.free_work, msecs_to_jiffies(10));
-			continue;
-		}
-
 		__i915_gem_object_pages_fini(obj);
-		i915_gem_object_unlock(obj);
 		__i915_gem_free_object(obj);
 
 		/* But keep the pointer alive for RCU-protected lookups */
@@ -359,7 +351,7 @@ void i915_gem_flush_free_objects(struct drm_i915_private *i915)
 static void __i915_gem_free_work(struct work_struct *work)
 {
 	struct drm_i915_private *i915 =
-		container_of(work, struct drm_i915_private, mm.free_work.work);
+		container_of(work, struct drm_i915_private, mm.free_work);
 
 	i915_gem_flush_free_objects(i915);
 }
@@ -391,7 +383,7 @@ static void i915_gem_free_object(struct drm_gem_object *gem_obj)
 	 */
 
 	if (llist_add(&obj->freed, &i915->mm.free_list))
-		queue_delayed_work(i915->wq, &i915->mm.free_work, 0);
+		queue_work(i915->wq, &i915->mm.free_work);
 }
 
 void __i915_gem_object_flush_frontbuffer(struct drm_i915_gem_object *obj,
@@ -731,6 +723,9 @@ bool i915_gem_object_needs_ccs_pages(struct drm_i915_gem_object *obj)
 	bool lmem_placement = false;
 	int i;
 
+	if (!HAS_FLAT_CCS(to_i915(obj->base.dev)))
+		return false;
+
 	for (i = 0; i < obj->mm.n_placements; i++) {
 		/* Compression is not allowed for the objects with smem placement */
 		if (obj->mm.placements[i]->type == INTEL_MEMORY_SYSTEM)
@@ -745,7 +740,7 @@ bool i915_gem_object_needs_ccs_pages(struct drm_i915_gem_object *obj)
 
 void i915_gem_init__objects(struct drm_i915_private *i915)
 {
-	INIT_DELAYED_WORK(&i915->mm.free_work, __i915_gem_free_work);
+	INIT_WORK(&i915->mm.free_work, __i915_gem_free_work);
 }
 
 void i915_objects_module_exit(void)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index 5cf36a130061..9f6b14ec189a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -335,7 +335,6 @@ struct drm_i915_gem_object {
 #define I915_BO_READONLY          BIT(7)
 #define I915_TILING_QUIRK_BIT     8 /* unknown swizzling; do not release! */
 #define I915_BO_PROTECTED         BIT(9)
-#define I915_BO_WAS_BOUND_BIT     10
 	/**
 	 * @mem_flags - Mutable placement-related flags
 	 *
@@ -616,6 +615,8 @@ struct drm_i915_gem_object {
 		 * pages were last acquired.
 		 */
 		bool dirty:1;
+
+		u32 tlb;
 	} mm;
 
 	struct {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 97c820eee115..8357dbdcab5c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -6,14 +6,15 @@
 
 #include <drm/drm_cache.h>
 
+#include "gt/intel_gt.h"
+#include "gt/intel_gt_pm.h"
+
 #include "i915_drv.h"
 #include "i915_gem_object.h"
 #include "i915_scatterlist.h"
 #include "i915_gem_lmem.h"
 #include "i915_gem_mman.h"
 
-#include "gt/intel_gt.h"
-
 void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj,
 				 struct sg_table *pages,
 				 unsigned int sg_page_sizes)
@@ -190,6 +191,18 @@ static void unmap_object(struct drm_i915_gem_object *obj, void *ptr)
 		vunmap(ptr);
 }
 
+static void flush_tlb_invalidate(struct drm_i915_gem_object *obj)
+{
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	struct intel_gt *gt = to_gt(i915);
+
+	if (!obj->mm.tlb)
+		return;
+
+	intel_gt_invalidate_tlb(gt, obj->mm.tlb);
+	obj->mm.tlb = 0;
+}
+
 struct sg_table *
 __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
 {
@@ -215,13 +228,7 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
 	__i915_gem_object_reset_page_iter(obj);
 	obj->mm.page_sizes.phys = obj->mm.page_sizes.sg = 0;
 
-	if (test_and_clear_bit(I915_BO_WAS_BOUND_BIT, &obj->flags)) {
-		struct drm_i915_private *i915 = to_i915(obj->base.dev);
-		intel_wakeref_t wakeref;
-
-		with_intel_runtime_pm_if_active(&i915->runtime_pm, wakeref)
-			intel_gt_invalidate_tlbs(to_gt(i915));
-	}
+	flush_tlb_invalidate(obj);
 
 	return pages;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index f131dc065f47..6f3ab7ade41a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -297,7 +297,7 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
 		i915_tt->is_shmem = true;
 	}
 
-	if (HAS_FLAT_CCS(i915) && i915_gem_object_needs_ccs_pages(obj))
+	if (i915_gem_object_needs_ccs_pages(obj))
 		ccs_pages = DIV_ROUND_UP(DIV_ROUND_UP(bo->base.size,
 						      NUM_BYTES_PER_CCS_BYTE),
 					 PAGE_SIZE);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 633a7e5dba3b..6b5d4ea22b67 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -166,6 +166,21 @@ struct intel_engine_execlists {
 	struct timer_list preempt;
 
 	/**
+	 * @preempt_target: active request at the time of the preemption request
+	 *
+	 * We force a preemption to occur if the pending contexts have not
+	 * been promoted to active upon receipt of the CS ack event within
+	 * the timeout. This timeout maybe chosen based on the target,
+	 * using a very short timeout if the context is no longer schedulable.
+	 * That short timeout may not be applicable to other contexts, so
+	 * if a context switch should happen within before the preemption
+	 * timeout, we may shoot early at an innocent context. To prevent this,
+	 * we record which context was active at the time of the preemption
+	 * request and only reset that context upon the timeout.
+	 */
+	const struct i915_request *preempt_target;
+
+	/**
 	 * @ccid: identifier for contexts submitted to this engine
 	 */
 	u32 ccid;
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 4b909cb88cdf..c718e6dc40b5 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -1241,6 +1241,9 @@ static unsigned long active_preempt_timeout(struct intel_engine_cs *engine,
 	if (!rq)
 		return 0;
 
+	/* Only allow ourselves to force reset the currently active context */
+	engine->execlists.preempt_target = rq;
+
 	/* Force a fast reset for terminated contexts (ignoring sysfs!) */
 	if (unlikely(intel_context_is_banned(rq->context) || bad_request(rq)))
 		return INTEL_CONTEXT_BANNED_PREEMPT_TIMEOUT_MS;
@@ -2427,8 +2430,24 @@ static void execlists_submission_tasklet(struct tasklet_struct *t)
 	GEM_BUG_ON(inactive - post > ARRAY_SIZE(post));
 
 	if (unlikely(preempt_timeout(engine))) {
+		const struct i915_request *rq = *engine->execlists.active;
+
+		/*
+		 * If after the preempt-timeout expired, we are still on the
+		 * same active request/context as before we initiated the
+		 * preemption, reset the engine.
+		 *
+		 * However, if we have processed a CS event to switch contexts,
+		 * but not yet processed the CS event for the pending
+		 * preemption, reset the timer allowing the new context to
+		 * gracefully exit.
+		 */
 		cancel_timer(&engine->execlists.preempt);
-		engine->execlists.error_interrupt |= ERROR_PREEMPT;
+		if (rq == engine->execlists.preempt_target)
+			engine->execlists.error_interrupt |= ERROR_PREEMPT;
+		else
+			set_timer_ms(&engine->execlists.preempt,
+				     active_preempt_timeout(engine, rq));
 	}
 
 	if (unlikely(READ_ONCE(engine->execlists.error_interrupt))) {
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 68c2b0d8f187..f435e06125aa 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -11,7 +11,9 @@
 #include "pxp/intel_pxp.h"
 
 #include "i915_drv.h"
+#include "i915_perf_oa_regs.h"
 #include "intel_context.h"
+#include "intel_engine_pm.h"
 #include "intel_engine_regs.h"
 #include "intel_ggtt_gmch.h"
 #include "intel_gt.h"
@@ -36,8 +38,6 @@ static void __intel_gt_init_early(struct intel_gt *gt)
 {
 	spin_lock_init(&gt->irq_lock);
 
-	mutex_init(&gt->tlb_invalidate_lock);
-
 	INIT_LIST_HEAD(&gt->closed_vma);
 	spin_lock_init(&gt->closed_lock);
 
@@ -48,6 +48,8 @@ static void __intel_gt_init_early(struct intel_gt *gt)
 	intel_gt_init_reset(gt);
 	intel_gt_init_requests(gt);
 	intel_gt_init_timelines(gt);
+	mutex_init(&gt->tlb.invalidate_lock);
+	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
 	intel_gt_pm_init_early(gt);
 
 	intel_uc_init_early(&gt->uc);
@@ -768,6 +770,7 @@ void intel_gt_driver_late_release_all(struct drm_i915_private *i915)
 		intel_gt_fini_requests(gt);
 		intel_gt_fini_reset(gt);
 		intel_gt_fini_timelines(gt);
+		mutex_destroy(&gt->tlb.invalidate_lock);
 		intel_engines_free(gt);
 	}
 }
@@ -906,7 +909,7 @@ get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8,
 	return rb;
 }
 
-void intel_gt_invalidate_tlbs(struct intel_gt *gt)
+static void mmio_invalidate_full(struct intel_gt *gt)
 {
 	static const i915_reg_t gen8_regs[] = {
 		[RENDER_CLASS]			= GEN8_RTCR,
@@ -924,13 +927,11 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 	struct drm_i915_private *i915 = gt->i915;
 	struct intel_uncore *uncore = gt->uncore;
 	struct intel_engine_cs *engine;
+	intel_engine_mask_t awake, tmp;
 	enum intel_engine_id id;
 	const i915_reg_t *regs;
 	unsigned int num = 0;
 
-	if (I915_SELFTEST_ONLY(gt->awake == -ENODEV))
-		return;
-
 	if (GRAPHICS_VER(i915) == 12) {
 		regs = gen12_regs;
 		num = ARRAY_SIZE(gen12_regs);
@@ -945,28 +946,41 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 			  "Platform does not implement TLB invalidation!"))
 		return;
 
-	GEM_TRACE("\n");
-
-	assert_rpm_wakelock_held(&i915->runtime_pm);
-
-	mutex_lock(&gt->tlb_invalidate_lock);
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
 
 	spin_lock_irq(&uncore->lock); /* serialise invalidate with GT reset */
 
+	awake = 0;
 	for_each_engine(engine, gt, id) {
 		struct reg_and_bit rb;
 
+		if (!intel_engine_pm_is_awake(engine))
+			continue;
+
 		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
 		if (!i915_mmio_reg_offset(rb.reg))
 			continue;
 
 		intel_uncore_write_fw(uncore, rb.reg, rb.bit);
+		awake |= engine->mask;
 	}
 
+	GT_TRACE(gt, "invalidated engines %08x\n", awake);
+
+	/* Wa_2207587034:tgl,dg1,rkl,adl-s,adl-p */
+	if (awake &&
+	    (IS_TIGERLAKE(i915) ||
+	     IS_DG1(i915) ||
+	     IS_ROCKETLAKE(i915) ||
+	     IS_ALDERLAKE_S(i915) ||
+	     IS_ALDERLAKE_P(i915)))
+		intel_uncore_write_fw(uncore, GEN12_OA_TLB_INV_CR, 1);
+
 	spin_unlock_irq(&uncore->lock);
 
-	for_each_engine(engine, gt, id) {
+	for_each_engine_masked(engine, gt, awake, tmp) {
+		struct reg_and_bit rb;
+
 		/*
 		 * HW architecture suggest typical invalidation time at 40us,
 		 * with pessimistic cases up to 100us and a recommendation to
@@ -974,12 +988,8 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 		 */
 		const unsigned int timeout_us = 100;
 		const unsigned int timeout_ms = 4;
-		struct reg_and_bit rb;
 
 		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
-		if (!i915_mmio_reg_offset(rb.reg))
-			continue;
-
 		if (__intel_wait_for_register_fw(uncore,
 						 rb.reg, rb.bit, 0,
 						 timeout_us, timeout_ms,
@@ -996,5 +1006,38 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 	 * transitions.
 	 */
 	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
-	mutex_unlock(&gt->tlb_invalidate_lock);
+}
+
+static bool tlb_seqno_passed(const struct intel_gt *gt, u32 seqno)
+{
+	u32 cur = intel_gt_tlb_seqno(gt);
+
+	/* Only skip if a *full* TLB invalidate barrier has passed */
+	return (s32)(cur - ALIGN(seqno, 2)) > 0;
+}
+
+void intel_gt_invalidate_tlb(struct intel_gt *gt, u32 seqno)
+{
+	intel_wakeref_t wakeref;
+
+	if (I915_SELFTEST_ONLY(gt->awake == -ENODEV))
+		return;
+
+	if (intel_gt_is_wedged(gt))
+		return;
+
+	if (tlb_seqno_passed(gt, seqno))
+		return;
+
+	with_intel_gt_pm_if_awake(gt, wakeref) {
+		mutex_lock(&gt->tlb.invalidate_lock);
+		if (tlb_seqno_passed(gt, seqno))
+			goto unlock;
+
+		mmio_invalidate_full(gt);
+
+		write_seqcount_invalidate(&gt->tlb.seqno);
+unlock:
+		mutex_unlock(&gt->tlb.invalidate_lock);
+	}
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 82d6f248d876..40b06adf509a 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -101,6 +101,16 @@ void intel_gt_info_print(const struct intel_gt_info *info,
 
 void intel_gt_watchdog_work(struct work_struct *work);
 
-void intel_gt_invalidate_tlbs(struct intel_gt *gt);
+static inline u32 intel_gt_tlb_seqno(const struct intel_gt *gt)
+{
+	return seqprop_sequence(&gt->tlb.seqno);
+}
+
+static inline u32 intel_gt_next_invalidate_tlb_full(const struct intel_gt *gt)
+{
+	return intel_gt_tlb_seqno(gt) | 1;
+}
+
+void intel_gt_invalidate_tlb(struct intel_gt *gt, u32 seqno);
 
 #endif /* __INTEL_GT_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
index bc898df7a48c..a334787a4939 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
@@ -55,6 +55,9 @@ static inline void intel_gt_pm_might_put(struct intel_gt *gt)
 	for (tmp = 1, intel_gt_pm_get(gt); tmp; \
 	     intel_gt_pm_put(gt), tmp = 0)
 
+#define with_intel_gt_pm_if_awake(gt, wf) \
+	for (wf = intel_gt_pm_get_if_awake(gt); wf; intel_gt_pm_put_async(gt), wf = 0)
+
 static inline int intel_gt_pm_wait_for_idle(struct intel_gt *gt)
 {
 	return intel_wakeref_wait_for_idle(&gt->wakeref);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c
index 73a8b46e0234..d09a0e845d09 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c
@@ -545,8 +545,7 @@ static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_ratl, RATL_MASK);
 static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_vr_thermalert, VR_THERMALERT_MASK);
 static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_vr_tdc, VR_TDC_MASK);
 
-static const struct attribute *freq_attrs[] = {
-	&dev_attr_punit_req_freq_mhz.attr,
+static const struct attribute *throttle_reason_attrs[] = {
 	&attr_throttle_reason_status.attr,
 	&attr_throttle_reason_pl1.attr,
 	&attr_throttle_reason_pl2.attr,
@@ -763,12 +762,20 @@ void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj)
 	if (!is_object_gt(kobj))
 		return;
 
-	ret = sysfs_create_files(kobj, freq_attrs);
+	ret = sysfs_create_file(kobj, &dev_attr_punit_req_freq_mhz.attr);
 	if (ret)
 		drm_warn(&gt->i915->drm,
-			 "failed to create gt%u throttle sysfs files (%pe)",
+			 "failed to create gt%u punit_req_freq_mhz sysfs (%pe)",
 			 gt->info.id, ERR_PTR(ret));
 
+	if (GRAPHICS_VER(gt->i915) >= 11) {
+		ret = sysfs_create_files(kobj, throttle_reason_attrs);
+		if (ret)
+			drm_warn(&gt->i915->drm,
+				 "failed to create gt%u throttle sysfs files (%pe)",
+				 gt->info.id, ERR_PTR(ret));
+	}
+
 	if (HAS_MEDIA_RATIO_MODE(gt->i915) && intel_uc_uses_guc_slpc(&gt->uc)) {
 		ret = sysfs_create_files(kobj, media_perf_power_attrs);
 		if (ret)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index df708802889d..3804a583382b 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -11,6 +11,7 @@
 #include <linux/llist.h>
 #include <linux/mutex.h>
 #include <linux/notifier.h>
+#include <linux/seqlock.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 #include <linux/workqueue.h>
@@ -83,7 +84,22 @@ struct intel_gt {
 	struct intel_uc uc;
 	struct intel_gsc gsc;
 
-	struct mutex tlb_invalidate_lock;
+	struct {
+		/* Serialize global tlb invalidations */
+		struct mutex invalidate_lock;
+
+		/*
+		 * Batch TLB invalidations
+		 *
+		 * After unbinding the PTE, we need to ensure the TLB
+		 * are invalidated prior to releasing the physical pages.
+		 * But we only need one such invalidation for all unbinds,
+		 * so we track how many TLB invalidations have been
+		 * performed since unbind the PTE and only emit an extra
+		 * invalidate if no full barrier has been passed.
+		 */
+		seqcount_mutex_t seqno;
+	} tlb;
 
 	struct i915_wa_list wa_list;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_llc.c b/drivers/gpu/drm/i915/gt/intel_llc.c
index 14fe65812e42..1d19c073ba2e 100644
--- a/drivers/gpu/drm/i915/gt/intel_llc.c
+++ b/drivers/gpu/drm/i915/gt/intel_llc.c
@@ -12,6 +12,7 @@
 #include "intel_llc.h"
 #include "intel_mchbar_regs.h"
 #include "intel_pcode.h"
+#include "intel_rps.h"
 
 struct ia_constants {
 	unsigned int min_gpu_freq;
@@ -55,9 +56,6 @@ static bool get_ia_constants(struct intel_llc *llc,
 	if (!HAS_LLC(i915) || IS_DGFX(i915))
 		return false;
 
-	if (rps->max_freq <= rps->min_freq)
-		return false;
-
 	consts->max_ia_freq = cpu_max_MHz();
 
 	consts->min_ring_freq =
@@ -65,13 +63,8 @@ static bool get_ia_constants(struct intel_llc *llc,
 	/* convert DDR frequency from units of 266.6MHz to bandwidth */
 	consts->min_ring_freq = mult_frac(consts->min_ring_freq, 8, 3);
 
-	consts->min_gpu_freq = rps->min_freq;
-	consts->max_gpu_freq = rps->max_freq;
-	if (GRAPHICS_VER(i915) >= 9) {
-		/* Convert GT frequency to 50 HZ units */
-		consts->min_gpu_freq /= GEN9_FREQ_SCALER;
-		consts->max_gpu_freq /= GEN9_FREQ_SCALER;
-	}
+	consts->min_gpu_freq = intel_rps_get_min_raw_freq(rps);
+	consts->max_gpu_freq = intel_rps_get_max_raw_freq(rps);
 
 	return true;
 }
@@ -131,6 +124,12 @@ static void gen6_update_ring_freq(struct intel_llc *llc)
 		return;
 
 	/*
+	 * Although this is unlikely on any platform during initialization,
+	 * let's ensure we don't get accidentally into infinite loop
+	 */
+	if (consts.max_gpu_freq <= consts.min_gpu_freq)
+		return;
+	/*
 	 * For each potential GPU frequency, load a ring frequency we'd like
 	 * to use for memory access.  We do this by specifying the IA frequency
 	 * the PCU should use as a reference to determine the ring frequency.
diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c
index 2c35324b5f68..933648cc90ff 100644
--- a/drivers/gpu/drm/i915/gt/intel_migrate.c
+++ b/drivers/gpu/drm/i915/gt/intel_migrate.c
@@ -638,9 +638,9 @@ static int emit_copy(struct i915_request *rq,
 	return 0;
 }
 
-static int scatter_list_length(struct scatterlist *sg)
+static u64 scatter_list_length(struct scatterlist *sg)
 {
-	int len = 0;
+	u64 len = 0;
 
 	while (sg && sg_dma_len(sg)) {
 		len += sg_dma_len(sg);
@@ -650,28 +650,26 @@ static int scatter_list_length(struct scatterlist *sg)
 	return len;
 }
 
-static void
+static int
 calculate_chunk_sz(struct drm_i915_private *i915, bool src_is_lmem,
-		   int *src_sz, u32 bytes_to_cpy, u32 ccs_bytes_to_cpy)
+		   u64 bytes_to_cpy, u64 ccs_bytes_to_cpy)
 {
-	if (ccs_bytes_to_cpy) {
-		if (!src_is_lmem)
-			/*
-			 * When CHUNK_SZ is passed all the pages upto CHUNK_SZ
-			 * will be taken for the blt. in Flat-ccs supported
-			 * platform Smem obj will have more pages than required
-			 * for main meory hence limit it to the required size
-			 * for main memory
-			 */
-			*src_sz = min_t(int, bytes_to_cpy, CHUNK_SZ);
-	} else { /* ccs handling is not required */
-		*src_sz = CHUNK_SZ;
-	}
+	if (ccs_bytes_to_cpy && !src_is_lmem)
+		/*
+		 * When CHUNK_SZ is passed all the pages upto CHUNK_SZ
+		 * will be taken for the blt. in Flat-ccs supported
+		 * platform Smem obj will have more pages than required
+		 * for main meory hence limit it to the required size
+		 * for main memory
+		 */
+		return min_t(u64, bytes_to_cpy, CHUNK_SZ);
+	else
+		return CHUNK_SZ;
 }
 
-static void get_ccs_sg_sgt(struct sgt_dma *it, u32 bytes_to_cpy)
+static void get_ccs_sg_sgt(struct sgt_dma *it, u64 bytes_to_cpy)
 {
-	u32 len;
+	u64 len;
 
 	do {
 		GEM_BUG_ON(!it->sg || !sg_dma_len(it->sg));
@@ -702,13 +700,13 @@ intel_context_migrate_copy(struct intel_context *ce,
 {
 	struct sgt_dma it_src = sg_sgt(src), it_dst = sg_sgt(dst), it_ccs;
 	struct drm_i915_private *i915 = ce->engine->i915;
-	u32 ccs_bytes_to_cpy = 0, bytes_to_cpy;
+	u64 ccs_bytes_to_cpy = 0, bytes_to_cpy;
 	enum i915_cache_level ccs_cache_level;
 	u32 src_offset, dst_offset;
 	u8 src_access, dst_access;
 	struct i915_request *rq;
-	int src_sz, dst_sz;
-	bool ccs_is_src;
+	u64 src_sz, dst_sz;
+	bool ccs_is_src, overwrite_ccs;
 	int err;
 
 	GEM_BUG_ON(ce->vm != ce->engine->gt->migrate.context->vm);
@@ -749,6 +747,8 @@ intel_context_migrate_copy(struct intel_context *ce,
 			get_ccs_sg_sgt(&it_ccs, bytes_to_cpy);
 	}
 
+	overwrite_ccs = HAS_FLAT_CCS(i915) && !ccs_bytes_to_cpy && dst_is_lmem;
+
 	src_offset = 0;
 	dst_offset = CHUNK_SZ;
 	if (HAS_64K_PAGES(ce->engine->i915)) {
@@ -788,8 +788,8 @@ intel_context_migrate_copy(struct intel_context *ce,
 		if (err)
 			goto out_rq;
 
-		calculate_chunk_sz(i915, src_is_lmem, &src_sz,
-				   bytes_to_cpy, ccs_bytes_to_cpy);
+		src_sz = calculate_chunk_sz(i915, src_is_lmem,
+					    bytes_to_cpy, ccs_bytes_to_cpy);
 
 		len = emit_pte(rq, &it_src, src_cache_level, src_is_lmem,
 			       src_offset, src_sz);
@@ -852,6 +852,25 @@ intel_context_migrate_copy(struct intel_context *ce,
 			if (err)
 				goto out_rq;
 			ccs_bytes_to_cpy -= ccs_sz;
+		} else if (overwrite_ccs) {
+			err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
+			if (err)
+				goto out_rq;
+
+			/*
+			 * While we can't always restore/manage the CCS state,
+			 * we still need to ensure we don't leak the CCS state
+			 * from the previous user, so make sure we overwrite it
+			 * with something.
+			 */
+			err = emit_copy_ccs(rq, dst_offset, INDIRECT_ACCESS,
+					    dst_offset, DIRECT_ACCESS, len);
+			if (err)
+				goto out_rq;
+
+			err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
+			if (err)
+				goto out_rq;
 		}
 
 		/* Arbitration is re-enabled between requests. */
diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
index d8b94d638559..6ee8d1127016 100644
--- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
@@ -206,8 +206,12 @@ void ppgtt_bind_vma(struct i915_address_space *vm,
 void ppgtt_unbind_vma(struct i915_address_space *vm,
 		      struct i915_vma_resource *vma_res)
 {
-	if (vma_res->allocated)
-		vm->clear_range(vm, vma_res->start, vma_res->vma_size);
+	if (!vma_res->allocated)
+		return;
+
+	vm->clear_range(vm, vma_res->start, vma_res->vma_size);
+	if (vma_res->tlb)
+		vma_invalidate_tlb(vm, vma_res->tlb);
 }
 
 static unsigned long pd_count(u64 size, int shift)
diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c
index 6e90032e12e9..aa6aed837194 100644
--- a/drivers/gpu/drm/i915/gt/intel_region_lmem.c
+++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.c
@@ -15,6 +15,7 @@
 #include "gt/intel_gt_mcr.h"
 #include "gt/intel_gt_regs.h"
 
+#ifdef CONFIG_64BIT
 static void _release_bars(struct pci_dev *pdev)
 {
 	int resno;
@@ -111,6 +112,9 @@ static void i915_resize_lmem_bar(struct drm_i915_private *i915, resource_size_t
 	pci_assign_unassigned_bus_resources(pdev->bus);
 	pci_write_config_dword(pdev, PCI_COMMAND, pci_cmd);
 }
+#else
+static void i915_resize_lmem_bar(struct drm_i915_private *i915, resource_size_t lmem_size) {}
+#endif
 
 static int
 region_lmem_release(struct intel_memory_region *mem)
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index fb3f57ee450b..7bb967034679 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -2126,6 +2126,31 @@ u32 intel_rps_get_max_frequency(struct intel_rps *rps)
 		return intel_gpu_freq(rps, rps->max_freq_softlimit);
 }
 
+/**
+ * intel_rps_get_max_raw_freq - returns the max frequency in some raw format.
+ * @rps: the intel_rps structure
+ *
+ * Returns the max frequency in a raw format. In newer platforms raw is in
+ * units of 50 MHz.
+ */
+u32 intel_rps_get_max_raw_freq(struct intel_rps *rps)
+{
+	struct intel_guc_slpc *slpc = rps_to_slpc(rps);
+	u32 freq;
+
+	if (rps_uses_slpc(rps)) {
+		return DIV_ROUND_CLOSEST(slpc->rp0_freq,
+					 GT_FREQUENCY_MULTIPLIER);
+	} else {
+		freq = rps->max_freq;
+		if (GRAPHICS_VER(rps_to_i915(rps)) >= 9) {
+			/* Convert GT frequency to 50 MHz units */
+			freq /= GEN9_FREQ_SCALER;
+		}
+		return freq;
+	}
+}
+
 u32 intel_rps_get_rp0_frequency(struct intel_rps *rps)
 {
 	struct intel_guc_slpc *slpc = rps_to_slpc(rps);
@@ -2214,6 +2239,31 @@ u32 intel_rps_get_min_frequency(struct intel_rps *rps)
 		return intel_gpu_freq(rps, rps->min_freq_softlimit);
 }
 
+/**
+ * intel_rps_get_min_raw_freq - returns the min frequency in some raw format.
+ * @rps: the intel_rps structure
+ *
+ * Returns the min frequency in a raw format. In newer platforms raw is in
+ * units of 50 MHz.
+ */
+u32 intel_rps_get_min_raw_freq(struct intel_rps *rps)
+{
+	struct intel_guc_slpc *slpc = rps_to_slpc(rps);
+	u32 freq;
+
+	if (rps_uses_slpc(rps)) {
+		return DIV_ROUND_CLOSEST(slpc->min_freq,
+					 GT_FREQUENCY_MULTIPLIER);
+	} else {
+		freq = rps->min_freq;
+		if (GRAPHICS_VER(rps_to_i915(rps)) >= 9) {
+			/* Convert GT frequency to 50 MHz units */
+			freq /= GEN9_FREQ_SCALER;
+		}
+		return freq;
+	}
+}
+
 static int set_min_freq(struct intel_rps *rps, u32 val)
 {
 	int ret = 0;
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h
index 1e8d56491308..4509dfdc52e0 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.h
+++ b/drivers/gpu/drm/i915/gt/intel_rps.h
@@ -37,8 +37,10 @@ u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat1);
 u32 intel_rps_read_actual_frequency(struct intel_rps *rps);
 u32 intel_rps_get_requested_frequency(struct intel_rps *rps);
 u32 intel_rps_get_min_frequency(struct intel_rps *rps);
+u32 intel_rps_get_min_raw_freq(struct intel_rps *rps);
 int intel_rps_set_min_frequency(struct intel_rps *rps, u32 val);
 u32 intel_rps_get_max_frequency(struct intel_rps *rps);
+u32 intel_rps_get_max_raw_freq(struct intel_rps *rps);
 int intel_rps_set_max_frequency(struct intel_rps *rps, u32 val);
 u32 intel_rps_get_rp0_frequency(struct intel_rps *rps);
 u32 intel_rps_get_rp1_frequency(struct intel_rps *rps);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 76916aed897a..3e91f44829e9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1438,7 +1438,12 @@ void intel_guc_busyness_park(struct intel_gt *gt)
 	if (!guc_submission_initialized(guc))
 		return;
 
-	cancel_delayed_work(&guc->timestamp.work);
+	/*
+	 * There is a race with suspend flow where the worker runs after suspend
+	 * and causes an unclaimed register access warning. Cancel the worker
+	 * synchronously here.
+	 */
+	cancel_delayed_work_sync(&guc->timestamp.work);
 
 	/*
 	 * Before parking, we should sample engine busyness stats if we need to.
@@ -4027,6 +4032,13 @@ static inline void guc_init_lrc_mapping(struct intel_guc *guc)
 	xa_destroy(&guc->context_lookup);
 
 	/*
+	 * A reset might have occurred while we had a pending stalled request,
+	 * so make sure we clean that up.
+	 */
+	guc->stalled_request = NULL;
+	guc->submission_stall_reason = STALL_NONE;
+
+	/*
 	 * Some contexts might have been pinned before we enabled GuC
 	 * submission, so we need to add them to the GuC bookeeping.
 	 * Also, after a reset the of the GuC we want to make sure that the
diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c
index 557f3314291a..3b81a6d35a7b 100644
--- a/drivers/gpu/drm/i915/gvt/aperture_gm.c
+++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c
@@ -298,7 +298,7 @@ no_enough_resource:
 }
 
 /**
- * inte_gvt_free_vgpu_resource - free HW resource owned by a vGPU
+ * intel_vgpu_free_resource() - free HW resource owned by a vGPU
  * @vgpu: a vGPU
  *
  * This function is used to free the HW resource owned by a vGPU.
@@ -328,7 +328,7 @@ void intel_vgpu_reset_resource(struct intel_vgpu *vgpu)
 }
 
 /**
- * intel_alloc_vgpu_resource - allocate HW resource for a vGPU
+ * intel_vgpu_alloc_resource() - allocate HW resource for a vGPU
  * @vgpu: vGPU
  * @param: vGPU creation params
  *
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index b4f69364f9a1..ce0eb03709c3 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -2341,7 +2341,7 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 			gvt_vgpu_err("fail to populate guest ggtt entry\n");
 			/* guest driver may read/write the entry when partial
 			 * update the entry in this situation p2m will fail
-			 * settting the shadow entry to point to a scratch page
+			 * setting the shadow entry to point to a scratch page
 			 */
 			ops->set_pfn(&m, gvt->gtt.scratch_mfn);
 		} else
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index beea5895e499..61423da36710 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -905,7 +905,7 @@ static int update_fdi_rx_iir_status(struct intel_vgpu *vgpu,
 	else if (FDI_RX_IMR_TO_PIPE(offset) != INVALID_INDEX)
 		index = FDI_RX_IMR_TO_PIPE(offset);
 	else {
-		gvt_vgpu_err("Unsupport registers %x\n", offset);
+		gvt_vgpu_err("Unsupported registers %x\n", offset);
 		return -EINVAL;
 	}
 
@@ -3052,7 +3052,7 @@ int intel_vgpu_default_mmio_read(struct intel_vgpu *vgpu, unsigned int offset,
 }
 
 /**
- * intel_t_default_mmio_write - default MMIO write handler
+ * intel_vgpu_default_mmio_write() - default MMIO write handler
  * @vgpu: a vGPU
  * @offset: access offset
  * @p_data: write data buffer
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index c85bafe7539e..1c6e941c9666 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -546,7 +546,7 @@ static void switch_mmio(struct intel_vgpu *pre,
 }
 
 /**
- * intel_gvt_switch_render_mmio - switch mmio context of specific engine
+ * intel_gvt_switch_mmio - switch mmio context of specific engine
  * @pre: the last vGPU that own the engine
  * @next: the vGPU to switch to
  * @engine: the engine
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d25647be25d1..086bbe8945d6 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -247,7 +247,7 @@ struct i915_gem_mm {
 	 * List of objects which are pending destruction.
 	 */
 	struct llist_head free_list;
-	struct delayed_work free_work;
+	struct work_struct free_work;
 	/**
 	 * Count of objects pending destructions. Used to skip needlessly
 	 * waiting on an RCU barrier if no objects are waiting to be freed.
@@ -1378,7 +1378,7 @@ static inline void i915_gem_drain_freed_objects(struct drm_i915_private *i915)
 	 * armed the work again.
 	 */
 	while (atomic_read(&i915->mm.free_count)) {
-		flush_delayed_work(&i915->mm.free_work);
+		flush_work(&i915->mm.free_work);
 		flush_delayed_work(&i915->bdev.wq);
 		rcu_barrier();
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 702e5b89be22..b605d0ceaefa 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1191,7 +1191,8 @@ void i915_gem_driver_release(struct drm_i915_private *dev_priv)
 
 	intel_uc_cleanup_firmwares(&to_gt(dev_priv)->uc);
 
-	i915_gem_drain_freed_objects(dev_priv);
+	/* Flush any outstanding work, including i915_gem_context.release_work. */
+	i915_gem_drain_workqueue(dev_priv);
 
 	drm_WARN_ON(&dev_priv->drm, !list_empty(&dev_priv->gem.contexts.list));
 }
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 3168d7007e10..135d04c2d41c 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1857,14 +1857,14 @@
 
 #define GT0_PERF_LIMIT_REASONS		_MMIO(0x1381a8)
 #define   GT0_PERF_LIMIT_REASONS_MASK	0xde3
-#define   PROCHOT_MASK			REG_BIT(1)
-#define   THERMAL_LIMIT_MASK		REG_BIT(2)
-#define   RATL_MASK			REG_BIT(6)
-#define   VR_THERMALERT_MASK		REG_BIT(7)
-#define   VR_TDC_MASK			REG_BIT(8)
-#define   POWER_LIMIT_4_MASK		REG_BIT(9)
-#define   POWER_LIMIT_1_MASK		REG_BIT(11)
-#define   POWER_LIMIT_2_MASK		REG_BIT(12)
+#define   PROCHOT_MASK			REG_BIT(0)
+#define   THERMAL_LIMIT_MASK		REG_BIT(1)
+#define   RATL_MASK			REG_BIT(5)
+#define   VR_THERMALERT_MASK		REG_BIT(6)
+#define   VR_TDC_MASK			REG_BIT(7)
+#define   POWER_LIMIT_4_MASK		REG_BIT(8)
+#define   POWER_LIMIT_1_MASK		REG_BIT(10)
+#define   POWER_LIMIT_2_MASK		REG_BIT(11)
 
 #define CHV_CLK_CTL1			_MMIO(0x101100)
 #define VLV_CLK_CTL2			_MMIO(0x101104)
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index ef3b04c7e153..373582cfd8f3 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -538,8 +538,6 @@ int i915_vma_bind(struct i915_vma *vma,
 				   bind_flags);
 	}
 
-	set_bit(I915_BO_WAS_BOUND_BIT, &vma->obj->flags);
-
 	atomic_or(bind_flags, &vma->flags);
 	return 0;
 }
@@ -1310,6 +1308,19 @@ err_unpin:
 	return err;
 }
 
+void vma_invalidate_tlb(struct i915_address_space *vm, u32 *tlb)
+{
+	/*
+	 * Before we release the pages that were bound by this vma, we
+	 * must invalidate all the TLBs that may still have a reference
+	 * back to our physical address. It only needs to be done once,
+	 * so after updating the PTE to point away from the pages, record
+	 * the most recent TLB invalidation seqno, and if we have not yet
+	 * flushed the TLBs upon release, perform a full invalidation.
+	 */
+	WRITE_ONCE(*tlb, intel_gt_next_invalidate_tlb_full(vm->gt));
+}
+
 static void __vma_put_pages(struct i915_vma *vma, unsigned int count)
 {
 	/* We allocate under vma_get_pages, so beware the shrinker */
@@ -1871,12 +1882,13 @@ int _i915_vma_move_to_active(struct i915_vma *vma,
 		enum dma_resv_usage usage;
 		int idx;
 
-		obj->read_domains = 0;
 		if (flags & EXEC_OBJECT_WRITE) {
 			usage = DMA_RESV_USAGE_WRITE;
 			obj->write_domain = I915_GEM_DOMAIN_RENDER;
+			obj->read_domains = 0;
 		} else {
 			usage = DMA_RESV_USAGE_READ;
+			obj->write_domain = 0;
 		}
 
 		dma_fence_array_for_each(curr, idx, fence)
@@ -1941,7 +1953,12 @@ struct dma_fence *__i915_vma_evict(struct i915_vma *vma, bool async)
 		vma->vm->skip_pte_rewrite;
 	trace_i915_vma_unbind(vma);
 
-	unbind_fence = i915_vma_resource_unbind(vma_res);
+	if (async)
+		unbind_fence = i915_vma_resource_unbind(vma_res,
+							&vma->obj->mm.tlb);
+	else
+		unbind_fence = i915_vma_resource_unbind(vma_res, NULL);
+
 	vma->resource = NULL;
 
 	atomic_and(~(I915_VMA_BIND_MASK | I915_VMA_ERROR | I915_VMA_GGTT_WRITE),
@@ -1949,10 +1966,13 @@ struct dma_fence *__i915_vma_evict(struct i915_vma *vma, bool async)
 
 	i915_vma_detach(vma);
 
-	if (!async && unbind_fence) {
-		dma_fence_wait(unbind_fence, false);
-		dma_fence_put(unbind_fence);
-		unbind_fence = NULL;
+	if (!async) {
+		if (unbind_fence) {
+			dma_fence_wait(unbind_fence, false);
+			dma_fence_put(unbind_fence);
+			unbind_fence = NULL;
+		}
+		vma_invalidate_tlb(vma->vm, &vma->obj->mm.tlb);
 	}
 
 	/*
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 88ca0bd9c900..33a58f605d75 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -213,6 +213,7 @@ bool i915_vma_misplaced(const struct i915_vma *vma,
 			u64 size, u64 alignment, u64 flags);
 void __i915_vma_set_map_and_fenceable(struct i915_vma *vma);
 void i915_vma_revoke_mmap(struct i915_vma *vma);
+void vma_invalidate_tlb(struct i915_address_space *vm, u32 *tlb);
 struct dma_fence *__i915_vma_evict(struct i915_vma *vma, bool async);
 int __i915_vma_unbind(struct i915_vma *vma);
 int __must_check i915_vma_unbind(struct i915_vma *vma);
diff --git a/drivers/gpu/drm/i915/i915_vma_resource.c b/drivers/gpu/drm/i915/i915_vma_resource.c
index 27c55027387a..5a67995ea5fe 100644
--- a/drivers/gpu/drm/i915/i915_vma_resource.c
+++ b/drivers/gpu/drm/i915/i915_vma_resource.c
@@ -223,10 +223,13 @@ i915_vma_resource_fence_notify(struct i915_sw_fence *fence,
  * Return: A refcounted pointer to a dma-fence that signals when unbinding is
  * complete.
  */
-struct dma_fence *i915_vma_resource_unbind(struct i915_vma_resource *vma_res)
+struct dma_fence *i915_vma_resource_unbind(struct i915_vma_resource *vma_res,
+					   u32 *tlb)
 {
 	struct i915_address_space *vm = vma_res->vm;
 
+	vma_res->tlb = tlb;
+
 	/* Reference for the sw fence */
 	i915_vma_resource_get(vma_res);
 
diff --git a/drivers/gpu/drm/i915/i915_vma_resource.h b/drivers/gpu/drm/i915/i915_vma_resource.h
index 5d8427caa2ba..06923d1816e7 100644
--- a/drivers/gpu/drm/i915/i915_vma_resource.h
+++ b/drivers/gpu/drm/i915/i915_vma_resource.h
@@ -67,6 +67,7 @@ struct i915_page_sizes {
  * taken when the unbind is scheduled.
  * @skip_pte_rewrite: During ggtt suspend and vm takedown pte rewriting
  * needs to be skipped for unbind.
+ * @tlb: pointer for obj->mm.tlb, if async unbind. Otherwise, NULL
  *
  * The lifetime of a struct i915_vma_resource is from a binding request to
  * the actual possible asynchronous unbind has completed.
@@ -119,6 +120,8 @@ struct i915_vma_resource {
 	bool immediate_unbind:1;
 	bool needs_wakeref:1;
 	bool skip_pte_rewrite:1;
+
+	u32 *tlb;
 };
 
 bool i915_vma_resource_hold(struct i915_vma_resource *vma_res,
@@ -131,7 +134,8 @@ struct i915_vma_resource *i915_vma_resource_alloc(void);
 
 void i915_vma_resource_free(struct i915_vma_resource *vma_res);
 
-struct dma_fence *i915_vma_resource_unbind(struct i915_vma_resource *vma_res);
+struct dma_fence *i915_vma_resource_unbind(struct i915_vma_resource *vma_res,
+					   u32 *tlb);
 
 void __i915_vma_resource_init(struct i915_vma_resource *vma_res);
 
diff --git a/drivers/gpu/drm/i915/intel_gvt_mmio_table.c b/drivers/gpu/drm/i915/intel_gvt_mmio_table.c
index 157e166672d7..5595639d0033 100644
--- a/drivers/gpu/drm/i915/intel_gvt_mmio_table.c
+++ b/drivers/gpu/drm/i915/intel_gvt_mmio_table.c
@@ -1076,7 +1076,8 @@ static int iterate_skl_plus_mmio(struct intel_gvt_mmio_table_iter *iter)
 	MMIO_D(GEN8_HDC_CHICKEN1);
 	MMIO_D(GEN9_WM_CHICKEN3);
 
-	if (IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv))
+	if (IS_KABYLAKE(dev_priv) ||
+	    IS_COFFEELAKE(dev_priv) || IS_COMETLAKE(dev_priv))
 		MMIO_D(GAMT_CHKN_BIT_REG);
 	if (!IS_BROXTON(dev_priv))
 		MMIO_D(GEN9_CTX_PREEMPT_REG);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index f06babdb3a8c..9fe4b583cc28 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -6561,7 +6561,10 @@ void skl_wm_get_hw_state(struct drm_i915_private *dev_priv)
 		enum plane_id plane_id;
 		u8 slices;
 
-		skl_pipe_wm_get_hw_state(crtc, &crtc_state->wm.skl.optimal);
+		memset(&crtc_state->wm.skl.optimal, 0,
+		       sizeof(crtc_state->wm.skl.optimal));
+		if (crtc_state->hw.active)
+			skl_pipe_wm_get_hw_state(crtc, &crtc_state->wm.skl.optimal);
 		crtc_state->wm.skl.raw = crtc_state->wm.skl.optimal;
 
 		memset(&dbuf_state->ddb[pipe], 0, sizeof(dbuf_state->ddb[pipe]));
@@ -6572,6 +6575,9 @@ void skl_wm_get_hw_state(struct drm_i915_private *dev_priv)
 			struct skl_ddb_entry *ddb_y =
 				&crtc_state->wm.skl.plane_ddb_y[plane_id];
 
+			if (!crtc_state->hw.active)
+				continue;
+
 			skl_ddb_get_hw_plane_state(dev_priv, crtc->pipe,
 						   plane_id, ddb, ddb_y);
 
diff --git a/drivers/gpu/drm/imx/dcss/dcss-kms.c b/drivers/gpu/drm/imx/dcss/dcss-kms.c
index 9b84df34a6a1..8cf3352d8858 100644
--- a/drivers/gpu/drm/imx/dcss/dcss-kms.c
+++ b/drivers/gpu/drm/imx/dcss/dcss-kms.c
@@ -142,8 +142,6 @@ struct dcss_kms_dev *dcss_kms_attach(struct dcss_dev *dcss)
 
 	drm_kms_helper_poll_init(drm);
 
-	drm_bridge_connector_enable_hpd(kms->connector);
-
 	ret = drm_dev_register(drm, 0);
 	if (ret)
 		goto cleanup_crtc;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 2d72cc5ddaba..6b6d5335c834 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -157,7 +157,7 @@ static void mtk_dither_config(struct device *dev, unsigned int w,
 {
 	struct mtk_ddp_comp_dev *priv = dev_get_drvdata(dev);
 
-	mtk_ddp_write(cmdq_pkt, h << 16 | w, &priv->cmdq_reg, priv->regs, DISP_REG_DITHER_SIZE);
+	mtk_ddp_write(cmdq_pkt, w << 16 | h, &priv->cmdq_reg, priv->regs, DISP_REG_DITHER_SIZE);
 	mtk_ddp_write(cmdq_pkt, DITHER_RELAY_MODE, &priv->cmdq_reg, priv->regs,
 		      DISP_REG_DITHER_CFG);
 	mtk_dither_set_common(priv->regs, &priv->cmdq_reg, bpc, DISP_REG_DITHER_CFG,
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 9cc406e1eee1..3b7d13028fb6 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -685,6 +685,16 @@ static void mtk_dsi_poweroff(struct mtk_dsi *dsi)
 	if (--dsi->refcount != 0)
 		return;
 
+	/*
+	 * mtk_dsi_stop() and mtk_dsi_start() is asymmetric, since
+	 * mtk_dsi_stop() should be called after mtk_drm_crtc_atomic_disable(),
+	 * which needs irq for vblank, and mtk_dsi_stop() will disable irq.
+	 * mtk_dsi_start() needs to be called in mtk_output_dsi_enable(),
+	 * after dsi is fully set.
+	 */
+	mtk_dsi_stop(dsi);
+
+	mtk_dsi_switch_to_cmd_mode(dsi, VM_DONE_INT_FLAG, 500);
 	mtk_dsi_reset_engine(dsi);
 	mtk_dsi_lane0_ulp_mode_enter(dsi);
 	mtk_dsi_clk_ulp_mode_enter(dsi);
@@ -735,17 +745,6 @@ static void mtk_output_dsi_disable(struct mtk_dsi *dsi)
 	if (!dsi->enabled)
 		return;
 
-	/*
-	 * mtk_dsi_stop() and mtk_dsi_start() is asymmetric, since
-	 * mtk_dsi_stop() should be called after mtk_drm_crtc_atomic_disable(),
-	 * which needs irq for vblank, and mtk_dsi_stop() will disable irq.
-	 * mtk_dsi_start() needs to be called in mtk_output_dsi_enable(),
-	 * after dsi is fully set.
-	 */
-	mtk_dsi_stop(dsi);
-
-	mtk_dsi_switch_to_cmd_mode(dsi, VM_DONE_INT_FLAG, 500);
-
 	dsi->enabled = false;
 }
 
@@ -808,10 +807,13 @@ static void mtk_dsi_bridge_atomic_post_disable(struct drm_bridge *bridge,
 
 static const struct drm_bridge_funcs mtk_dsi_bridge_funcs = {
 	.attach = mtk_dsi_bridge_attach,
+	.atomic_destroy_state = drm_atomic_helper_bridge_destroy_state,
 	.atomic_disable = mtk_dsi_bridge_atomic_disable,
+	.atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state,
 	.atomic_enable = mtk_dsi_bridge_atomic_enable,
 	.atomic_pre_enable = mtk_dsi_bridge_atomic_pre_enable,
 	.atomic_post_disable = mtk_dsi_bridge_atomic_post_disable,
+	.atomic_reset = drm_atomic_helper_bridge_reset,
 	.mode_set = mtk_dsi_bridge_mode_set,
 };
 
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index 1b70938cfd2c..bd4ca11d3ff5 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -115,8 +115,11 @@ static bool meson_vpu_has_available_connectors(struct device *dev)
 	for_each_endpoint_of_node(dev->of_node, ep) {
 		/* If the endpoint node exists, consider it enabled */
 		remote = of_graph_get_remote_port(ep);
-		if (remote)
+		if (remote) {
+			of_node_put(remote);
+			of_node_put(ep);
 			return true;
+		}
 	}
 
 	return false;
diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c
index b9ac932af8d0..03acc68abf2c 100644
--- a/drivers/gpu/drm/meson/meson_plane.c
+++ b/drivers/gpu/drm/meson/meson_plane.c
@@ -170,7 +170,7 @@ static void meson_plane_atomic_update(struct drm_plane *plane,
 
 	/* Enable OSD and BLK0, set max global alpha */
 	priv->viu.osd1_ctrl_stat = OSD_ENABLE |
-				   (0xFF << OSD_GLOBAL_ALPHA_SHIFT) |
+				   (0x100 << OSD_GLOBAL_ALPHA_SHIFT) |
 				   OSD_BLK0_ENABLE;
 
 	priv->viu.osd1_ctrl_stat2 = readl(priv->io_base +
diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c
index bb7e109534de..d4b907889a21 100644
--- a/drivers/gpu/drm/meson/meson_viu.c
+++ b/drivers/gpu/drm/meson/meson_viu.c
@@ -94,7 +94,7 @@ static void meson_viu_set_g12a_osd1_matrix(struct meson_drm *priv,
 		priv->io_base + _REG(VPP_WRAP_OSD1_MATRIX_COEF11_12));
 	writel(((m[9] & 0x1fff) << 16) | (m[10] & 0x1fff),
 		priv->io_base + _REG(VPP_WRAP_OSD1_MATRIX_COEF20_21));
-	writel((m[11] & 0x1fff) << 16,
+	writel((m[11] & 0x1fff),
 		priv->io_base +	_REG(VPP_WRAP_OSD1_MATRIX_COEF22));
 
 	writel(((m[18] & 0xfff) << 16) | (m[19] & 0xfff),
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c
index 251a1bb648cc..a222bf76804f 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.c
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.c
@@ -262,7 +262,11 @@ mgag200_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ret)
 		return ret;
 
-	drm_fbdev_generic_setup(dev, 0);
+	/*
+	 * FIXME: A 24-bit color depth does not work with 24 bpp on
+	 * G200ER. Force 32 bpp.
+	 */
+	drm_fbdev_generic_setup(dev, 32);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index c682d4e02d1b..52a626117f70 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -2061,6 +2061,12 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 
 	intf_cfg.stream_sel = 0; /* Don't care value for video mode */
 	intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
+
+	if (phys_enc->hw_intf)
+		intf_cfg.intf = phys_enc->hw_intf->idx;
+	if (phys_enc->hw_wb)
+		intf_cfg.wb = phys_enc->hw_wb->idx;
+
 	if (phys_enc->hw_pp->merge_3d)
 		intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx;
 
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index ab6aa13b1639..013ca02e17cb 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -1214,7 +1214,7 @@ static int dp_ctrl_link_train_2(struct dp_ctrl_private *ctrl,
 	if (ret)
 		return ret;
 
-	dp_ctrl_train_pattern_set(ctrl, pattern | DP_RECOVERED_CLOCK_OUT_EN);
+	dp_ctrl_train_pattern_set(ctrl, pattern);
 
 	for (tries = 0; tries <= maximum_retries; tries++) {
 		drm_dp_link_train_channel_eq_delay(ctrl->aux, ctrl->panel->dpcd);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
index 2c23324a2296..72c018e26f47 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
@@ -109,7 +109,7 @@ static const char * const dsi_8996_bus_clk_names[] = {
 static const struct msm_dsi_config msm8996_dsi_cfg = {
 	.io_offset = DSI_6G_REG_SHIFT,
 	.reg_cfg = {
-		.num = 2,
+		.num = 3,
 		.regs = {
 			{"vdda", 18160, 1 },	/* 1.25 V */
 			{"vcca", 17000, 32 },	/* 0.925 V */
@@ -148,7 +148,7 @@ static const char * const dsi_sdm660_bus_clk_names[] = {
 static const struct msm_dsi_config sdm660_dsi_cfg = {
 	.io_offset = DSI_6G_REG_SHIFT,
 	.reg_cfg = {
-		.num = 2,
+		.num = 1,
 		.regs = {
 			{"vdda", 12560, 4 },	/* 1.2 V */
 		},
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index a39de3bdc7fa..56dfa2d24be1 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -347,7 +347,7 @@ int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
 	} else {
 		timing->shared_timings.clk_pre =
 			linear_inter(tmax, tmin, pcnt2, 0, false);
-			timing->shared_timings.clk_pre_inc_by_2 = 0;
+		timing->shared_timings.clk_pre_inc_by_2 = 0;
 	}
 
 	timing->ta_go = 3;
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 1ed4cd09dbf8..16884db272de 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -469,6 +469,8 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
 		}
 	}
 
+	drm_helper_move_panel_connectors_to_head(ddev);
+
 	ddev->mode_config.funcs = &mode_config_funcs;
 	ddev->mode_config.helper_private = &mode_config_helper_funcs;
 
diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
index d1f70426f554..85c443a37e4e 100644
--- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c
+++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
@@ -213,6 +213,8 @@ void msm_devfreq_init(struct msm_gpu *gpu)
 
 	if (IS_ERR(df->devfreq)) {
 		DRM_DEV_ERROR(&gpu->pdev->dev, "Couldn't initialize GPU devfreq\n");
+		dev_pm_qos_remove_request(&df->idle_freq);
+		dev_pm_qos_remove_request(&df->boost_freq);
 		df->devfreq = NULL;
 		return;
 	}
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
index a92ffde53f0b..db2f847c8535 100644
--- a/drivers/gpu/drm/msm/msm_rd.c
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -196,6 +196,9 @@ static int rd_open(struct inode *inode, struct file *file)
 	file->private_data = rd;
 	rd->open = true;
 
+	/* Reset fifo to clear any previously unread data: */
+	rd->fifo.head = rd->fifo.tail = 0;
+
 	/* the parsing tools need to know gpu-id to know which
 	 * register database to load.
 	 *
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 05076e530e7d..e29175e4b44c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -820,6 +820,15 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict,
 		if (ret == 0) {
 			ret = nouveau_fence_new(chan, false, &fence);
 			if (ret == 0) {
+				/* TODO: figure out a better solution here
+				 *
+				 * wait on the fence here explicitly as going through
+				 * ttm_bo_move_accel_cleanup somehow doesn't seem to do it.
+				 *
+				 * Without this the operation can timeout and we'll fallback to a
+				 * software copy, which might take several minutes to finish.
+				 */
+				nouveau_fence_wait(fence, false, false);
 				ret = ttm_bo_move_accel_cleanup(bo,
 								&fence->base,
 								evict, false,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 568182e68dd7..d8cf71fb0512 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -2605,6 +2605,27 @@ nv172_chipset = {
 };
 
 static const struct nvkm_device_chip
+nv173_chipset = {
+	.name = "GA103",
+	.bar      = { 0x00000001, tu102_bar_new },
+	.bios     = { 0x00000001, nvkm_bios_new },
+	.devinit  = { 0x00000001, ga100_devinit_new },
+	.fb       = { 0x00000001, ga102_fb_new },
+	.gpio     = { 0x00000001, ga102_gpio_new },
+	.i2c      = { 0x00000001, gm200_i2c_new },
+	.imem     = { 0x00000001, nv50_instmem_new },
+	.mc       = { 0x00000001, ga100_mc_new },
+	.mmu      = { 0x00000001, tu102_mmu_new },
+	.pci      = { 0x00000001, gp100_pci_new },
+	.privring = { 0x00000001, gm200_privring_new },
+	.timer    = { 0x00000001, gk20a_timer_new },
+	.top      = { 0x00000001, ga100_top_new },
+	.disp     = { 0x00000001, ga102_disp_new },
+	.dma      = { 0x00000001, gv100_dma_new },
+	.fifo     = { 0x00000001, ga102_fifo_new },
+};
+
+static const struct nvkm_device_chip
 nv174_chipset = {
 	.name = "GA104",
 	.bar      = { 0x00000001, tu102_bar_new },
@@ -3067,6 +3088,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		case 0x167: device->chip = &nv167_chipset; break;
 		case 0x168: device->chip = &nv168_chipset; break;
 		case 0x172: device->chip = &nv172_chipset; break;
+		case 0x173: device->chip = &nv173_chipset; break;
 		case 0x174: device->chip = &nv174_chipset; break;
 		case 0x176: device->chip = &nv176_chipset; break;
 		case 0x177: device->chip = &nv177_chipset; break;
diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c
index cdb154c8b866..b75c690bb0cc 100644
--- a/drivers/gpu/drm/panel/panel-edp.c
+++ b/drivers/gpu/drm/panel/panel-edp.c
@@ -1295,7 +1295,8 @@ static const struct panel_desc innolux_n116bca_ea1 = {
 	},
 	.delay = {
 		.hpd_absent = 200,
-		.prepare_to_enable = 80,
+		.enable = 80,
+		.disable = 50,
 		.unprepare = 500,
 	},
 };
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index ff5e1a44c43a..1e716c23019a 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -2257,7 +2257,7 @@ static const struct panel_desc innolux_g121i1_l01 = {
 		.enable = 200,
 		.disable = 20,
 	},
-	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG,
 	.connector_type = DRM_MODE_CONNECTOR_LVDS,
 };
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index 5110cd9b2425..fe5f12f16a63 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -131,6 +131,17 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 		return PTR_ERR(opp);
 
 	panfrost_devfreq_profile.initial_freq = cur_freq;
+
+	/*
+	 * Set the recommend OPP this will enable and configure the regulator
+	 * if any and will avoid a switch off by regulator_late_cleanup()
+	 */
+	ret = dev_pm_opp_set_opp(dev, opp);
+	if (ret) {
+		DRM_DEV_ERROR(dev, "Couldn't set recommended OPP\n");
+		return ret;
+	}
+
 	dev_pm_opp_put(opp);
 
 	/*
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 2b12389f841a..ee0165687239 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1605,6 +1605,9 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend,
 		if (r) {
 			/* delay GPU reset to resume */
 			radeon_fence_driver_force_completion(rdev, i);
+		} else {
+			/* finish executing delayed work */
+			flush_delayed_work(&rdev->fence_drv[i].lockup_work);
 		}
 	}
 
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c
index c204e9b95c1f..518ee13b1d6f 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c
@@ -283,8 +283,9 @@ static int cdn_dp_connector_get_modes(struct drm_connector *connector)
 	return ret;
 }
 
-static int cdn_dp_connector_mode_valid(struct drm_connector *connector,
-				       struct drm_display_mode *mode)
+static enum drm_mode_status
+cdn_dp_connector_mode_valid(struct drm_connector *connector,
+			    struct drm_display_mode *mode)
 {
 	struct cdn_dp_device *dp = connector_to_dp(connector);
 	struct drm_display_info *display_info = &dp->connector.display_info;
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
index e4631f515ba4..f9aa8b96c695 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
@@ -1439,11 +1439,15 @@ static void rk3568_set_intf_mux(struct vop2_video_port *vp, int id,
 		die &= ~RK3568_SYS_DSP_INFACE_EN_HDMI_MUX;
 		die |= RK3568_SYS_DSP_INFACE_EN_HDMI |
 			   FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_HDMI_MUX, vp->id);
+		dip &= ~RK3568_DSP_IF_POL__HDMI_PIN_POL;
+		dip |= FIELD_PREP(RK3568_DSP_IF_POL__HDMI_PIN_POL, polflags);
 		break;
 	case ROCKCHIP_VOP2_EP_EDP0:
 		die &= ~RK3568_SYS_DSP_INFACE_EN_EDP_MUX;
 		die |= RK3568_SYS_DSP_INFACE_EN_EDP |
 			   FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_EDP_MUX, vp->id);
+		dip &= ~RK3568_DSP_IF_POL__EDP_PIN_POL;
+		dip |= FIELD_PREP(RK3568_DSP_IF_POL__EDP_PIN_POL, polflags);
 		break;
 	case ROCKCHIP_VOP2_EP_MIPI0:
 		die &= ~RK3568_SYS_DSP_INFACE_EN_MIPI0_MUX;
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index b4dfa166eccd..34234a144e87 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -531,7 +531,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 				    struct drm_display_mode *mode)
 {
 	struct mipi_dsi_device *device = dsi->device;
-	unsigned int Bpp = mipi_dsi_pixel_format_to_bpp(device->format) / 8;
+	int Bpp = mipi_dsi_pixel_format_to_bpp(device->format) / 8;
 	u16 hbp = 0, hfp = 0, hsa = 0, hblk = 0, vblk = 0;
 	u32 basic_ctl = 0;
 	size_t bytes;
@@ -555,7 +555,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 		 * (4 bytes). Its minimal size is therefore 10 bytes
 		 */
 #define HSA_PACKET_OVERHEAD	10
-		hsa = max((unsigned int)HSA_PACKET_OVERHEAD,
+		hsa = max(HSA_PACKET_OVERHEAD,
 			  (mode->hsync_end - mode->hsync_start) * Bpp - HSA_PACKET_OVERHEAD);
 
 		/*
@@ -564,7 +564,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 		 * therefore 6 bytes
 		 */
 #define HBP_PACKET_OVERHEAD	6
-		hbp = max((unsigned int)HBP_PACKET_OVERHEAD,
+		hbp = max(HBP_PACKET_OVERHEAD,
 			  (mode->htotal - mode->hsync_end) * Bpp - HBP_PACKET_OVERHEAD);
 
 		/*
@@ -574,7 +574,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 		 * 16 bytes
 		 */
 #define HFP_PACKET_OVERHEAD	16
-		hfp = max((unsigned int)HFP_PACKET_OVERHEAD,
+		hfp = max(HFP_PACKET_OVERHEAD,
 			  (mode->hsync_start - mode->hdisplay) * Bpp - HFP_PACKET_OVERHEAD);
 
 		/*
@@ -583,7 +583,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 		 * bytes). Its minimal size is therefore 10 bytes.
 		 */
 #define HBLK_PACKET_OVERHEAD	10
-		hblk = max((unsigned int)HBLK_PACKET_OVERHEAD,
+		hblk = max(HBLK_PACKET_OVERHEAD,
 			   (mode->htotal - (mode->hsync_end - mode->hsync_start)) * Bpp -
 			   HBLK_PACKET_OVERHEAD);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 0e210df65c30..97184c333526 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -912,7 +912,7 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 	/*
 	 * We might need to add a TTM.
 	 */
-	if (bo->resource->mem_type == TTM_PL_SYSTEM) {
+	if (!bo->resource || bo->resource->mem_type == TTM_PL_SYSTEM) {
 		ret = ttm_tt_create(bo, true);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 1cbfb00c1d65..911141d16e95 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -236,16 +236,19 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	if (bo->type != ttm_bo_type_sg)
 		fbo->base.base.resv = &fbo->base.base._resv;
 
-	if (fbo->base.resource) {
-		ttm_resource_set_bo(fbo->base.resource, &fbo->base);
-		bo->resource = NULL;
-	}
-
 	dma_resv_init(&fbo->base.base._resv);
 	fbo->base.base.dev = NULL;
 	ret = dma_resv_trylock(&fbo->base.base._resv);
 	WARN_ON(!ret);
 
+	if (fbo->base.resource) {
+		ttm_resource_set_bo(fbo->base.resource, &fbo->base);
+		bo->resource = NULL;
+		ttm_bo_set_bulk_move(&fbo->base, NULL);
+	} else {
+		fbo->base.bulk_move = NULL;
+	}
+
 	ret = dma_resv_reserve_fences(&fbo->base.base._resv, 1);
 	if (ret) {
 		kfree(fbo);
diff --git a/drivers/gpu/drm/vc4/Kconfig b/drivers/gpu/drm/vc4/Kconfig
index 061be9a6619d..b0f3117102ca 100644
--- a/drivers/gpu/drm/vc4/Kconfig
+++ b/drivers/gpu/drm/vc4/Kconfig
@@ -8,6 +8,7 @@ config DRM_VC4
 	depends on DRM
 	depends on SND && SND_SOC
 	depends on COMMON_CLK
+	depends on PM
 	select DRM_DISPLAY_HDMI_HELPER
 	select DRM_DISPLAY_HELPER
 	select DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 592c3b5d03e6..1e5f68704d7d 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -2855,7 +2855,7 @@ static int vc5_hdmi_init_resources(struct vc4_hdmi *vc4_hdmi)
 	return 0;
 }
 
-static int __maybe_unused vc4_hdmi_runtime_suspend(struct device *dev)
+static int vc4_hdmi_runtime_suspend(struct device *dev)
 {
 	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
 
@@ -2972,17 +2972,15 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 			vc4_hdmi->disable_4kp60 = true;
 	}
 
+	pm_runtime_enable(dev);
+
 	/*
-	 * We need to have the device powered up at this point to call
-	 * our reset hook and for the CEC init.
+	 *  We need to have the device powered up at this point to call
+	 *  our reset hook and for the CEC init.
 	 */
-	ret = vc4_hdmi_runtime_resume(dev);
+	ret = pm_runtime_resume_and_get(dev);
 	if (ret)
-		goto err_put_ddc;
-
-	pm_runtime_get_noresume(dev);
-	pm_runtime_set_active(dev);
-	pm_runtime_enable(dev);
+		goto err_disable_runtime_pm;
 
 	if ((of_device_is_compatible(dev->of_node, "brcm,bcm2711-hdmi0") ||
 	     of_device_is_compatible(dev->of_node, "brcm,bcm2711-hdmi1")) &&
@@ -3028,6 +3026,7 @@ err_destroy_conn:
 err_destroy_encoder:
 	drm_encoder_cleanup(encoder);
 	pm_runtime_put_sync(dev);
+err_disable_runtime_pm:
 	pm_runtime_disable(dev);
 err_put_ddc:
 	put_device(&vc4_hdmi->ddc->dev);
diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
index 4b90c86ee5f8..47774b9ab3de 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
@@ -288,11 +288,29 @@ int amd_sfh_irq_init(struct amd_mp2_dev *privdata)
 	return 0;
 }
 
+static const struct dmi_system_id dmi_nodevs[] = {
+	{
+		/*
+		 * Google Chromebooks use Chrome OS Embedded Controller Sensor
+		 * Hub instead of Sensor Hub Fusion and leaves MP2
+		 * uninitialized, which disables all functionalities, even
+		 * including the registers necessary for feature detections.
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+		},
+	},
+	{ }
+};
+
 static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct amd_mp2_dev *privdata;
 	int rc;
 
+	if (dmi_first_match(dmi_nodevs))
+		return -ENODEV;
+
 	privdata = devm_kzalloc(&pdev->dev, sizeof(*privdata), GFP_KERNEL);
 	if (!privdata)
 		return -ENOMEM;
diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 08c9a9a60ae4..b59c3dafa6a4 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -1212,6 +1212,13 @@ static __u8 *asus_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		rdesc = new_rdesc;
 	}
 
+	if (drvdata->quirks & QUIRK_ROG_NKEY_KEYBOARD &&
+			*rsize == 331 && rdesc[190] == 0x85 && rdesc[191] == 0x5a &&
+			rdesc[204] == 0x95 && rdesc[205] == 0x05) {
+		hid_info(hdev, "Fixing up Asus N-KEY keyb report descriptor\n");
+		rdesc[205] = 0x01;
+	}
+
 	return rdesc;
 }
 
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 0fb720a96399..f80d6193fca6 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -185,6 +185,8 @@
 #define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021   0x029c
 #define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021   0x029a
 #define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_2021   0x029f
+#define USB_DEVICE_ID_APPLE_TOUCHBAR_BACKLIGHT 0x8102
+#define USB_DEVICE_ID_APPLE_TOUCHBAR_DISPLAY 0x8302
 
 #define USB_VENDOR_ID_ASUS		0x0486
 #define USB_DEVICE_ID_ASUS_T91MT	0x0185
@@ -414,6 +416,7 @@
 #define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN	0x2706
 #define I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN	0x261A
 #define I2C_DEVICE_ID_SURFACE_GO2_TOUCHSCREEN	0x2A1C
+#define I2C_DEVICE_ID_LENOVO_YOGA_C630_TOUCHSCREEN	0x279F
 
 #define USB_VENDOR_ID_ELECOM		0x056e
 #define USB_DEVICE_ID_ELECOM_BM084	0x0061
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 48c1c02c69f4..859aeb07542e 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -383,6 +383,8 @@ static const struct hid_device_id hid_battery_quirks[] = {
 	  HID_BATTERY_QUIRK_IGNORE },
 	{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_SURFACE_GO2_TOUCHSCREEN),
 	  HID_BATTERY_QUIRK_IGNORE },
+	{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_LENOVO_YOGA_C630_TOUCHSCREEN),
+	  HID_BATTERY_QUIRK_IGNORE },
 	{}
 };
 
@@ -1532,7 +1534,10 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct
 			 * assume ours
 			 */
 			if (!report->tool)
-				hid_report_set_tool(report, input, usage->code);
+				report->tool = usage->code;
+
+			/* drivers may have changed the value behind our back, resend it */
+			hid_report_set_tool(report, input, report->tool);
 		} else {
 			hid_report_release_tool(report, input, usage->code);
 		}
diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c
index 92ac4f605f13..6028af3c3aae 100644
--- a/drivers/hid/hid-nintendo.c
+++ b/drivers/hid/hid-nintendo.c
@@ -1221,6 +1221,7 @@ static void joycon_parse_report(struct joycon_ctlr *ctlr,
 
 	spin_lock_irqsave(&ctlr->lock, flags);
 	if (IS_ENABLED(CONFIG_NINTENDO_FF) && rep->vibrator_report &&
+	    ctlr->ctlr_state != JOYCON_CTLR_STATE_REMOVED &&
 	    (msecs - ctlr->rumble_msecs) >= JC_RUMBLE_PERIOD_MS &&
 	    (ctlr->rumble_queue_head != ctlr->rumble_queue_tail ||
 	     ctlr->rumble_zero_countdown > 0)) {
@@ -1545,12 +1546,13 @@ static int joycon_set_rumble(struct joycon_ctlr *ctlr, u16 amp_r, u16 amp_l,
 		ctlr->rumble_queue_head = 0;
 	memcpy(ctlr->rumble_data[ctlr->rumble_queue_head], data,
 	       JC_RUMBLE_DATA_SIZE);
-	spin_unlock_irqrestore(&ctlr->lock, flags);
 
 	/* don't wait for the periodic send (reduces latency) */
-	if (schedule_now)
+	if (schedule_now && ctlr->ctlr_state != JOYCON_CTLR_STATE_REMOVED)
 		queue_work(ctlr->rumble_queue, &ctlr->rumble_worker);
 
+	spin_unlock_irqrestore(&ctlr->lock, flags);
+
 	return 0;
 }
 
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index dc67717d2dab..70f602c64fd1 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -314,6 +314,8 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_TOUCHBAR_BACKLIGHT) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_TOUCHBAR_DISPLAY) },
 #endif
 #if IS_ENABLED(CONFIG_HID_APPLEIR)
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_IRCONTROL) },
diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c
index a3b151b29bd7..fc616db4231b 100644
--- a/drivers/hid/hid-steam.c
+++ b/drivers/hid/hid-steam.c
@@ -134,6 +134,11 @@ static int steam_recv_report(struct steam_device *steam,
 	int ret;
 
 	r = steam->hdev->report_enum[HID_FEATURE_REPORT].report_id_hash[0];
+	if (!r) {
+		hid_err(steam->hdev, "No HID_FEATURE_REPORT submitted -  nothing to read\n");
+		return -EINVAL;
+	}
+
 	if (hid_report_len(r) < 64)
 		return -EINVAL;
 
@@ -165,6 +170,11 @@ static int steam_send_report(struct steam_device *steam,
 	int ret;
 
 	r = steam->hdev->report_enum[HID_FEATURE_REPORT].report_id_hash[0];
+	if (!r) {
+		hid_err(steam->hdev, "No HID_FEATURE_REPORT submitted -  nothing to read\n");
+		return -EINVAL;
+	}
+
 	if (hid_report_len(r) < 64)
 		return -EINVAL;
 
diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c
index c3e6d69fdfbd..cf1679b0d4fb 100644
--- a/drivers/hid/hid-thrustmaster.c
+++ b/drivers/hid/hid-thrustmaster.c
@@ -67,12 +67,13 @@ static const struct tm_wheel_info tm_wheels_infos[] = {
 	{0x0200, 0x0005, "Thrustmaster T300RS (Missing Attachment)"},
 	{0x0206, 0x0005, "Thrustmaster T300RS"},
 	{0x0209, 0x0005, "Thrustmaster T300RS (Open Wheel Attachment)"},
+	{0x020a, 0x0005, "Thrustmaster T300RS (Sparco R383 Mod)"},
 	{0x0204, 0x0005, "Thrustmaster T300 Ferrari Alcantara Edition"},
 	{0x0002, 0x0002, "Thrustmaster T500RS"}
 	//{0x0407, 0x0001, "Thrustmaster TMX"}
 };
 
-static const uint8_t tm_wheels_infos_length = 4;
+static const uint8_t tm_wheels_infos_length = 7;
 
 /*
  * This structs contains (in little endian) the response data
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index 681614a8302a..197b1e7bf029 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -350,6 +350,8 @@ static int hidraw_release(struct inode * inode, struct file * file)
 	down_write(&minors_rwsem);
 
 	spin_lock_irqsave(&hidraw_table[minor]->list_lock, flags);
+	for (int i = list->tail; i < list->head; i++)
+		kfree(list->buffer[i].value);
 	list_del(&list->node);
 	spin_unlock_irqrestore(&hidraw_table[minor]->list_lock, flags);
 	kfree(list);
diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
index e600dbf04dfc..fc108f19a64c 100644
--- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h
+++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
@@ -32,6 +32,7 @@
 #define ADL_P_DEVICE_ID		0x51FC
 #define ADL_N_DEVICE_ID		0x54FC
 #define RPL_S_DEVICE_ID		0x7A78
+#define MTL_P_DEVICE_ID		0x7E45
 
 #define	REVISION_ID_CHT_A0	0x6
 #define	REVISION_ID_CHT_Ax_SI	0x0
diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index 2c67ec17bec6..7120b30ac51d 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -43,6 +43,7 @@ static const struct pci_device_id ish_pci_tbl[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, ADL_P_DEVICE_ID)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, ADL_N_DEVICE_ID)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, RPL_S_DEVICE_ID)},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MTL_P_DEVICE_ID)},
 	{0, }
 };
 MODULE_DEVICE_TABLE(pci, ish_pci_tbl);
diff --git a/drivers/hid/intel-ish-hid/ishtp-hid.h b/drivers/hid/intel-ish-hid/ishtp-hid.h
index 6a5cc11aefd8..35dddc5015b3 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid.h
+++ b/drivers/hid/intel-ish-hid/ishtp-hid.h
@@ -105,7 +105,7 @@ struct report_list {
  * @multi_packet_cnt:	Count of fragmented packet count
  *
  * This structure is used to store completion flags and per client data like
- * like report description, number of HID devices etc.
+ * report description, number of HID devices etc.
  */
 struct ishtp_cl_data {
 	/* completion flags */
diff --git a/drivers/hid/intel-ish-hid/ishtp/client.c b/drivers/hid/intel-ish-hid/ishtp/client.c
index 405e0d5212cc..df0a825694f5 100644
--- a/drivers/hid/intel-ish-hid/ishtp/client.c
+++ b/drivers/hid/intel-ish-hid/ishtp/client.c
@@ -626,13 +626,14 @@ static void ishtp_cl_read_complete(struct ishtp_cl_rb *rb)
 }
 
 /**
- * ipc_tx_callback() - IPC tx callback function
+ * ipc_tx_send() - IPC tx send function
  * @prm: Pointer to client device instance
  *
- * Send message over IPC either first time or on callback on previous message
- * completion
+ * Send message over IPC. Message will be split into fragments
+ * if message size is bigger than IPC FIFO size, and all
+ * fragments will be sent one by one.
  */
-static void ipc_tx_callback(void *prm)
+static void ipc_tx_send(void *prm)
 {
 	struct ishtp_cl	*cl = prm;
 	struct ishtp_cl_tx_ring	*cl_msg;
@@ -677,32 +678,41 @@ static void ipc_tx_callback(void *prm)
 			    list);
 	rem = cl_msg->send_buf.size - cl->tx_offs;
 
-	ishtp_hdr.host_addr = cl->host_client_id;
-	ishtp_hdr.fw_addr = cl->fw_client_id;
-	ishtp_hdr.reserved = 0;
-	pmsg = cl_msg->send_buf.data + cl->tx_offs;
+	while (rem > 0) {
+		ishtp_hdr.host_addr = cl->host_client_id;
+		ishtp_hdr.fw_addr = cl->fw_client_id;
+		ishtp_hdr.reserved = 0;
+		pmsg = cl_msg->send_buf.data + cl->tx_offs;
+
+		if (rem <= dev->mtu) {
+			/* Last fragment or only one packet */
+			ishtp_hdr.length = rem;
+			ishtp_hdr.msg_complete = 1;
+			/* Submit to IPC queue with no callback */
+			ishtp_write_message(dev, &ishtp_hdr, pmsg);
+			cl->tx_offs = 0;
+			cl->sending = 0;
 
-	if (rem <= dev->mtu) {
-		ishtp_hdr.length = rem;
-		ishtp_hdr.msg_complete = 1;
-		cl->sending = 0;
-		list_del_init(&cl_msg->list);	/* Must be before write */
-		spin_unlock_irqrestore(&cl->tx_list_spinlock, tx_flags);
-		/* Submit to IPC queue with no callback */
-		ishtp_write_message(dev, &ishtp_hdr, pmsg);
-		spin_lock_irqsave(&cl->tx_free_list_spinlock, tx_free_flags);
-		list_add_tail(&cl_msg->list, &cl->tx_free_list.list);
-		++cl->tx_ring_free_size;
-		spin_unlock_irqrestore(&cl->tx_free_list_spinlock,
-			tx_free_flags);
-	} else {
-		/* Send IPC fragment */
-		spin_unlock_irqrestore(&cl->tx_list_spinlock, tx_flags);
-		cl->tx_offs += dev->mtu;
-		ishtp_hdr.length = dev->mtu;
-		ishtp_hdr.msg_complete = 0;
-		ishtp_send_msg(dev, &ishtp_hdr, pmsg, ipc_tx_callback, cl);
+			break;
+		} else {
+			/* Send ipc fragment */
+			ishtp_hdr.length = dev->mtu;
+			ishtp_hdr.msg_complete = 0;
+			/* All fregments submitted to IPC queue with no callback */
+			ishtp_write_message(dev, &ishtp_hdr, pmsg);
+			cl->tx_offs += dev->mtu;
+			rem = cl_msg->send_buf.size - cl->tx_offs;
+		}
 	}
+
+	list_del_init(&cl_msg->list);
+	spin_unlock_irqrestore(&cl->tx_list_spinlock, tx_flags);
+
+	spin_lock_irqsave(&cl->tx_free_list_spinlock, tx_free_flags);
+	list_add_tail(&cl_msg->list, &cl->tx_free_list.list);
+	++cl->tx_ring_free_size;
+	spin_unlock_irqrestore(&cl->tx_free_list_spinlock,
+		tx_free_flags);
 }
 
 /**
@@ -720,7 +730,7 @@ static void ishtp_cl_send_msg_ipc(struct ishtp_device *dev,
 		return;
 
 	cl->tx_offs = 0;
-	ipc_tx_callback(cl);
+	ipc_tx_send(cl);
 	++cl->send_msg_cnt_ipc;
 }
 
diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c
index 660036da7449..922d83eb7ddf 100644
--- a/drivers/hv/hv_fcopy.c
+++ b/drivers/hv/hv_fcopy.c
@@ -129,7 +129,7 @@ static void fcopy_send_data(struct work_struct *dummy)
 
 	/*
 	 * The  strings sent from the host are encoded in
-	 * in utf16; convert it to utf8 strings.
+	 * utf16; convert it to utf8 strings.
 	 * The host assures us that the utf16 strings will not exceed
 	 * the max lengths specified. We will however, reserve room
 	 * for the string terminating character - in the utf16s_utf8s()
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 23c680d1a0f5..7b9f3fc3adf7 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -35,6 +35,7 @@
 #include <linux/kernel.h>
 #include <linux/syscore_ops.h>
 #include <linux/dma-map-ops.h>
+#include <linux/pci.h>
 #include <clocksource/hyperv_timer.h>
 #include "hyperv_vmbus.h"
 
@@ -2262,26 +2263,43 @@ static int vmbus_acpi_remove(struct acpi_device *device)
 
 static void vmbus_reserve_fb(void)
 {
-	int size;
+	resource_size_t start = 0, size;
+	struct pci_dev *pdev;
+
+	if (efi_enabled(EFI_BOOT)) {
+		/* Gen2 VM: get FB base from EFI framebuffer */
+		start = screen_info.lfb_base;
+		size = max_t(__u32, screen_info.lfb_size, 0x800000);
+	} else {
+		/* Gen1 VM: get FB base from PCI */
+		pdev = pci_get_device(PCI_VENDOR_ID_MICROSOFT,
+				      PCI_DEVICE_ID_HYPERV_VIDEO, NULL);
+		if (!pdev)
+			return;
+
+		if (pdev->resource[0].flags & IORESOURCE_MEM) {
+			start = pci_resource_start(pdev, 0);
+			size = pci_resource_len(pdev, 0);
+		}
+
+		/*
+		 * Release the PCI device so hyperv_drm or hyperv_fb driver can
+		 * grab it later.
+		 */
+		pci_dev_put(pdev);
+	}
+
+	if (!start)
+		return;
+
 	/*
 	 * Make a claim for the frame buffer in the resource tree under the
 	 * first node, which will be the one below 4GB.  The length seems to
 	 * be underreported, particularly in a Generation 1 VM.  So start out
 	 * reserving a larger area and make it smaller until it succeeds.
 	 */
-
-	if (screen_info.lfb_base) {
-		if (efi_enabled(EFI_BOOT))
-			size = max_t(__u32, screen_info.lfb_size, 0x800000);
-		else
-			size = max_t(__u32, screen_info.lfb_size, 0x4000000);
-
-		for (; !fb_mmio && (size >= 0x100000); size >>= 1) {
-			fb_mmio = __request_region(hyperv_mmio,
-						   screen_info.lfb_base, size,
-						   fb_mmio_name, 0);
-		}
-	}
+	for (; !fb_mmio && (size >= 0x100000); size >>= 1)
+		fb_mmio = __request_region(hyperv_mmio, start, size, fb_mmio_name, 0);
 }
 
 /**
@@ -2313,7 +2331,7 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj,
 			bool fb_overlap_ok)
 {
 	struct resource *iter, *shadow;
-	resource_size_t range_min, range_max, start;
+	resource_size_t range_min, range_max, start, end;
 	const char *dev_n = dev_name(&device_obj->device);
 	int retval;
 
@@ -2348,6 +2366,14 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj,
 		range_max = iter->end;
 		start = (range_min + align - 1) & ~(align - 1);
 		for (; start + size - 1 <= range_max; start += align) {
+			end = start + size - 1;
+
+			/* Skip the whole fb_mmio region if not fb_overlap_ok */
+			if (!fb_overlap_ok && fb_mmio &&
+			    (((start >= fb_mmio->start) && (start <= fb_mmio->end)) ||
+			     ((end >= fb_mmio->start) && (end <= fb_mmio->end))))
+				continue;
+
 			shadow = __request_region(iter, start, size, NULL,
 						  IORESOURCE_BUSY);
 			if (!shadow)
@@ -2427,7 +2453,8 @@ static int vmbus_acpi_add(struct acpi_device *device)
 	 * Some ancestor of the vmbus acpi device (Gen1 or Gen2
 	 * firmware) is the VMOD that has the mmio ranges. Get that.
 	 */
-	for (ancestor = device->parent; ancestor; ancestor = ancestor->parent) {
+	for (ancestor = acpi_dev_parent(device); ancestor;
+	     ancestor = acpi_dev_parent(ancestor)) {
 		result = acpi_walk_resources(ancestor->handle, METHOD_NAME__CRS,
 					     vmbus_walk_resources, NULL);
 
diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c
index d2545a1be9fc..44e04c75d0d3 100644
--- a/drivers/hwmon/acpi_power_meter.c
+++ b/drivers/hwmon/acpi_power_meter.c
@@ -598,7 +598,7 @@ static int read_domain_devices(struct acpi_power_meter_resource *resource)
 			continue;
 
 		/* Create a symlink to domain objects */
-		obj = acpi_bus_get_acpi_device(element->reference.handle);
+		obj = acpi_get_acpi_dev(element->reference.handle);
 		resource->domain_devices[i] = obj;
 		if (!obj)
 			continue;
diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c
index 61a4684fc020..81e688975c6a 100644
--- a/drivers/hwmon/asus-ec-sensors.c
+++ b/drivers/hwmon/asus-ec-sensors.c
@@ -266,9 +266,7 @@ static const struct ec_sensor_info sensors_family_intel_600[] = {
 #define SENSOR_SET_WATER_BLOCK                                                 \
 	(SENSOR_TEMP_WATER_BLOCK_IN | SENSOR_TEMP_WATER_BLOCK_OUT)
 
-
 struct ec_board_info {
-	const char *board_names[MAX_IDENTICAL_BOARD_VARIATIONS];
 	unsigned long sensors;
 	/*
 	 * Defines which mutex to use for guarding access to the state and the
@@ -281,152 +279,194 @@ struct ec_board_info {
 	enum board_family family;
 };
 
-static const struct ec_board_info board_info[] = {
-	{
-		.board_names = {"PRIME X470-PRO"},
-		.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
-			SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM |
-			SENSOR_FAN_CPU_OPT |
-			SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE,
-		.mutex_path = ACPI_GLOBAL_LOCK_PSEUDO_PATH,
-		.family = family_amd_400_series,
-	},
-	{
-		.board_names = {"PRIME X570-PRO"},
-		.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM |
-			SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET,
-		.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
-		.family = family_amd_500_series,
-	},
-	{
-		.board_names = {"ProArt X570-CREATOR WIFI"},
-		.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM |
-			SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CPU_OPT |
-			SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE,
-	},
-	{
-		.board_names = {"Pro WS X570-ACE"},
-		.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM |
-			SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET |
-			SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE,
-		.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
-		.family = family_amd_500_series,
-	},
-	{
-		.board_names = {"ROG CROSSHAIR VIII DARK HERO"},
-		.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
-			SENSOR_TEMP_T_SENSOR |
-			SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER |
-			SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW |
-			SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE,
-		.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
-		.family = family_amd_500_series,
-	},
-	{
-		.board_names = {
-			"ROG CROSSHAIR VIII FORMULA",
-			"ROG CROSSHAIR VIII HERO",
-			"ROG CROSSHAIR VIII HERO (WI-FI)",
-		},
-		.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
-			SENSOR_TEMP_T_SENSOR |
-			SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER |
-			SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET |
-			SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU |
-			SENSOR_IN_CPU_CORE,
-		.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
-		.family = family_amd_500_series,
-	},
-	{
-		.board_names = {
-			"ROG MAXIMUS XI HERO",
-			"ROG MAXIMUS XI HERO (WI-FI)",
-		},
-		.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
-			SENSOR_TEMP_T_SENSOR |
-			SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER |
-			SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW,
-		.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
-		.family = family_intel_300_series,
-	},
-	{
-		.board_names = {"ROG CROSSHAIR VIII IMPACT"},
-		.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
-			SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM |
-			SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU |
-			SENSOR_IN_CPU_CORE,
-		.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
-		.family = family_amd_500_series,
-	},
-	{
-		.board_names = {"ROG STRIX B550-E GAMING"},
-		.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
-			SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM |
-			SENSOR_FAN_CPU_OPT,
-		.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
-		.family = family_amd_500_series,
-	},
-	{
-		.board_names = {"ROG STRIX B550-I GAMING"},
-		.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
-			SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM |
-			SENSOR_FAN_VRM_HS | SENSOR_CURR_CPU |
-			SENSOR_IN_CPU_CORE,
-		.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
-		.family = family_amd_500_series,
-	},
-	{
-		.board_names = {"ROG STRIX X570-E GAMING"},
-		.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
-			SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM |
-			SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU |
-			SENSOR_IN_CPU_CORE,
-		.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
-		.family = family_amd_500_series,
-	},
-	{
-		.board_names = {"ROG STRIX X570-E GAMING WIFI II"},
-		.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
-			SENSOR_TEMP_T_SENSOR | SENSOR_CURR_CPU |
-			SENSOR_IN_CPU_CORE,
-		.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
-		.family = family_amd_500_series,
-	},
-	{
-		.board_names = {"ROG STRIX X570-F GAMING"},
-		.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
-			SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET,
-		.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
-		.family = family_amd_500_series,
-	},
-	{
-		.board_names = {"ROG STRIX X570-I GAMING"},
-		.sensors = SENSOR_TEMP_CHIPSET | SENSOR_TEMP_VRM |
-			SENSOR_TEMP_T_SENSOR |
-			SENSOR_FAN_VRM_HS | SENSOR_FAN_CHIPSET |
-			SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE,
-		.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
-		.family = family_amd_500_series,
-	},
-	{
-		.board_names = {"ROG STRIX Z690-A GAMING WIFI D4"},
-		.sensors = SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM,
-		.mutex_path = ASUS_HW_ACCESS_MUTEX_RMTW_ASMX,
-		.family = family_intel_600_series,
-	},
-	{
-		.board_names = {"ROG ZENITH II EXTREME"},
-		.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_T_SENSOR |
-			SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER |
-			SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET | SENSOR_FAN_VRM_HS |
-			SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE |
-			SENSOR_SET_WATER_BLOCK |
-			SENSOR_TEMP_T_SENSOR_2 | SENSOR_TEMP_SENSOR_EXTRA_1 |
-			SENSOR_TEMP_SENSOR_EXTRA_2 | SENSOR_TEMP_SENSOR_EXTRA_3,
-		.mutex_path = ASUS_HW_ACCESS_MUTEX_SB_PCI0_SBRG_SIO1_MUT0,
-		.family = family_amd_500_series,
-	},
-	{}
+static const struct ec_board_info board_info_prime_x470_pro = {
+	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
+		SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM |
+		SENSOR_FAN_CPU_OPT |
+		SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE,
+	.mutex_path = ACPI_GLOBAL_LOCK_PSEUDO_PATH,
+	.family = family_amd_400_series,
+};
+
+static const struct ec_board_info board_info_prime_x570_pro = {
+	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM |
+		SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET,
+	.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
+	.family = family_amd_500_series,
+};
+
+static const struct ec_board_info board_info_pro_art_x570_creator_wifi = {
+	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM |
+		SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CPU_OPT |
+		SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE,
+	.family = family_amd_500_series,
+};
+
+static const struct ec_board_info board_info_pro_ws_x570_ace = {
+	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM |
+		SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET |
+		SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE,
+	.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
+	.family = family_amd_500_series,
+};
+
+static const struct ec_board_info board_info_crosshair_viii_dark_hero = {
+	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
+		SENSOR_TEMP_T_SENSOR |
+		SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER |
+		SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW |
+		SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE,
+	.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
+	.family = family_amd_500_series,
+};
+
+static const struct ec_board_info board_info_crosshair_viii_hero = {
+	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
+		SENSOR_TEMP_T_SENSOR |
+		SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER |
+		SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET |
+		SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU |
+		SENSOR_IN_CPU_CORE,
+	.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
+	.family = family_amd_500_series,
+};
+
+static const struct ec_board_info board_info_maximus_xi_hero = {
+	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
+		SENSOR_TEMP_T_SENSOR |
+		SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER |
+		SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW,
+	.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
+	.family = family_intel_300_series,
+};
+
+static const struct ec_board_info board_info_crosshair_viii_impact = {
+	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
+		SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM |
+		SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU |
+		SENSOR_IN_CPU_CORE,
+	.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
+	.family = family_amd_500_series,
+};
+
+static const struct ec_board_info board_info_strix_b550_e_gaming = {
+	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
+		SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM |
+		SENSOR_FAN_CPU_OPT,
+	.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
+	.family = family_amd_500_series,
+};
+
+static const struct ec_board_info board_info_strix_b550_i_gaming = {
+	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
+		SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM |
+		SENSOR_FAN_VRM_HS | SENSOR_CURR_CPU |
+		SENSOR_IN_CPU_CORE,
+	.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
+	.family = family_amd_500_series,
+};
+
+static const struct ec_board_info board_info_strix_x570_e_gaming = {
+	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
+		SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM |
+		SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU |
+		SENSOR_IN_CPU_CORE,
+	.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
+	.family = family_amd_500_series,
+};
+
+static const struct ec_board_info board_info_strix_x570_e_gaming_wifi_ii = {
+	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
+		SENSOR_TEMP_T_SENSOR | SENSOR_CURR_CPU |
+		SENSOR_IN_CPU_CORE,
+	.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
+	.family = family_amd_500_series,
+};
+
+static const struct ec_board_info board_info_strix_x570_f_gaming = {
+	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
+		SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET,
+	.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
+	.family = family_amd_500_series,
+};
+
+static const struct ec_board_info board_info_strix_x570_i_gaming = {
+	.sensors = SENSOR_TEMP_CHIPSET | SENSOR_TEMP_VRM |
+		SENSOR_TEMP_T_SENSOR |
+		SENSOR_FAN_VRM_HS | SENSOR_FAN_CHIPSET |
+		SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE,
+	.mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
+	.family = family_amd_500_series,
+};
+
+static const struct ec_board_info board_info_strix_z690_a_gaming_wifi_d4 = {
+	.sensors = SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM,
+	.mutex_path = ASUS_HW_ACCESS_MUTEX_RMTW_ASMX,
+	.family = family_intel_600_series,
+};
+
+static const struct ec_board_info board_info_zenith_ii_extreme = {
+	.sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_T_SENSOR |
+		SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER |
+		SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET | SENSOR_FAN_VRM_HS |
+		SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE |
+		SENSOR_SET_WATER_BLOCK |
+		SENSOR_TEMP_T_SENSOR_2 | SENSOR_TEMP_SENSOR_EXTRA_1 |
+		SENSOR_TEMP_SENSOR_EXTRA_2 | SENSOR_TEMP_SENSOR_EXTRA_3,
+	.mutex_path = ASUS_HW_ACCESS_MUTEX_SB_PCI0_SBRG_SIO1_MUT0,
+	.family = family_amd_500_series,
+};
+
+#define DMI_EXACT_MATCH_ASUS_BOARD_NAME(name, board_info)                      \
+	{                                                                      \
+		.matches = {                                                   \
+			DMI_EXACT_MATCH(DMI_BOARD_VENDOR,                      \
+					"ASUSTeK COMPUTER INC."),              \
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, name),                 \
+		},                                                             \
+		.driver_data = (void *)board_info,                              \
+	}
+
+static const struct dmi_system_id dmi_table[] = {
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("PRIME X470-PRO",
+					&board_info_prime_x470_pro),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("PRIME X570-PRO",
+					&board_info_prime_x570_pro),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ProArt X570-CREATOR WIFI",
+					&board_info_pro_art_x570_creator_wifi),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("Pro WS X570-ACE",
+					&board_info_pro_ws_x570_ace),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII DARK HERO",
+					&board_info_crosshair_viii_dark_hero),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII FORMULA",
+					&board_info_crosshair_viii_hero),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII HERO",
+					&board_info_crosshair_viii_hero),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII HERO (WI-FI)",
+					&board_info_crosshair_viii_hero),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG MAXIMUS XI HERO",
+					&board_info_maximus_xi_hero),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG MAXIMUS XI HERO (WI-FI)",
+					&board_info_maximus_xi_hero),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII IMPACT",
+					&board_info_crosshair_viii_impact),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX B550-E GAMING",
+					&board_info_strix_b550_e_gaming),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX B550-I GAMING",
+					&board_info_strix_b550_i_gaming),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX X570-E GAMING",
+					&board_info_strix_x570_e_gaming),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX X570-E GAMING WIFI II",
+					&board_info_strix_x570_e_gaming_wifi_ii),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX X570-F GAMING",
+					&board_info_strix_x570_f_gaming),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX X570-I GAMING",
+					&board_info_strix_x570_i_gaming),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX Z690-A GAMING WIFI D4",
+					&board_info_strix_z690_a_gaming_wifi_d4),
+	DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG ZENITH II EXTREME",
+					&board_info_zenith_ii_extreme),
+	{},
 };
 
 struct ec_sensor {
@@ -537,12 +577,12 @@ static int find_ec_sensor_index(const struct ec_sensors_data *ec,
 	return -ENOENT;
 }
 
-static int __init bank_compare(const void *a, const void *b)
+static int bank_compare(const void *a, const void *b)
 {
 	return *((const s8 *)a) - *((const s8 *)b);
 }
 
-static void __init setup_sensor_data(struct ec_sensors_data *ec)
+static void setup_sensor_data(struct ec_sensors_data *ec)
 {
 	struct ec_sensor *s = ec->sensors;
 	bool bank_found;
@@ -574,7 +614,7 @@ static void __init setup_sensor_data(struct ec_sensors_data *ec)
 	sort(ec->banks, ec->nr_banks, 1, bank_compare, NULL);
 }
 
-static void __init fill_ec_registers(struct ec_sensors_data *ec)
+static void fill_ec_registers(struct ec_sensors_data *ec)
 {
 	const struct ec_sensor_info *si;
 	unsigned int i, j, register_idx = 0;
@@ -589,7 +629,7 @@ static void __init fill_ec_registers(struct ec_sensors_data *ec)
 	}
 }
 
-static int __init setup_lock_data(struct device *dev)
+static int setup_lock_data(struct device *dev)
 {
 	const char *mutex_path;
 	int status;
@@ -812,7 +852,7 @@ static umode_t asus_ec_hwmon_is_visible(const void *drvdata,
 	return find_ec_sensor_index(state, type, channel) >= 0 ? S_IRUGO : 0;
 }
 
-static int __init
+static int
 asus_ec_hwmon_add_chan_info(struct hwmon_channel_info *asus_ec_hwmon_chan,
 			     struct device *dev, int num,
 			     enum hwmon_sensor_types type, u32 config)
@@ -841,27 +881,15 @@ static struct hwmon_chip_info asus_ec_chip_info = {
 	.ops = &asus_ec_hwmon_ops,
 };
 
-static const struct ec_board_info * __init get_board_info(void)
+static const struct ec_board_info *get_board_info(void)
 {
-	const char *dmi_board_vendor = dmi_get_system_info(DMI_BOARD_VENDOR);
-	const char *dmi_board_name = dmi_get_system_info(DMI_BOARD_NAME);
-	const struct ec_board_info *board;
-
-	if (!dmi_board_vendor || !dmi_board_name ||
-	    strcasecmp(dmi_board_vendor, "ASUSTeK COMPUTER INC."))
-		return NULL;
-
-	for (board = board_info; board->sensors; board++) {
-		if (match_string(board->board_names,
-				 MAX_IDENTICAL_BOARD_VARIATIONS,
-				 dmi_board_name) >= 0)
-			return board;
-	}
+	const struct dmi_system_id *dmi_entry;
 
-	return NULL;
+	dmi_entry = dmi_first_match(dmi_table);
+	return dmi_entry ? dmi_entry->driver_data : NULL;
 }
 
-static int __init asus_ec_probe(struct platform_device *pdev)
+static int asus_ec_probe(struct platform_device *pdev)
 {
 	const struct hwmon_channel_info **ptr_asus_ec_ci;
 	int nr_count[hwmon_max] = { 0 }, nr_types = 0;
@@ -970,29 +998,37 @@ static int __init asus_ec_probe(struct platform_device *pdev)
 	return PTR_ERR_OR_ZERO(hwdev);
 }
 
-
-static const struct acpi_device_id acpi_ec_ids[] = {
-	/* Embedded Controller Device */
-	{ "PNP0C09", 0 },
-	{}
-};
+MODULE_DEVICE_TABLE(dmi, dmi_table);
 
 static struct platform_driver asus_ec_sensors_platform_driver = {
 	.driver = {
 		.name	= "asus-ec-sensors",
-		.acpi_match_table = acpi_ec_ids,
 	},
+	.probe = asus_ec_probe,
 };
 
-MODULE_DEVICE_TABLE(acpi, acpi_ec_ids);
-/*
- * we use module_platform_driver_probe() rather than module_platform_driver()
- * because the probe function (and its dependants) are marked with __init, which
- * means we can't put it into the .probe member of the platform_driver struct
- * above, and we can't mark the asus_ec_sensors_platform_driver object as __init
- * because the object is referenced from the module exit code.
- */
-module_platform_driver_probe(asus_ec_sensors_platform_driver, asus_ec_probe);
+static struct platform_device *asus_ec_sensors_platform_device;
+
+static int __init asus_ec_init(void)
+{
+	asus_ec_sensors_platform_device =
+		platform_create_bundle(&asus_ec_sensors_platform_driver,
+				       asus_ec_probe, NULL, 0, NULL, 0);
+
+	if (IS_ERR(asus_ec_sensors_platform_device))
+		return PTR_ERR(asus_ec_sensors_platform_device);
+
+	return 0;
+}
+
+static void __exit asus_ec_exit(void)
+{
+	platform_device_unregister(asus_ec_sensors_platform_device);
+	platform_driver_unregister(&asus_ec_sensors_platform_driver);
+}
+
+module_init(asus_ec_init);
+module_exit(asus_ec_exit);
 
 module_param_named(mutex_path, mutex_path_override, charp, 0);
 MODULE_PARM_DESC(mutex_path,
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index befe989ca7b9..fbf3f5a4ecb6 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -391,6 +391,9 @@ static int gpio_fan_set_cur_state(struct thermal_cooling_device *cdev,
 	if (!fan_data)
 		return -EINVAL;
 
+	if (state >= fan_data->num_speed)
+		return -EINVAL;
+
 	set_fan_speed(fan_data, state);
 	return 0;
 }
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 2e2cd79d89eb..4218750d5a66 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -151,9 +151,9 @@ static DEFINE_IDA(hwmon_ida);
  * between hwmon and thermal_sys modules.
  */
 #ifdef CONFIG_THERMAL_OF
-static int hwmon_thermal_get_temp(void *data, int *temp)
+static int hwmon_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct hwmon_thermal_data *tdata = data;
+	struct hwmon_thermal_data *tdata = tz->devdata;
 	struct hwmon_device *hwdev = to_hwmon_device(tdata->dev);
 	int ret;
 	long t;
@@ -168,9 +168,9 @@ static int hwmon_thermal_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static int hwmon_thermal_set_trips(void *data, int low, int high)
+static int hwmon_thermal_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	struct hwmon_thermal_data *tdata = data;
+	struct hwmon_thermal_data *tdata = tz->devdata;
 	struct hwmon_device *hwdev = to_hwmon_device(tdata->dev);
 	const struct hwmon_chip_info *chip = hwdev->chip;
 	const struct hwmon_channel_info **info = chip->info;
@@ -203,7 +203,7 @@ static int hwmon_thermal_set_trips(void *data, int low, int high)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops hwmon_thermal_ops = {
+static const struct thermal_zone_device_ops hwmon_thermal_ops = {
 	.get_temp = hwmon_thermal_get_temp,
 	.set_trips = hwmon_thermal_set_trips,
 };
@@ -227,8 +227,8 @@ static int hwmon_thermal_add_sensor(struct device *dev, int index)
 	tdata->dev = dev;
 	tdata->index = index;
 
-	tzd = devm_thermal_zone_of_sensor_register(dev, index, tdata,
-						   &hwmon_thermal_ops);
+	tzd = devm_thermal_of_zone_register(dev, index, tdata,
+					    &hwmon_thermal_ops);
 	if (IS_ERR(tzd)) {
 		if (PTR_ERR(tzd) != -ENODEV)
 			return PTR_ERR(tzd);
diff --git a/drivers/hwmon/mr75203.c b/drivers/hwmon/mr75203.c
index 26278b0f17a9..9259779cc2df 100644
--- a/drivers/hwmon/mr75203.c
+++ b/drivers/hwmon/mr75203.c
@@ -68,8 +68,9 @@
 
 /* VM Individual Macro Register */
 #define VM_COM_REG_SIZE	0x200
-#define VM_SDIF_DONE(n)	(VM_COM_REG_SIZE + 0x34 + 0x200 * (n))
-#define VM_SDIF_DATA(n)	(VM_COM_REG_SIZE + 0x40 + 0x200 * (n))
+#define VM_SDIF_DONE(vm)	(VM_COM_REG_SIZE + 0x34 + 0x200 * (vm))
+#define VM_SDIF_DATA(vm, ch)	\
+	(VM_COM_REG_SIZE + 0x40 + 0x200 * (vm) + 0x4 * (ch))
 
 /* SDA Slave Register */
 #define IP_CTRL			0x00
@@ -115,6 +116,7 @@ struct pvt_device {
 	u32			t_num;
 	u32			p_num;
 	u32			v_num;
+	u32			c_num;
 	u32			ip_freq;
 	u8			*vm_idx;
 };
@@ -178,14 +180,15 @@ static int pvt_read_in(struct device *dev, u32 attr, int channel, long *val)
 {
 	struct pvt_device *pvt = dev_get_drvdata(dev);
 	struct regmap *v_map = pvt->v_map;
+	u8 vm_idx, ch_idx;
 	u32 n, stat;
-	u8 vm_idx;
 	int ret;
 
-	if (channel >= pvt->v_num)
+	if (channel >= pvt->v_num * pvt->c_num)
 		return -EINVAL;
 
-	vm_idx = pvt->vm_idx[channel];
+	vm_idx = pvt->vm_idx[channel / pvt->c_num];
+	ch_idx = channel % pvt->c_num;
 
 	switch (attr) {
 	case hwmon_in_input:
@@ -196,13 +199,23 @@ static int pvt_read_in(struct device *dev, u32 attr, int channel, long *val)
 		if (ret)
 			return ret;
 
-		ret = regmap_read(v_map, VM_SDIF_DATA(vm_idx), &n);
+		ret = regmap_read(v_map, VM_SDIF_DATA(vm_idx, ch_idx), &n);
 		if(ret < 0)
 			return ret;
 
 		n &= SAMPLE_DATA_MSK;
-		/* Convert the N bitstream count into voltage */
-		*val = (PVT_N_CONST * n - PVT_R_CONST) >> PVT_CONV_BITS;
+		/*
+		 * Convert the N bitstream count into voltage.
+		 * To support negative voltage calculation for 64bit machines
+		 * n must be cast to long, since n and *val differ both in
+		 * signedness and in size.
+		 * Division is used instead of right shift, because for signed
+		 * numbers, the sign bit is used to fill the vacated bit
+		 * positions, and if the number is negative, 1 is used.
+		 * BIT(x) may not be used instead of (1 << x) because it's
+		 * unsigned.
+		 */
+		*val = (PVT_N_CONST * (long)n - PVT_R_CONST) / (1 << PVT_CONV_BITS);
 
 		return 0;
 	default:
@@ -375,6 +388,19 @@ static int pvt_init(struct pvt_device *pvt)
 		if (ret)
 			return ret;
 
+		val = (BIT(pvt->c_num) - 1) | VM_CH_INIT |
+		      IP_POLL << SDIF_ADDR_SFT | SDIF_WRN_W | SDIF_PROG;
+		ret = regmap_write(v_map, SDIF_W, val);
+		if (ret < 0)
+			return ret;
+
+		ret = regmap_read_poll_timeout(v_map, SDIF_STAT,
+					       val, !(val & SDIF_BUSY),
+					       PVT_POLL_DELAY_US,
+					       PVT_POLL_TIMEOUT_US);
+		if (ret)
+			return ret;
+
 		val = CFG1_VOL_MEAS_MODE | CFG1_PARALLEL_OUT |
 		      CFG1_14_BIT | IP_CFG << SDIF_ADDR_SFT |
 		      SDIF_WRN_W | SDIF_PROG;
@@ -489,8 +515,8 @@ static int pvt_reset_control_deassert(struct device *dev, struct pvt_device *pvt
 
 static int mr75203_probe(struct platform_device *pdev)
 {
+	u32 ts_num, vm_num, pd_num, ch_num, val, index, i;
 	const struct hwmon_channel_info **pvt_info;
-	u32 ts_num, vm_num, pd_num, val, index, i;
 	struct device *dev = &pdev->dev;
 	u32 *temp_config, *in_config;
 	struct device *hwmon_dev;
@@ -531,9 +557,11 @@ static int mr75203_probe(struct platform_device *pdev)
 	ts_num = (val & TS_NUM_MSK) >> TS_NUM_SFT;
 	pd_num = (val & PD_NUM_MSK) >> PD_NUM_SFT;
 	vm_num = (val & VM_NUM_MSK) >> VM_NUM_SFT;
+	ch_num = (val & CH_NUM_MSK) >> CH_NUM_SFT;
 	pvt->t_num = ts_num;
 	pvt->p_num = pd_num;
 	pvt->v_num = vm_num;
+	pvt->c_num = ch_num;
 	val = 0;
 	if (ts_num)
 		val++;
@@ -570,7 +598,7 @@ static int mr75203_probe(struct platform_device *pdev)
 	}
 
 	if (vm_num) {
-		u32 num = vm_num;
+		u32 total_ch;
 
 		ret = pvt_get_regmap(pdev, "vm", pvt);
 		if (ret)
@@ -584,30 +612,30 @@ static int mr75203_probe(struct platform_device *pdev)
 		ret = device_property_read_u8_array(dev, "intel,vm-map",
 						    pvt->vm_idx, vm_num);
 		if (ret) {
-			num = 0;
+			/*
+			 * Incase intel,vm-map property is not defined, we
+			 * assume incremental channel numbers.
+			 */
+			for (i = 0; i < vm_num; i++)
+				pvt->vm_idx[i] = i;
 		} else {
 			for (i = 0; i < vm_num; i++)
 				if (pvt->vm_idx[i] >= vm_num ||
 				    pvt->vm_idx[i] == 0xff) {
-					num = i;
+					pvt->v_num = i;
+					vm_num = i;
 					break;
 				}
 		}
 
-		/*
-		 * Incase intel,vm-map property is not defined, we assume
-		 * incremental channel numbers.
-		 */
-		for (i = num; i < vm_num; i++)
-			pvt->vm_idx[i] = i;
-
-		in_config = devm_kcalloc(dev, num + 1,
+		total_ch = ch_num * vm_num;
+		in_config = devm_kcalloc(dev, total_ch + 1,
 					 sizeof(*in_config), GFP_KERNEL);
 		if (!in_config)
 			return -ENOMEM;
 
-		memset32(in_config, HWMON_I_INPUT, num);
-		in_config[num] = 0;
+		memset32(in_config, HWMON_I_INPUT, total_ch);
+		in_config[total_ch] = 0;
 		pvt_in.config = in_config;
 
 		pvt_info[index++] = &pvt_in;
diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c
index f10bac8860fc..7ec04934747e 100644
--- a/drivers/hwmon/pmbus/pmbus_core.c
+++ b/drivers/hwmon/pmbus/pmbus_core.c
@@ -1270,9 +1270,9 @@ struct pmbus_thermal_data {
 	struct pmbus_sensor *sensor;
 };
 
-static int pmbus_thermal_get_temp(void *data, int *temp)
+static int pmbus_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct pmbus_thermal_data *tdata = data;
+	struct pmbus_thermal_data *tdata = tz->devdata;
 	struct pmbus_sensor *sensor = tdata->sensor;
 	struct pmbus_data *pmbus_data = tdata->pmbus_data;
 	struct i2c_client *client = to_i2c_client(pmbus_data->dev);
@@ -1296,7 +1296,7 @@ static int pmbus_thermal_get_temp(void *data, int *temp)
 	return ret;
 }
 
-static const struct thermal_zone_of_device_ops pmbus_thermal_ops = {
+static const struct thermal_zone_device_ops pmbus_thermal_ops = {
 	.get_temp = pmbus_thermal_get_temp,
 };
 
@@ -1314,8 +1314,8 @@ static int pmbus_thermal_add_sensor(struct pmbus_data *pmbus_data,
 	tdata->sensor = sensor;
 	tdata->pmbus_data = pmbus_data;
 
-	tzd = devm_thermal_zone_of_sensor_register(dev, index, tdata,
-						   &pmbus_thermal_ops);
+	tzd = devm_thermal_of_zone_register(dev, index, tdata,
+					    &pmbus_thermal_ops);
 	/*
 	 * If CONFIG_THERMAL_OF is disabled, this returns -ENODEV,
 	 * so ignore that error but forward any other error.
@@ -2861,7 +2861,7 @@ static int pmbus_regulator_get_low_margin(struct i2c_client *client, int page)
 		.data = -1,
 	};
 
-	if (!data->vout_low[page]) {
+	if (data->vout_low[page] < 0) {
 		if (pmbus_check_word_register(client, page, PMBUS_MFR_VOUT_MIN))
 			s.data = _pmbus_read_word_data(client, page, 0xff,
 						       PMBUS_MFR_VOUT_MIN);
@@ -2887,7 +2887,7 @@ static int pmbus_regulator_get_high_margin(struct i2c_client *client, int page)
 		.data = -1,
 	};
 
-	if (!data->vout_high[page]) {
+	if (data->vout_high[page] < 0) {
 		if (pmbus_check_word_register(client, page, PMBUS_MFR_VOUT_MAX))
 			s.data = _pmbus_read_word_data(client, page, 0xff,
 						       PMBUS_MFR_VOUT_MAX);
@@ -3016,11 +3016,10 @@ static int pmbus_regulator_register(struct pmbus_data *data)
 
 		rdev = devm_regulator_register(dev, &info->reg_desc[i],
 					       &config);
-		if (IS_ERR(rdev)) {
-			dev_err(dev, "Failed to register %s regulator\n",
-				info->reg_desc[i].name);
-			return PTR_ERR(rdev);
-		}
+		if (IS_ERR(rdev))
+			return dev_err_probe(dev, PTR_ERR(rdev),
+					     "Failed to register %s regulator\n",
+					     info->reg_desc[i].name);
 	}
 
 	return 0;
@@ -3320,6 +3319,7 @@ int pmbus_do_probe(struct i2c_client *client, struct pmbus_driver_info *info)
 	struct pmbus_data *data;
 	size_t groups_num = 0;
 	int ret;
+	int i;
 	char *name;
 
 	if (!info)
@@ -3353,6 +3353,11 @@ int pmbus_do_probe(struct i2c_client *client, struct pmbus_driver_info *info)
 	data->currpage = -1;
 	data->currphase = -1;
 
+	for (i = 0; i < ARRAY_SIZE(data->vout_low); i++) {
+		data->vout_low[i] = -1;
+		data->vout_high[i] = -1;
+	}
+
 	ret = pmbus_init_common(client, data, info);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/hwmon/scpi-hwmon.c b/drivers/hwmon/scpi-hwmon.c
index 5187c6dd5a4f..4d75385f7d5e 100644
--- a/drivers/hwmon/scpi-hwmon.c
+++ b/drivers/hwmon/scpi-hwmon.c
@@ -62,9 +62,9 @@ static void scpi_scale_reading(u64 *value, struct sensor_data *sensor)
 	}
 }
 
-static int scpi_read_temp(void *dev, int *temp)
+static int scpi_read_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct scpi_thermal_zone *zone = dev;
+	struct scpi_thermal_zone *zone = tz->devdata;
 	struct scpi_sensors *scpi_sensors = zone->scpi_sensors;
 	struct scpi_ops *scpi_ops = scpi_sensors->scpi_ops;
 	struct sensor_data *sensor = &scpi_sensors->data[zone->sensor_id];
@@ -121,7 +121,7 @@ scpi_show_label(struct device *dev, struct device_attribute *attr, char *buf)
 	return sprintf(buf, "%s\n", sensor->info.name);
 }
 
-static const struct thermal_zone_of_device_ops scpi_sensor_ops = {
+static const struct thermal_zone_device_ops scpi_sensor_ops = {
 	.get_temp = scpi_read_temp,
 };
 
@@ -275,10 +275,10 @@ static int scpi_hwmon_probe(struct platform_device *pdev)
 
 		zone->sensor_id = i;
 		zone->scpi_sensors = scpi_sensors;
-		z = devm_thermal_zone_of_sensor_register(dev,
-							 sensor->info.sensor_id,
-							 zone,
-							 &scpi_sensor_ops);
+		z = devm_thermal_of_zone_register(dev,
+						  sensor->info.sensor_id,
+						  zone,
+						  &scpi_sensor_ops);
 		/*
 		 * The call to thermal_zone_of_sensor_register returns
 		 * an error for sensors that are not associated with
diff --git a/drivers/hwmon/tps23861.c b/drivers/hwmon/tps23861.c
index 42762e87b014..f7c59ff7ae8e 100644
--- a/drivers/hwmon/tps23861.c
+++ b/drivers/hwmon/tps23861.c
@@ -493,18 +493,20 @@ static char *tps23861_port_poe_plus_status(struct tps23861_data *data, int port)
 
 static int tps23861_port_resistance(struct tps23861_data *data, int port)
 {
-	u16 regval;
+	unsigned int raw_val;
+	__le16 regval;
 
 	regmap_bulk_read(data->regmap,
 			 PORT_1_RESISTANCE_LSB + PORT_N_RESISTANCE_LSB_OFFSET * (port - 1),
 			 &regval,
 			 2);
 
-	switch (FIELD_GET(PORT_RESISTANCE_RSN_MASK, regval)) {
+	raw_val = le16_to_cpu(regval);
+	switch (FIELD_GET(PORT_RESISTANCE_RSN_MASK, raw_val)) {
 	case PORT_RESISTANCE_RSN_OTHER:
-		return (FIELD_GET(PORT_RESISTANCE_MASK, regval) * RESISTANCE_LSB) / 10000;
+		return (FIELD_GET(PORT_RESISTANCE_MASK, raw_val) * RESISTANCE_LSB) / 10000;
 	case PORT_RESISTANCE_RSN_LOW:
-		return (FIELD_GET(PORT_RESISTANCE_MASK, regval) * RESISTANCE_LSB_LOW) / 10000;
+		return (FIELD_GET(PORT_RESISTANCE_MASK, raw_val) * RESISTANCE_LSB_LOW) / 10000;
 	case PORT_RESISTANCE_RSN_SHORT:
 	case PORT_RESISTANCE_RSN_OPEN:
 	default:
diff --git a/drivers/i2c/busses/i2c-amd-mp2-plat.c b/drivers/i2c/busses/i2c-amd-mp2-plat.c
index 84b7e6cbc67b..423fe0c8a471 100644
--- a/drivers/i2c/busses/i2c-amd-mp2-plat.c
+++ b/drivers/i2c/busses/i2c-amd-mp2-plat.c
@@ -244,14 +244,18 @@ static const struct i2c_adapter_quirks amd_i2c_dev_quirks = {
 
 static int i2c_amd_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
 	int ret;
 	struct amd_i2c_dev *i2c_dev;
-	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
 	struct amd_mp2_dev *mp2_dev;
-	const char *uid;
+	u64 uid;
 
-	if (!adev)
-		return -ENODEV;
+	ret = acpi_dev_uid_to_integer(ACPI_COMPANION(dev), &uid);
+	if (ret)
+		return dev_err_probe(dev, ret, "missing UID/bus id!\n");
+	if (uid >= 2)
+		return dev_err_probe(dev, -EINVAL, "incorrect UID/bus id \"%llu\"!\n", uid);
+	dev_dbg(dev, "bus id is %llu\n", uid);
 
 	/* The ACPI namespace doesn't contain information about which MP2 PCI
 	 * device an AMDI0011 ACPI device is related to, so assume that there's
@@ -266,6 +270,7 @@ static int i2c_amd_probe(struct platform_device *pdev)
 	if (!i2c_dev)
 		return -ENOMEM;
 
+	i2c_dev->common.bus_id = uid;
 	i2c_dev->common.mp2_dev = mp2_dev;
 	i2c_dev->pdev = pdev;
 	platform_set_drvdata(pdev, i2c_dev);
@@ -276,20 +281,6 @@ static int i2c_amd_probe(struct platform_device *pdev)
 	i2c_dev->common.resume = &i2c_amd_resume;
 #endif
 
-	uid = adev->pnp.unique_id;
-	if (!uid) {
-		dev_err(&pdev->dev, "missing UID/bus id!\n");
-		return -EINVAL;
-	} else if (strcmp(uid, "0") == 0) {
-		i2c_dev->common.bus_id = 0;
-	} else if (strcmp(uid, "1") == 0) {
-		i2c_dev->common.bus_id = 1;
-	} else {
-		dev_err(&pdev->dev, "incorrect UID/bus id \"%s\"!\n", uid);
-		return -EINVAL;
-	}
-	dev_dbg(&pdev->dev, "bus id is %u\n", i2c_dev->common.bus_id);
-
 	/* Register the adapter */
 	amd_mp2_pm_runtime_get(mp2_dev);
 
diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c
index 471c47db546b..c836cf884185 100644
--- a/drivers/i2c/busses/i2c-davinci.c
+++ b/drivers/i2c/busses/i2c-davinci.c
@@ -823,7 +823,7 @@ static int davinci_i2c_probe(struct platform_device *pdev)
 	r = pm_runtime_resume_and_get(dev->dev);
 	if (r < 0) {
 		dev_err(dev->dev, "failed to runtime_get device: %d\n", r);
-		return r;
+		goto err_pm;
 	}
 
 	i2c_davinci_init(dev);
@@ -882,6 +882,7 @@ static int davinci_i2c_probe(struct platform_device *pdev)
 err_unuse_clocks:
 	pm_runtime_dont_use_autosuspend(dev->dev);
 	pm_runtime_put_sync(dev->dev);
+err_pm:
 	pm_runtime_disable(dev->dev);
 
 	return r;
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 78fb1a4274a6..3082183bd66a 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1572,9 +1572,7 @@ static int i2c_imx_remove(struct platform_device *pdev)
 	struct imx_i2c_struct *i2c_imx = platform_get_drvdata(pdev);
 	int irq, ret;
 
-	ret = pm_runtime_resume_and_get(&pdev->dev);
-	if (ret < 0)
-		return ret;
+	ret = pm_runtime_get_sync(&pdev->dev);
 
 	hrtimer_cancel(&i2c_imx->slave_timer);
 
@@ -1585,17 +1583,21 @@ static int i2c_imx_remove(struct platform_device *pdev)
 	if (i2c_imx->dma)
 		i2c_imx_dma_free(i2c_imx);
 
-	/* setup chip registers to defaults */
-	imx_i2c_write_reg(0, i2c_imx, IMX_I2C_IADR);
-	imx_i2c_write_reg(0, i2c_imx, IMX_I2C_IFDR);
-	imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2CR);
-	imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2SR);
+	if (ret >= 0) {
+		/* setup chip registers to defaults */
+		imx_i2c_write_reg(0, i2c_imx, IMX_I2C_IADR);
+		imx_i2c_write_reg(0, i2c_imx, IMX_I2C_IFDR);
+		imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2CR);
+		imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2SR);
+		clk_disable(i2c_imx->clk);
+	}
 
 	clk_notifier_unregister(i2c_imx->clk, &i2c_imx->clk_change_nb);
 	irq = platform_get_irq(pdev, 0);
 	if (irq >= 0)
 		free_irq(irq, i2c_imx);
-	clk_disable_unprepare(i2c_imx->clk);
+
+	clk_unprepare(i2c_imx->clk);
 
 	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
diff --git a/drivers/i2c/busses/i2c-mlxbf.c b/drivers/i2c/busses/i2c-mlxbf.c
index 8716032f030a..60908c5737f1 100644
--- a/drivers/i2c/busses/i2c-mlxbf.c
+++ b/drivers/i2c/busses/i2c-mlxbf.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/bitfield.h>
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
@@ -63,13 +64,14 @@
  */
 #define MLXBF_I2C_TYU_PLL_OUT_FREQ  (400 * 1000 * 1000)
 /* Reference clock for Bluefield - 156 MHz. */
-#define MLXBF_I2C_PLL_IN_FREQ       (156 * 1000 * 1000)
+#define MLXBF_I2C_PLL_IN_FREQ       156250000ULL
 
 /* Constant used to determine the PLL frequency. */
-#define MLNXBF_I2C_COREPLL_CONST    16384
+#define MLNXBF_I2C_COREPLL_CONST    16384ULL
+
+#define MLXBF_I2C_FREQUENCY_1GHZ  1000000000ULL
 
 /* PLL registers. */
-#define MLXBF_I2C_CORE_PLL_REG0         0x0
 #define MLXBF_I2C_CORE_PLL_REG1         0x4
 #define MLXBF_I2C_CORE_PLL_REG2         0x8
 
@@ -181,22 +183,15 @@
 #define MLXBF_I2C_COREPLL_FREQ          MLXBF_I2C_TYU_PLL_OUT_FREQ
 
 /* Core PLL TYU configuration. */
-#define MLXBF_I2C_COREPLL_CORE_F_TYU_MASK   GENMASK(12, 0)
-#define MLXBF_I2C_COREPLL_CORE_OD_TYU_MASK  GENMASK(3, 0)
-#define MLXBF_I2C_COREPLL_CORE_R_TYU_MASK   GENMASK(5, 0)
-
-#define MLXBF_I2C_COREPLL_CORE_F_TYU_SHIFT  3
-#define MLXBF_I2C_COREPLL_CORE_OD_TYU_SHIFT 16
-#define MLXBF_I2C_COREPLL_CORE_R_TYU_SHIFT  20
+#define MLXBF_I2C_COREPLL_CORE_F_TYU_MASK   GENMASK(15, 3)
+#define MLXBF_I2C_COREPLL_CORE_OD_TYU_MASK  GENMASK(19, 16)
+#define MLXBF_I2C_COREPLL_CORE_R_TYU_MASK   GENMASK(25, 20)
 
 /* Core PLL YU configuration. */
 #define MLXBF_I2C_COREPLL_CORE_F_YU_MASK    GENMASK(25, 0)
 #define MLXBF_I2C_COREPLL_CORE_OD_YU_MASK   GENMASK(3, 0)
-#define MLXBF_I2C_COREPLL_CORE_R_YU_MASK    GENMASK(5, 0)
+#define MLXBF_I2C_COREPLL_CORE_R_YU_MASK    GENMASK(31, 26)
 
-#define MLXBF_I2C_COREPLL_CORE_F_YU_SHIFT   0
-#define MLXBF_I2C_COREPLL_CORE_OD_YU_SHIFT  1
-#define MLXBF_I2C_COREPLL_CORE_R_YU_SHIFT   26
 
 /* Core PLL frequency. */
 static u64 mlxbf_i2c_corepll_frequency;
@@ -479,8 +474,6 @@ static struct mutex mlxbf_i2c_bus_lock;
 #define MLXBF_I2C_MASK_8    GENMASK(7, 0)
 #define MLXBF_I2C_MASK_16   GENMASK(15, 0)
 
-#define MLXBF_I2C_FREQUENCY_1GHZ  1000000000
-
 /*
  * Function to poll a set of bits at a specific address; it checks whether
  * the bits are equal to zero when eq_zero is set to 'true', and not equal
@@ -669,7 +662,7 @@ static int mlxbf_i2c_smbus_enable(struct mlxbf_i2c_priv *priv, u8 slave,
 	/* Clear status bits. */
 	writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_STATUS);
 	/* Set the cause data. */
-	writel(~0x0, priv->smbus->io + MLXBF_I2C_CAUSE_OR_CLEAR);
+	writel(~0x0, priv->mst_cause->io + MLXBF_I2C_CAUSE_OR_CLEAR);
 	/* Zero PEC byte. */
 	writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_PEC);
 	/* Zero byte count. */
@@ -738,6 +731,9 @@ mlxbf_i2c_smbus_start_transaction(struct mlxbf_i2c_priv *priv,
 		if (flags & MLXBF_I2C_F_WRITE) {
 			write_en = 1;
 			write_len += operation->length;
+			if (data_idx + operation->length >
+					MLXBF_I2C_MASTER_DATA_DESC_SIZE)
+				return -ENOBUFS;
 			memcpy(data_desc + data_idx,
 			       operation->buffer, operation->length);
 			data_idx += operation->length;
@@ -1407,24 +1403,19 @@ static int mlxbf_i2c_init_master(struct platform_device *pdev,
 	return 0;
 }
 
-static u64 mlxbf_calculate_freq_from_tyu(struct mlxbf_i2c_resource *corepll_res)
+static u64 mlxbf_i2c_calculate_freq_from_tyu(struct mlxbf_i2c_resource *corepll_res)
 {
-	u64 core_frequency, pad_frequency;
+	u64 core_frequency;
 	u8 core_od, core_r;
 	u32 corepll_val;
 	u16 core_f;
 
-	pad_frequency = MLXBF_I2C_PLL_IN_FREQ;
-
 	corepll_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG1);
 
 	/* Get Core PLL configuration bits. */
-	core_f = rol32(corepll_val, MLXBF_I2C_COREPLL_CORE_F_TYU_SHIFT) &
-			MLXBF_I2C_COREPLL_CORE_F_TYU_MASK;
-	core_od = rol32(corepll_val, MLXBF_I2C_COREPLL_CORE_OD_TYU_SHIFT) &
-			MLXBF_I2C_COREPLL_CORE_OD_TYU_MASK;
-	core_r = rol32(corepll_val, MLXBF_I2C_COREPLL_CORE_R_TYU_SHIFT) &
-			MLXBF_I2C_COREPLL_CORE_R_TYU_MASK;
+	core_f = FIELD_GET(MLXBF_I2C_COREPLL_CORE_F_TYU_MASK, corepll_val);
+	core_od = FIELD_GET(MLXBF_I2C_COREPLL_CORE_OD_TYU_MASK, corepll_val);
+	core_r = FIELD_GET(MLXBF_I2C_COREPLL_CORE_R_TYU_MASK, corepll_val);
 
 	/*
 	 * Compute PLL output frequency as follow:
@@ -1436,31 +1427,26 @@ static u64 mlxbf_calculate_freq_from_tyu(struct mlxbf_i2c_resource *corepll_res)
 	 * Where PLL_OUT_FREQ and PLL_IN_FREQ refer to CoreFrequency
 	 * and PadFrequency, respectively.
 	 */
-	core_frequency = pad_frequency * (++core_f);
+	core_frequency = MLXBF_I2C_PLL_IN_FREQ * (++core_f);
 	core_frequency /= (++core_r) * (++core_od);
 
 	return core_frequency;
 }
 
-static u64 mlxbf_calculate_freq_from_yu(struct mlxbf_i2c_resource *corepll_res)
+static u64 mlxbf_i2c_calculate_freq_from_yu(struct mlxbf_i2c_resource *corepll_res)
 {
 	u32 corepll_reg1_val, corepll_reg2_val;
-	u64 corepll_frequency, pad_frequency;
+	u64 corepll_frequency;
 	u8 core_od, core_r;
 	u32 core_f;
 
-	pad_frequency = MLXBF_I2C_PLL_IN_FREQ;
-
 	corepll_reg1_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG1);
 	corepll_reg2_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG2);
 
 	/* Get Core PLL configuration bits */
-	core_f = rol32(corepll_reg1_val, MLXBF_I2C_COREPLL_CORE_F_YU_SHIFT) &
-			MLXBF_I2C_COREPLL_CORE_F_YU_MASK;
-	core_r = rol32(corepll_reg1_val, MLXBF_I2C_COREPLL_CORE_R_YU_SHIFT) &
-			MLXBF_I2C_COREPLL_CORE_R_YU_MASK;
-	core_od = rol32(corepll_reg2_val,  MLXBF_I2C_COREPLL_CORE_OD_YU_SHIFT) &
-			MLXBF_I2C_COREPLL_CORE_OD_YU_MASK;
+	core_f = FIELD_GET(MLXBF_I2C_COREPLL_CORE_F_YU_MASK, corepll_reg1_val);
+	core_r = FIELD_GET(MLXBF_I2C_COREPLL_CORE_R_YU_MASK, corepll_reg1_val);
+	core_od = FIELD_GET(MLXBF_I2C_COREPLL_CORE_OD_YU_MASK, corepll_reg2_val);
 
 	/*
 	 * Compute PLL output frequency as follow:
@@ -1472,7 +1458,7 @@ static u64 mlxbf_calculate_freq_from_yu(struct mlxbf_i2c_resource *corepll_res)
 	 * Where PLL_OUT_FREQ and PLL_IN_FREQ refer to CoreFrequency
 	 * and PadFrequency, respectively.
 	 */
-	corepll_frequency = (pad_frequency * core_f) / MLNXBF_I2C_COREPLL_CONST;
+	corepll_frequency = (MLXBF_I2C_PLL_IN_FREQ * core_f) / MLNXBF_I2C_COREPLL_CONST;
 	corepll_frequency /= (++core_r) * (++core_od);
 
 	return corepll_frequency;
@@ -2180,14 +2166,14 @@ static struct mlxbf_i2c_chip_info mlxbf_i2c_chip[] = {
 			[1] = &mlxbf_i2c_corepll_res[MLXBF_I2C_CHIP_TYPE_1],
 			[2] = &mlxbf_i2c_gpio_res[MLXBF_I2C_CHIP_TYPE_1]
 		},
-		.calculate_freq = mlxbf_calculate_freq_from_tyu
+		.calculate_freq = mlxbf_i2c_calculate_freq_from_tyu
 	},
 	[MLXBF_I2C_CHIP_TYPE_2] = {
 		.type = MLXBF_I2C_CHIP_TYPE_2,
 		.shared_res = {
 			[0] = &mlxbf_i2c_corepll_res[MLXBF_I2C_CHIP_TYPE_2]
 		},
-		.calculate_freq = mlxbf_calculate_freq_from_yu
+		.calculate_freq = mlxbf_i2c_calculate_freq_from_yu
 	}
 };
 
@@ -2229,35 +2215,27 @@ MODULE_DEVICE_TABLE(acpi, mlxbf_i2c_acpi_ids);
 static int mlxbf_i2c_acpi_probe(struct device *dev, struct mlxbf_i2c_priv *priv)
 {
 	const struct acpi_device_id *aid;
-	struct acpi_device *adev;
-	unsigned long bus_id = 0;
-	const char *uid;
+	u64 bus_id;
 	int ret;
 
 	if (acpi_disabled)
 		return -ENOENT;
 
-	adev = ACPI_COMPANION(dev);
-	if (!adev)
-		return -ENXIO;
-
 	aid = acpi_match_device(mlxbf_i2c_acpi_ids, dev);
 	if (!aid)
 		return -ENODEV;
 
 	priv->chip = (struct mlxbf_i2c_chip_info *)aid->driver_data;
 
-	uid = acpi_device_uid(adev);
-	if (!uid || !(*uid)) {
+	ret = acpi_dev_uid_to_integer(ACPI_COMPANION(dev), &bus_id);
+	if (ret) {
 		dev_err(dev, "Cannot retrieve UID\n");
-		return -ENODEV;
+		return ret;
 	}
 
-	ret = kstrtoul(uid, 0, &bus_id);
-	if (!ret)
-		priv->bus = bus_id;
+	priv->bus = bus_id;
 
-	return ret;
+	return 0;
 }
 #else
 static int mlxbf_i2c_acpi_probe(struct device *dev, struct mlxbf_i2c_priv *priv)
diff --git a/drivers/i2c/busses/i2c-scmi.c b/drivers/i2c/busses/i2c-scmi.c
index 79798fc7462a..6746aa46d96c 100644
--- a/drivers/i2c/busses/i2c-scmi.c
+++ b/drivers/i2c/busses/i2c-scmi.c
@@ -30,7 +30,7 @@ struct acpi_smbus_cmi {
 	u8 cap_info:1;
 	u8 cap_read:1;
 	u8 cap_write:1;
-	const struct smbus_methods_t *methods;
+	struct smbus_methods_t *methods;
 };
 
 static const struct smbus_methods_t smbus_methods = {
@@ -361,6 +361,7 @@ static acpi_status acpi_smbus_cmi_query_methods(acpi_handle handle, u32 level,
 static int acpi_smbus_cmi_add(struct acpi_device *device)
 {
 	struct acpi_smbus_cmi *smbus_cmi;
+	const struct acpi_device_id *id;
 	int ret;
 
 	smbus_cmi = kzalloc(sizeof(struct acpi_smbus_cmi), GFP_KERNEL);
@@ -368,7 +369,6 @@ static int acpi_smbus_cmi_add(struct acpi_device *device)
 		return -ENOMEM;
 
 	smbus_cmi->handle = device->handle;
-	smbus_cmi->methods = device_get_match_data(&device->dev);
 	strcpy(acpi_device_name(device), ACPI_SMBUS_HC_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_SMBUS_HC_CLASS);
 	device->driver_data = smbus_cmi;
@@ -376,6 +376,11 @@ static int acpi_smbus_cmi_add(struct acpi_device *device)
 	smbus_cmi->cap_read = 0;
 	smbus_cmi->cap_write = 0;
 
+	for (id = acpi_smbus_cmi_ids; id->id[0]; id++)
+		if (!strcmp(id->id, acpi_device_hid(device)))
+			smbus_cmi->methods =
+				(struct smbus_methods_t *) id->driver_data;
+
 	acpi_walk_namespace(ACPI_TYPE_METHOD, smbus_cmi->handle, 1,
 			    acpi_smbus_cmi_query_methods, NULL, smbus_cmi, NULL);
 
diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c
index 774507b54b57..313904be5f3b 100644
--- a/drivers/i2c/i2c-mux.c
+++ b/drivers/i2c/i2c-mux.c
@@ -243,9 +243,10 @@ struct i2c_mux_core *i2c_mux_alloc(struct i2c_adapter *parent,
 				   int (*deselect)(struct i2c_mux_core *, u32))
 {
 	struct i2c_mux_core *muxc;
+	size_t mux_size;
 
-	muxc = devm_kzalloc(dev, struct_size(muxc, adapter, max_adapters)
-			    + sizeof_priv, GFP_KERNEL);
+	mux_size = struct_size(muxc, adapter, max_adapters);
+	muxc = devm_kzalloc(dev, size_add(mux_size, sizeof_priv), GFP_KERNEL);
 	if (!muxc)
 		return NULL;
 	if (sizeof_priv)
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 3e101719689a..cfeb24d40d37 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -928,6 +928,51 @@ static struct cpuidle_state adl_l_cstates[] __initdata = {
 		.enter = NULL }
 };
 
+static struct cpuidle_state adl_n_cstates[] __initdata = {
+	{
+		.name = "C1",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_UNUSABLE,
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C1E",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 2,
+		.target_residency = 4,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6",
+		.desc = "MWAIT 0x20",
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 195,
+		.target_residency = 585,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C8",
+		.desc = "MWAIT 0x40",
+		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 260,
+		.target_residency = 1040,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C10",
+		.desc = "MWAIT 0x60",
+		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 660,
+		.target_residency = 1980,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.enter = NULL }
+};
+
 static struct cpuidle_state spr_cstates[] __initdata = {
 	{
 		.name = "C1",
@@ -1309,6 +1354,10 @@ static const struct idle_cpu idle_cpu_adl_l __initconst = {
 	.state_table = adl_l_cstates,
 };
 
+static const struct idle_cpu idle_cpu_adl_n __initconst = {
+	.state_table = adl_n_cstates,
+};
+
 static const struct idle_cpu idle_cpu_spr __initconst = {
 	.state_table = spr_cstates,
 	.disable_promotion_to_c1e = true,
@@ -1379,6 +1428,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&idle_cpu_icx),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&idle_cpu_adl),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&idle_cpu_adl_l),
+	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,		&idle_cpu_adl_n),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&idle_cpu_spr),
 	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL,	&idle_cpu_knl),
 	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM,	&idle_cpu_knl),
@@ -1507,7 +1557,7 @@ static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv)
 		state = &drv->states[drv->state_count++];
 
 		snprintf(state->name, CPUIDLE_NAME_LEN, "C%d_ACPI", cstate);
-		strlcpy(state->desc, cx->desc, CPUIDLE_DESC_LEN);
+		strscpy(state->desc, cx->desc, CPUIDLE_DESC_LEN);
 		state->exit_latency = cx->latency;
 		/*
 		 * For C1-type C-states use the same number for both the exit
@@ -1816,6 +1866,7 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 		break;
 	case INTEL_FAM6_ALDERLAKE:
 	case INTEL_FAM6_ALDERLAKE_L:
+	case INTEL_FAM6_ALDERLAKE_N:
 		adl_idle_state_table_update();
 		break;
 	}
diff --git a/drivers/iio/adc/ad7292.c b/drivers/iio/adc/ad7292.c
index 92c68d467c50..a2f9fda25ff3 100644
--- a/drivers/iio/adc/ad7292.c
+++ b/drivers/iio/adc/ad7292.c
@@ -287,10 +287,8 @@ static int ad7292_probe(struct spi_device *spi)
 
 		ret = devm_add_action_or_reset(&spi->dev,
 					       ad7292_regulator_disable, st);
-		if (ret) {
-			regulator_disable(st->reg);
+		if (ret)
 			return ret;
-		}
 
 		ret = regulator_get_voltage(st->reg);
 		if (ret < 0)
diff --git a/drivers/iio/adc/mcp3911.c b/drivers/iio/adc/mcp3911.c
index 1cb4590fe412..890af7dca62d 100644
--- a/drivers/iio/adc/mcp3911.c
+++ b/drivers/iio/adc/mcp3911.c
@@ -40,8 +40,8 @@
 #define MCP3911_CHANNEL(x)		(MCP3911_REG_CHANNEL0 + x * 3)
 #define MCP3911_OFFCAL(x)		(MCP3911_REG_OFFCAL_CH0 + x * 6)
 
-/* Internal voltage reference in uV */
-#define MCP3911_INT_VREF_UV		1200000
+/* Internal voltage reference in mV */
+#define MCP3911_INT_VREF_MV		1200
 
 #define MCP3911_REG_READ(reg, id)	((((reg) << 1) | ((id) << 5) | (1 << 0)) & 0xff)
 #define MCP3911_REG_WRITE(reg, id)	((((reg) << 1) | ((id) << 5) | (0 << 0)) & 0xff)
@@ -113,6 +113,8 @@ static int mcp3911_read_raw(struct iio_dev *indio_dev,
 		if (ret)
 			goto out;
 
+		*val = sign_extend32(*val, 23);
+
 		ret = IIO_VAL_INT;
 		break;
 
@@ -137,11 +139,18 @@ static int mcp3911_read_raw(struct iio_dev *indio_dev,
 
 			*val = ret / 1000;
 		} else {
-			*val = MCP3911_INT_VREF_UV;
+			*val = MCP3911_INT_VREF_MV;
 		}
 
-		*val2 = 24;
-		ret = IIO_VAL_FRACTIONAL_LOG2;
+		/*
+		 * For 24bit Conversion
+		 * Raw = ((Voltage)/(Vref) * 2^23 * Gain * 1.5
+		 * Voltage = Raw * (Vref)/(2^23 * Gain * 1.5)
+		 */
+
+		/* val2 = (2^23 * 1.5) */
+		*val2 = 12582912;
+		ret = IIO_VAL_FRACTIONAL;
 		break;
 	}
 
@@ -208,7 +217,14 @@ static int mcp3911_config(struct mcp3911 *adc)
 	u32 configreg;
 	int ret;
 
-	device_property_read_u32(dev, "device-addr", &adc->dev_addr);
+	ret = device_property_read_u32(dev, "microchip,device-addr", &adc->dev_addr);
+
+	/*
+	 * Fallback to "device-addr" due to historical mismatch between
+	 * dt-bindings and implementation
+	 */
+	if (ret)
+		device_property_read_u32(dev, "device-addr", &adc->dev_addr);
 	if (adc->dev_addr > 3) {
 		dev_err(&adc->spi->dev,
 			"invalid device address (%i). Must be in range 0-3.\n",
diff --git a/drivers/iio/adc/sun4i-gpadc-iio.c b/drivers/iio/adc/sun4i-gpadc-iio.c
index 2d393a4dfff6..a6ade70dedf8 100644
--- a/drivers/iio/adc/sun4i-gpadc-iio.c
+++ b/drivers/iio/adc/sun4i-gpadc-iio.c
@@ -412,9 +412,9 @@ static int sun4i_gpadc_runtime_resume(struct device *dev)
 	return 0;
 }
 
-static int sun4i_gpadc_get_temp(void *data, int *temp)
+static int sun4i_gpadc_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct sun4i_gpadc_iio *info = data;
+	struct sun4i_gpadc_iio *info = tz->devdata;
 	int val, scale, offset;
 
 	if (sun4i_gpadc_temp_read(info->indio_dev, &val))
@@ -428,7 +428,7 @@ static int sun4i_gpadc_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops sun4i_ts_tz_ops = {
+static const struct thermal_zone_device_ops sun4i_ts_tz_ops = {
 	.get_temp = &sun4i_gpadc_get_temp,
 };
 
@@ -637,9 +637,9 @@ static int sun4i_gpadc_probe(struct platform_device *pdev)
 	pm_runtime_enable(&pdev->dev);
 
 	if (IS_ENABLED(CONFIG_THERMAL_OF)) {
-		info->tzd = thermal_zone_of_sensor_register(info->sensor_device,
-							    0, info,
-							    &sun4i_ts_tz_ops);
+		info->tzd = devm_thermal_of_zone_register(info->sensor_device,
+							  0, info,
+							  &sun4i_ts_tz_ops);
 		/*
 		 * Do not fail driver probing when failing to register in
 		 * thermal because no thermal DT node is found.
@@ -681,8 +681,6 @@ static int sun4i_gpadc_remove(struct platform_device *pdev)
 	if (!IS_ENABLED(CONFIG_THERMAL_OF))
 		return 0;
 
-	thermal_zone_of_sensor_unregister(info->sensor_device, info->tzd);
-
 	if (!info->no_irq)
 		iio_map_array_unregister(indio_dev);
 
diff --git a/drivers/iio/light/cm32181.c b/drivers/iio/light/cm32181.c
index edbe6a3138d0..001055d09750 100644
--- a/drivers/iio/light/cm32181.c
+++ b/drivers/iio/light/cm32181.c
@@ -505,7 +505,7 @@ static int cm32181_resume(struct device *dev)
 					 cm32181->conf_regs[CM32181_REG_ADDR_CMD]);
 }
 
-DEFINE_SIMPLE_DEV_PM_OPS(cm32181_pm_ops, cm32181_suspend, cm32181_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(cm32181_pm_ops, cm32181_suspend, cm32181_resume);
 
 static const struct of_device_id cm32181_of_match[] = {
 	{ .compatible = "capella,cm3218" },
diff --git a/drivers/iio/light/cm3605.c b/drivers/iio/light/cm3605.c
index c721b69d5095..0b30db77f78b 100644
--- a/drivers/iio/light/cm3605.c
+++ b/drivers/iio/light/cm3605.c
@@ -226,8 +226,10 @@ static int cm3605_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0)
-		return dev_err_probe(dev, irq, "failed to get irq\n");
+	if (irq < 0) {
+		ret = dev_err_probe(dev, irq, "failed to get irq\n");
+		goto out_disable_aset;
+	}
 
 	ret = devm_request_threaded_irq(dev, irq, cm3605_prox_irq,
 					NULL, 0, "cm3605", indio_dev);
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 46d06678dfbe..be317f2665a9 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1841,8 +1841,8 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id,
 		}
 
 		if (!validate_net_dev(*net_dev,
-				 (struct sockaddr *)&req->listen_addr_storage,
-				 (struct sockaddr *)&req->src_addr_storage)) {
+				 (struct sockaddr *)&req->src_addr_storage,
+				 (struct sockaddr *)&req->listen_addr_storage)) {
 			id_priv = ERR_PTR(-EHOSTUNREACH);
 			goto err;
 		}
diff --git a/drivers/infiniband/core/umem_dmabuf.c b/drivers/infiniband/core/umem_dmabuf.c
index fce80a4a5147..04c04e6d24c3 100644
--- a/drivers/infiniband/core/umem_dmabuf.c
+++ b/drivers/infiniband/core/umem_dmabuf.c
@@ -18,6 +18,7 @@ int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf)
 	struct scatterlist *sg;
 	unsigned long start, end, cur = 0;
 	unsigned int nmap = 0;
+	long ret;
 	int i;
 
 	dma_resv_assert_held(umem_dmabuf->attach->dmabuf->resv);
@@ -67,9 +68,14 @@ wait_fence:
 	 * may be not up-to-date. Wait for the exporter to finish
 	 * the migration.
 	 */
-	return dma_resv_wait_timeout(umem_dmabuf->attach->dmabuf->resv,
+	ret = dma_resv_wait_timeout(umem_dmabuf->attach->dmabuf->resv,
 				     DMA_RESV_USAGE_KERNEL,
 				     false, MAX_SCHEDULE_TIMEOUT);
+	if (ret < 0)
+		return ret;
+	if (ret == 0)
+		return -ETIMEDOUT;
+	return 0;
 }
 EXPORT_SYMBOL(ib_umem_dmabuf_map_pages);
 
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 186ed8859920..d39e16c211e8 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -462,7 +462,7 @@ retry:
 		mutex_unlock(&umem_odp->umem_mutex);
 
 out_put_mm:
-	mmput(owning_mm);
+	mmput_async(owning_mm);
 out_put_task:
 	if (owning_process)
 		put_task_struct(owning_process);
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index c16017f6e8db..14392c942f49 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -2468,31 +2468,24 @@ static int accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
 			opt2 |= CCTRL_ECN_V(1);
 	}
 
-	skb_get(skb);
-	rpl = cplhdr(skb);
 	if (!is_t4(adapter_type)) {
-		BUILD_BUG_ON(sizeof(*rpl5) != roundup(sizeof(*rpl5), 16));
-		skb_trim(skb, sizeof(*rpl5));
-		rpl5 = (void *)rpl;
-		INIT_TP_WR(rpl5, ep->hwtid);
-	} else {
-		skb_trim(skb, sizeof(*rpl));
-		INIT_TP_WR(rpl, ep->hwtid);
-	}
-	OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL,
-						    ep->hwtid));
-
-	if (CHELSIO_CHIP_VERSION(adapter_type) > CHELSIO_T4) {
 		u32 isn = (prandom_u32() & ~7UL) - 1;
+
+		skb = get_skb(skb, roundup(sizeof(*rpl5), 16), GFP_KERNEL);
+		rpl5 = __skb_put_zero(skb, roundup(sizeof(*rpl5), 16));
+		rpl = (void *)rpl5;
+		INIT_TP_WR_CPL(rpl5, CPL_PASS_ACCEPT_RPL, ep->hwtid);
 		opt2 |= T5_OPT_2_VALID_F;
 		opt2 |= CONG_CNTRL_V(CONG_ALG_TAHOE);
 		opt2 |= T5_ISS_F;
-		rpl5 = (void *)rpl;
-		memset_after(rpl5, 0, iss);
 		if (peer2peer)
 			isn += 4;
 		rpl5->iss = cpu_to_be32(isn);
 		pr_debug("iss %u\n", be32_to_cpu(rpl5->iss));
+	} else {
+		skb = get_skb(skb, sizeof(*rpl), GFP_KERNEL);
+		rpl = __skb_put_zero(skb, sizeof(*rpl));
+		INIT_TP_WR_CPL(rpl, CPL_PASS_ACCEPT_RPL, ep->hwtid);
 	}
 
 	rpl->opt0 = cpu_to_be64(opt0);
diff --git a/drivers/infiniband/hw/erdma/erdma_qp.c b/drivers/infiniband/hw/erdma/erdma_qp.c
index 72f08171a28a..bc3ec22a62c5 100644
--- a/drivers/infiniband/hw/erdma/erdma_qp.c
+++ b/drivers/infiniband/hw/erdma/erdma_qp.c
@@ -407,7 +407,7 @@ static int erdma_push_one_sqe(struct erdma_qp *qp, u16 *pi,
 			     to_erdma_access_flags(reg_wr(send_wr)->access);
 		regmr_sge->addr = cpu_to_le64(mr->ibmr.iova);
 		regmr_sge->length = cpu_to_le32(mr->ibmr.length);
-		regmr_sge->stag = cpu_to_le32(mr->ibmr.lkey);
+		regmr_sge->stag = cpu_to_le32(reg_wr(send_wr)->key);
 		attrs = FIELD_PREP(ERDMA_SQE_MR_MODE_MASK, 0) |
 			FIELD_PREP(ERDMA_SQE_MR_ACCESS_MASK, mr->access) |
 			FIELD_PREP(ERDMA_SQE_MR_MTT_CNT_MASK,
diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.c b/drivers/infiniband/hw/erdma/erdma_verbs.c
index a7a3d42e2016..699bd3f59cd3 100644
--- a/drivers/infiniband/hw/erdma/erdma_verbs.c
+++ b/drivers/infiniband/hw/erdma/erdma_verbs.c
@@ -280,7 +280,7 @@ int erdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr,
 	attr->vendor_id = PCI_VENDOR_ID_ALIBABA;
 	attr->vendor_part_id = dev->pdev->device;
 	attr->hw_ver = dev->pdev->revision;
-	attr->max_qp = dev->attrs.max_qp;
+	attr->max_qp = dev->attrs.max_qp - 1;
 	attr->max_qp_wr = min(dev->attrs.max_send_wr, dev->attrs.max_recv_wr);
 	attr->max_qp_rd_atom = dev->attrs.max_ord;
 	attr->max_qp_init_rd_atom = dev->attrs.max_ird;
@@ -291,7 +291,7 @@ int erdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr,
 	attr->max_send_sge = dev->attrs.max_send_sge;
 	attr->max_recv_sge = dev->attrs.max_recv_sge;
 	attr->max_sge_rd = dev->attrs.max_sge_rd;
-	attr->max_cq = dev->attrs.max_cq;
+	attr->max_cq = dev->attrs.max_cq - 1;
 	attr->max_cqe = dev->attrs.max_cqe;
 	attr->max_mr = dev->attrs.max_mr;
 	attr->max_pd = dev->attrs.max_pd;
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index f848eedc6a23..d24996526c4d 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -730,7 +730,6 @@ struct hns_roce_caps {
 	u32		num_qps;
 	u32		num_pi_qps;
 	u32		reserved_qps;
-	int		num_qpc_timer;
 	u32		num_srqs;
 	u32		max_wqes;
 	u32		max_srq_wrs;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index cbdafaac678a..c780646bd60a 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -1977,7 +1977,7 @@ static void set_default_caps(struct hns_roce_dev *hr_dev)
 
 	caps->num_mtpts		= HNS_ROCE_V2_MAX_MTPT_NUM;
 	caps->num_pds		= HNS_ROCE_V2_MAX_PD_NUM;
-	caps->num_qpc_timer	= HNS_ROCE_V2_MAX_QPC_TIMER_NUM;
+	caps->qpc_timer_bt_num	= HNS_ROCE_V2_MAX_QPC_TIMER_BT_NUM;
 	caps->cqc_timer_bt_num	= HNS_ROCE_V2_MAX_CQC_TIMER_BT_NUM;
 
 	caps->max_qp_init_rdma	= HNS_ROCE_V2_MAX_QP_INIT_RDMA;
@@ -2273,7 +2273,6 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev)
 	caps->max_rq_sg		     = le16_to_cpu(resp_a->max_rq_sg);
 	caps->max_rq_sg = roundup_pow_of_two(caps->max_rq_sg);
 	caps->max_extend_sg	     = le32_to_cpu(resp_a->max_extend_sg);
-	caps->num_qpc_timer	     = le16_to_cpu(resp_a->num_qpc_timer);
 	caps->max_srq_sges	     = le16_to_cpu(resp_a->max_srq_sges);
 	caps->max_srq_sges = roundup_pow_of_two(caps->max_srq_sges);
 	caps->num_aeq_vectors	     = resp_a->num_aeq_vectors;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index f96debac30fe..64797109bab6 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -36,11 +36,11 @@
 #include <linux/bitops.h>
 
 #define HNS_ROCE_V2_MAX_QP_NUM			0x1000
-#define HNS_ROCE_V2_MAX_QPC_TIMER_NUM		0x200
 #define HNS_ROCE_V2_MAX_WQE_NUM			0x8000
 #define HNS_ROCE_V2_MAX_SRQ_WR			0x8000
 #define HNS_ROCE_V2_MAX_SRQ_SGE			64
 #define HNS_ROCE_V2_MAX_CQ_NUM			0x100000
+#define HNS_ROCE_V2_MAX_QPC_TIMER_BT_NUM	0x100
 #define HNS_ROCE_V2_MAX_CQC_TIMER_BT_NUM	0x100
 #define HNS_ROCE_V2_MAX_SRQ_NUM			0x100000
 #define HNS_ROCE_V2_MAX_CQE_NUM			0x400000
@@ -83,7 +83,7 @@
 
 #define HNS_ROCE_V2_QPC_TIMER_ENTRY_SZ		PAGE_SIZE
 #define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ		PAGE_SIZE
-#define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED		0xFFFFF000
+#define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED		0xFFFF000
 #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM		2
 #define HNS_ROCE_INVALID_LKEY			0x0
 #define HNS_ROCE_INVALID_SGE_LENGTH		0x80000000
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index c8af4ebd7cbd..4ccb217b2841 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -725,7 +725,7 @@ static int hns_roce_init_hem(struct hns_roce_dev *hr_dev)
 		ret = hns_roce_init_hem_table(hr_dev, &hr_dev->qpc_timer_table,
 					      HEM_TYPE_QPC_TIMER,
 					      hr_dev->caps.qpc_timer_entry_sz,
-					      hr_dev->caps.num_qpc_timer, 1);
+					      hr_dev->caps.qpc_timer_bt_num, 1);
 		if (ret) {
 			dev_err(dev,
 				"Failed to init QPC timer memory, aborting.\n");
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index 48d3616a6d71..7bee7f6c5e70 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -462,11 +462,8 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap,
 	hr_qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge) +
 					      hr_qp->rq.rsv_sge);
 
-	if (hr_dev->caps.max_rq_sg <= HNS_ROCE_SGE_IN_WQE)
-		hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz);
-	else
-		hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz *
-					    hr_qp->rq.max_gs);
+	hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz *
+				    hr_qp->rq.max_gs);
 
 	hr_qp->rq.wqe_cnt = cnt;
 	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_RQ_INLINE &&
diff --git a/drivers/infiniband/hw/irdma/uk.c b/drivers/infiniband/hw/irdma/uk.c
index daeab5daed5b..a6e5d350a94c 100644
--- a/drivers/infiniband/hw/irdma/uk.c
+++ b/drivers/infiniband/hw/irdma/uk.c
@@ -497,7 +497,8 @@ int irdma_uk_send(struct irdma_qp_uk *qp, struct irdma_post_sq_info *info,
 			      FIELD_PREP(IRDMAQPSQ_IMMDATA, info->imm_data));
 		i = 0;
 	} else {
-		qp->wqe_ops.iw_set_fragment(wqe, 0, op_info->sg_list,
+		qp->wqe_ops.iw_set_fragment(wqe, 0,
+					    frag_cnt ? op_info->sg_list : NULL,
 					    qp->swqe_polarity);
 		i = 1;
 	}
@@ -1005,6 +1006,7 @@ int irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq,
 	int ret_code;
 	bool move_cq_head = true;
 	u8 polarity;
+	u8 op_type;
 	bool ext_valid;
 	__le64 *ext_cqe;
 
@@ -1187,7 +1189,6 @@ int irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq,
 			do {
 				__le64 *sw_wqe;
 				u64 wqe_qword;
-				u8 op_type;
 				u32 tail;
 
 				tail = qp->sq_ring.tail;
@@ -1204,6 +1205,8 @@ int irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq,
 					break;
 				}
 			} while (1);
+			if (op_type == IRDMA_OP_TYPE_BIND_MW && info->minor_err == FLUSH_PROT_ERR)
+				info->minor_err = FLUSH_MW_BIND_ERR;
 			qp->sq_flush_seen = true;
 			if (!IRDMA_RING_MORE_WORK(qp->sq_ring))
 				qp->sq_flush_complete = true;
diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c
index fdf4cc88cb91..075defaabee5 100644
--- a/drivers/infiniband/hw/irdma/utils.c
+++ b/drivers/infiniband/hw/irdma/utils.c
@@ -590,11 +590,14 @@ static int irdma_wait_event(struct irdma_pci_f *rf,
 	cqp_error = cqp_request->compl_info.error;
 	if (cqp_error) {
 		err_code = -EIO;
-		if (cqp_request->compl_info.maj_err_code == 0xFFFF &&
-		    cqp_request->compl_info.min_err_code == 0x8029) {
-			if (!rf->reset) {
-				rf->reset = true;
-				rf->gen_ops.request_reset(rf);
+		if (cqp_request->compl_info.maj_err_code == 0xFFFF) {
+			if (cqp_request->compl_info.min_err_code == 0x8002)
+				err_code = -EBUSY;
+			else if (cqp_request->compl_info.min_err_code == 0x8029) {
+				if (!rf->reset) {
+					rf->reset = true;
+					rf->gen_ops.request_reset(rf);
+				}
 			}
 		}
 	}
@@ -2598,7 +2601,7 @@ void irdma_generate_flush_completions(struct irdma_qp *iwqp)
 		spin_unlock_irqrestore(&iwqp->lock, flags2);
 		spin_unlock_irqrestore(&iwqp->iwscq->lock, flags1);
 		if (compl_generated)
-			irdma_comp_handler(iwqp->iwrcq);
+			irdma_comp_handler(iwqp->iwscq);
 	} else {
 		spin_unlock_irqrestore(&iwqp->iwscq->lock, flags1);
 		mod_delayed_work(iwqp->iwdev->cleanup_wq, &iwqp->dwork_flush,
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 9b07b8af2997..9b207f5084eb 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -39,15 +39,18 @@ static int irdma_query_device(struct ib_device *ibdev,
 	props->max_send_sge = hw_attrs->uk_attrs.max_hw_wq_frags;
 	props->max_recv_sge = hw_attrs->uk_attrs.max_hw_wq_frags;
 	props->max_cq = rf->max_cq - rf->used_cqs;
-	props->max_cqe = rf->max_cqe;
+	props->max_cqe = rf->max_cqe - 1;
 	props->max_mr = rf->max_mr - rf->used_mrs;
 	props->max_mw = props->max_mr;
 	props->max_pd = rf->max_pd - rf->used_pds;
 	props->max_sge_rd = hw_attrs->uk_attrs.max_hw_read_sges;
 	props->max_qp_rd_atom = hw_attrs->max_hw_ird;
 	props->max_qp_init_rd_atom = hw_attrs->max_hw_ord;
-	if (rdma_protocol_roce(ibdev, 1))
+	if (rdma_protocol_roce(ibdev, 1)) {
+		props->device_cap_flags |= IB_DEVICE_RC_RNR_NAK_GEN;
 		props->max_pkeys = IRDMA_PKEY_TBL_SZ;
+	}
+
 	props->max_ah = rf->max_ah;
 	props->max_mcast_grp = rf->max_mcg;
 	props->max_mcast_qp_attach = IRDMA_MAX_MGS_PER_CTX;
@@ -3009,6 +3012,7 @@ static int irdma_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata)
 	struct irdma_pble_alloc *palloc = &iwpbl->pble_alloc;
 	struct irdma_cqp_request *cqp_request;
 	struct cqp_cmds_info *cqp_info;
+	int status;
 
 	if (iwmr->type != IRDMA_MEMREG_TYPE_MEM) {
 		if (iwmr->region) {
@@ -3039,8 +3043,11 @@ static int irdma_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata)
 	cqp_info->post_sq = 1;
 	cqp_info->in.u.dealloc_stag.dev = &iwdev->rf->sc_dev;
 	cqp_info->in.u.dealloc_stag.scratch = (uintptr_t)cqp_request;
-	irdma_handle_cqp_op(iwdev->rf, cqp_request);
+	status = irdma_handle_cqp_op(iwdev->rf, cqp_request);
 	irdma_put_cqp_request(&iwdev->rf->cqp, cqp_request);
+	if (status)
+		return status;
+
 	irdma_free_stag(iwdev, iwmr->stag);
 done:
 	if (iwpbl->pbl_allocated)
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index 293ed709e5ed..b4dc52392275 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -166,6 +166,12 @@ static int process_pma_cmd(struct mlx5_ib_dev *dev, u32 port_num,
 		mdev = dev->mdev;
 		mdev_port_num = 1;
 	}
+	if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1) {
+		/* set local port to one for Function-Per-Port HCA. */
+		mdev = dev->mdev;
+		mdev_port_num = 1;
+	}
+
 	/* Declaring support of extended counters */
 	if (in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO) {
 		struct ib_class_port_info cpi = {};
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index a174a0eee8dc..883d7c60143e 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2738,26 +2738,24 @@ static int set_has_smi_cap(struct mlx5_ib_dev *dev)
 	int err;
 	int port;
 
-	for (port = 1; port <= ARRAY_SIZE(dev->port_caps); port++) {
-		dev->port_caps[port - 1].has_smi = false;
-		if (MLX5_CAP_GEN(dev->mdev, port_type) ==
-		    MLX5_CAP_PORT_TYPE_IB) {
-			if (MLX5_CAP_GEN(dev->mdev, ib_virt)) {
-				err = mlx5_query_hca_vport_context(dev->mdev, 0,
-								   port, 0,
-								   &vport_ctx);
-				if (err) {
-					mlx5_ib_err(dev, "query_hca_vport_context for port=%d failed %d\n",
-						    port, err);
-					return err;
-				}
-				dev->port_caps[port - 1].has_smi =
-					vport_ctx.has_smi;
-			} else {
-				dev->port_caps[port - 1].has_smi = true;
-			}
+	if (MLX5_CAP_GEN(dev->mdev, port_type) != MLX5_CAP_PORT_TYPE_IB)
+		return 0;
+
+	for (port = 1; port <= dev->num_ports; port++) {
+		if (!MLX5_CAP_GEN(dev->mdev, ib_virt)) {
+			dev->port_caps[port - 1].has_smi = true;
+			continue;
 		}
+		err = mlx5_query_hca_vport_context(dev->mdev, 0, port, 0,
+						   &vport_ctx);
+		if (err) {
+			mlx5_ib_err(dev, "query_hca_vport_context for port=%d failed %d\n",
+				    port, err);
+			return err;
+		}
+		dev->port_caps[port - 1].has_smi = vport_ctx.has_smi;
 	}
+
 	return 0;
 }
 
@@ -4338,7 +4336,7 @@ static int mlx5r_probe(struct auxiliary_device *adev,
 	dev->mdev = mdev;
 	dev->num_ports = num_ports;
 
-	if (ll == IB_LINK_LAYER_ETHERNET && !mlx5_is_roce_init_enabled(mdev))
+	if (ll == IB_LINK_LAYER_ETHERNET && !mlx5_get_roce_state(mdev))
 		profile = &raw_eth_profile;
 	else
 		profile = &pf_profile;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 2e2ad3918385..e66bf72f1f04 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -708,6 +708,7 @@ struct mlx5_ib_umr_context {
 };
 
 enum {
+	MLX5_UMR_STATE_UNINIT,
 	MLX5_UMR_STATE_ACTIVE,
 	MLX5_UMR_STATE_RECOVER,
 	MLX5_UMR_STATE_ERR,
diff --git a/drivers/infiniband/hw/mlx5/umr.c b/drivers/infiniband/hw/mlx5/umr.c
index e00b94d1b1ea..d5105b5c9979 100644
--- a/drivers/infiniband/hw/mlx5/umr.c
+++ b/drivers/infiniband/hw/mlx5/umr.c
@@ -177,6 +177,7 @@ int mlx5r_umr_resource_init(struct mlx5_ib_dev *dev)
 
 	sema_init(&dev->umrc.sem, MAX_UMR_WR);
 	mutex_init(&dev->umrc.lock);
+	dev->umrc.state = MLX5_UMR_STATE_ACTIVE;
 
 	return 0;
 
@@ -191,6 +192,8 @@ destroy_pd:
 
 void mlx5r_umr_resource_cleanup(struct mlx5_ib_dev *dev)
 {
+	if (dev->umrc.state == MLX5_UMR_STATE_UNINIT)
+		return;
 	ib_destroy_qp(dev->umrc.qp);
 	ib_free_cq(dev->umrc.cq);
 	ib_dealloc_pd(dev->umrc.pd);
diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c
index 1f4e60257700..7d47b521070b 100644
--- a/drivers/infiniband/sw/siw/siw_qp_tx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_tx.c
@@ -29,7 +29,7 @@ static struct page *siw_get_pblpage(struct siw_mem *mem, u64 addr, int *idx)
 	dma_addr_t paddr = siw_pbl_get_buffer(pbl, offset, NULL, idx);
 
 	if (paddr)
-		return virt_to_page(paddr);
+		return virt_to_page((void *)paddr);
 
 	return NULL;
 }
@@ -533,13 +533,23 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 					kunmap_local(kaddr);
 				}
 			} else {
-				u64 va = sge->laddr + sge_off;
+				/*
+				 * Cast to an uintptr_t to preserve all 64 bits
+				 * in sge->laddr.
+				 */
+				uintptr_t va = (uintptr_t)(sge->laddr + sge_off);
 
-				page_array[seg] = virt_to_page(va & PAGE_MASK);
+				/*
+				 * virt_to_page() takes a (void *) pointer
+				 * so cast to a (void *) meaning it will be 64
+				 * bits on a 64 bit platform and 32 bits on a
+				 * 32 bit platform.
+				 */
+				page_array[seg] = virt_to_page((void *)(va & PAGE_MASK));
 				if (do_crc)
 					crypto_shash_update(
 						c_tx->mpa_crc_hd,
-						(void *)(uintptr_t)va,
+						(void *)va,
 						plen);
 			}
 
diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c
index bd5f3b5e1727..7b83f48f60c5 100644
--- a/drivers/infiniband/ulp/iser/iser_initiator.c
+++ b/drivers/infiniband/ulp/iser/iser_initiator.c
@@ -537,6 +537,7 @@ void iser_login_rsp(struct ib_cq *cq, struct ib_wc *wc)
 	struct iscsi_hdr *hdr;
 	char *data;
 	int length;
+	bool full_feature_phase;
 
 	if (unlikely(wc->status != IB_WC_SUCCESS)) {
 		iser_err_comp(wc, "login_rsp");
@@ -550,6 +551,9 @@ void iser_login_rsp(struct ib_cq *cq, struct ib_wc *wc)
 	hdr = desc->rsp + sizeof(struct iser_ctrl);
 	data = desc->rsp + ISER_HEADERS_LEN;
 	length = wc->byte_len - ISER_HEADERS_LEN;
+	full_feature_phase = ((hdr->flags & ISCSI_FULL_FEATURE_PHASE) ==
+			      ISCSI_FULL_FEATURE_PHASE) &&
+			     (hdr->flags & ISCSI_FLAG_CMD_FINAL);
 
 	iser_dbg("op 0x%x itt 0x%x dlen %d\n", hdr->opcode,
 		 hdr->itt, length);
@@ -560,7 +564,8 @@ void iser_login_rsp(struct ib_cq *cq, struct ib_wc *wc)
 				      desc->rsp_dma, ISER_RX_LOGIN_SIZE,
 				      DMA_FROM_DEVICE);
 
-	if (iser_conn->iscsi_conn->session->discovery_sess)
+	if (!full_feature_phase ||
+	    iser_conn->iscsi_conn->session->discovery_sess)
 		return;
 
 	/* Post the first RX buffer that is skipped in iser_post_rx_bufs() */
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index baecde41d126..449904dac0a9 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -1004,7 +1004,8 @@ rtrs_clt_get_copy_req(struct rtrs_clt_path *alive_path,
 static int rtrs_post_rdma_write_sg(struct rtrs_clt_con *con,
 				   struct rtrs_clt_io_req *req,
 				   struct rtrs_rbuf *rbuf, bool fr_en,
-				   u32 size, u32 imm, struct ib_send_wr *wr,
+				   u32 count, u32 size, u32 imm,
+				   struct ib_send_wr *wr,
 				   struct ib_send_wr *tail)
 {
 	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
@@ -1024,12 +1025,12 @@ static int rtrs_post_rdma_write_sg(struct rtrs_clt_con *con,
 		num_sge = 2;
 		ptail = tail;
 	} else {
-		for_each_sg(req->sglist, sg, req->sg_cnt, i) {
+		for_each_sg(req->sglist, sg, count, i) {
 			sge[i].addr   = sg_dma_address(sg);
 			sge[i].length = sg_dma_len(sg);
 			sge[i].lkey   = clt_path->s.dev->ib_pd->local_dma_lkey;
 		}
-		num_sge = 1 + req->sg_cnt;
+		num_sge = 1 + count;
 	}
 	sge[i].addr   = req->iu->dma_addr;
 	sge[i].length = size;
@@ -1142,7 +1143,7 @@ static int rtrs_clt_write_req(struct rtrs_clt_io_req *req)
 	 */
 	rtrs_clt_update_all_stats(req, WRITE);
 
-	ret = rtrs_post_rdma_write_sg(req->con, req, rbuf, fr_en,
+	ret = rtrs_post_rdma_write_sg(req->con, req, rbuf, fr_en, count,
 				      req->usr_len + sizeof(*msg),
 				      imm, wr, &inv_wr);
 	if (ret) {
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
index 34c03bde5064..4894e7329d88 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
@@ -595,7 +595,7 @@ static int map_cont_bufs(struct rtrs_srv_path *srv_path)
 		struct sg_table *sgt = &srv_mr->sgt;
 		struct scatterlist *s;
 		struct ib_mr *mr;
-		int nr, chunks;
+		int nr, nr_sgt, chunks;
 
 		chunks = chunks_per_mr * mri;
 		if (!always_invalidate)
@@ -610,19 +610,19 @@ static int map_cont_bufs(struct rtrs_srv_path *srv_path)
 			sg_set_page(s, srv->chunks[chunks + i],
 				    max_chunk_size, 0);
 
-		nr = ib_dma_map_sg(srv_path->s.dev->ib_dev, sgt->sgl,
+		nr_sgt = ib_dma_map_sg(srv_path->s.dev->ib_dev, sgt->sgl,
 				   sgt->nents, DMA_BIDIRECTIONAL);
-		if (nr < sgt->nents) {
-			err = nr < 0 ? nr : -EINVAL;
+		if (!nr_sgt) {
+			err = -EINVAL;
 			goto free_sg;
 		}
 		mr = ib_alloc_mr(srv_path->s.dev->ib_pd, IB_MR_TYPE_MEM_REG,
-				 sgt->nents);
+				 nr_sgt);
 		if (IS_ERR(mr)) {
 			err = PTR_ERR(mr);
 			goto unmap_sg;
 		}
-		nr = ib_map_mr_sg(mr, sgt->sgl, sgt->nents,
+		nr = ib_map_mr_sg(mr, sgt->sgl, nr_sgt,
 				  NULL, max_chunk_size);
 		if (nr < 0 || nr < sgt->nents) {
 			err = nr < 0 ? nr : -EINVAL;
@@ -641,7 +641,7 @@ static int map_cont_bufs(struct rtrs_srv_path *srv_path)
 			}
 		}
 		/* Eventually dma addr for each chunk can be cached */
-		for_each_sg(sgt->sgl, s, sgt->orig_nents, i)
+		for_each_sg(sgt->sgl, s, nr_sgt, i)
 			srv_path->dma_addr[chunks + i] = sg_dma_address(s);
 
 		ib_update_fast_reg_key(mr, ib_inc_rkey(mr->rkey));
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 7720ea270ed8..d7f69e593a63 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -1961,7 +1961,8 @@ static void srp_process_rsp(struct srp_rdma_ch *ch, struct srp_rsp *rsp)
 		if (scmnd) {
 			req = scsi_cmd_priv(scmnd);
 			scmnd = srp_claim_req(ch, req, NULL, scmnd);
-		} else {
+		}
+		if (!scmnd) {
 			shost_printk(KERN_ERR, target->scsi_host,
 				     "Null scmnd for RSP w/tag %#016llx received on ch %td / QP %#x\n",
 				     rsp->tag, ch - target->ch, ch->qp->qp_num);
diff --git a/drivers/input/joystick/iforce/iforce-main.c b/drivers/input/joystick/iforce/iforce-main.c
index b2a68bc9f0b4..b86de1312512 100644
--- a/drivers/input/joystick/iforce/iforce-main.c
+++ b/drivers/input/joystick/iforce/iforce-main.c
@@ -50,6 +50,7 @@ static struct iforce_device iforce_device[] = {
 	{ 0x046d, 0xc291, "Logitech WingMan Formula Force",		btn_wheel, abs_wheel, ff_iforce },
 	{ 0x05ef, 0x020a, "AVB Top Shot Pegasus",			btn_joystick_avb, abs_avb_pegasus, ff_iforce },
 	{ 0x05ef, 0x8884, "AVB Mag Turbo Force",			btn_wheel, abs_wheel, ff_iforce },
+	{ 0x05ef, 0x8886, "Boeder Force Feedback Wheel",		btn_wheel, abs_wheel, ff_iforce },
 	{ 0x05ef, 0x8888, "AVB Top Shot Force Feedback Racing Wheel",	btn_wheel, abs_wheel, ff_iforce }, //?
 	{ 0x061c, 0xc0a4, "ACT LABS Force RS",                          btn_wheel, abs_wheel, ff_iforce }, //?
 	{ 0x061c, 0xc084, "ACT LABS Force RS",				btn_wheel, abs_wheel, ff_iforce },
diff --git a/drivers/input/joystick/iforce/iforce-serio.c b/drivers/input/joystick/iforce/iforce-serio.c
index f95a81b9fac7..2380546d7978 100644
--- a/drivers/input/joystick/iforce/iforce-serio.c
+++ b/drivers/input/joystick/iforce/iforce-serio.c
@@ -39,7 +39,7 @@ static void iforce_serio_xmit(struct iforce *iforce)
 
 again:
 	if (iforce->xmit.head == iforce->xmit.tail) {
-		clear_bit(IFORCE_XMIT_RUNNING, iforce->xmit_flags);
+		iforce_clear_xmit_and_wake(iforce);
 		spin_unlock_irqrestore(&iforce->xmit_lock, flags);
 		return;
 	}
@@ -64,7 +64,7 @@ again:
 	if (test_and_clear_bit(IFORCE_XMIT_AGAIN, iforce->xmit_flags))
 		goto again;
 
-	clear_bit(IFORCE_XMIT_RUNNING, iforce->xmit_flags);
+	iforce_clear_xmit_and_wake(iforce);
 
 	spin_unlock_irqrestore(&iforce->xmit_lock, flags);
 }
@@ -169,7 +169,7 @@ static irqreturn_t iforce_serio_irq(struct serio *serio,
 			iforce_serio->cmd_response_len = iforce_serio->len;
 
 			/* Signal that command is done */
-			wake_up(&iforce->wait);
+			wake_up_all(&iforce->wait);
 		} else if (likely(iforce->type)) {
 			iforce_process_packet(iforce, iforce_serio->id,
 					      iforce_serio->data_in,
diff --git a/drivers/input/joystick/iforce/iforce-usb.c b/drivers/input/joystick/iforce/iforce-usb.c
index ea58805c480f..cba92bd590a8 100644
--- a/drivers/input/joystick/iforce/iforce-usb.c
+++ b/drivers/input/joystick/iforce/iforce-usb.c
@@ -30,7 +30,7 @@ static void __iforce_usb_xmit(struct iforce *iforce)
 	spin_lock_irqsave(&iforce->xmit_lock, flags);
 
 	if (iforce->xmit.head == iforce->xmit.tail) {
-		clear_bit(IFORCE_XMIT_RUNNING, iforce->xmit_flags);
+		iforce_clear_xmit_and_wake(iforce);
 		spin_unlock_irqrestore(&iforce->xmit_lock, flags);
 		return;
 	}
@@ -58,9 +58,9 @@ static void __iforce_usb_xmit(struct iforce *iforce)
 	XMIT_INC(iforce->xmit.tail, n);
 
 	if ( (n=usb_submit_urb(iforce_usb->out, GFP_ATOMIC)) ) {
-		clear_bit(IFORCE_XMIT_RUNNING, iforce->xmit_flags);
 		dev_warn(&iforce_usb->intf->dev,
 			 "usb_submit_urb failed %d\n", n);
+		iforce_clear_xmit_and_wake(iforce);
 	}
 
 	/* The IFORCE_XMIT_RUNNING bit is not cleared here. That's intended.
@@ -175,15 +175,15 @@ static void iforce_usb_out(struct urb *urb)
 	struct iforce *iforce = &iforce_usb->iforce;
 
 	if (urb->status) {
-		clear_bit(IFORCE_XMIT_RUNNING, iforce->xmit_flags);
 		dev_dbg(&iforce_usb->intf->dev, "urb->status %d, exiting\n",
 			urb->status);
+		iforce_clear_xmit_and_wake(iforce);
 		return;
 	}
 
 	__iforce_usb_xmit(iforce);
 
-	wake_up(&iforce->wait);
+	wake_up_all(&iforce->wait);
 }
 
 static int iforce_usb_probe(struct usb_interface *intf,
diff --git a/drivers/input/joystick/iforce/iforce.h b/drivers/input/joystick/iforce/iforce.h
index 6aa761ebbdf7..9ccb9107ccbe 100644
--- a/drivers/input/joystick/iforce/iforce.h
+++ b/drivers/input/joystick/iforce/iforce.h
@@ -119,6 +119,12 @@ static inline int iforce_get_id_packet(struct iforce *iforce, u8 id,
 					 response_data, response_len);
 }
 
+static inline void iforce_clear_xmit_and_wake(struct iforce *iforce)
+{
+	clear_bit(IFORCE_XMIT_RUNNING, iforce->xmit_flags);
+	wake_up_all(&iforce->wait);
+}
+
 /* Public functions */
 /* iforce-main.c */
 int iforce_init_device(struct device *parent, u16 bustype,
diff --git a/drivers/input/keyboard/iqs62x-keys.c b/drivers/input/keyboard/iqs62x-keys.c
index 93446b21f98f..db793a550c25 100644
--- a/drivers/input/keyboard/iqs62x-keys.c
+++ b/drivers/input/keyboard/iqs62x-keys.c
@@ -77,6 +77,7 @@ static int iqs62x_keys_parse_prop(struct platform_device *pdev,
 		if (ret) {
 			dev_err(&pdev->dev, "Failed to read switch code: %d\n",
 				ret);
+			fwnode_handle_put(child);
 			return ret;
 		}
 		iqs62x_keys->switches[i].code = val;
@@ -90,6 +91,8 @@ static int iqs62x_keys_parse_prop(struct platform_device *pdev,
 			iqs62x_keys->switches[i].flag = (i == IQS62X_SW_HALL_N ?
 							 IQS62X_EVENT_HALL_N_T :
 							 IQS62X_EVENT_HALL_S_T);
+
+		fwnode_handle_put(child);
 	}
 
 	return 0;
diff --git a/drivers/input/keyboard/snvs_pwrkey.c b/drivers/input/keyboard/snvs_pwrkey.c
index 65286762b02a..ad8660be0127 100644
--- a/drivers/input/keyboard/snvs_pwrkey.c
+++ b/drivers/input/keyboard/snvs_pwrkey.c
@@ -20,7 +20,7 @@
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
 
-#define SNVS_HPVIDR1_REG	0xF8
+#define SNVS_HPVIDR1_REG	0xBF8
 #define SNVS_LPSR_REG		0x4C	/* LP Status Register */
 #define SNVS_LPCR_REG		0x38	/* LP Control Register */
 #define SNVS_HPSR_REG		0x14
diff --git a/drivers/input/misc/rk805-pwrkey.c b/drivers/input/misc/rk805-pwrkey.c
index 3fb64dbda1a2..76873aa005b4 100644
--- a/drivers/input/misc/rk805-pwrkey.c
+++ b/drivers/input/misc/rk805-pwrkey.c
@@ -98,6 +98,7 @@ static struct platform_driver rk805_pwrkey_driver = {
 };
 module_platform_driver(rk805_pwrkey_driver);
 
+MODULE_ALIAS("platform:rk805-pwrkey");
 MODULE_AUTHOR("Joseph Chen <chenjh@rock-chips.com>");
 MODULE_DESCRIPTION("RK805 PMIC Power Key driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 434d48ae4b12..ffad142801b3 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -186,7 +186,6 @@ static const char * const smbus_pnp_ids[] = {
 	"LEN2044", /* L470  */
 	"LEN2054", /* E480 */
 	"LEN2055", /* E580 */
-	"LEN2064", /* T14 Gen 1 AMD / P14s Gen 1 AMD */
 	"LEN2068", /* T14 Gen 1 */
 	"SYN3052", /* HP EliteBook 840 G4 */
 	"SYN3221", /* HP 15-ay000 */
diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index d016505fc081..21c0dddbe41d 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -95,6 +95,7 @@ static const struct goodix_chip_data gt9x_chip_data = {
 
 static const struct goodix_chip_id goodix_chip_ids[] = {
 	{ .id = "1151", .data = &gt1x_chip_data },
+	{ .id = "1158", .data = &gt1x_chip_data },
 	{ .id = "5663", .data = &gt1x_chip_data },
 	{ .id = "5688", .data = &gt1x_chip_data },
 	{ .id = "917S", .data = &gt1x_chip_data },
@@ -1508,6 +1509,7 @@ MODULE_DEVICE_TABLE(acpi, goodix_acpi_match);
 #ifdef CONFIG_OF
 static const struct of_device_id goodix_of_match[] = {
 	{ .compatible = "goodix,gt1151" },
+	{ .compatible = "goodix,gt1158" },
 	{ .compatible = "goodix,gt5663" },
 	{ .compatible = "goodix,gt5688" },
 	{ .compatible = "goodix,gt911" },
diff --git a/drivers/input/touchscreen/melfas_mip4.c b/drivers/input/touchscreen/melfas_mip4.c
index 2745bf1aee38..83f4be05e27b 100644
--- a/drivers/input/touchscreen/melfas_mip4.c
+++ b/drivers/input/touchscreen/melfas_mip4.c
@@ -1453,7 +1453,7 @@ static int mip4_probe(struct i2c_client *client, const struct i2c_device_id *id)
 					      "ce", GPIOD_OUT_LOW);
 	if (IS_ERR(ts->gpio_ce)) {
 		error = PTR_ERR(ts->gpio_ce);
-		if (error != EPROBE_DEFER)
+		if (error != -EPROBE_DEFER)
 			dev_err(&client->dev,
 				"Failed to get gpio: %d\n", error);
 		return error;
diff --git a/drivers/input/touchscreen/sun4i-ts.c b/drivers/input/touchscreen/sun4i-ts.c
index 742a7e96c1b5..73eb8f80be6e 100644
--- a/drivers/input/touchscreen/sun4i-ts.c
+++ b/drivers/input/touchscreen/sun4i-ts.c
@@ -192,12 +192,12 @@ static int sun4i_get_temp(const struct sun4i_ts_data *ts, int *temp)
 	return 0;
 }
 
-static int sun4i_get_tz_temp(void *data, int *temp)
+static int sun4i_get_tz_temp(struct thermal_zone_device *tz, int *temp)
 {
-	return sun4i_get_temp(data, temp);
+	return sun4i_get_temp(tz->devdata, temp);
 }
 
-static const struct thermal_zone_of_device_ops sun4i_ts_tz_ops = {
+static const struct thermal_zone_device_ops sun4i_ts_tz_ops = {
 	.get_temp = sun4i_get_tz_temp,
 };
 
@@ -356,8 +356,8 @@ static int sun4i_ts_probe(struct platform_device *pdev)
 	if (IS_ERR(hwmon))
 		return PTR_ERR(hwmon);
 
-	thermal = devm_thermal_zone_of_sensor_register(ts->dev, 0, ts,
-						       &sun4i_ts_tz_ops);
+	thermal = devm_thermal_of_zone_register(ts->dev, 0, ts,
+						&sun4i_ts_tz_ops);
 	if (IS_ERR(thermal))
 		return PTR_ERR(thermal);
 
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 65b8e4fd8217..828672a46a3d 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -939,7 +939,8 @@ static void build_completion_wait(struct iommu_cmd *cmd,
 	memset(cmd, 0, sizeof(*cmd));
 	cmd->data[0] = lower_32_bits(paddr) | CMD_COMPL_WAIT_STORE_MASK;
 	cmd->data[1] = upper_32_bits(paddr);
-	cmd->data[2] = data;
+	cmd->data[2] = lower_32_bits(data);
+	cmd->data[3] = upper_32_bits(data);
 	CMD_SET_TYPE(cmd, CMD_COMPL_WAIT);
 }
 
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
index 696d5555be57..6a1f02c62dff 100644
--- a/drivers/iommu/amd/iommu_v2.c
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -777,6 +777,8 @@ int amd_iommu_init_device(struct pci_dev *pdev, int pasids)
 	if (dev_state->domain == NULL)
 		goto out_free_states;
 
+	/* See iommu_is_default_domain() */
+	dev_state->domain->type = IOMMU_DOMAIN_IDENTITY;
 	amd_iommu_domain_direct_map(dev_state->domain);
 
 	ret = amd_iommu_domain_enable_v2(dev_state->domain, pasids);
diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c
index 51bd66a45a11..e190bb8c225c 100644
--- a/drivers/iommu/hyperv-iommu.c
+++ b/drivers/iommu/hyperv-iommu.c
@@ -68,7 +68,6 @@ static int hyperv_irq_remapping_alloc(struct irq_domain *domain,
 {
 	struct irq_alloc_info *info = arg;
 	struct irq_data *irq_data;
-	struct irq_desc *desc;
 	int ret = 0;
 
 	if (!info || info->type != X86_IRQ_ALLOC_TYPE_IOAPIC || nr_irqs > 1)
@@ -90,8 +89,7 @@ static int hyperv_irq_remapping_alloc(struct irq_domain *domain,
 	 * Hypver-V IO APIC irq affinity should be in the scope of
 	 * ioapic_max_cpumask because no irq remapping support.
 	 */
-	desc = irq_data_to_desc(irq_data);
-	cpumask_copy(desc->irq_common_data.affinity, &ioapic_max_cpumask);
+	irq_data_update_affinity(irq_data, &ioapic_max_cpumask);
 
 	return 0;
 }
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 7cca030a508e..31bc50e538a3 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -163,38 +163,6 @@ static phys_addr_t root_entry_uctp(struct root_entry *re)
 	return re->hi & VTD_PAGE_MASK;
 }
 
-static inline void context_clear_pasid_enable(struct context_entry *context)
-{
-	context->lo &= ~(1ULL << 11);
-}
-
-static inline bool context_pasid_enabled(struct context_entry *context)
-{
-	return !!(context->lo & (1ULL << 11));
-}
-
-static inline void context_set_copied(struct context_entry *context)
-{
-	context->hi |= (1ull << 3);
-}
-
-static inline bool context_copied(struct context_entry *context)
-{
-	return !!(context->hi & (1ULL << 3));
-}
-
-static inline bool __context_present(struct context_entry *context)
-{
-	return (context->lo & 1);
-}
-
-bool context_present(struct context_entry *context)
-{
-	return context_pasid_enabled(context) ?
-	     __context_present(context) :
-	     __context_present(context) && !context_copied(context);
-}
-
 static inline void context_set_present(struct context_entry *context)
 {
 	context->lo |= 1;
@@ -242,6 +210,26 @@ static inline void context_clear_entry(struct context_entry *context)
 	context->hi = 0;
 }
 
+static inline bool context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	if (!iommu->copied_tables)
+		return false;
+
+	return test_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
+static inline void
+set_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	set_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
+static inline void
+clear_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	clear_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
 /*
  * This domain is a statically identity mapping domain.
  *	1. This domain creats a static 1:1 mapping to all usable memory.
@@ -402,14 +390,36 @@ static inline int domain_pfn_supported(struct dmar_domain *domain,
 	return !(addr_width < BITS_PER_LONG && pfn >> addr_width);
 }
 
+/*
+ * Calculate the Supported Adjusted Guest Address Widths of an IOMMU.
+ * Refer to 11.4.2 of the VT-d spec for the encoding of each bit of
+ * the returned SAGAW.
+ */
+static unsigned long __iommu_calculate_sagaw(struct intel_iommu *iommu)
+{
+	unsigned long fl_sagaw, sl_sagaw;
+
+	fl_sagaw = BIT(2) | (cap_5lp_support(iommu->cap) ? BIT(3) : 0);
+	sl_sagaw = cap_sagaw(iommu->cap);
+
+	/* Second level only. */
+	if (!sm_supported(iommu) || !ecap_flts(iommu->ecap))
+		return sl_sagaw;
+
+	/* First level only. */
+	if (!ecap_slts(iommu->ecap))
+		return fl_sagaw;
+
+	return fl_sagaw & sl_sagaw;
+}
+
 static int __iommu_calculate_agaw(struct intel_iommu *iommu, int max_gaw)
 {
 	unsigned long sagaw;
 	int agaw;
 
-	sagaw = cap_sagaw(iommu->cap);
-	for (agaw = width_to_agaw(max_gaw);
-	     agaw >= 0; agaw--) {
+	sagaw = __iommu_calculate_sagaw(iommu);
+	for (agaw = width_to_agaw(max_gaw); agaw >= 0; agaw--) {
 		if (test_bit(agaw, &sagaw))
 			break;
 	}
@@ -505,8 +515,9 @@ static int domain_update_device_node(struct dmar_domain *domain)
 {
 	struct device_domain_info *info;
 	int nid = NUMA_NO_NODE;
+	unsigned long flags;
 
-	spin_lock(&domain->lock);
+	spin_lock_irqsave(&domain->lock, flags);
 	list_for_each_entry(info, &domain->devices, link) {
 		/*
 		 * There could possibly be multiple device numa nodes as devices
@@ -518,7 +529,7 @@ static int domain_update_device_node(struct dmar_domain *domain)
 		if (nid != NUMA_NO_NODE)
 			break;
 	}
-	spin_unlock(&domain->lock);
+	spin_unlock_irqrestore(&domain->lock, flags);
 
 	return nid;
 }
@@ -578,6 +589,13 @@ struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
 	struct context_entry *context;
 	u64 *entry;
 
+	/*
+	 * Except that the caller requested to allocate a new entry,
+	 * returning a copied context entry makes no sense.
+	 */
+	if (!alloc && context_copied(iommu, bus, devfn))
+		return NULL;
+
 	entry = &root->lo;
 	if (sm_supported(iommu)) {
 		if (devfn >= 0x80) {
@@ -795,32 +813,11 @@ static void free_context_table(struct intel_iommu *iommu)
 }
 
 #ifdef CONFIG_DMAR_DEBUG
-static void pgtable_walk(struct intel_iommu *iommu, unsigned long pfn, u8 bus, u8 devfn)
+static void pgtable_walk(struct intel_iommu *iommu, unsigned long pfn,
+			 u8 bus, u8 devfn, struct dma_pte *parent, int level)
 {
-	struct device_domain_info *info;
-	struct dma_pte *parent, *pte;
-	struct dmar_domain *domain;
-	struct pci_dev *pdev;
-	int offset, level;
-
-	pdev = pci_get_domain_bus_and_slot(iommu->segment, bus, devfn);
-	if (!pdev)
-		return;
-
-	info = dev_iommu_priv_get(&pdev->dev);
-	if (!info || !info->domain) {
-		pr_info("device [%02x:%02x.%d] not probed\n",
-			bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
-		return;
-	}
-
-	domain = info->domain;
-	level = agaw_to_level(domain->agaw);
-	parent = domain->pgd;
-	if (!parent) {
-		pr_info("no page table setup\n");
-		return;
-	}
+	struct dma_pte *pte;
+	int offset;
 
 	while (1) {
 		offset = pfn_level_offset(pfn, level);
@@ -847,9 +844,10 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
 	struct pasid_entry *entries, *pte;
 	struct context_entry *ctx_entry;
 	struct root_entry *rt_entry;
+	int i, dir_index, index, level;
 	u8 devfn = source_id & 0xff;
 	u8 bus = source_id >> 8;
-	int i, dir_index, index;
+	struct dma_pte *pgtable;
 
 	pr_info("Dump %s table entries for IOVA 0x%llx\n", iommu->name, addr);
 
@@ -877,8 +875,11 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
 		ctx_entry->hi, ctx_entry->lo);
 
 	/* legacy mode does not require PASID entries */
-	if (!sm_supported(iommu))
+	if (!sm_supported(iommu)) {
+		level = agaw_to_level(ctx_entry->hi & 7);
+		pgtable = phys_to_virt(ctx_entry->lo & VTD_PAGE_MASK);
 		goto pgtable_walk;
+	}
 
 	/* get the pointer to pasid directory entry */
 	dir = phys_to_virt(ctx_entry->lo & VTD_PAGE_MASK);
@@ -905,8 +906,16 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
 	for (i = 0; i < ARRAY_SIZE(pte->val); i++)
 		pr_info("pasid table entry[%d]: 0x%016llx\n", i, pte->val[i]);
 
+	if (pasid_pte_get_pgtt(pte) == PASID_ENTRY_PGTT_FL_ONLY) {
+		level = pte->val[2] & BIT_ULL(2) ? 5 : 4;
+		pgtable = phys_to_virt(pte->val[2] & VTD_PAGE_MASK);
+	} else {
+		level = agaw_to_level((pte->val[0] >> 2) & 0x7);
+		pgtable = phys_to_virt(pte->val[0] & VTD_PAGE_MASK);
+	}
+
 pgtable_walk:
-	pgtable_walk(iommu, addr >> VTD_PAGE_SHIFT, bus, devfn);
+	pgtable_walk(iommu, addr >> VTD_PAGE_SHIFT, bus, devfn, pgtable, level);
 }
 #endif
 
@@ -1345,19 +1354,20 @@ iommu_support_dev_iotlb(struct dmar_domain *domain, struct intel_iommu *iommu,
 			u8 bus, u8 devfn)
 {
 	struct device_domain_info *info;
+	unsigned long flags;
 
 	if (!iommu->qi)
 		return NULL;
 
-	spin_lock(&domain->lock);
+	spin_lock_irqsave(&domain->lock, flags);
 	list_for_each_entry(info, &domain->devices, link) {
 		if (info->iommu == iommu && info->bus == bus &&
 		    info->devfn == devfn) {
-			spin_unlock(&domain->lock);
+			spin_unlock_irqrestore(&domain->lock, flags);
 			return info->ats_supported ? info : NULL;
 		}
 	}
-	spin_unlock(&domain->lock);
+	spin_unlock_irqrestore(&domain->lock, flags);
 
 	return NULL;
 }
@@ -1366,8 +1376,9 @@ static void domain_update_iotlb(struct dmar_domain *domain)
 {
 	struct device_domain_info *info;
 	bool has_iotlb_device = false;
+	unsigned long flags;
 
-	spin_lock(&domain->lock);
+	spin_lock_irqsave(&domain->lock, flags);
 	list_for_each_entry(info, &domain->devices, link) {
 		if (info->ats_enabled) {
 			has_iotlb_device = true;
@@ -1375,7 +1386,7 @@ static void domain_update_iotlb(struct dmar_domain *domain)
 		}
 	}
 	domain->has_iotlb_device = has_iotlb_device;
-	spin_unlock(&domain->lock);
+	spin_unlock_irqrestore(&domain->lock, flags);
 }
 
 static void iommu_enable_dev_iotlb(struct device_domain_info *info)
@@ -1467,14 +1478,15 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 				  u64 addr, unsigned mask)
 {
 	struct device_domain_info *info;
+	unsigned long flags;
 
 	if (!domain->has_iotlb_device)
 		return;
 
-	spin_lock(&domain->lock);
+	spin_lock_irqsave(&domain->lock, flags);
 	list_for_each_entry(info, &domain->devices, link)
 		__iommu_flush_dev_iotlb(info, addr, mask);
-	spin_unlock(&domain->lock);
+	spin_unlock_irqrestore(&domain->lock, flags);
 }
 
 static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
@@ -1688,6 +1700,11 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
 		iommu->domain_ids = NULL;
 	}
 
+	if (iommu->copied_tables) {
+		bitmap_free(iommu->copied_tables);
+		iommu->copied_tables = NULL;
+	}
+
 	/* free context mapping */
 	free_context_table(iommu);
 
@@ -1913,7 +1930,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 		goto out_unlock;
 
 	ret = 0;
-	if (context_present(context))
+	if (context_present(context) && !context_copied(iommu, bus, devfn))
 		goto out_unlock;
 
 	/*
@@ -1925,7 +1942,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 	 * in-flight DMA will exist, and we don't need to worry anymore
 	 * hereafter.
 	 */
-	if (context_copied(context)) {
+	if (context_copied(iommu, bus, devfn)) {
 		u16 did_old = context_domain_id(context);
 
 		if (did_old < cap_ndoms(iommu->cap)) {
@@ -1936,6 +1953,8 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 			iommu->flush.flush_iotlb(iommu, did_old, 0, 0,
 						 DMA_TLB_DSI_FLUSH);
 		}
+
+		clear_context_copied(iommu, bus, devfn);
 	}
 
 	context_clear_entry(context);
@@ -2429,6 +2448,7 @@ static int domain_add_dev_info(struct dmar_domain *domain, struct device *dev)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu;
+	unsigned long flags;
 	u8 bus, devfn;
 	int ret;
 
@@ -2440,9 +2460,9 @@ static int domain_add_dev_info(struct dmar_domain *domain, struct device *dev)
 	if (ret)
 		return ret;
 	info->domain = domain;
-	spin_lock(&domain->lock);
+	spin_lock_irqsave(&domain->lock, flags);
 	list_add(&info->link, &domain->devices);
-	spin_unlock(&domain->lock);
+	spin_unlock_irqrestore(&domain->lock, flags);
 
 	/* PASID table is mandatory for a PCI device in scalable mode. */
 	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
@@ -2684,32 +2704,14 @@ static int copy_context_table(struct intel_iommu *iommu,
 		/* Now copy the context entry */
 		memcpy(&ce, old_ce + idx, sizeof(ce));
 
-		if (!__context_present(&ce))
+		if (!context_present(&ce))
 			continue;
 
 		did = context_domain_id(&ce);
 		if (did >= 0 && did < cap_ndoms(iommu->cap))
 			set_bit(did, iommu->domain_ids);
 
-		/*
-		 * We need a marker for copied context entries. This
-		 * marker needs to work for the old format as well as
-		 * for extended context entries.
-		 *
-		 * Bit 67 of the context entry is used. In the old
-		 * format this bit is available to software, in the
-		 * extended format it is the PGE bit, but PGE is ignored
-		 * by HW if PASIDs are disabled (and thus still
-		 * available).
-		 *
-		 * So disable PASIDs first and then mark the entry
-		 * copied. This means that we don't copy PASID
-		 * translations from the old kernel, but this is fine as
-		 * faults there are not fatal.
-		 */
-		context_clear_pasid_enable(&ce);
-		context_set_copied(&ce);
-
+		set_context_copied(iommu, bus, devfn);
 		new_ce[idx] = ce;
 	}
 
@@ -2735,8 +2737,8 @@ static int copy_translation_tables(struct intel_iommu *iommu)
 	bool new_ext, ext;
 
 	rtaddr_reg = dmar_readq(iommu->reg + DMAR_RTADDR_REG);
-	ext        = !!(rtaddr_reg & DMA_RTADDR_RTT);
-	new_ext    = !!ecap_ecs(iommu->ecap);
+	ext        = !!(rtaddr_reg & DMA_RTADDR_SMT);
+	new_ext    = !!sm_supported(iommu);
 
 	/*
 	 * The RTT bit can only be changed when translation is disabled,
@@ -2747,6 +2749,10 @@ static int copy_translation_tables(struct intel_iommu *iommu)
 	if (new_ext != ext)
 		return -EINVAL;
 
+	iommu->copied_tables = bitmap_zalloc(BIT_ULL(16), GFP_KERNEL);
+	if (!iommu->copied_tables)
+		return -ENOMEM;
+
 	old_rt_phys = rtaddr_reg & VTD_PAGE_MASK;
 	if (!old_rt_phys)
 		return -EINVAL;
@@ -4080,6 +4086,7 @@ static void dmar_remove_one_dev_info(struct device *dev)
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct dmar_domain *domain = info->domain;
 	struct intel_iommu *iommu = info->iommu;
+	unsigned long flags;
 
 	if (!dev_is_real_dma_subdevice(info->dev)) {
 		if (dev_is_pci(info->dev) && sm_supported(iommu))
@@ -4091,9 +4098,9 @@ static void dmar_remove_one_dev_info(struct device *dev)
 		intel_pasid_free_table(info->dev);
 	}
 
-	spin_lock(&domain->lock);
+	spin_lock_irqsave(&domain->lock, flags);
 	list_del(&info->link);
-	spin_unlock(&domain->lock);
+	spin_unlock_irqrestore(&domain->lock, flags);
 
 	domain_detach_iommu(domain, iommu);
 	info->domain = NULL;
@@ -4412,19 +4419,20 @@ static void domain_set_force_snooping(struct dmar_domain *domain)
 static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	unsigned long flags;
 
 	if (dmar_domain->force_snooping)
 		return true;
 
-	spin_lock(&dmar_domain->lock);
+	spin_lock_irqsave(&dmar_domain->lock, flags);
 	if (!domain_support_force_snooping(dmar_domain)) {
-		spin_unlock(&dmar_domain->lock);
+		spin_unlock_irqrestore(&dmar_domain->lock, flags);
 		return false;
 	}
 
 	domain_set_force_snooping(dmar_domain);
 	dmar_domain->force_snooping = true;
-	spin_unlock(&dmar_domain->lock);
+	spin_unlock_irqrestore(&dmar_domain->lock, flags);
 
 	return true;
 }
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index fae45bbb0c7f..74b0e19e23ee 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -197,7 +197,6 @@
 #define ecap_dis(e)		(((e) >> 27) & 0x1)
 #define ecap_nest(e)		(((e) >> 26) & 0x1)
 #define ecap_mts(e)		(((e) >> 25) & 0x1)
-#define ecap_ecs(e)		(((e) >> 24) & 0x1)
 #define ecap_iotlb_offset(e) 	((((e) >> 8) & 0x3ff) * 16)
 #define ecap_max_iotlb_offset(e) (ecap_iotlb_offset(e) + 16)
 #define ecap_coherent(e)	((e) & 0x1)
@@ -265,7 +264,6 @@
 #define DMA_GSTS_CFIS (((u32)1) << 23)
 
 /* DMA_RTADDR_REG */
-#define DMA_RTADDR_RTT (((u64)1) << 11)
 #define DMA_RTADDR_SMT (((u64)1) << 10)
 
 /* CCMD_REG */
@@ -579,6 +577,7 @@ struct intel_iommu {
 
 #ifdef CONFIG_INTEL_IOMMU
 	unsigned long 	*domain_ids; /* bitmap of domains */
+	unsigned long	*copied_tables; /* bitmap of copied tables */
 	spinlock_t	lock; /* protect context, domain ids */
 	struct root_entry *root_entry; /* virtual address */
 
@@ -701,6 +700,11 @@ static inline int nr_pte_to_next_page(struct dma_pte *pte)
 		(struct dma_pte *)ALIGN((unsigned long)pte, VTD_PAGE_SIZE) - pte;
 }
 
+static inline bool context_present(struct context_entry *context)
+{
+	return (context->lo & 1);
+}
+
 extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev);
 
 extern int dmar_enable_qi(struct intel_iommu *iommu);
@@ -784,7 +788,6 @@ static inline void intel_iommu_debugfs_init(void) {}
 #endif /* CONFIG_INTEL_IOMMU_DEBUGFS */
 
 extern const struct attribute_group *intel_iommu_groups[];
-bool context_present(struct context_entry *context);
 struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
 					 u8 devfn, int alloc);
 
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 780fb7071577..3a808146b50f 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -3076,6 +3076,24 @@ out:
 	return ret;
 }
 
+static bool iommu_is_default_domain(struct iommu_group *group)
+{
+	if (group->domain == group->default_domain)
+		return true;
+
+	/*
+	 * If the default domain was set to identity and it is still an identity
+	 * domain then we consider this a pass. This happens because of
+	 * amd_iommu_init_device() replacing the default idenytity domain with an
+	 * identity domain that has a different configuration for AMDGPU.
+	 */
+	if (group->default_domain &&
+	    group->default_domain->type == IOMMU_DOMAIN_IDENTITY &&
+	    group->domain && group->domain->type == IOMMU_DOMAIN_IDENTITY)
+		return true;
+	return false;
+}
+
 /**
  * iommu_device_use_default_domain() - Device driver wants to handle device
  *                                     DMA through the kernel DMA API.
@@ -3094,8 +3112,7 @@ int iommu_device_use_default_domain(struct device *dev)
 
 	mutex_lock(&group->mutex);
 	if (group->owner_cnt) {
-		if (group->domain != group->default_domain ||
-		    group->owner) {
+		if (group->owner || !iommu_is_default_domain(group)) {
 			ret = -EBUSY;
 			goto unlock_out;
 		}
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 41f4eb005219..5696314ae69e 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -40,7 +40,7 @@ static int of_iommu_xlate(struct device *dev,
 	 * a proper probe-ordering dependency mechanism in future.
 	 */
 	if (!ops)
-		return -ENODEV;
+		return driver_deferred_probe_check_state(dev);
 
 	if (!try_module_get(ops->owner))
 		return -ENODEV;
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 08eeafc9529f..80151176ba12 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -1006,7 +1006,18 @@ static int viommu_of_xlate(struct device *dev, struct of_phandle_args *args)
 	return iommu_fwspec_add_ids(dev, args->args, 1);
 }
 
+static bool viommu_capable(enum iommu_cap cap)
+{
+	switch (cap) {
+	case IOMMU_CAP_CACHE_COHERENCY:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static struct iommu_ops viommu_ops = {
+	.capable		= viommu_capable,
 	.domain_alloc		= viommu_domain_alloc,
 	.probe_device		= viommu_probe_device,
 	.probe_finalize		= viommu_probe_finalize,
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 66b9fa408bf2..eb5ea5b69cfa 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -561,6 +561,11 @@ config IRQ_LOONGARCH_CPU
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
+	select LOONGSON_LIOINTC
+	select LOONGSON_EIOINTC
+	select LOONGSON_PCH_PIC
+	select LOONGSON_PCH_MSI
+	select LOONGSON_PCH_LPC
 	help
 	  Support for the LoongArch CPU Interrupt Controller. For details of
 	  irq chip hierarchy on LoongArch platforms please read the document
@@ -623,8 +628,9 @@ config LOONGSON_PCH_MSI
 
 config LOONGSON_PCH_LPC
 	bool "Loongson PCH LPC Controller"
+	depends on LOONGARCH
 	depends on MACH_LOONGSON64
-	default (MACH_LOONGSON64 && LOONGARCH)
+	default MACH_LOONGSON64
 	select IRQ_DOMAIN_HIERARCHY
 	help
 	  Support for the Loongson PCH LPC Controller.
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 5ff09de6c48f..beead1a0191c 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1574,13 +1574,15 @@ static int its_select_cpu(struct irq_data *d,
 			  const struct cpumask *aff_mask)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
-	cpumask_var_t tmpmask;
+	static DEFINE_RAW_SPINLOCK(tmpmask_lock);
+	static struct cpumask __tmpmask;
+	struct cpumask *tmpmask;
+	unsigned long flags;
 	int cpu, node;
-
-	if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC))
-		return -ENOMEM;
-
 	node = its_dev->its->numa_node;
+	tmpmask = &__tmpmask;
+
+	raw_spin_lock_irqsave(&tmpmask_lock, flags);
 
 	if (!irqd_affinity_is_managed(d)) {
 		/* First try the NUMA node */
@@ -1634,7 +1636,7 @@ static int its_select_cpu(struct irq_data *d,
 		cpu = cpumask_pick_least_loaded(d, tmpmask);
 	}
 out:
-	free_cpumask_var(tmpmask);
+	raw_spin_unlock_irqrestore(&tmpmask_lock, flags);
 
 	pr_debug("IRQ%d -> %*pbl CPU%d\n", d->irq, cpumask_pr_args(aff_mask), cpu);
 	return cpu;
diff --git a/drivers/irqchip/irq-loongarch-cpu.c b/drivers/irqchip/irq-loongarch-cpu.c
index 327f3ab62c03..741612ba6a52 100644
--- a/drivers/irqchip/irq-loongarch-cpu.c
+++ b/drivers/irqchip/irq-loongarch-cpu.c
@@ -129,7 +129,7 @@ static int __init cpuintc_acpi_init(union acpi_subtable_headers *header,
 	clear_csr_ecfg(ECFG0_IM);
 	clear_csr_estat(ESTATF_IP);
 
-	cpuintc_handle = irq_domain_alloc_fwnode(NULL);
+	cpuintc_handle = irq_domain_alloc_named_fwnode("CPUINTC");
 	irq_domain = irq_domain_create_linear(cpuintc_handle, EXCCODE_INT_NUM,
 					&loongarch_cpu_intc_irq_domain_ops, NULL);
 
diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c
index 80d8ca6f2d46..16e9af8d8b1e 100644
--- a/drivers/irqchip/irq-loongson-eiointc.c
+++ b/drivers/irqchip/irq-loongson-eiointc.c
@@ -111,11 +111,15 @@ static int eiointc_set_irq_affinity(struct irq_data *d, const struct cpumask *af
 	regaddr = EIOINTC_REG_ENABLE + ((vector >> 5) << 2);
 
 	/* Mask target vector */
-	csr_any_send(regaddr, EIOINTC_ALL_ENABLE & (~BIT(vector & 0x1F)), 0x0, 0);
+	csr_any_send(regaddr, EIOINTC_ALL_ENABLE & (~BIT(vector & 0x1F)),
+			0x0, priv->node * CORES_PER_EIO_NODE);
+
 	/* Set route for target vector */
 	eiointc_set_irq_route(vector, cpu, priv->node, &priv->node_map);
+
 	/* Unmask target vector */
-	csr_any_send(regaddr, EIOINTC_ALL_ENABLE, 0x0, 0);
+	csr_any_send(regaddr, EIOINTC_ALL_ENABLE,
+			0x0, priv->node * CORES_PER_EIO_NODE);
 
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 
@@ -286,7 +290,7 @@ static void acpi_set_vec_parent(int node, struct irq_domain *parent, struct acpi
 	}
 }
 
-struct irq_domain *acpi_get_vec_parent(int node, struct acpi_vector_group *vec_group)
+static struct irq_domain *acpi_get_vec_parent(int node, struct acpi_vector_group *vec_group)
 {
 	int i;
 
@@ -344,7 +348,8 @@ int __init eiointc_acpi_init(struct irq_domain *parent,
 	if (!priv)
 		return -ENOMEM;
 
-	priv->domain_handle = irq_domain_alloc_fwnode((phys_addr_t *)acpi_eiointc);
+	priv->domain_handle = irq_domain_alloc_named_id_fwnode("EIOPIC",
+							       acpi_eiointc->node);
 	if (!priv->domain_handle) {
 		pr_err("Unable to allocate domain handle\n");
 		goto out_free_priv;
diff --git a/drivers/irqchip/irq-loongson-liointc.c b/drivers/irqchip/irq-loongson-liointc.c
index c4f3c886ad61..0da8716f8f24 100644
--- a/drivers/irqchip/irq-loongson-liointc.c
+++ b/drivers/irqchip/irq-loongson-liointc.c
@@ -207,7 +207,7 @@ static int liointc_init(phys_addr_t addr, unsigned long size, int revision,
 					"reg-names", core_reg_names[i]);
 
 			if (index < 0)
-				return -EINVAL;
+				goto out_iounmap;
 
 			priv->core_isr[i] = of_iomap(node, index);
 		}
@@ -360,7 +360,7 @@ int __init liointc_acpi_init(struct irq_domain *parent, struct acpi_madt_lio_pic
 	parent_irq[0] = irq_create_mapping(parent, acpi_liointc->cascade[0]);
 	parent_irq[1] = irq_create_mapping(parent, acpi_liointc->cascade[1]);
 
-	domain_handle = irq_domain_alloc_fwnode((phys_addr_t *)acpi_liointc);
+	domain_handle = irq_domain_alloc_fwnode(&acpi_liointc->address);
 	if (!domain_handle) {
 		pr_err("Unable to allocate domain handle\n");
 		return -ENOMEM;
diff --git a/drivers/irqchip/irq-loongson-pch-msi.c b/drivers/irqchip/irq-loongson-pch-msi.c
index d0e8551bebfa..a72ede90ffc6 100644
--- a/drivers/irqchip/irq-loongson-pch-msi.c
+++ b/drivers/irqchip/irq-loongson-pch-msi.c
@@ -282,7 +282,7 @@ int __init pch_msi_acpi_init(struct irq_domain *parent,
 	int ret;
 	struct fwnode_handle *domain_handle;
 
-	domain_handle = irq_domain_alloc_fwnode((phys_addr_t *)acpi_pchmsi);
+	domain_handle = irq_domain_alloc_fwnode(&acpi_pchmsi->msg_address);
 	ret = pch_msi_init(acpi_pchmsi->msg_address, acpi_pchmsi->start,
 				acpi_pchmsi->count, parent, domain_handle);
 	if (ret < 0)
diff --git a/drivers/irqchip/irq-loongson-pch-pic.c b/drivers/irqchip/irq-loongson-pch-pic.c
index b6f1392964b1..c01b9c257005 100644
--- a/drivers/irqchip/irq-loongson-pch-pic.c
+++ b/drivers/irqchip/irq-loongson-pch-pic.c
@@ -48,25 +48,6 @@ static struct pch_pic *pch_pic_priv[MAX_IO_PICS];
 
 struct fwnode_handle *pch_pic_handle[MAX_IO_PICS];
 
-int find_pch_pic(u32 gsi)
-{
-	int i;
-
-	/* Find the PCH_PIC that manages this GSI. */
-	for (i = 0; i < MAX_IO_PICS; i++) {
-		struct pch_pic *priv = pch_pic_priv[i];
-
-		if (!priv)
-			return -1;
-
-		if (gsi >= priv->gsi_base && gsi < (priv->gsi_base + priv->vec_count))
-			return i;
-	}
-
-	pr_err("ERROR: Unable to locate PCH_PIC for GSI %d\n", gsi);
-	return -1;
-}
-
 static void pch_pic_bitset(struct pch_pic *priv, int offset, int bit)
 {
 	u32 reg;
@@ -325,6 +306,25 @@ IRQCHIP_DECLARE(pch_pic, "loongson,pch-pic-1.0", pch_pic_of_init);
 #endif
 
 #ifdef CONFIG_ACPI
+int find_pch_pic(u32 gsi)
+{
+	int i;
+
+	/* Find the PCH_PIC that manages this GSI. */
+	for (i = 0; i < MAX_IO_PICS; i++) {
+		struct pch_pic *priv = pch_pic_priv[i];
+
+		if (!priv)
+			return -1;
+
+		if (gsi >= priv->gsi_base && gsi < (priv->gsi_base + priv->vec_count))
+			return i;
+	}
+
+	pr_err("ERROR: Unable to locate PCH_PIC for GSI %d\n", gsi);
+	return -1;
+}
+
 static int __init
 pch_lpc_parse_madt(union acpi_subtable_headers *header,
 		       const unsigned long end)
@@ -349,7 +349,7 @@ int __init pch_pic_acpi_init(struct irq_domain *parent,
 
 	vec_base = acpi_pchpic->gsi_base - GSI_MIN_PCH_IRQ;
 
-	domain_handle = irq_domain_alloc_fwnode((phys_addr_t *)acpi_pchpic);
+	domain_handle = irq_domain_alloc_fwnode(&acpi_pchpic->address);
 	if (!domain_handle) {
 		pr_err("Unable to allocate domain handle\n");
 		return -ENOMEM;
diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index a73763d475f0..6a3f7498ea8e 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -716,7 +716,7 @@ static int stm32_exti_h_domain_alloc(struct irq_domain *dm,
 
 	irq_domain_set_hwirq_and_chip(dm, virq, hwirq, chip, chip_data);
 
-	if (!host_data->drv_data || !host_data->drv_data->desc_irqs)
+	if (!host_data->drv_data->desc_irqs)
 		return -EINVAL;
 
 	desc_irq = host_data->drv_data->desc_irqs[hwirq];
diff --git a/drivers/md/dm-verity-loadpin.c b/drivers/md/dm-verity-loadpin.c
index 387ec43aef72..4f78cc55c251 100644
--- a/drivers/md/dm-verity-loadpin.c
+++ b/drivers/md/dm-verity-loadpin.c
@@ -14,6 +14,7 @@ LIST_HEAD(dm_verity_loadpin_trusted_root_digests);
 
 static bool is_trusted_verity_target(struct dm_target *ti)
 {
+	int verity_mode;
 	u8 *root_digest;
 	unsigned int digest_size;
 	struct dm_verity_loadpin_trusted_root_digest *trd;
@@ -22,6 +23,13 @@ static bool is_trusted_verity_target(struct dm_target *ti)
 	if (!dm_is_verity_target(ti))
 		return false;
 
+	verity_mode = dm_verity_get_mode(ti);
+
+	if ((verity_mode != DM_VERITY_MODE_EIO) &&
+	    (verity_mode != DM_VERITY_MODE_RESTART) &&
+	    (verity_mode != DM_VERITY_MODE_PANIC))
+		return false;
+
 	if (dm_verity_get_root_digest(ti, &root_digest, &digest_size))
 		return false;
 
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 94b6cb599db4..8a00cc42e498 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -1447,6 +1447,22 @@ bool dm_is_verity_target(struct dm_target *ti)
 }
 
 /*
+ * Get the verity mode (error behavior) of a verity target.
+ *
+ * Returns the verity mode of the target, or -EINVAL if 'ti' is not a verity
+ * target.
+ */
+int dm_verity_get_mode(struct dm_target *ti)
+{
+	struct dm_verity *v = ti->private;
+
+	if (!dm_is_verity_target(ti))
+		return -EINVAL;
+
+	return v->mode;
+}
+
+/*
  * Get the root digest of a verity target.
  *
  * Returns a copy of the root digest, the caller is responsible for
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index 45455de1b4bc..98f306ec6a33 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -134,6 +134,7 @@ extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io,
 				 sector_t block, u8 *digest, bool *is_zero);
 
 extern bool dm_is_verity_target(struct dm_target *ti);
+extern int dm_verity_get_mode(struct dm_target *ti);
 extern int dm_verity_get_root_digest(struct dm_target *ti, u8 **root_digest,
 				     unsigned int *digest_size);
 
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 742b2349fea3..10e0c5381d01 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -876,8 +876,8 @@ static int join(struct mddev *mddev, int nodes)
 	memset(str, 0, 64);
 	sprintf(str, "%pU", mddev->uuid);
 	ret = dlm_new_lockspace(str, mddev->bitmap_info.cluster_name,
-				DLM_LSFL_FS, LVB_SIZE,
-				&md_ls_ops, mddev, &ops_rv, &cinfo->lockspace);
+				0, LVB_SIZE, &md_ls_ops, mddev,
+				&ops_rv, &cinfo->lockspace);
 	if (ret)
 		goto err;
 	wait_for_completion(&cinfo->completion);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index afaf36b2f6ab..729be2c5296c 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5620,6 +5620,7 @@ struct mddev *md_alloc(dev_t dev, char *name)
 	 * removed (mddev_delayed_delete).
 	 */
 	flush_workqueue(md_misc_wq);
+	flush_workqueue(md_rdev_misc_wq);
 
 	mutex_lock(&disks_mutex);
 	mddev = mddev_alloc(dev);
@@ -6238,11 +6239,11 @@ static void mddev_detach(struct mddev *mddev)
 static void __md_stop(struct mddev *mddev)
 {
 	struct md_personality *pers = mddev->pers;
+	md_bitmap_destroy(mddev);
 	mddev_detach(mddev);
 	/* Ensure ->event_work is done */
 	if (mddev->event_work.func)
 		flush_workqueue(md_misc_wq);
-	md_bitmap_destroy(mddev);
 	spin_lock(&mddev->lock);
 	mddev->pers = NULL;
 	spin_unlock(&mddev->lock);
@@ -6260,6 +6261,7 @@ void md_stop(struct mddev *mddev)
 	/* stop the array and free an attached data structures.
 	 * This is called from dm-raid
 	 */
+	__md_stop_writes(mddev);
 	__md_stop(mddev);
 	bioset_exit(&mddev->bio_set);
 	bioset_exit(&mddev->sync_set);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 9117fcdee1be..64d6e4cd8a3a 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2639,18 +2639,18 @@ static void check_decay_read_errors(struct mddev *mddev, struct md_rdev *rdev)
 }
 
 static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector,
-			    int sectors, struct page *page, int rw)
+			    int sectors, struct page *page, enum req_op op)
 {
 	sector_t first_bad;
 	int bad_sectors;
 
 	if (is_badblock(rdev, sector, sectors, &first_bad, &bad_sectors)
-	    && (rw == READ || test_bit(WriteErrorSeen, &rdev->flags)))
+	    && (op == REQ_OP_READ || test_bit(WriteErrorSeen, &rdev->flags)))
 		return -1;
-	if (sync_page_io(rdev, sector, sectors << 9, page, rw, false))
+	if (sync_page_io(rdev, sector, sectors << 9, page, op, false))
 		/* success */
 		return 1;
-	if (rw == WRITE) {
+	if (op == REQ_OP_WRITE) {
 		set_bit(WriteErrorSeen, &rdev->flags);
 		if (!test_and_set_bit(WantReplacement, &rdev->flags))
 			set_bit(MD_RECOVERY_NEEDED,
@@ -2780,7 +2780,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			if (r10_sync_page_io(rdev,
 					     r10_bio->devs[sl].addr +
 					     sect,
-					     s, conf->tmppage, WRITE)
+					     s, conf->tmppage, REQ_OP_WRITE)
 			    == 0) {
 				/* Well, this device is dead */
 				pr_notice("md/raid10:%s: read correction write failed (%d sectors at %llu on %pg)\n",
@@ -2814,8 +2814,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			switch (r10_sync_page_io(rdev,
 					     r10_bio->devs[sl].addr +
 					     sect,
-					     s, conf->tmppage,
-						 READ)) {
+					     s, conf->tmppage, REQ_OP_READ)) {
 			case 0:
 				/* Well, this device is dead */
 				pr_notice("md/raid10:%s: unable to read back corrected sectors (%d sectors at %llu on %pg)\n",
diff --git a/drivers/media/dvb-core/dvb_vb2.c b/drivers/media/dvb-core/dvb_vb2.c
index a1bd6d9c9223..909df82fed33 100644
--- a/drivers/media/dvb-core/dvb_vb2.c
+++ b/drivers/media/dvb-core/dvb_vb2.c
@@ -354,6 +354,12 @@ int dvb_vb2_reqbufs(struct dvb_vb2_ctx *ctx, struct dmx_requestbuffers *req)
 
 int dvb_vb2_querybuf(struct dvb_vb2_ctx *ctx, struct dmx_buffer *b)
 {
+	struct vb2_queue *q = &ctx->vb_q;
+
+	if (b->index >= q->num_buffers) {
+		dprintk(1, "[%s] buffer index out of range\n", ctx->name);
+		return -EINVAL;
+	}
 	vb2_core_querybuf(&ctx->vb_q, b->index, b);
 	dprintk(3, "[%s] index=%d\n", ctx->name, b->index);
 	return 0;
@@ -378,8 +384,13 @@ int dvb_vb2_expbuf(struct dvb_vb2_ctx *ctx, struct dmx_exportbuffer *exp)
 
 int dvb_vb2_qbuf(struct dvb_vb2_ctx *ctx, struct dmx_buffer *b)
 {
+	struct vb2_queue *q = &ctx->vb_q;
 	int ret;
 
+	if (b->index >= q->num_buffers) {
+		dprintk(1, "[%s] buffer index out of range\n", ctx->name);
+		return -EINVAL;
+	}
 	ret = vb2_core_qbuf(&ctx->vb_q, b->index, b, NULL);
 	if (ret) {
 		dprintk(1, "[%s] index=%d errno=%d\n", ctx->name,
diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c
index 95e8c29ccc65..d2f5f30582a9 100644
--- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c
+++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c
@@ -228,7 +228,6 @@ static int mtk_vcodec_probe(struct platform_device *pdev)
 {
 	struct mtk_vcodec_dev *dev;
 	struct video_device *vfd_enc;
-	struct resource *res;
 	phandle rproc_phandle;
 	enum mtk_vcodec_fw_type fw_type;
 	int ret;
@@ -272,14 +271,12 @@ static int mtk_vcodec_probe(struct platform_device *pdev)
 		goto err_res;
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (res == NULL) {
-		dev_err(&pdev->dev, "failed to get irq resource");
-		ret = -ENOENT;
+	dev->enc_irq = platform_get_irq(pdev, 0);
+	if (dev->enc_irq < 0) {
+		ret = dev->enc_irq;
 		goto err_res;
 	}
 
-	dev->enc_irq = platform_get_irq(pdev, 0);
 	irq_set_status_flags(dev->enc_irq, IRQ_NOAUTOEN);
 	ret = devm_request_irq(&pdev->dev, dev->enc_irq,
 			       mtk_vcodec_enc_irq_handler,
diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c
index 0834d5f866fd..39d2b03e2631 100644
--- a/drivers/media/rc/mceusb.c
+++ b/drivers/media/rc/mceusb.c
@@ -1416,42 +1416,37 @@ static void mceusb_gen1_init(struct mceusb_dev *ir)
 {
 	int ret;
 	struct device *dev = ir->dev;
-	char *data;
-
-	data = kzalloc(USB_CTRL_MSG_SZ, GFP_KERNEL);
-	if (!data) {
-		dev_err(dev, "%s: memory allocation failed!", __func__);
-		return;
-	}
+	char data[USB_CTRL_MSG_SZ];
 
 	/*
 	 * This is a strange one. Windows issues a set address to the device
 	 * on the receive control pipe and expect a certain value pair back
 	 */
-	ret = usb_control_msg(ir->usbdev, usb_rcvctrlpipe(ir->usbdev, 0),
-			      USB_REQ_SET_ADDRESS, USB_TYPE_VENDOR, 0, 0,
-			      data, USB_CTRL_MSG_SZ, 3000);
+	ret = usb_control_msg_recv(ir->usbdev, 0, USB_REQ_SET_ADDRESS,
+				   USB_DIR_IN | USB_TYPE_VENDOR,
+				   0, 0, data, USB_CTRL_MSG_SZ, 3000,
+				   GFP_KERNEL);
 	dev_dbg(dev, "set address - ret = %d", ret);
 	dev_dbg(dev, "set address - data[0] = %d, data[1] = %d",
 						data[0], data[1]);
 
 	/* set feature: bit rate 38400 bps */
-	ret = usb_control_msg(ir->usbdev, usb_sndctrlpipe(ir->usbdev, 0),
-			      USB_REQ_SET_FEATURE, USB_TYPE_VENDOR,
-			      0xc04e, 0x0000, NULL, 0, 3000);
+	ret = usb_control_msg_send(ir->usbdev, 0,
+				   USB_REQ_SET_FEATURE, USB_TYPE_VENDOR,
+				   0xc04e, 0x0000, NULL, 0, 3000, GFP_KERNEL);
 
 	dev_dbg(dev, "set feature - ret = %d", ret);
 
 	/* bRequest 4: set char length to 8 bits */
-	ret = usb_control_msg(ir->usbdev, usb_sndctrlpipe(ir->usbdev, 0),
-			      4, USB_TYPE_VENDOR,
-			      0x0808, 0x0000, NULL, 0, 3000);
+	ret = usb_control_msg_send(ir->usbdev, 0,
+				   4, USB_TYPE_VENDOR,
+				   0x0808, 0x0000, NULL, 0, 3000, GFP_KERNEL);
 	dev_dbg(dev, "set char length - retB = %d", ret);
 
 	/* bRequest 2: set handshaking to use DTR/DSR */
-	ret = usb_control_msg(ir->usbdev, usb_sndctrlpipe(ir->usbdev, 0),
-			      2, USB_TYPE_VENDOR,
-			      0x0000, 0x0100, NULL, 0, 3000);
+	ret = usb_control_msg_send(ir->usbdev, 0,
+				   2, USB_TYPE_VENDOR,
+				   0x0000, 0x0100, NULL, 0, 3000, GFP_KERNEL);
 	dev_dbg(dev, "set handshake  - retC = %d", ret);
 
 	/* device resume */
@@ -1459,8 +1454,6 @@ static void mceusb_gen1_init(struct mceusb_dev *ir)
 
 	/* get hw/sw revision? */
 	mce_command_out(ir, GET_REVISION, sizeof(GET_REVISION));
-
-	kfree(data);
 }
 
 static void mceusb_gen2_init(struct mceusb_dev *ir)
diff --git a/drivers/media/usb/b2c2/flexcop-usb.c b/drivers/media/usb/b2c2/flexcop-usb.c
index 7835bb0f32fc..e012b21c4fd7 100644
--- a/drivers/media/usb/b2c2/flexcop-usb.c
+++ b/drivers/media/usb/b2c2/flexcop-usb.c
@@ -511,7 +511,7 @@ static int flexcop_usb_init(struct flexcop_usb *fc_usb)
 
 	if (fc_usb->uintf->cur_altsetting->desc.bNumEndpoints < 1)
 		return -ENODEV;
-	if (!usb_endpoint_is_isoc_in(&fc_usb->uintf->cur_altsetting->endpoint[1].desc))
+	if (!usb_endpoint_is_isoc_in(&fc_usb->uintf->cur_altsetting->endpoint[0].desc))
 		return -ENODEV;
 
 	switch (fc_usb->udev->speed) {
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index 9c05776f11d1..d509a4a2f08e 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -2740,7 +2740,7 @@ static const struct usb_device_id uvc_ids[] = {
 	  .idProduct		= 0x4034,
 	  .bInterfaceClass	= USB_CLASS_VIDEO,
 	  .bInterfaceSubClass	= 1,
-	  .bInterfaceProtocol	= 0,
+	  .bInterfaceProtocol	= UVC_PC_PROTOCOL_15,
 	  .driver_info		= (kernel_ulong_t)&uvc_ctrl_power_line_limited },
 	/* LogiLink Wireless Webcam */
 	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index 0f3d6b5667b0..55c26e7d370e 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -1040,6 +1040,8 @@ int v4l2_compat_get_array_args(struct file *file, void *mbuf,
 {
 	int err = 0;
 
+	memset(mbuf, 0, array_size);
+
 	switch (cmd) {
 	case VIDIOC_G_FMT32:
 	case VIDIOC_S_FMT32:
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index c314025d977e..e6fd355a2e92 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -2872,9 +2872,9 @@ static const struct v4l2_ioctl_info v4l2_ioctls[] = {
 	IOCTL_INFO(VIDIOC_S_PRIORITY, v4l_s_priority, v4l_print_u32, INFO_FL_PRIO),
 	IOCTL_INFO(VIDIOC_G_SLICED_VBI_CAP, v4l_g_sliced_vbi_cap, v4l_print_sliced_vbi_cap, INFO_FL_CLEAR(v4l2_sliced_vbi_cap, type)),
 	IOCTL_INFO(VIDIOC_LOG_STATUS, v4l_log_status, v4l_print_newline, 0),
-	IOCTL_INFO(VIDIOC_G_EXT_CTRLS, v4l_g_ext_ctrls, v4l_print_ext_controls, INFO_FL_CTRL),
-	IOCTL_INFO(VIDIOC_S_EXT_CTRLS, v4l_s_ext_ctrls, v4l_print_ext_controls, INFO_FL_PRIO | INFO_FL_CTRL),
-	IOCTL_INFO(VIDIOC_TRY_EXT_CTRLS, v4l_try_ext_ctrls, v4l_print_ext_controls, INFO_FL_CTRL),
+	IOCTL_INFO(VIDIOC_G_EXT_CTRLS, v4l_g_ext_ctrls, v4l_print_ext_controls, INFO_FL_CTRL | INFO_FL_ALWAYS_COPY),
+	IOCTL_INFO(VIDIOC_S_EXT_CTRLS, v4l_s_ext_ctrls, v4l_print_ext_controls, INFO_FL_PRIO | INFO_FL_CTRL | INFO_FL_ALWAYS_COPY),
+	IOCTL_INFO(VIDIOC_TRY_EXT_CTRLS, v4l_try_ext_ctrls, v4l_print_ext_controls, INFO_FL_CTRL | INFO_FL_ALWAYS_COPY),
 	IOCTL_INFO(VIDIOC_ENUM_FRAMESIZES, v4l_stub_enum_framesizes, v4l_print_frmsizeenum, INFO_FL_CLEAR(v4l2_frmsizeenum, pixel_format)),
 	IOCTL_INFO(VIDIOC_ENUM_FRAMEINTERVALS, v4l_stub_enum_frameintervals, v4l_print_frmivalenum, INFO_FL_CLEAR(v4l2_frmivalenum, height)),
 	IOCTL_INFO(VIDIOC_G_ENC_INDEX, v4l_stub_g_enc_index, v4l_print_enc_idx, 0),
@@ -3367,8 +3367,7 @@ video_usercopy(struct file *file, unsigned int orig_cmd, unsigned long arg,
 		array_buf = kvmalloc(array_size, GFP_KERNEL);
 		err = -ENOMEM;
 		if (array_buf == NULL)
-			goto out_array_args;
-		err = -EFAULT;
+			goto out;
 		if (in_compat_syscall())
 			err = v4l2_compat_get_array_args(file, array_buf,
 							 user_ptr, array_size,
@@ -3377,7 +3376,7 @@ video_usercopy(struct file *file, unsigned int orig_cmd, unsigned long arg,
 			err = copy_from_user(array_buf, user_ptr, array_size) ?
 								-EFAULT : 0;
 		if (err)
-			goto out_array_args;
+			goto out;
 		*kernel_ptr = array_buf;
 	}
 
@@ -3395,6 +3394,13 @@ video_usercopy(struct file *file, unsigned int orig_cmd, unsigned long arg,
 			trace_v4l2_qbuf(video_devdata(file)->minor, parg);
 	}
 
+	/*
+	 * Some ioctls can return an error, but still have valid
+	 * results that must be returned.
+	 */
+	if (err < 0 && !always_copy)
+		goto out;
+
 	if (has_array_args) {
 		*kernel_ptr = (void __force *)user_ptr;
 		if (in_compat_syscall()) {
@@ -3409,16 +3415,8 @@ video_usercopy(struct file *file, unsigned int orig_cmd, unsigned long arg,
 		} else if (copy_to_user(user_ptr, array_buf, array_size)) {
 			err = -EFAULT;
 		}
-		goto out_array_args;
 	}
-	/*
-	 * Some ioctls can return an error, but still have valid
-	 * results that must be returned.
-	 */
-	if (err < 0 && !always_copy)
-		goto out;
 
-out_array_args:
 	if (video_put_user((void __user *)arg, parg, cmd, orig_cmd))
 		err = -EFAULT;
 out:
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 93ebd174d848..5d9e3483b89d 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -25,7 +25,7 @@
 #define SDSP_DOMAIN_ID (2)
 #define CDSP_DOMAIN_ID (3)
 #define FASTRPC_DEV_MAX		4 /* adsp, mdsp, slpi, cdsp*/
-#define FASTRPC_MAX_SESSIONS	13 /*12 compute, 1 cpz*/
+#define FASTRPC_MAX_SESSIONS	14
 #define FASTRPC_MAX_VMIDS	16
 #define FASTRPC_ALIGN		128
 #define FASTRPC_MAX_FDLIST	16
@@ -1943,7 +1943,12 @@ static int fastrpc_cb_probe(struct platform_device *pdev)
 	of_property_read_u32(dev->of_node, "qcom,nsessions", &sessions);
 
 	spin_lock_irqsave(&cctx->lock, flags);
-	sess = &cctx->session[cctx->sesscount];
+	if (cctx->sesscount >= FASTRPC_MAX_SESSIONS) {
+		dev_err(&pdev->dev, "too many sessions\n");
+		spin_unlock_irqrestore(&cctx->lock, flags);
+		return -ENOSPC;
+	}
+	sess = &cctx->session[cctx->sesscount++];
 	sess->used = false;
 	sess->valid = true;
 	sess->dev = dev;
@@ -1956,13 +1961,12 @@ static int fastrpc_cb_probe(struct platform_device *pdev)
 		struct fastrpc_session_ctx *dup_sess;
 
 		for (i = 1; i < sessions; i++) {
-			if (cctx->sesscount++ >= FASTRPC_MAX_SESSIONS)
+			if (cctx->sesscount >= FASTRPC_MAX_SESSIONS)
 				break;
-			dup_sess = &cctx->session[cctx->sesscount];
+			dup_sess = &cctx->session[cctx->sesscount++];
 			memcpy(dup_sess, sess, sizeof(*dup_sess));
 		}
 	}
-	cctx->sesscount++;
 	spin_unlock_irqrestore(&cctx->lock, flags);
 	rc = dma_set_mask(dev, DMA_BIT_MASK(32));
 	if (rc) {
diff --git a/drivers/misc/lkdtm/cfi.c b/drivers/misc/lkdtm/cfi.c
index 71483cb1e422..5245cf6013c9 100644
--- a/drivers/misc/lkdtm/cfi.c
+++ b/drivers/misc/lkdtm/cfi.c
@@ -20,6 +20,13 @@ static noinline int lkdtm_increment_int(int *counter)
 
 	return *counter;
 }
+
+/* Don't allow the compiler to inline the calls. */
+static noinline void lkdtm_indirect_call(void (*func)(int *))
+{
+	func(&called_count);
+}
+
 /*
  * This tries to call an indirect function with a mismatched prototype.
  */
@@ -29,15 +36,11 @@ static void lkdtm_CFI_FORWARD_PROTO(void)
 	 * Matches lkdtm_increment_void()'s prototype, but not
 	 * lkdtm_increment_int()'s prototype.
 	 */
-	void (*func)(int *);
-
 	pr_info("Calling matched prototype ...\n");
-	func = lkdtm_increment_void;
-	func(&called_count);
+	lkdtm_indirect_call(lkdtm_increment_void);
 
 	pr_info("Calling mismatched prototype ...\n");
-	func = (void *)lkdtm_increment_int;
-	func(&called_count);
+	lkdtm_indirect_call((void *)lkdtm_increment_int);
 
 	pr_err("FAIL: survived mismatched prototype function call!\n");
 	pr_expected_config(CONFIG_CFI_CLANG);
diff --git a/drivers/misc/lkdtm/fortify.c b/drivers/misc/lkdtm/fortify.c
index 080293fa3c52..015927665678 100644
--- a/drivers/misc/lkdtm/fortify.c
+++ b/drivers/misc/lkdtm/fortify.c
@@ -10,28 +10,31 @@
 
 static volatile int fortify_scratch_space;
 
-static void lkdtm_FORTIFIED_OBJECT(void)
+static void lkdtm_FORTIFY_STR_OBJECT(void)
 {
 	struct target {
 		char a[10];
-	} target[2] = {};
+		int foo;
+	} target[3] = {};
 	/*
 	 * Using volatile prevents the compiler from determining the value of
 	 * 'size' at compile time. Without that, we would get a compile error
 	 * rather than a runtime error.
 	 */
-	volatile int size = 11;
+	volatile int size = 20;
+
+	pr_info("trying to strcmp() past the end of a struct\n");
 
-	pr_info("trying to read past the end of a struct\n");
+	strncpy(target[0].a, target[1].a, size);
 
 	/* Store result to global to prevent the code from being eliminated */
-	fortify_scratch_space = memcmp(&target[0], &target[1], size);
+	fortify_scratch_space = target[0].a[3];
 
-	pr_err("FAIL: fortify did not block an object overread!\n");
+	pr_err("FAIL: fortify did not block a strncpy() object write overflow!\n");
 	pr_expected_config(CONFIG_FORTIFY_SOURCE);
 }
 
-static void lkdtm_FORTIFIED_SUBOBJECT(void)
+static void lkdtm_FORTIFY_STR_MEMBER(void)
 {
 	struct target {
 		char a[10];
@@ -44,7 +47,7 @@ static void lkdtm_FORTIFIED_SUBOBJECT(void)
 	strscpy(src, "over ten bytes", size);
 	size = strlen(src) + 1;
 
-	pr_info("trying to strncpy past the end of a member of a struct\n");
+	pr_info("trying to strncpy() past the end of a struct member...\n");
 
 	/*
 	 * strncpy(target.a, src, 20); will hit a compile error because the
@@ -56,7 +59,72 @@ static void lkdtm_FORTIFIED_SUBOBJECT(void)
 	/* Store result to global to prevent the code from being eliminated */
 	fortify_scratch_space = target.a[3];
 
-	pr_err("FAIL: fortify did not block an sub-object overrun!\n");
+	pr_err("FAIL: fortify did not block a strncpy() struct member write overflow!\n");
+	pr_expected_config(CONFIG_FORTIFY_SOURCE);
+
+	kfree(src);
+}
+
+static void lkdtm_FORTIFY_MEM_OBJECT(void)
+{
+	int before[10];
+	struct target {
+		char a[10];
+		int foo;
+	} target = {};
+	int after[10];
+	/*
+	 * Using volatile prevents the compiler from determining the value of
+	 * 'size' at compile time. Without that, we would get a compile error
+	 * rather than a runtime error.
+	 */
+	volatile int size = 20;
+
+	memset(before, 0, sizeof(before));
+	memset(after, 0, sizeof(after));
+	fortify_scratch_space = before[5];
+	fortify_scratch_space = after[5];
+
+	pr_info("trying to memcpy() past the end of a struct\n");
+
+	pr_info("0: %zu\n", __builtin_object_size(&target, 0));
+	pr_info("1: %zu\n", __builtin_object_size(&target, 1));
+	pr_info("s: %d\n", size);
+	memcpy(&target, &before, size);
+
+	/* Store result to global to prevent the code from being eliminated */
+	fortify_scratch_space = target.a[3];
+
+	pr_err("FAIL: fortify did not block a memcpy() object write overflow!\n");
+	pr_expected_config(CONFIG_FORTIFY_SOURCE);
+}
+
+static void lkdtm_FORTIFY_MEM_MEMBER(void)
+{
+	struct target {
+		char a[10];
+		char b[10];
+	} target;
+	volatile int size = 20;
+	char *src;
+
+	src = kmalloc(size, GFP_KERNEL);
+	strscpy(src, "over ten bytes", size);
+	size = strlen(src) + 1;
+
+	pr_info("trying to memcpy() past the end of a struct member...\n");
+
+	/*
+	 * strncpy(target.a, src, 20); will hit a compile error because the
+	 * compiler knows at build time that target.a < 20 bytes. Use a
+	 * volatile to force a runtime error.
+	 */
+	memcpy(target.a, src, size);
+
+	/* Store result to global to prevent the code from being eliminated */
+	fortify_scratch_space = target.a[3];
+
+	pr_err("FAIL: fortify did not block a memcpy() struct member write overflow!\n");
 	pr_expected_config(CONFIG_FORTIFY_SOURCE);
 
 	kfree(src);
@@ -67,7 +135,7 @@ static void lkdtm_FORTIFIED_SUBOBJECT(void)
  * strscpy and generate a panic because there is a write overflow (i.e. src
  * length is greater than dst length).
  */
-static void lkdtm_FORTIFIED_STRSCPY(void)
+static void lkdtm_FORTIFY_STRSCPY(void)
 {
 	char *src;
 	char dst[5];
@@ -136,9 +204,11 @@ static void lkdtm_FORTIFIED_STRSCPY(void)
 }
 
 static struct crashtype crashtypes[] = {
-	CRASHTYPE(FORTIFIED_OBJECT),
-	CRASHTYPE(FORTIFIED_SUBOBJECT),
-	CRASHTYPE(FORTIFIED_STRSCPY),
+	CRASHTYPE(FORTIFY_STR_OBJECT),
+	CRASHTYPE(FORTIFY_STR_MEMBER),
+	CRASHTYPE(FORTIFY_MEM_OBJECT),
+	CRASHTYPE(FORTIFY_MEM_MEMBER),
+	CRASHTYPE(FORTIFY_STRSCPY),
 };
 
 struct crashtype_category fortify_crashtypes = {
diff --git a/drivers/misc/lkdtm/usercopy.c b/drivers/misc/lkdtm/usercopy.c
index 6215ec995cd3..67db57249a34 100644
--- a/drivers/misc/lkdtm/usercopy.c
+++ b/drivers/misc/lkdtm/usercopy.c
@@ -330,7 +330,7 @@ static void lkdtm_USERCOPY_KERNEL(void)
 
 	pr_info("attempting bad copy_to_user from kernel text: %px\n",
 		vm_mmap);
-	if (copy_to_user((void __user *)user_addr, function_nocfi(vm_mmap),
+	if (copy_to_user((void __user *)user_addr, vm_mmap,
 			 unconst + PAGE_SIZE)) {
 		pr_warn("copy_to_user failed, but lacked Oops\n");
 		goto free_user;
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index cee4c0b59f43..3662bf5320ce 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -870,7 +870,8 @@ try_again:
 	 * the CCS bit is set as well. We deliberately deviate from the spec in
 	 * regards to this, which allows UHS-I to be supported for SDSC cards.
 	 */
-	if (!mmc_host_is_spi(host) && rocr && (*rocr & SD_ROCR_S18A)) {
+	if (!mmc_host_is_spi(host) && (ocr & SD_OCR_S18R) &&
+	    rocr && (*rocr & SD_ROCR_S18A)) {
 		err = mmc_set_uhs_voltage(host, pocr);
 		if (err == -EAGAIN) {
 			retries--;
@@ -949,16 +950,17 @@ int mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card,
 
 		/* Erase init depends on CSD and SSR */
 		mmc_init_erase(card);
-
-		/*
-		 * Fetch switch information from card.
-		 */
-		err = mmc_read_switch(card);
-		if (err)
-			return err;
 	}
 
 	/*
+	 * Fetch switch information from card. Note, sd3_bus_mode can change if
+	 * voltage switch outcome changes, so do this always.
+	 */
+	err = mmc_read_switch(card);
+	if (err)
+		return err;
+
+	/*
 	 * For SPI, enable CRC as appropriate.
 	 * This CRC enable is located AFTER the reading of the
 	 * card registers because some SDHC cards are not able
@@ -1480,26 +1482,15 @@ retry:
 	if (!v18_fixup_failed && !mmc_host_is_spi(host) && mmc_host_uhs(host) &&
 	    mmc_sd_card_using_v18(card) &&
 	    host->ios.signal_voltage != MMC_SIGNAL_VOLTAGE_180) {
-		/*
-		 * Re-read switch information in case it has changed since
-		 * oldcard was initialized.
-		 */
-		if (oldcard) {
-			err = mmc_read_switch(card);
-			if (err)
-				goto free_card;
-		}
-		if (mmc_sd_card_using_v18(card)) {
-			if (mmc_host_set_uhs_voltage(host) ||
-			    mmc_sd_init_uhs_card(card)) {
-				v18_fixup_failed = true;
-				mmc_power_cycle(host, ocr);
-				if (!oldcard)
-					mmc_remove_card(card);
-				goto retry;
-			}
-			goto done;
+		if (mmc_host_set_uhs_voltage(host) ||
+		    mmc_sd_init_uhs_card(card)) {
+			v18_fixup_failed = true;
+			mmc_power_cycle(host, ocr);
+			if (!oldcard)
+				mmc_remove_card(card);
+			goto retry;
 		}
+		goto cont;
 	}
 
 	/* Initialization sequence for UHS-I cards */
@@ -1534,7 +1525,7 @@ retry:
 			mmc_set_bus_width(host, MMC_BUS_WIDTH_4);
 		}
 	}
-
+cont:
 	if (!oldcard) {
 		/* Read/parse the extension registers. */
 		err = sd_read_ext_regs(card);
@@ -1566,7 +1557,7 @@ retry:
 		err = -EINVAL;
 		goto free_card;
 	}
-done:
+
 	host->card = card;
 	return 0;
 
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 10c563999d3d..e63608834411 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -171,6 +171,7 @@ config MMC_SDHCI_OF_ASPEED
 config MMC_SDHCI_OF_ASPEED_TEST
 	bool "Tests for the ASPEED SDHCI driver" if !KUNIT_ALL_TESTS
 	depends on MMC_SDHCI_OF_ASPEED && KUNIT
+	depends on (MMC_SDHCI_OF_ASPEED=m || KUNIT=y)
 	default KUNIT_ALL_TESTS
 	help
 	  Enable KUnit tests for the ASPEED SDHCI driver. Select this
diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c
index 2f08d442e557..fc462995cf94 100644
--- a/drivers/mmc/host/meson-gx-mmc.c
+++ b/drivers/mmc/host/meson-gx-mmc.c
@@ -1172,8 +1172,10 @@ static int meson_mmc_probe(struct platform_device *pdev)
 	}
 
 	ret = device_reset_optional(&pdev->dev);
-	if (ret)
-		return dev_err_probe(&pdev->dev, ret, "device reset failed\n");
+	if (ret) {
+		dev_err_probe(&pdev->dev, ret, "device reset failed\n");
+		goto free_host;
+	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	host->regs = devm_ioremap_resource(&pdev->dev, res);
diff --git a/drivers/mmc/host/mmc_hsq.c b/drivers/mmc/host/mmc_hsq.c
index a5e05ed0fda3..9d35453e7371 100644
--- a/drivers/mmc/host/mmc_hsq.c
+++ b/drivers/mmc/host/mmc_hsq.c
@@ -34,7 +34,7 @@ static void mmc_hsq_pump_requests(struct mmc_hsq *hsq)
 	spin_lock_irqsave(&hsq->lock, flags);
 
 	/* Make sure we are not already running a request now */
-	if (hsq->mrq) {
+	if (hsq->mrq || hsq->recovery_halt) {
 		spin_unlock_irqrestore(&hsq->lock, flags);
 		return;
 	}
diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c
index b6eb75f4bbfc..dfc3ffd5b1f8 100644
--- a/drivers/mmc/host/moxart-mmc.c
+++ b/drivers/mmc/host/moxart-mmc.c
@@ -111,8 +111,8 @@
 #define CLK_DIV_MASK		0x7f
 
 /* REG_BUS_WIDTH */
-#define BUS_WIDTH_8		BIT(2)
-#define BUS_WIDTH_4		BIT(1)
+#define BUS_WIDTH_4_SUPPORT	BIT(3)
+#define BUS_WIDTH_4		BIT(2)
 #define BUS_WIDTH_1		BIT(0)
 
 #define MMC_VDD_360		23
@@ -524,9 +524,6 @@ static void moxart_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	case MMC_BUS_WIDTH_4:
 		writel(BUS_WIDTH_4, host->base + REG_BUS_WIDTH);
 		break;
-	case MMC_BUS_WIDTH_8:
-		writel(BUS_WIDTH_8, host->base + REG_BUS_WIDTH);
-		break;
 	default:
 		writel(BUS_WIDTH_1, host->base + REG_BUS_WIDTH);
 		break;
@@ -651,16 +648,8 @@ static int moxart_probe(struct platform_device *pdev)
 		dmaengine_slave_config(host->dma_chan_rx, &cfg);
 	}
 
-	switch ((readl(host->base + REG_BUS_WIDTH) >> 3) & 3) {
-	case 1:
+	if (readl(host->base + REG_BUS_WIDTH) & BUS_WIDTH_4_SUPPORT)
 		mmc->caps |= MMC_CAP_4_BIT_DATA;
-		break;
-	case 2:
-		mmc->caps |= MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA;
-		break;
-	default:
-		break;
-	}
 
 	writel(0, host->base + REG_INTERRUPT_MASK);
 
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 4ff73d1883de..69d78604d1fc 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -2446,6 +2446,9 @@ static void msdc_cqe_disable(struct mmc_host *mmc, bool recovery)
 	/* disable busy check */
 	sdr_clr_bits(host->base + MSDC_PATCH_BIT1, MSDC_PB1_BUSY_CHECK_SEL);
 
+	val = readl(host->base + MSDC_INT);
+	writel(val, host->base + MSDC_INT);
+
 	if (recovery) {
 		sdr_set_field(host->base + MSDC_DMA_CTRL,
 			      MSDC_DMA_CTRL_STOP, 1);
@@ -2932,11 +2935,14 @@ static int __maybe_unused msdc_suspend(struct device *dev)
 	struct mmc_host *mmc = dev_get_drvdata(dev);
 	struct msdc_host *host = mmc_priv(mmc);
 	int ret;
+	u32 val;
 
 	if (mmc->caps2 & MMC_CAP2_CQE) {
 		ret = cqhci_suspend(mmc);
 		if (ret)
 			return ret;
+		val = readl(host->base + MSDC_INT);
+		writel(val, host->base + MSDC_INT);
 	}
 
 	/*
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index 0db9490dc659..e4003f6058eb 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -648,7 +648,7 @@ static int pxamci_probe(struct platform_device *pdev)
 
 	ret = pxamci_of_init(pdev, mmc);
 	if (ret)
-		return ret;
+		goto out;
 
 	host = mmc_priv(mmc);
 	host->mmc = mmc;
@@ -672,7 +672,7 @@ static int pxamci_probe(struct platform_device *pdev)
 
 	ret = pxamci_init_ocr(host);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	mmc->caps = 0;
 	host->cmdat = 0;
diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c
index 4e904850973c..a7343d4bc50e 100644
--- a/drivers/mmc/host/sdhci-of-dwcmshc.c
+++ b/drivers/mmc/host/sdhci-of-dwcmshc.c
@@ -349,6 +349,15 @@ static const struct sdhci_pltfm_data sdhci_dwcmshc_pdata = {
 	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
 };
 
+#ifdef CONFIG_ACPI
+static const struct sdhci_pltfm_data sdhci_dwcmshc_bf3_pdata = {
+	.ops = &sdhci_dwcmshc_ops,
+	.quirks = SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+		   SDHCI_QUIRK2_ACMD23_BROKEN,
+};
+#endif
+
 static const struct sdhci_pltfm_data sdhci_dwcmshc_rk35xx_pdata = {
 	.ops = &sdhci_dwcmshc_rk35xx_ops,
 	.quirks = SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN |
@@ -431,7 +440,10 @@ MODULE_DEVICE_TABLE(of, sdhci_dwcmshc_dt_ids);
 
 #ifdef CONFIG_ACPI
 static const struct acpi_device_id sdhci_dwcmshc_acpi_ids[] = {
-	{ .id = "MLNXBF30" },
+	{
+		.id = "MLNXBF30",
+		.driver_data = (kernel_ulong_t)&sdhci_dwcmshc_bf3_pdata,
+	},
 	{}
 };
 #endif
@@ -447,7 +459,7 @@ static int dwcmshc_probe(struct platform_device *pdev)
 	int err;
 	u32 extra;
 
-	pltfm_data = of_device_get_match_data(&pdev->dev);
+	pltfm_data = device_get_match_data(&pdev->dev);
 	if (!pltfm_data) {
 		dev_err(&pdev->dev, "Error: No device match data found\n");
 		return -ENODEV;
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 7689ffec5ad1..251172890af7 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -3928,7 +3928,7 @@ bool sdhci_cqe_irq(struct sdhci_host *host, u32 intmask, int *cmd_error,
 
 	if (intmask & (SDHCI_INT_INDEX | SDHCI_INT_END_BIT | SDHCI_INT_CRC)) {
 		*cmd_error = -EILSEQ;
-		if (!mmc_op_tuning(host->cmd->opcode))
+		if (!mmc_op_tuning(SDHCI_GET_CMD(sdhci_readw(host, SDHCI_COMMAND))))
 			sdhci_err_stats_inc(host, CMD_CRC);
 	} else if (intmask & SDHCI_INT_TIMEOUT) {
 		*cmd_error = -ETIMEDOUT;
@@ -3938,7 +3938,7 @@ bool sdhci_cqe_irq(struct sdhci_host *host, u32 intmask, int *cmd_error,
 
 	if (intmask & (SDHCI_INT_DATA_END_BIT | SDHCI_INT_DATA_CRC)) {
 		*data_error = -EILSEQ;
-		if (!mmc_op_tuning(host->cmd->opcode))
+		if (!mmc_op_tuning(SDHCI_GET_CMD(sdhci_readw(host, SDHCI_COMMAND))))
 			sdhci_err_stats_inc(host, DAT_CRC);
 	} else if (intmask & SDHCI_INT_DATA_TIMEOUT) {
 		*data_error = -ETIMEDOUT;
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index d7fb33c078e8..e58a1e0cadd2 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -84,11 +84,13 @@ enum ad_link_speed_type {
 static const u8 null_mac_addr[ETH_ALEN + 2] __long_aligned = {
 	0, 0, 0, 0, 0, 0
 };
-static u16 ad_ticks_per_sec;
+
+static const u16 ad_ticks_per_sec = 1000 / AD_TIMER_INTERVAL;
 static const int ad_delta_in_ticks = (AD_TIMER_INTERVAL * HZ) / 1000;
 
-static const u8 lacpdu_mcast_addr[ETH_ALEN + 2] __long_aligned =
-	MULTICAST_LACPDU_ADDR;
+const u8 lacpdu_mcast_addr[ETH_ALEN + 2] __long_aligned = {
+	0x01, 0x80, 0xC2, 0x00, 0x00, 0x02
+};
 
 /* ================= main 802.3ad protocol functions ================== */
 static int ad_lacpdu_send(struct port *port);
@@ -2001,36 +2003,24 @@ void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout)
 /**
  * bond_3ad_initialize - initialize a bond's 802.3ad parameters and structures
  * @bond: bonding struct to work on
- * @tick_resolution: tick duration (millisecond resolution)
  *
  * Can be called only after the mac address of the bond is set.
  */
-void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution)
+void bond_3ad_initialize(struct bonding *bond)
 {
-	/* check that the bond is not initialized yet */
-	if (!MAC_ADDRESS_EQUAL(&(BOND_AD_INFO(bond).system.sys_mac_addr),
-				bond->dev->dev_addr)) {
-
-		BOND_AD_INFO(bond).aggregator_identifier = 0;
-
-		BOND_AD_INFO(bond).system.sys_priority =
-			bond->params.ad_actor_sys_prio;
-		if (is_zero_ether_addr(bond->params.ad_actor_system))
-			BOND_AD_INFO(bond).system.sys_mac_addr =
-			    *((struct mac_addr *)bond->dev->dev_addr);
-		else
-			BOND_AD_INFO(bond).system.sys_mac_addr =
-			    *((struct mac_addr *)bond->params.ad_actor_system);
-
-		/* initialize how many times this module is called in one
-		 * second (should be about every 100ms)
-		 */
-		ad_ticks_per_sec = tick_resolution;
+	BOND_AD_INFO(bond).aggregator_identifier = 0;
+	BOND_AD_INFO(bond).system.sys_priority =
+		bond->params.ad_actor_sys_prio;
+	if (is_zero_ether_addr(bond->params.ad_actor_system))
+		BOND_AD_INFO(bond).system.sys_mac_addr =
+		    *((struct mac_addr *)bond->dev->dev_addr);
+	else
+		BOND_AD_INFO(bond).system.sys_mac_addr =
+		    *((struct mac_addr *)bond->params.ad_actor_system);
 
-		bond_3ad_initiate_agg_selection(bond,
-						AD_AGGREGATOR_SELECTION_TIMER *
-						ad_ticks_per_sec);
-	}
+	bond_3ad_initiate_agg_selection(bond,
+					AD_AGGREGATOR_SELECTION_TIMER *
+					ad_ticks_per_sec);
 }
 
 /**
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 50e60843020c..86d42306aa5e 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -865,12 +865,8 @@ static void bond_hw_addr_flush(struct net_device *bond_dev,
 	dev_uc_unsync(slave_dev, bond_dev);
 	dev_mc_unsync(slave_dev, bond_dev);
 
-	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
-		/* del lacpdu mc addr from mc list */
-		u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;
-
-		dev_mc_del(slave_dev, lacpdu_multicast);
-	}
+	if (BOND_MODE(bond) == BOND_MODE_8023AD)
+		dev_mc_del(slave_dev, lacpdu_mcast_addr);
 }
 
 /*--------------------------- Active slave change ---------------------------*/
@@ -890,7 +886,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
 		if (bond->dev->flags & IFF_ALLMULTI)
 			dev_set_allmulti(old_active->dev, -1);
 
-		bond_hw_addr_flush(bond->dev, old_active->dev);
+		if (bond->dev->flags & IFF_UP)
+			bond_hw_addr_flush(bond->dev, old_active->dev);
 	}
 
 	if (new_active) {
@@ -901,10 +898,12 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
 		if (bond->dev->flags & IFF_ALLMULTI)
 			dev_set_allmulti(new_active->dev, 1);
 
-		netif_addr_lock_bh(bond->dev);
-		dev_uc_sync(new_active->dev, bond->dev);
-		dev_mc_sync(new_active->dev, bond->dev);
-		netif_addr_unlock_bh(bond->dev);
+		if (bond->dev->flags & IFF_UP) {
+			netif_addr_lock_bh(bond->dev);
+			dev_uc_sync(new_active->dev, bond->dev);
+			dev_mc_sync(new_active->dev, bond->dev);
+			netif_addr_unlock_bh(bond->dev);
+		}
 	}
 }
 
@@ -2081,7 +2080,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 			/* Initialize AD with the number of times that the AD timer is called in 1 second
 			 * can be called only after the mac address of the bond is set
 			 */
-			bond_3ad_initialize(bond, 1000/AD_TIMER_INTERVAL);
+			bond_3ad_initialize(bond);
 		} else {
 			SLAVE_AD_INFO(new_slave)->id =
 				SLAVE_AD_INFO(prev_slave)->id + 1;
@@ -2166,16 +2165,14 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 			}
 		}
 
-		netif_addr_lock_bh(bond_dev);
-		dev_mc_sync_multiple(slave_dev, bond_dev);
-		dev_uc_sync_multiple(slave_dev, bond_dev);
-		netif_addr_unlock_bh(bond_dev);
-
-		if (BOND_MODE(bond) == BOND_MODE_8023AD) {
-			/* add lacpdu mc addr to mc list */
-			u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;
+		if (bond_dev->flags & IFF_UP) {
+			netif_addr_lock_bh(bond_dev);
+			dev_mc_sync_multiple(slave_dev, bond_dev);
+			dev_uc_sync_multiple(slave_dev, bond_dev);
+			netif_addr_unlock_bh(bond_dev);
 
-			dev_mc_add(slave_dev, lacpdu_multicast);
+			if (BOND_MODE(bond) == BOND_MODE_8023AD)
+				dev_mc_add(slave_dev, lacpdu_mcast_addr);
 		}
 	}
 
@@ -2447,7 +2444,8 @@ static int __bond_release_one(struct net_device *bond_dev,
 		if (old_flags & IFF_ALLMULTI)
 			dev_set_allmulti(slave_dev, -1);
 
-		bond_hw_addr_flush(bond_dev, slave_dev);
+		if (old_flags & IFF_UP)
+			bond_hw_addr_flush(bond_dev, slave_dev);
 	}
 
 	slave_disable_netpoll(slave);
@@ -3167,6 +3165,9 @@ static void bond_ns_send_all(struct bonding *bond, struct slave *slave)
 found:
 		if (!ipv6_dev_get_saddr(dev_net(dst->dev), dst->dev, &targets[i], 0, &saddr))
 			bond_ns_send(slave, &targets[i], &saddr, tags);
+		else
+			bond_ns_send(slave, &targets[i], &in6addr_any, tags);
+
 		dst_release(dst);
 		kfree(tags);
 	}
@@ -3198,12 +3199,19 @@ static bool bond_has_this_ip6(struct bonding *bond, struct in6_addr *addr)
 	return ret;
 }
 
-static void bond_validate_ns(struct bonding *bond, struct slave *slave,
+static void bond_validate_na(struct bonding *bond, struct slave *slave,
 			     struct in6_addr *saddr, struct in6_addr *daddr)
 {
 	int i;
 
-	if (ipv6_addr_any(saddr) || !bond_has_this_ip6(bond, daddr)) {
+	/* Ignore NAs that:
+	 * 1. Source address is unspecified address.
+	 * 2. Dest address is neither all-nodes multicast address nor
+	 *    exist on bond interface.
+	 */
+	if (ipv6_addr_any(saddr) ||
+	    (!ipv6_addr_equal(daddr, &in6addr_linklocal_allnodes) &&
+	     !bond_has_this_ip6(bond, daddr))) {
 		slave_dbg(bond->dev, slave->dev, "%s: sip %pI6c tip %pI6c not found\n",
 			  __func__, saddr, daddr);
 		return;
@@ -3246,14 +3254,14 @@ static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond,
 	 * see bond_arp_rcv().
 	 */
 	if (bond_is_active_slave(slave))
-		bond_validate_ns(bond, slave, saddr, daddr);
+		bond_validate_na(bond, slave, saddr, daddr);
 	else if (curr_active_slave &&
 		 time_after(slave_last_rx(bond, curr_active_slave),
 			    curr_active_slave->last_link_up))
-		bond_validate_ns(bond, slave, saddr, daddr);
+		bond_validate_na(bond, slave, saddr, daddr);
 	else if (curr_arp_slave &&
 		 bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1))
-		bond_validate_ns(bond, slave, saddr, daddr);
+		bond_validate_na(bond, slave, saddr, daddr);
 
 out:
 	return RX_HANDLER_ANOTHER;
@@ -4174,6 +4182,12 @@ static int bond_open(struct net_device *bond_dev)
 	struct list_head *iter;
 	struct slave *slave;
 
+	if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN && !bond->rr_tx_counter) {
+		bond->rr_tx_counter = alloc_percpu(u32);
+		if (!bond->rr_tx_counter)
+			return -ENOMEM;
+	}
+
 	/* reset slave->backup and slave->inactive */
 	if (bond_has_slaves(bond)) {
 		bond_for_each_slave(bond, slave, iter) {
@@ -4211,6 +4225,9 @@ static int bond_open(struct net_device *bond_dev)
 		/* register to receive LACPDUs */
 		bond->recv_probe = bond_3ad_lacpdu_recv;
 		bond_3ad_initiate_agg_selection(bond, 1);
+
+		bond_for_each_slave(bond, slave, iter)
+			dev_mc_add(slave->dev, lacpdu_mcast_addr);
 	}
 
 	if (bond_mode_can_use_xmit_hash(bond))
@@ -4222,6 +4239,7 @@ static int bond_open(struct net_device *bond_dev)
 static int bond_close(struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
+	struct slave *slave;
 
 	bond_work_cancel_all(bond);
 	bond->send_peer_notif = 0;
@@ -4229,6 +4247,19 @@ static int bond_close(struct net_device *bond_dev)
 		bond_alb_deinitialize(bond);
 	bond->recv_probe = NULL;
 
+	if (bond_uses_primary(bond)) {
+		rcu_read_lock();
+		slave = rcu_dereference(bond->curr_active_slave);
+		if (slave)
+			bond_hw_addr_flush(bond_dev, slave->dev);
+		rcu_read_unlock();
+	} else {
+		struct list_head *iter;
+
+		bond_for_each_slave(bond, slave, iter)
+			bond_hw_addr_flush(bond_dev, slave->dev);
+	}
+
 	return 0;
 }
 
@@ -6218,15 +6249,6 @@ static int bond_init(struct net_device *bond_dev)
 	if (!bond->wq)
 		return -ENOMEM;
 
-	if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN) {
-		bond->rr_tx_counter = alloc_percpu(u32);
-		if (!bond->rr_tx_counter) {
-			destroy_workqueue(bond->wq);
-			bond->wq = NULL;
-			return -ENOMEM;
-		}
-	}
-
 	spin_lock_init(&bond->stats_lock);
 	netdev_lockdep_set_classes(bond_dev);
 
diff --git a/drivers/net/can/c_can/c_can.h b/drivers/net/can/c_can/c_can.h
index f23a03300a81..029cd8194ed5 100644
--- a/drivers/net/can/c_can/c_can.h
+++ b/drivers/net/can/c_can/c_can.h
@@ -235,9 +235,22 @@ static inline u8 c_can_get_tx_tail(const struct c_can_tx_ring *ring)
 	return ring->tail & (ring->obj_num - 1);
 }
 
-static inline u8 c_can_get_tx_free(const struct c_can_tx_ring *ring)
+static inline u8 c_can_get_tx_free(const struct c_can_priv *priv,
+				   const struct c_can_tx_ring *ring)
 {
-	return ring->obj_num - (ring->head - ring->tail);
+	u8 head = c_can_get_tx_head(ring);
+	u8 tail = c_can_get_tx_tail(ring);
+
+	if (priv->type == BOSCH_D_CAN)
+		return ring->obj_num - (ring->head - ring->tail);
+
+	/* This is not a FIFO. C/D_CAN sends out the buffers
+	 * prioritized. The lowest buffer number wins.
+	 */
+	if (head < tail)
+		return 0;
+
+	return ring->obj_num - head;
 }
 
 #endif /* C_CAN_H */
diff --git a/drivers/net/can/c_can/c_can_main.c b/drivers/net/can/c_can/c_can_main.c
index dc8132862f33..d6605dbb7737 100644
--- a/drivers/net/can/c_can/c_can_main.c
+++ b/drivers/net/can/c_can/c_can_main.c
@@ -429,7 +429,7 @@ static void c_can_setup_receive_object(struct net_device *dev, int iface,
 static bool c_can_tx_busy(const struct c_can_priv *priv,
 			  const struct c_can_tx_ring *tx_ring)
 {
-	if (c_can_get_tx_free(tx_ring) > 0)
+	if (c_can_get_tx_free(priv, tx_ring) > 0)
 		return false;
 
 	netif_stop_queue(priv->dev);
@@ -437,7 +437,7 @@ static bool c_can_tx_busy(const struct c_can_priv *priv,
 	/* Memory barrier before checking tx_free (head and tail) */
 	smp_mb();
 
-	if (c_can_get_tx_free(tx_ring) == 0) {
+	if (c_can_get_tx_free(priv, tx_ring) == 0) {
 		netdev_dbg(priv->dev,
 			   "Stopping tx-queue (tx_head=0x%08x, tx_tail=0x%08x, len=%d).\n",
 			   tx_ring->head, tx_ring->tail,
@@ -465,7 +465,7 @@ static netdev_tx_t c_can_start_xmit(struct sk_buff *skb,
 
 	idx = c_can_get_tx_head(tx_ring);
 	tx_ring->head++;
-	if (c_can_get_tx_free(tx_ring) == 0)
+	if (c_can_get_tx_free(priv, tx_ring) == 0)
 		netif_stop_queue(dev);
 
 	if (idx < c_can_get_tx_tail(tx_ring))
@@ -748,7 +748,7 @@ static void c_can_do_tx(struct net_device *dev)
 		return;
 
 	tx_ring->tail += pkts;
-	if (c_can_get_tx_free(tx_ring)) {
+	if (c_can_get_tx_free(priv, tx_ring)) {
 		/* Make sure that anybody stopping the queue after
 		 * this sees the new tx_ring->tail.
 		 */
@@ -760,8 +760,7 @@ static void c_can_do_tx(struct net_device *dev)
 	stats->tx_packets += pkts;
 
 	tail = c_can_get_tx_tail(tx_ring);
-
-	if (tail == 0) {
+	if (priv->type == BOSCH_D_CAN && tail == 0) {
 		u8 head = c_can_get_tx_head(tx_ring);
 
 		/* Start transmission for all cached messages */
diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index f857968efed7..ccb438eca517 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -941,11 +941,6 @@ static struct sk_buff *flexcan_mailbox_read(struct can_rx_offload *offload,
 	u32 reg_ctrl, reg_id, reg_iflag1;
 	int i;
 
-	if (unlikely(drop)) {
-		skb = ERR_PTR(-ENOBUFS);
-		goto mark_as_read;
-	}
-
 	mb = flexcan_get_mb(priv, n);
 
 	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_USE_RX_MAILBOX) {
@@ -974,6 +969,11 @@ static struct sk_buff *flexcan_mailbox_read(struct can_rx_offload *offload,
 		reg_ctrl = priv->read(&mb->can_ctrl);
 	}
 
+	if (unlikely(drop)) {
+		skb = ERR_PTR(-ENOBUFS);
+		goto mark_as_read;
+	}
+
 	if (reg_ctrl & FLEXCAN_MB_CNT_EDL)
 		skb = alloc_canfd_skb(offload->dev, &cfd);
 	else
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index baf749c8cda3..c1ff3c046d62 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -824,6 +824,7 @@ static int gs_can_open(struct net_device *netdev)
 		flags |= GS_CAN_MODE_TRIPLE_SAMPLE;
 
 	/* finally start device */
+	dev->can.state = CAN_STATE_ERROR_ACTIVE;
 	dm->mode = cpu_to_le32(GS_CAN_MODE_START);
 	dm->flags = cpu_to_le32(flags);
 	rc = usb_control_msg(interface_to_usbdev(dev->iface),
@@ -835,13 +836,12 @@ static int gs_can_open(struct net_device *netdev)
 	if (rc < 0) {
 		netdev_err(netdev, "Couldn't start device (err=%d)\n", rc);
 		kfree(dm);
+		dev->can.state = CAN_STATE_STOPPED;
 		return rc;
 	}
 
 	kfree(dm);
 
-	dev->can.state = CAN_STATE_ERROR_ACTIVE;
-
 	parent->active_channels++;
 	if (!(dev->can.ctrlmode & CAN_CTRLMODE_LISTENONLY))
 		netif_start_queue(netdev);
@@ -925,17 +925,21 @@ static int gs_usb_set_identify(struct net_device *netdev, bool do_identify)
 }
 
 /* blink LED's for finding the this interface */
-static int gs_usb_set_phys_id(struct net_device *dev,
+static int gs_usb_set_phys_id(struct net_device *netdev,
 			      enum ethtool_phys_id_state state)
 {
+	const struct gs_can *dev = netdev_priv(netdev);
 	int rc = 0;
 
+	if (!(dev->feature & GS_CAN_FEATURE_IDENTIFY))
+		return -EOPNOTSUPP;
+
 	switch (state) {
 	case ETHTOOL_ID_ACTIVE:
-		rc = gs_usb_set_identify(dev, GS_CAN_IDENTIFY_ON);
+		rc = gs_usb_set_identify(netdev, GS_CAN_IDENTIFY_ON);
 		break;
 	case ETHTOOL_ID_INACTIVE:
-		rc = gs_usb_set_identify(dev, GS_CAN_IDENTIFY_OFF);
+		rc = gs_usb_set_identify(netdev, GS_CAN_IDENTIFY_OFF);
 		break;
 	default:
 		break;
@@ -1072,9 +1076,10 @@ static struct gs_can *gs_make_candev(unsigned int channel,
 		dev->feature |= GS_CAN_FEATURE_REQ_USB_QUIRK_LPC546XX |
 			GS_CAN_FEATURE_QUIRK_BREQ_CANTACT_PRO;
 
-	if (le32_to_cpu(dconf->sw_version) > 1)
-		if (feature & GS_CAN_FEATURE_IDENTIFY)
-			netdev->ethtool_ops = &gs_usb_ethtool_ops;
+	/* GS_CAN_FEATURE_IDENTIFY is only supported for sw_version > 1 */
+	if (!(le32_to_cpu(dconf->sw_version) > 1 &&
+	      feature & GS_CAN_FEATURE_IDENTIFY))
+		dev->feature &= ~GS_CAN_FEATURE_IDENTIFY;
 
 	kfree(bt_const);
 
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 4b14d80d27ed..e4f446db0ca1 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -613,6 +613,9 @@ int ksz9477_fdb_dump(struct ksz_device *dev, int port,
 			goto exit;
 		}
 
+		if (!(ksz_data & ALU_VALID))
+			continue;
+
 		/* read ALU table */
 		ksz9477_read_table(dev, alu_table);
 
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index ed7d137cba99..872aba63e7d4 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -170,6 +170,13 @@ static const struct ksz_dev_ops ksz8_dev_ops = {
 	.exit = ksz8_switch_exit,
 };
 
+static void ksz9477_phylink_mac_link_up(struct ksz_device *dev, int port,
+					unsigned int mode,
+					phy_interface_t interface,
+					struct phy_device *phydev, int speed,
+					int duplex, bool tx_pause,
+					bool rx_pause);
+
 static const struct ksz_dev_ops ksz9477_dev_ops = {
 	.setup = ksz9477_setup,
 	.get_port_addr = ksz9477_get_port_addr,
@@ -196,6 +203,7 @@ static const struct ksz_dev_ops ksz9477_dev_ops = {
 	.mdb_del = ksz9477_mdb_del,
 	.change_mtu = ksz9477_change_mtu,
 	.max_mtu = ksz9477_max_mtu,
+	.phylink_mac_link_up = ksz9477_phylink_mac_link_up,
 	.config_cpu_port = ksz9477_config_cpu_port,
 	.enable_stp_addr = ksz9477_enable_stp_addr,
 	.reset = ksz9477_reset_switch,
@@ -230,6 +238,7 @@ static const struct ksz_dev_ops lan937x_dev_ops = {
 	.mdb_del = ksz9477_mdb_del,
 	.change_mtu = lan937x_change_mtu,
 	.max_mtu = ksz9477_max_mtu,
+	.phylink_mac_link_up = ksz9477_phylink_mac_link_up,
 	.config_cpu_port = lan937x_config_cpu_port,
 	.enable_stp_addr = ksz9477_enable_stp_addr,
 	.reset = lan937x_reset_switch,
@@ -803,9 +812,15 @@ static void ksz_phylink_get_caps(struct dsa_switch *ds, int port,
 	if (dev->info->supports_rgmii[port])
 		phy_interface_set_rgmii(config->supported_interfaces);
 
-	if (dev->info->internal_phy[port])
+	if (dev->info->internal_phy[port]) {
 		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
 			  config->supported_interfaces);
+		/* Compatibility for phylib's default interface type when the
+		 * phy-mode property is absent
+		 */
+		__set_bit(PHY_INTERFACE_MODE_GMII,
+			  config->supported_interfaces);
+	}
 
 	if (dev->dev_ops->get_caps)
 		dev->dev_ops->get_caps(dev, port, config);
@@ -962,6 +977,7 @@ static void ksz_update_port_member(struct ksz_device *dev, int port)
 static int ksz_setup(struct dsa_switch *ds)
 {
 	struct ksz_device *dev = ds->priv;
+	struct ksz_port *p;
 	const u16 *regs;
 	int ret;
 
@@ -1001,6 +1017,14 @@ static int ksz_setup(struct dsa_switch *ds)
 			return ret;
 	}
 
+	/* Start with learning disabled on standalone user ports, and enabled
+	 * on the CPU port. In lack of other finer mechanisms, learning on the
+	 * CPU port will avoid flooding bridge local addresses on the network
+	 * in some cases.
+	 */
+	p = &dev->ports[dev->cpu_port];
+	p->learning = true;
+
 	/* start switch */
 	regmap_update_bits(dev->regmap[0], regs[S_START_CTRL],
 			   SW_START, SW_START);
@@ -1277,6 +1301,8 @@ void ksz_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
 	ksz_pread8(dev, port, regs[P_STP_CTRL], &data);
 	data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE);
 
+	p = &dev->ports[port];
+
 	switch (state) {
 	case BR_STATE_DISABLED:
 		data |= PORT_LEARN_DISABLE;
@@ -1286,9 +1312,13 @@ void ksz_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
 		break;
 	case BR_STATE_LEARNING:
 		data |= PORT_RX_ENABLE;
+		if (!p->learning)
+			data |= PORT_LEARN_DISABLE;
 		break;
 	case BR_STATE_FORWARDING:
 		data |= (PORT_TX_ENABLE | PORT_RX_ENABLE);
+		if (!p->learning)
+			data |= PORT_LEARN_DISABLE;
 		break;
 	case BR_STATE_BLOCKING:
 		data |= PORT_LEARN_DISABLE;
@@ -1300,12 +1330,38 @@ void ksz_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
 
 	ksz_pwrite8(dev, port, regs[P_STP_CTRL], data);
 
-	p = &dev->ports[port];
 	p->stp_state = state;
 
 	ksz_update_port_member(dev, port);
 }
 
+static int ksz_port_pre_bridge_flags(struct dsa_switch *ds, int port,
+				     struct switchdev_brport_flags flags,
+				     struct netlink_ext_ack *extack)
+{
+	if (flags.mask & ~BR_LEARNING)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int ksz_port_bridge_flags(struct dsa_switch *ds, int port,
+				 struct switchdev_brport_flags flags,
+				 struct netlink_ext_ack *extack)
+{
+	struct ksz_device *dev = ds->priv;
+	struct ksz_port *p = &dev->ports[port];
+
+	if (flags.mask & BR_LEARNING) {
+		p->learning = !!(flags.val & BR_LEARNING);
+
+		/* Make the change take effect immediately */
+		ksz_port_stp_state_set(ds, port, p->stp_state);
+	}
+
+	return 0;
+}
+
 static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds,
 						  int port,
 						  enum dsa_tag_protocol mp)
@@ -1609,13 +1665,13 @@ static void ksz_duplex_flowctrl(struct ksz_device *dev, int port, int duplex,
 	ksz_prmw8(dev, port, regs[P_XMII_CTRL_0], mask, val);
 }
 
-static void ksz_phylink_mac_link_up(struct dsa_switch *ds, int port,
-				    unsigned int mode,
-				    phy_interface_t interface,
-				    struct phy_device *phydev, int speed,
-				    int duplex, bool tx_pause, bool rx_pause)
+static void ksz9477_phylink_mac_link_up(struct ksz_device *dev, int port,
+					unsigned int mode,
+					phy_interface_t interface,
+					struct phy_device *phydev, int speed,
+					int duplex, bool tx_pause,
+					bool rx_pause)
 {
-	struct ksz_device *dev = ds->priv;
 	struct ksz_port *p;
 
 	p = &dev->ports[port];
@@ -1629,6 +1685,15 @@ static void ksz_phylink_mac_link_up(struct dsa_switch *ds, int port,
 	ksz_port_set_xmii_speed(dev, port, speed);
 
 	ksz_duplex_flowctrl(dev, port, duplex, tx_pause, rx_pause);
+}
+
+static void ksz_phylink_mac_link_up(struct dsa_switch *ds, int port,
+				    unsigned int mode,
+				    phy_interface_t interface,
+				    struct phy_device *phydev, int speed,
+				    int duplex, bool tx_pause, bool rx_pause)
+{
+	struct ksz_device *dev = ds->priv;
 
 	if (dev->dev_ops->phylink_mac_link_up)
 		dev->dev_ops->phylink_mac_link_up(dev, port, mode, interface,
@@ -1719,6 +1784,8 @@ static const struct dsa_switch_ops ksz_switch_ops = {
 	.port_bridge_join	= ksz_port_bridge_join,
 	.port_bridge_leave	= ksz_port_bridge_leave,
 	.port_stp_state_set	= ksz_port_stp_state_set,
+	.port_pre_bridge_flags	= ksz_port_pre_bridge_flags,
+	.port_bridge_flags	= ksz_port_bridge_flags,
 	.port_fast_age		= ksz_port_fast_age,
 	.port_vlan_filtering	= ksz_port_vlan_filtering,
 	.port_vlan_add		= ksz_port_vlan_add,
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index 764ada3a0f42..0d9520dc6d2d 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -65,6 +65,7 @@ struct ksz_chip_data {
 
 struct ksz_port {
 	bool remove_tag;		/* Remove Tag flag set, for ksz8795 only */
+	bool learning;
 	int stp_state;
 	struct phy_device phydev;
 
diff --git a/drivers/net/dsa/microchip/lan937x_main.c b/drivers/net/dsa/microchip/lan937x_main.c
index daedd2bf20c1..5579644e8fde 100644
--- a/drivers/net/dsa/microchip/lan937x_main.c
+++ b/drivers/net/dsa/microchip/lan937x_main.c
@@ -244,10 +244,6 @@ void lan937x_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 		lan937x_port_cfg(dev, port, REG_PORT_CTRL_0,
 				 PORT_TAIL_TAG_ENABLE, true);
 
-	/* disable frame check length field */
-	lan937x_port_cfg(dev, port, REG_PORT_MAC_CTRL_0, PORT_CHECK_LENGTH,
-			 false);
-
 	/* set back pressure for half duplex */
 	lan937x_port_cfg(dev, port, REG_PORT_MAC_CTRL_1, PORT_BACK_PRESSURE,
 			 true);
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 835807911be0..409d5c3d76ea 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -506,14 +506,19 @@ static bool mt7531_dual_sgmii_supported(struct mt7530_priv *priv)
 static int
 mt7531_pad_setup(struct dsa_switch *ds, phy_interface_t interface)
 {
-	struct mt7530_priv *priv = ds->priv;
+	return 0;
+}
+
+static void
+mt7531_pll_setup(struct mt7530_priv *priv)
+{
 	u32 top_sig;
 	u32 hwstrap;
 	u32 xtal;
 	u32 val;
 
 	if (mt7531_dual_sgmii_supported(priv))
-		return 0;
+		return;
 
 	val = mt7530_read(priv, MT7531_CREV);
 	top_sig = mt7530_read(priv, MT7531_TOP_SIG_SR);
@@ -592,8 +597,6 @@ mt7531_pad_setup(struct dsa_switch *ds, phy_interface_t interface)
 	val |= EN_COREPLL;
 	mt7530_write(priv, MT7531_PLLGP_EN, val);
 	usleep_range(25, 35);
-
-	return 0;
 }
 
 static void
@@ -2326,11 +2329,17 @@ mt7531_setup(struct dsa_switch *ds)
 		return -ENODEV;
 	}
 
+	/* all MACs must be forced link-down before sw reset */
+	for (i = 0; i < MT7530_NUM_PORTS; i++)
+		mt7530_write(priv, MT7530_PMCR_P(i), MT7531_FORCE_LNK);
+
 	/* Reset the switch through internal reset */
 	mt7530_write(priv, MT7530_SYS_CTRL,
 		     SYS_CTRL_PHY_RST | SYS_CTRL_SW_RST |
 		     SYS_CTRL_REG_RST);
 
+	mt7531_pll_setup(priv);
+
 	if (mt7531_dual_sgmii_supported(priv)) {
 		priv->p5_intf_sel = P5_INTF_SEL_GMAC5_SGMII;
 
@@ -2887,8 +2896,6 @@ mt7531_cpu_port_config(struct dsa_switch *ds, int port)
 	case 6:
 		interface = PHY_INTERFACE_MODE_2500BASEX;
 
-		mt7531_pad_setup(ds, interface);
-
 		priv->p6_interface = interface;
 		break;
 	default:
diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c
index a4c6eb9a52d0..83dca9179aa0 100644
--- a/drivers/net/dsa/mv88e6060.c
+++ b/drivers/net/dsa/mv88e6060.c
@@ -118,6 +118,9 @@ static int mv88e6060_setup_port(struct mv88e6060_priv *priv, int p)
 	int addr = REG_PORT(p);
 	int ret;
 
+	if (dsa_is_unused_port(priv->ds, p))
+		return 0;
+
 	/* Do not force flow control, disable Ingress and Egress
 	 * Header tagging, disable VLAN tunneling, and set the port
 	 * state to Forwarding.  Additionally, if this is the CPU
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index b4034b78c0ca..f8f19a85744c 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -22,6 +22,7 @@
 #define VSC9959_NUM_PORTS		6
 
 #define VSC9959_TAS_GCL_ENTRY_MAX	63
+#define VSC9959_TAS_MIN_GATE_LEN_NS	33
 #define VSC9959_VCAP_POLICER_BASE	63
 #define VSC9959_VCAP_POLICER_MAX	383
 #define VSC9959_SWITCH_PCI_BAR		4
@@ -274,27 +275,98 @@ static const u32 vsc9959_rew_regmap[] = {
 
 static const u32 vsc9959_sys_regmap[] = {
 	REG(SYS_COUNT_RX_OCTETS,		0x000000),
+	REG(SYS_COUNT_RX_UNICAST,		0x000004),
 	REG(SYS_COUNT_RX_MULTICAST,		0x000008),
+	REG(SYS_COUNT_RX_BROADCAST,		0x00000c),
 	REG(SYS_COUNT_RX_SHORTS,		0x000010),
 	REG(SYS_COUNT_RX_FRAGMENTS,		0x000014),
 	REG(SYS_COUNT_RX_JABBERS,		0x000018),
+	REG(SYS_COUNT_RX_CRC_ALIGN_ERRS,	0x00001c),
+	REG(SYS_COUNT_RX_SYM_ERRS,		0x000020),
 	REG(SYS_COUNT_RX_64,			0x000024),
 	REG(SYS_COUNT_RX_65_127,		0x000028),
 	REG(SYS_COUNT_RX_128_255,		0x00002c),
-	REG(SYS_COUNT_RX_256_1023,		0x000030),
-	REG(SYS_COUNT_RX_1024_1526,		0x000034),
-	REG(SYS_COUNT_RX_1527_MAX,		0x000038),
-	REG(SYS_COUNT_RX_LONGS,			0x000044),
+	REG(SYS_COUNT_RX_256_511,		0x000030),
+	REG(SYS_COUNT_RX_512_1023,		0x000034),
+	REG(SYS_COUNT_RX_1024_1526,		0x000038),
+	REG(SYS_COUNT_RX_1527_MAX,		0x00003c),
+	REG(SYS_COUNT_RX_PAUSE,			0x000040),
+	REG(SYS_COUNT_RX_CONTROL,		0x000044),
+	REG(SYS_COUNT_RX_LONGS,			0x000048),
+	REG(SYS_COUNT_RX_CLASSIFIED_DROPS,	0x00004c),
+	REG(SYS_COUNT_RX_RED_PRIO_0,		0x000050),
+	REG(SYS_COUNT_RX_RED_PRIO_1,		0x000054),
+	REG(SYS_COUNT_RX_RED_PRIO_2,		0x000058),
+	REG(SYS_COUNT_RX_RED_PRIO_3,		0x00005c),
+	REG(SYS_COUNT_RX_RED_PRIO_4,		0x000060),
+	REG(SYS_COUNT_RX_RED_PRIO_5,		0x000064),
+	REG(SYS_COUNT_RX_RED_PRIO_6,		0x000068),
+	REG(SYS_COUNT_RX_RED_PRIO_7,		0x00006c),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_0,		0x000070),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_1,		0x000074),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_2,		0x000078),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_3,		0x00007c),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_4,		0x000080),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_5,		0x000084),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_6,		0x000088),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_7,		0x00008c),
+	REG(SYS_COUNT_RX_GREEN_PRIO_0,		0x000090),
+	REG(SYS_COUNT_RX_GREEN_PRIO_1,		0x000094),
+	REG(SYS_COUNT_RX_GREEN_PRIO_2,		0x000098),
+	REG(SYS_COUNT_RX_GREEN_PRIO_3,		0x00009c),
+	REG(SYS_COUNT_RX_GREEN_PRIO_4,		0x0000a0),
+	REG(SYS_COUNT_RX_GREEN_PRIO_5,		0x0000a4),
+	REG(SYS_COUNT_RX_GREEN_PRIO_6,		0x0000a8),
+	REG(SYS_COUNT_RX_GREEN_PRIO_7,		0x0000ac),
 	REG(SYS_COUNT_TX_OCTETS,		0x000200),
+	REG(SYS_COUNT_TX_UNICAST,		0x000204),
+	REG(SYS_COUNT_TX_MULTICAST,		0x000208),
+	REG(SYS_COUNT_TX_BROADCAST,		0x00020c),
 	REG(SYS_COUNT_TX_COLLISION,		0x000210),
 	REG(SYS_COUNT_TX_DROPS,			0x000214),
+	REG(SYS_COUNT_TX_PAUSE,			0x000218),
 	REG(SYS_COUNT_TX_64,			0x00021c),
 	REG(SYS_COUNT_TX_65_127,		0x000220),
-	REG(SYS_COUNT_TX_128_511,		0x000224),
-	REG(SYS_COUNT_TX_512_1023,		0x000228),
-	REG(SYS_COUNT_TX_1024_1526,		0x00022c),
-	REG(SYS_COUNT_TX_1527_MAX,		0x000230),
+	REG(SYS_COUNT_TX_128_255,		0x000224),
+	REG(SYS_COUNT_TX_256_511,		0x000228),
+	REG(SYS_COUNT_TX_512_1023,		0x00022c),
+	REG(SYS_COUNT_TX_1024_1526,		0x000230),
+	REG(SYS_COUNT_TX_1527_MAX,		0x000234),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_0,		0x000238),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_1,		0x00023c),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_2,		0x000240),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_3,		0x000244),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_4,		0x000248),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_5,		0x00024c),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_6,		0x000250),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_7,		0x000254),
+	REG(SYS_COUNT_TX_GREEN_PRIO_0,		0x000258),
+	REG(SYS_COUNT_TX_GREEN_PRIO_1,		0x00025c),
+	REG(SYS_COUNT_TX_GREEN_PRIO_2,		0x000260),
+	REG(SYS_COUNT_TX_GREEN_PRIO_3,		0x000264),
+	REG(SYS_COUNT_TX_GREEN_PRIO_4,		0x000268),
+	REG(SYS_COUNT_TX_GREEN_PRIO_5,		0x00026c),
+	REG(SYS_COUNT_TX_GREEN_PRIO_6,		0x000270),
+	REG(SYS_COUNT_TX_GREEN_PRIO_7,		0x000274),
 	REG(SYS_COUNT_TX_AGING,			0x000278),
+	REG(SYS_COUNT_DROP_LOCAL,		0x000400),
+	REG(SYS_COUNT_DROP_TAIL,		0x000404),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_0,	0x000408),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_1,	0x00040c),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_2,	0x000410),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_3,	0x000414),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_4,	0x000418),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_5,	0x00041c),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_6,	0x000420),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_7,	0x000424),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_0,	0x000428),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_1,	0x00042c),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_2,	0x000430),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_3,	0x000434),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_4,	0x000438),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_5,	0x00043c),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_6,	0x000440),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_7,	0x000444),
 	REG(SYS_RESET_CFG,			0x000e00),
 	REG(SYS_SR_ETYPE_CFG,			0x000e04),
 	REG(SYS_VLAN_ETYPE_CFG,			0x000e08),
@@ -547,100 +619,379 @@ static const struct reg_field vsc9959_regfields[REGFIELD_MAX] = {
 	[SYS_PAUSE_CFG_PAUSE_ENA] = REG_FIELD_ID(SYS_PAUSE_CFG, 0, 1, 7, 4),
 };
 
-static const struct ocelot_stat_layout vsc9959_stats_layout[] = {
-	{ .offset = 0x00,	.name = "rx_octets", },
-	{ .offset = 0x01,	.name = "rx_unicast", },
-	{ .offset = 0x02,	.name = "rx_multicast", },
-	{ .offset = 0x03,	.name = "rx_broadcast", },
-	{ .offset = 0x04,	.name = "rx_shorts", },
-	{ .offset = 0x05,	.name = "rx_fragments", },
-	{ .offset = 0x06,	.name = "rx_jabbers", },
-	{ .offset = 0x07,	.name = "rx_crc_align_errs", },
-	{ .offset = 0x08,	.name = "rx_sym_errs", },
-	{ .offset = 0x09,	.name = "rx_frames_below_65_octets", },
-	{ .offset = 0x0A,	.name = "rx_frames_65_to_127_octets", },
-	{ .offset = 0x0B,	.name = "rx_frames_128_to_255_octets", },
-	{ .offset = 0x0C,	.name = "rx_frames_256_to_511_octets", },
-	{ .offset = 0x0D,	.name = "rx_frames_512_to_1023_octets", },
-	{ .offset = 0x0E,	.name = "rx_frames_1024_to_1526_octets", },
-	{ .offset = 0x0F,	.name = "rx_frames_over_1526_octets", },
-	{ .offset = 0x10,	.name = "rx_pause", },
-	{ .offset = 0x11,	.name = "rx_control", },
-	{ .offset = 0x12,	.name = "rx_longs", },
-	{ .offset = 0x13,	.name = "rx_classified_drops", },
-	{ .offset = 0x14,	.name = "rx_red_prio_0", },
-	{ .offset = 0x15,	.name = "rx_red_prio_1", },
-	{ .offset = 0x16,	.name = "rx_red_prio_2", },
-	{ .offset = 0x17,	.name = "rx_red_prio_3", },
-	{ .offset = 0x18,	.name = "rx_red_prio_4", },
-	{ .offset = 0x19,	.name = "rx_red_prio_5", },
-	{ .offset = 0x1A,	.name = "rx_red_prio_6", },
-	{ .offset = 0x1B,	.name = "rx_red_prio_7", },
-	{ .offset = 0x1C,	.name = "rx_yellow_prio_0", },
-	{ .offset = 0x1D,	.name = "rx_yellow_prio_1", },
-	{ .offset = 0x1E,	.name = "rx_yellow_prio_2", },
-	{ .offset = 0x1F,	.name = "rx_yellow_prio_3", },
-	{ .offset = 0x20,	.name = "rx_yellow_prio_4", },
-	{ .offset = 0x21,	.name = "rx_yellow_prio_5", },
-	{ .offset = 0x22,	.name = "rx_yellow_prio_6", },
-	{ .offset = 0x23,	.name = "rx_yellow_prio_7", },
-	{ .offset = 0x24,	.name = "rx_green_prio_0", },
-	{ .offset = 0x25,	.name = "rx_green_prio_1", },
-	{ .offset = 0x26,	.name = "rx_green_prio_2", },
-	{ .offset = 0x27,	.name = "rx_green_prio_3", },
-	{ .offset = 0x28,	.name = "rx_green_prio_4", },
-	{ .offset = 0x29,	.name = "rx_green_prio_5", },
-	{ .offset = 0x2A,	.name = "rx_green_prio_6", },
-	{ .offset = 0x2B,	.name = "rx_green_prio_7", },
-	{ .offset = 0x80,	.name = "tx_octets", },
-	{ .offset = 0x81,	.name = "tx_unicast", },
-	{ .offset = 0x82,	.name = "tx_multicast", },
-	{ .offset = 0x83,	.name = "tx_broadcast", },
-	{ .offset = 0x84,	.name = "tx_collision", },
-	{ .offset = 0x85,	.name = "tx_drops", },
-	{ .offset = 0x86,	.name = "tx_pause", },
-	{ .offset = 0x87,	.name = "tx_frames_below_65_octets", },
-	{ .offset = 0x88,	.name = "tx_frames_65_to_127_octets", },
-	{ .offset = 0x89,	.name = "tx_frames_128_255_octets", },
-	{ .offset = 0x8B,	.name = "tx_frames_256_511_octets", },
-	{ .offset = 0x8C,	.name = "tx_frames_1024_1526_octets", },
-	{ .offset = 0x8D,	.name = "tx_frames_over_1526_octets", },
-	{ .offset = 0x8E,	.name = "tx_yellow_prio_0", },
-	{ .offset = 0x8F,	.name = "tx_yellow_prio_1", },
-	{ .offset = 0x90,	.name = "tx_yellow_prio_2", },
-	{ .offset = 0x91,	.name = "tx_yellow_prio_3", },
-	{ .offset = 0x92,	.name = "tx_yellow_prio_4", },
-	{ .offset = 0x93,	.name = "tx_yellow_prio_5", },
-	{ .offset = 0x94,	.name = "tx_yellow_prio_6", },
-	{ .offset = 0x95,	.name = "tx_yellow_prio_7", },
-	{ .offset = 0x96,	.name = "tx_green_prio_0", },
-	{ .offset = 0x97,	.name = "tx_green_prio_1", },
-	{ .offset = 0x98,	.name = "tx_green_prio_2", },
-	{ .offset = 0x99,	.name = "tx_green_prio_3", },
-	{ .offset = 0x9A,	.name = "tx_green_prio_4", },
-	{ .offset = 0x9B,	.name = "tx_green_prio_5", },
-	{ .offset = 0x9C,	.name = "tx_green_prio_6", },
-	{ .offset = 0x9D,	.name = "tx_green_prio_7", },
-	{ .offset = 0x9E,	.name = "tx_aged", },
-	{ .offset = 0x100,	.name = "drop_local", },
-	{ .offset = 0x101,	.name = "drop_tail", },
-	{ .offset = 0x102,	.name = "drop_yellow_prio_0", },
-	{ .offset = 0x103,	.name = "drop_yellow_prio_1", },
-	{ .offset = 0x104,	.name = "drop_yellow_prio_2", },
-	{ .offset = 0x105,	.name = "drop_yellow_prio_3", },
-	{ .offset = 0x106,	.name = "drop_yellow_prio_4", },
-	{ .offset = 0x107,	.name = "drop_yellow_prio_5", },
-	{ .offset = 0x108,	.name = "drop_yellow_prio_6", },
-	{ .offset = 0x109,	.name = "drop_yellow_prio_7", },
-	{ .offset = 0x10A,	.name = "drop_green_prio_0", },
-	{ .offset = 0x10B,	.name = "drop_green_prio_1", },
-	{ .offset = 0x10C,	.name = "drop_green_prio_2", },
-	{ .offset = 0x10D,	.name = "drop_green_prio_3", },
-	{ .offset = 0x10E,	.name = "drop_green_prio_4", },
-	{ .offset = 0x10F,	.name = "drop_green_prio_5", },
-	{ .offset = 0x110,	.name = "drop_green_prio_6", },
-	{ .offset = 0x111,	.name = "drop_green_prio_7", },
-	OCELOT_STAT_END
+static const struct ocelot_stat_layout vsc9959_stats_layout[OCELOT_NUM_STATS] = {
+	[OCELOT_STAT_RX_OCTETS] = {
+		.name = "rx_octets",
+		.reg = SYS_COUNT_RX_OCTETS,
+	},
+	[OCELOT_STAT_RX_UNICAST] = {
+		.name = "rx_unicast",
+		.reg = SYS_COUNT_RX_UNICAST,
+	},
+	[OCELOT_STAT_RX_MULTICAST] = {
+		.name = "rx_multicast",
+		.reg = SYS_COUNT_RX_MULTICAST,
+	},
+	[OCELOT_STAT_RX_BROADCAST] = {
+		.name = "rx_broadcast",
+		.reg = SYS_COUNT_RX_BROADCAST,
+	},
+	[OCELOT_STAT_RX_SHORTS] = {
+		.name = "rx_shorts",
+		.reg = SYS_COUNT_RX_SHORTS,
+	},
+	[OCELOT_STAT_RX_FRAGMENTS] = {
+		.name = "rx_fragments",
+		.reg = SYS_COUNT_RX_FRAGMENTS,
+	},
+	[OCELOT_STAT_RX_JABBERS] = {
+		.name = "rx_jabbers",
+		.reg = SYS_COUNT_RX_JABBERS,
+	},
+	[OCELOT_STAT_RX_CRC_ALIGN_ERRS] = {
+		.name = "rx_crc_align_errs",
+		.reg = SYS_COUNT_RX_CRC_ALIGN_ERRS,
+	},
+	[OCELOT_STAT_RX_SYM_ERRS] = {
+		.name = "rx_sym_errs",
+		.reg = SYS_COUNT_RX_SYM_ERRS,
+	},
+	[OCELOT_STAT_RX_64] = {
+		.name = "rx_frames_below_65_octets",
+		.reg = SYS_COUNT_RX_64,
+	},
+	[OCELOT_STAT_RX_65_127] = {
+		.name = "rx_frames_65_to_127_octets",
+		.reg = SYS_COUNT_RX_65_127,
+	},
+	[OCELOT_STAT_RX_128_255] = {
+		.name = "rx_frames_128_to_255_octets",
+		.reg = SYS_COUNT_RX_128_255,
+	},
+	[OCELOT_STAT_RX_256_511] = {
+		.name = "rx_frames_256_to_511_octets",
+		.reg = SYS_COUNT_RX_256_511,
+	},
+	[OCELOT_STAT_RX_512_1023] = {
+		.name = "rx_frames_512_to_1023_octets",
+		.reg = SYS_COUNT_RX_512_1023,
+	},
+	[OCELOT_STAT_RX_1024_1526] = {
+		.name = "rx_frames_1024_to_1526_octets",
+		.reg = SYS_COUNT_RX_1024_1526,
+	},
+	[OCELOT_STAT_RX_1527_MAX] = {
+		.name = "rx_frames_over_1526_octets",
+		.reg = SYS_COUNT_RX_1527_MAX,
+	},
+	[OCELOT_STAT_RX_PAUSE] = {
+		.name = "rx_pause",
+		.reg = SYS_COUNT_RX_PAUSE,
+	},
+	[OCELOT_STAT_RX_CONTROL] = {
+		.name = "rx_control",
+		.reg = SYS_COUNT_RX_CONTROL,
+	},
+	[OCELOT_STAT_RX_LONGS] = {
+		.name = "rx_longs",
+		.reg = SYS_COUNT_RX_LONGS,
+	},
+	[OCELOT_STAT_RX_CLASSIFIED_DROPS] = {
+		.name = "rx_classified_drops",
+		.reg = SYS_COUNT_RX_CLASSIFIED_DROPS,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_0] = {
+		.name = "rx_red_prio_0",
+		.reg = SYS_COUNT_RX_RED_PRIO_0,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_1] = {
+		.name = "rx_red_prio_1",
+		.reg = SYS_COUNT_RX_RED_PRIO_1,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_2] = {
+		.name = "rx_red_prio_2",
+		.reg = SYS_COUNT_RX_RED_PRIO_2,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_3] = {
+		.name = "rx_red_prio_3",
+		.reg = SYS_COUNT_RX_RED_PRIO_3,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_4] = {
+		.name = "rx_red_prio_4",
+		.reg = SYS_COUNT_RX_RED_PRIO_4,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_5] = {
+		.name = "rx_red_prio_5",
+		.reg = SYS_COUNT_RX_RED_PRIO_5,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_6] = {
+		.name = "rx_red_prio_6",
+		.reg = SYS_COUNT_RX_RED_PRIO_6,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_7] = {
+		.name = "rx_red_prio_7",
+		.reg = SYS_COUNT_RX_RED_PRIO_7,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_0] = {
+		.name = "rx_yellow_prio_0",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_1] = {
+		.name = "rx_yellow_prio_1",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_2] = {
+		.name = "rx_yellow_prio_2",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_3] = {
+		.name = "rx_yellow_prio_3",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_4] = {
+		.name = "rx_yellow_prio_4",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_5] = {
+		.name = "rx_yellow_prio_5",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_6] = {
+		.name = "rx_yellow_prio_6",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_7] = {
+		.name = "rx_yellow_prio_7",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_0] = {
+		.name = "rx_green_prio_0",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_1] = {
+		.name = "rx_green_prio_1",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_2] = {
+		.name = "rx_green_prio_2",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_3] = {
+		.name = "rx_green_prio_3",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_4] = {
+		.name = "rx_green_prio_4",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_5] = {
+		.name = "rx_green_prio_5",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_6] = {
+		.name = "rx_green_prio_6",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_7] = {
+		.name = "rx_green_prio_7",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_7,
+	},
+	[OCELOT_STAT_TX_OCTETS] = {
+		.name = "tx_octets",
+		.reg = SYS_COUNT_TX_OCTETS,
+	},
+	[OCELOT_STAT_TX_UNICAST] = {
+		.name = "tx_unicast",
+		.reg = SYS_COUNT_TX_UNICAST,
+	},
+	[OCELOT_STAT_TX_MULTICAST] = {
+		.name = "tx_multicast",
+		.reg = SYS_COUNT_TX_MULTICAST,
+	},
+	[OCELOT_STAT_TX_BROADCAST] = {
+		.name = "tx_broadcast",
+		.reg = SYS_COUNT_TX_BROADCAST,
+	},
+	[OCELOT_STAT_TX_COLLISION] = {
+		.name = "tx_collision",
+		.reg = SYS_COUNT_TX_COLLISION,
+	},
+	[OCELOT_STAT_TX_DROPS] = {
+		.name = "tx_drops",
+		.reg = SYS_COUNT_TX_DROPS,
+	},
+	[OCELOT_STAT_TX_PAUSE] = {
+		.name = "tx_pause",
+		.reg = SYS_COUNT_TX_PAUSE,
+	},
+	[OCELOT_STAT_TX_64] = {
+		.name = "tx_frames_below_65_octets",
+		.reg = SYS_COUNT_TX_64,
+	},
+	[OCELOT_STAT_TX_65_127] = {
+		.name = "tx_frames_65_to_127_octets",
+		.reg = SYS_COUNT_TX_65_127,
+	},
+	[OCELOT_STAT_TX_128_255] = {
+		.name = "tx_frames_128_255_octets",
+		.reg = SYS_COUNT_TX_128_255,
+	},
+	[OCELOT_STAT_TX_256_511] = {
+		.name = "tx_frames_256_511_octets",
+		.reg = SYS_COUNT_TX_256_511,
+	},
+	[OCELOT_STAT_TX_512_1023] = {
+		.name = "tx_frames_512_1023_octets",
+		.reg = SYS_COUNT_TX_512_1023,
+	},
+	[OCELOT_STAT_TX_1024_1526] = {
+		.name = "tx_frames_1024_1526_octets",
+		.reg = SYS_COUNT_TX_1024_1526,
+	},
+	[OCELOT_STAT_TX_1527_MAX] = {
+		.name = "tx_frames_over_1526_octets",
+		.reg = SYS_COUNT_TX_1527_MAX,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_0] = {
+		.name = "tx_yellow_prio_0",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_1] = {
+		.name = "tx_yellow_prio_1",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_2] = {
+		.name = "tx_yellow_prio_2",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_3] = {
+		.name = "tx_yellow_prio_3",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_4] = {
+		.name = "tx_yellow_prio_4",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_5] = {
+		.name = "tx_yellow_prio_5",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_6] = {
+		.name = "tx_yellow_prio_6",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_7] = {
+		.name = "tx_yellow_prio_7",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_0] = {
+		.name = "tx_green_prio_0",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_1] = {
+		.name = "tx_green_prio_1",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_2] = {
+		.name = "tx_green_prio_2",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_3] = {
+		.name = "tx_green_prio_3",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_4] = {
+		.name = "tx_green_prio_4",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_5] = {
+		.name = "tx_green_prio_5",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_6] = {
+		.name = "tx_green_prio_6",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_7] = {
+		.name = "tx_green_prio_7",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_7,
+	},
+	[OCELOT_STAT_TX_AGED] = {
+		.name = "tx_aged",
+		.reg = SYS_COUNT_TX_AGING,
+	},
+	[OCELOT_STAT_DROP_LOCAL] = {
+		.name = "drop_local",
+		.reg = SYS_COUNT_DROP_LOCAL,
+	},
+	[OCELOT_STAT_DROP_TAIL] = {
+		.name = "drop_tail",
+		.reg = SYS_COUNT_DROP_TAIL,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_0] = {
+		.name = "drop_yellow_prio_0",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_1] = {
+		.name = "drop_yellow_prio_1",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_2] = {
+		.name = "drop_yellow_prio_2",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_3] = {
+		.name = "drop_yellow_prio_3",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_4] = {
+		.name = "drop_yellow_prio_4",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_5] = {
+		.name = "drop_yellow_prio_5",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_6] = {
+		.name = "drop_yellow_prio_6",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_7] = {
+		.name = "drop_yellow_prio_7",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_0] = {
+		.name = "drop_green_prio_0",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_1] = {
+		.name = "drop_green_prio_1",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_2] = {
+		.name = "drop_green_prio_2",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_3] = {
+		.name = "drop_green_prio_3",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_4] = {
+		.name = "drop_green_prio_4",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_5] = {
+		.name = "drop_green_prio_5",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_6] = {
+		.name = "drop_green_prio_6",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_7] = {
+		.name = "drop_green_prio_7",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_7,
+	},
 };
 
 static const struct vcap_field vsc9959_vcap_es0_keys[] = {
@@ -1128,6 +1479,23 @@ static void vsc9959_mdio_bus_free(struct ocelot *ocelot)
 	mdiobus_free(felix->imdio);
 }
 
+/* The switch considers any frame (regardless of size) as eligible for
+ * transmission if the traffic class gate is open for at least 33 ns.
+ * Overruns are prevented by cropping an interval at the end of the gate time
+ * slot for which egress scheduling is blocked, but we need to still keep 33 ns
+ * available for one packet to be transmitted, otherwise the port tc will hang.
+ * This function returns the size of a gate interval that remains available for
+ * setting the guard band, after reserving the space for one egress frame.
+ */
+static u64 vsc9959_tas_remaining_gate_len_ps(u64 gate_len_ns)
+{
+	/* Gate always open */
+	if (gate_len_ns == U64_MAX)
+		return U64_MAX;
+
+	return (gate_len_ns - VSC9959_TAS_MIN_GATE_LEN_NS) * PSEC_PER_NSEC;
+}
+
 /* Extract shortest continuous gate open intervals in ns for each traffic class
  * of a cyclic tc-taprio schedule. If a gate is always open, the duration is
  * considered U64_MAX. If the gate is always closed, it is considered 0.
@@ -1189,6 +1557,65 @@ static void vsc9959_tas_min_gate_lengths(struct tc_taprio_qopt_offload *taprio,
 			min_gate_len[tc] = 0;
 }
 
+/* ocelot_write_rix is a macro that concatenates QSYS_MAXSDU_CFG_* with _RSZ,
+ * so we need to spell out the register access to each traffic class in helper
+ * functions, to simplify callers
+ */
+static void vsc9959_port_qmaxsdu_set(struct ocelot *ocelot, int port, int tc,
+				     u32 max_sdu)
+{
+	switch (tc) {
+	case 0:
+		ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_0,
+				 port);
+		break;
+	case 1:
+		ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_1,
+				 port);
+		break;
+	case 2:
+		ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_2,
+				 port);
+		break;
+	case 3:
+		ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_3,
+				 port);
+		break;
+	case 4:
+		ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_4,
+				 port);
+		break;
+	case 5:
+		ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_5,
+				 port);
+		break;
+	case 6:
+		ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_6,
+				 port);
+		break;
+	case 7:
+		ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_7,
+				 port);
+		break;
+	}
+}
+
+static u32 vsc9959_port_qmaxsdu_get(struct ocelot *ocelot, int port, int tc)
+{
+	switch (tc) {
+	case 0: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_0, port);
+	case 1: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_1, port);
+	case 2: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_2, port);
+	case 3: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_3, port);
+	case 4: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_4, port);
+	case 5: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_5, port);
+	case 6: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_6, port);
+	case 7: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_7, port);
+	default:
+		return 0;
+	}
+}
+
 /* Update QSYS_PORT_MAX_SDU to make sure the static guard bands added by the
  * switch (see the ALWAYS_GUARD_BAND_SCH_Q comment) are correct at all MTU
  * values (the default value is 1518). Also, for traffic class windows smaller
@@ -1245,11 +1672,16 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
 
 	vsc9959_tas_min_gate_lengths(ocelot_port->taprio, min_gate_len);
 
+	mutex_lock(&ocelot->fwd_domain_lock);
+
 	for (tc = 0; tc < OCELOT_NUM_TC; tc++) {
+		u64 remaining_gate_len_ps;
 		u32 max_sdu;
 
-		if (min_gate_len[tc] == U64_MAX /* Gate always open */ ||
-		    min_gate_len[tc] * PSEC_PER_NSEC > needed_bit_time_ps) {
+		remaining_gate_len_ps =
+			vsc9959_tas_remaining_gate_len_ps(min_gate_len[tc]);
+
+		if (remaining_gate_len_ps > needed_bit_time_ps) {
 			/* Setting QMAXSDU_CFG to 0 disables oversized frame
 			 * dropping.
 			 */
@@ -1262,9 +1694,15 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
 			/* If traffic class doesn't support a full MTU sized
 			 * frame, make sure to enable oversize frame dropping
 			 * for frames larger than the smallest that would fit.
+			 *
+			 * However, the exact same register, QSYS_QMAXSDU_CFG_*,
+			 * controls not only oversized frame dropping, but also
+			 * per-tc static guard band lengths, so it reduces the
+			 * useful gate interval length. Therefore, be careful
+			 * to calculate a guard band (and therefore max_sdu)
+			 * that still leaves 33 ns available in the time slot.
 			 */
-			max_sdu = div_u64(min_gate_len[tc] * PSEC_PER_NSEC,
-					  picos_per_byte);
+			max_sdu = div_u64(remaining_gate_len_ps, picos_per_byte);
 			/* A TC gate may be completely closed, which is a
 			 * special case where all packets are oversized.
 			 * Any limit smaller than 64 octets accomplishes this
@@ -1287,47 +1725,14 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
 				 max_sdu);
 		}
 
-		/* ocelot_write_rix is a macro that concatenates
-		 * QSYS_MAXSDU_CFG_* with _RSZ, so we need to spell out
-		 * the writes to each traffic class
-		 */
-		switch (tc) {
-		case 0:
-			ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_0,
-					 port);
-			break;
-		case 1:
-			ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_1,
-					 port);
-			break;
-		case 2:
-			ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_2,
-					 port);
-			break;
-		case 3:
-			ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_3,
-					 port);
-			break;
-		case 4:
-			ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_4,
-					 port);
-			break;
-		case 5:
-			ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_5,
-					 port);
-			break;
-		case 6:
-			ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_6,
-					 port);
-			break;
-		case 7:
-			ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_7,
-					 port);
-			break;
-		}
+		vsc9959_port_qmaxsdu_set(ocelot, port, tc, max_sdu);
 	}
 
 	ocelot_write_rix(ocelot, maxlen, QSYS_PORT_MAX_SDU, port);
+
+	ocelot->ops->cut_through_fwd(ocelot);
+
+	mutex_unlock(&ocelot->fwd_domain_lock);
 }
 
 static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port,
@@ -1354,13 +1759,13 @@ static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port,
 		break;
 	}
 
+	mutex_lock(&ocelot->tas_lock);
+
 	ocelot_rmw_rix(ocelot,
 		       QSYS_TAG_CONFIG_LINK_SPEED(tas_speed),
 		       QSYS_TAG_CONFIG_LINK_SPEED_M,
 		       QSYS_TAG_CONFIG, port);
 
-	mutex_lock(&ocelot->tas_lock);
-
 	if (ocelot_port->taprio)
 		vsc9959_tas_guard_bands_update(ocelot, port);
 
@@ -2166,7 +2571,7 @@ static void vsc9959_psfp_sgi_table_del(struct ocelot *ocelot,
 static void vsc9959_psfp_counters_get(struct ocelot *ocelot, u32 index,
 				      struct felix_stream_filter_counters *counters)
 {
-	mutex_lock(&ocelot->stats_lock);
+	spin_lock(&ocelot->stats_lock);
 
 	ocelot_rmw(ocelot, SYS_STAT_CFG_STAT_VIEW(index),
 		   SYS_STAT_CFG_STAT_VIEW_M,
@@ -2183,7 +2588,7 @@ static void vsc9959_psfp_counters_get(struct ocelot *ocelot, u32 index,
 		     SYS_STAT_CFG_STAT_CLEAR_SHOT(0x10),
 		     SYS_STAT_CFG);
 
-	mutex_unlock(&ocelot->stats_lock);
+	spin_unlock(&ocelot->stats_lock);
 }
 
 static int vsc9959_psfp_filter_add(struct ocelot *ocelot, int port,
@@ -2420,7 +2825,7 @@ static void vsc9959_cut_through_fwd(struct ocelot *ocelot)
 {
 	struct felix *felix = ocelot_to_felix(ocelot);
 	struct dsa_switch *ds = felix->ds;
-	int port, other_port;
+	int tc, port, other_port;
 
 	lockdep_assert_held(&ocelot->fwd_domain_lock);
 
@@ -2464,19 +2869,27 @@ static void vsc9959_cut_through_fwd(struct ocelot *ocelot)
 				min_speed = other_ocelot_port->speed;
 		}
 
-		/* Enable cut-through forwarding for all traffic classes. */
-		if (ocelot_port->speed == min_speed)
+		/* Enable cut-through forwarding for all traffic classes that
+		 * don't have oversized dropping enabled, since this check is
+		 * bypassed in cut-through mode.
+		 */
+		if (ocelot_port->speed == min_speed) {
 			val = GENMASK(7, 0);
 
+			for (tc = 0; tc < OCELOT_NUM_TC; tc++)
+				if (vsc9959_port_qmaxsdu_get(ocelot, port, tc))
+					val &= ~BIT(tc);
+		}
+
 set:
 		tmp = ocelot_read_rix(ocelot, ANA_CUT_THRU_CFG, port);
 		if (tmp == val)
 			continue;
 
 		dev_dbg(ocelot->dev,
-			"port %d fwd mask 0x%lx speed %d min_speed %d, %s cut-through forwarding\n",
+			"port %d fwd mask 0x%lx speed %d min_speed %d, %s cut-through forwarding on TC mask 0x%x\n",
 			port, mask, ocelot_port->speed, min_speed,
-			val ? "enabling" : "disabling");
+			val ? "enabling" : "disabling", val);
 
 		ocelot_write_rix(ocelot, val, ANA_CUT_THRU_CFG, port);
 	}
diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c
index ea0649211356..b34f4cdfe814 100644
--- a/drivers/net/dsa/ocelot/seville_vsc9953.c
+++ b/drivers/net/dsa/ocelot/seville_vsc9953.c
@@ -270,27 +270,98 @@ static const u32 vsc9953_rew_regmap[] = {
 
 static const u32 vsc9953_sys_regmap[] = {
 	REG(SYS_COUNT_RX_OCTETS,		0x000000),
+	REG(SYS_COUNT_RX_UNICAST,		0x000004),
 	REG(SYS_COUNT_RX_MULTICAST,		0x000008),
+	REG(SYS_COUNT_RX_BROADCAST,		0x00000c),
 	REG(SYS_COUNT_RX_SHORTS,		0x000010),
 	REG(SYS_COUNT_RX_FRAGMENTS,		0x000014),
 	REG(SYS_COUNT_RX_JABBERS,		0x000018),
+	REG(SYS_COUNT_RX_CRC_ALIGN_ERRS,	0x00001c),
+	REG(SYS_COUNT_RX_SYM_ERRS,		0x000020),
 	REG(SYS_COUNT_RX_64,			0x000024),
 	REG(SYS_COUNT_RX_65_127,		0x000028),
 	REG(SYS_COUNT_RX_128_255,		0x00002c),
-	REG(SYS_COUNT_RX_256_1023,		0x000030),
-	REG(SYS_COUNT_RX_1024_1526,		0x000034),
-	REG(SYS_COUNT_RX_1527_MAX,		0x000038),
+	REG(SYS_COUNT_RX_256_511,		0x000030),
+	REG(SYS_COUNT_RX_512_1023,		0x000034),
+	REG(SYS_COUNT_RX_1024_1526,		0x000038),
+	REG(SYS_COUNT_RX_1527_MAX,		0x00003c),
+	REG(SYS_COUNT_RX_PAUSE,			0x000040),
+	REG(SYS_COUNT_RX_CONTROL,		0x000044),
 	REG(SYS_COUNT_RX_LONGS,			0x000048),
+	REG(SYS_COUNT_RX_CLASSIFIED_DROPS,	0x00004c),
+	REG(SYS_COUNT_RX_RED_PRIO_0,		0x000050),
+	REG(SYS_COUNT_RX_RED_PRIO_1,		0x000054),
+	REG(SYS_COUNT_RX_RED_PRIO_2,		0x000058),
+	REG(SYS_COUNT_RX_RED_PRIO_3,		0x00005c),
+	REG(SYS_COUNT_RX_RED_PRIO_4,		0x000060),
+	REG(SYS_COUNT_RX_RED_PRIO_5,		0x000064),
+	REG(SYS_COUNT_RX_RED_PRIO_6,		0x000068),
+	REG(SYS_COUNT_RX_RED_PRIO_7,		0x00006c),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_0,		0x000070),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_1,		0x000074),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_2,		0x000078),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_3,		0x00007c),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_4,		0x000080),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_5,		0x000084),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_6,		0x000088),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_7,		0x00008c),
+	REG(SYS_COUNT_RX_GREEN_PRIO_0,		0x000090),
+	REG(SYS_COUNT_RX_GREEN_PRIO_1,		0x000094),
+	REG(SYS_COUNT_RX_GREEN_PRIO_2,		0x000098),
+	REG(SYS_COUNT_RX_GREEN_PRIO_3,		0x00009c),
+	REG(SYS_COUNT_RX_GREEN_PRIO_4,		0x0000a0),
+	REG(SYS_COUNT_RX_GREEN_PRIO_5,		0x0000a4),
+	REG(SYS_COUNT_RX_GREEN_PRIO_6,		0x0000a8),
+	REG(SYS_COUNT_RX_GREEN_PRIO_7,		0x0000ac),
 	REG(SYS_COUNT_TX_OCTETS,		0x000100),
+	REG(SYS_COUNT_TX_UNICAST,		0x000104),
+	REG(SYS_COUNT_TX_MULTICAST,		0x000108),
+	REG(SYS_COUNT_TX_BROADCAST,		0x00010c),
 	REG(SYS_COUNT_TX_COLLISION,		0x000110),
 	REG(SYS_COUNT_TX_DROPS,			0x000114),
+	REG(SYS_COUNT_TX_PAUSE,			0x000118),
 	REG(SYS_COUNT_TX_64,			0x00011c),
 	REG(SYS_COUNT_TX_65_127,		0x000120),
-	REG(SYS_COUNT_TX_128_511,		0x000124),
-	REG(SYS_COUNT_TX_512_1023,		0x000128),
-	REG(SYS_COUNT_TX_1024_1526,		0x00012c),
-	REG(SYS_COUNT_TX_1527_MAX,		0x000130),
+	REG(SYS_COUNT_TX_128_255,		0x000124),
+	REG(SYS_COUNT_TX_256_511,		0x000128),
+	REG(SYS_COUNT_TX_512_1023,		0x00012c),
+	REG(SYS_COUNT_TX_1024_1526,		0x000130),
+	REG(SYS_COUNT_TX_1527_MAX,		0x000134),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_0,		0x000138),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_1,		0x00013c),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_2,		0x000140),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_3,		0x000144),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_4,		0x000148),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_5,		0x00014c),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_6,		0x000150),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_7,		0x000154),
+	REG(SYS_COUNT_TX_GREEN_PRIO_0,		0x000158),
+	REG(SYS_COUNT_TX_GREEN_PRIO_1,		0x00015c),
+	REG(SYS_COUNT_TX_GREEN_PRIO_2,		0x000160),
+	REG(SYS_COUNT_TX_GREEN_PRIO_3,		0x000164),
+	REG(SYS_COUNT_TX_GREEN_PRIO_4,		0x000168),
+	REG(SYS_COUNT_TX_GREEN_PRIO_5,		0x00016c),
+	REG(SYS_COUNT_TX_GREEN_PRIO_6,		0x000170),
+	REG(SYS_COUNT_TX_GREEN_PRIO_7,		0x000174),
 	REG(SYS_COUNT_TX_AGING,			0x000178),
+	REG(SYS_COUNT_DROP_LOCAL,		0x000200),
+	REG(SYS_COUNT_DROP_TAIL,		0x000204),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_0,	0x000208),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_1,	0x00020c),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_2,	0x000210),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_3,	0x000214),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_4,	0x000218),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_5,	0x00021c),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_6,	0x000220),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_7,	0x000224),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_0,	0x000228),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_1,	0x00022c),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_2,	0x000230),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_3,	0x000234),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_4,	0x000238),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_5,	0x00023c),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_6,	0x000240),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_7,	0x000244),
 	REG(SYS_RESET_CFG,			0x000318),
 	REG_RESERVED(SYS_SR_ETYPE_CFG),
 	REG(SYS_VLAN_ETYPE_CFG,			0x000320),
@@ -543,101 +614,379 @@ static const struct reg_field vsc9953_regfields[REGFIELD_MAX] = {
 	[SYS_PAUSE_CFG_PAUSE_ENA] = REG_FIELD_ID(SYS_PAUSE_CFG, 0, 1, 11, 4),
 };
 
-static const struct ocelot_stat_layout vsc9953_stats_layout[] = {
-	{ .offset = 0x00,	.name = "rx_octets", },
-	{ .offset = 0x01,	.name = "rx_unicast", },
-	{ .offset = 0x02,	.name = "rx_multicast", },
-	{ .offset = 0x03,	.name = "rx_broadcast", },
-	{ .offset = 0x04,	.name = "rx_shorts", },
-	{ .offset = 0x05,	.name = "rx_fragments", },
-	{ .offset = 0x06,	.name = "rx_jabbers", },
-	{ .offset = 0x07,	.name = "rx_crc_align_errs", },
-	{ .offset = 0x08,	.name = "rx_sym_errs", },
-	{ .offset = 0x09,	.name = "rx_frames_below_65_octets", },
-	{ .offset = 0x0A,	.name = "rx_frames_65_to_127_octets", },
-	{ .offset = 0x0B,	.name = "rx_frames_128_to_255_octets", },
-	{ .offset = 0x0C,	.name = "rx_frames_256_to_511_octets", },
-	{ .offset = 0x0D,	.name = "rx_frames_512_to_1023_octets", },
-	{ .offset = 0x0E,	.name = "rx_frames_1024_to_1526_octets", },
-	{ .offset = 0x0F,	.name = "rx_frames_over_1526_octets", },
-	{ .offset = 0x10,	.name = "rx_pause", },
-	{ .offset = 0x11,	.name = "rx_control", },
-	{ .offset = 0x12,	.name = "rx_longs", },
-	{ .offset = 0x13,	.name = "rx_classified_drops", },
-	{ .offset = 0x14,	.name = "rx_red_prio_0", },
-	{ .offset = 0x15,	.name = "rx_red_prio_1", },
-	{ .offset = 0x16,	.name = "rx_red_prio_2", },
-	{ .offset = 0x17,	.name = "rx_red_prio_3", },
-	{ .offset = 0x18,	.name = "rx_red_prio_4", },
-	{ .offset = 0x19,	.name = "rx_red_prio_5", },
-	{ .offset = 0x1A,	.name = "rx_red_prio_6", },
-	{ .offset = 0x1B,	.name = "rx_red_prio_7", },
-	{ .offset = 0x1C,	.name = "rx_yellow_prio_0", },
-	{ .offset = 0x1D,	.name = "rx_yellow_prio_1", },
-	{ .offset = 0x1E,	.name = "rx_yellow_prio_2", },
-	{ .offset = 0x1F,	.name = "rx_yellow_prio_3", },
-	{ .offset = 0x20,	.name = "rx_yellow_prio_4", },
-	{ .offset = 0x21,	.name = "rx_yellow_prio_5", },
-	{ .offset = 0x22,	.name = "rx_yellow_prio_6", },
-	{ .offset = 0x23,	.name = "rx_yellow_prio_7", },
-	{ .offset = 0x24,	.name = "rx_green_prio_0", },
-	{ .offset = 0x25,	.name = "rx_green_prio_1", },
-	{ .offset = 0x26,	.name = "rx_green_prio_2", },
-	{ .offset = 0x27,	.name = "rx_green_prio_3", },
-	{ .offset = 0x28,	.name = "rx_green_prio_4", },
-	{ .offset = 0x29,	.name = "rx_green_prio_5", },
-	{ .offset = 0x2A,	.name = "rx_green_prio_6", },
-	{ .offset = 0x2B,	.name = "rx_green_prio_7", },
-	{ .offset = 0x40,	.name = "tx_octets", },
-	{ .offset = 0x41,	.name = "tx_unicast", },
-	{ .offset = 0x42,	.name = "tx_multicast", },
-	{ .offset = 0x43,	.name = "tx_broadcast", },
-	{ .offset = 0x44,	.name = "tx_collision", },
-	{ .offset = 0x45,	.name = "tx_drops", },
-	{ .offset = 0x46,	.name = "tx_pause", },
-	{ .offset = 0x47,	.name = "tx_frames_below_65_octets", },
-	{ .offset = 0x48,	.name = "tx_frames_65_to_127_octets", },
-	{ .offset = 0x49,	.name = "tx_frames_128_255_octets", },
-	{ .offset = 0x4A,	.name = "tx_frames_256_511_octets", },
-	{ .offset = 0x4B,	.name = "tx_frames_512_1023_octets", },
-	{ .offset = 0x4C,	.name = "tx_frames_1024_1526_octets", },
-	{ .offset = 0x4D,	.name = "tx_frames_over_1526_octets", },
-	{ .offset = 0x4E,	.name = "tx_yellow_prio_0", },
-	{ .offset = 0x4F,	.name = "tx_yellow_prio_1", },
-	{ .offset = 0x50,	.name = "tx_yellow_prio_2", },
-	{ .offset = 0x51,	.name = "tx_yellow_prio_3", },
-	{ .offset = 0x52,	.name = "tx_yellow_prio_4", },
-	{ .offset = 0x53,	.name = "tx_yellow_prio_5", },
-	{ .offset = 0x54,	.name = "tx_yellow_prio_6", },
-	{ .offset = 0x55,	.name = "tx_yellow_prio_7", },
-	{ .offset = 0x56,	.name = "tx_green_prio_0", },
-	{ .offset = 0x57,	.name = "tx_green_prio_1", },
-	{ .offset = 0x58,	.name = "tx_green_prio_2", },
-	{ .offset = 0x59,	.name = "tx_green_prio_3", },
-	{ .offset = 0x5A,	.name = "tx_green_prio_4", },
-	{ .offset = 0x5B,	.name = "tx_green_prio_5", },
-	{ .offset = 0x5C,	.name = "tx_green_prio_6", },
-	{ .offset = 0x5D,	.name = "tx_green_prio_7", },
-	{ .offset = 0x5E,	.name = "tx_aged", },
-	{ .offset = 0x80,	.name = "drop_local", },
-	{ .offset = 0x81,	.name = "drop_tail", },
-	{ .offset = 0x82,	.name = "drop_yellow_prio_0", },
-	{ .offset = 0x83,	.name = "drop_yellow_prio_1", },
-	{ .offset = 0x84,	.name = "drop_yellow_prio_2", },
-	{ .offset = 0x85,	.name = "drop_yellow_prio_3", },
-	{ .offset = 0x86,	.name = "drop_yellow_prio_4", },
-	{ .offset = 0x87,	.name = "drop_yellow_prio_5", },
-	{ .offset = 0x88,	.name = "drop_yellow_prio_6", },
-	{ .offset = 0x89,	.name = "drop_yellow_prio_7", },
-	{ .offset = 0x8A,	.name = "drop_green_prio_0", },
-	{ .offset = 0x8B,	.name = "drop_green_prio_1", },
-	{ .offset = 0x8C,	.name = "drop_green_prio_2", },
-	{ .offset = 0x8D,	.name = "drop_green_prio_3", },
-	{ .offset = 0x8E,	.name = "drop_green_prio_4", },
-	{ .offset = 0x8F,	.name = "drop_green_prio_5", },
-	{ .offset = 0x90,	.name = "drop_green_prio_6", },
-	{ .offset = 0x91,	.name = "drop_green_prio_7", },
-	OCELOT_STAT_END
+static const struct ocelot_stat_layout vsc9953_stats_layout[OCELOT_NUM_STATS] = {
+	[OCELOT_STAT_RX_OCTETS] = {
+		.name = "rx_octets",
+		.reg = SYS_COUNT_RX_OCTETS,
+	},
+	[OCELOT_STAT_RX_UNICAST] = {
+		.name = "rx_unicast",
+		.reg = SYS_COUNT_RX_UNICAST,
+	},
+	[OCELOT_STAT_RX_MULTICAST] = {
+		.name = "rx_multicast",
+		.reg = SYS_COUNT_RX_MULTICAST,
+	},
+	[OCELOT_STAT_RX_BROADCAST] = {
+		.name = "rx_broadcast",
+		.reg = SYS_COUNT_RX_BROADCAST,
+	},
+	[OCELOT_STAT_RX_SHORTS] = {
+		.name = "rx_shorts",
+		.reg = SYS_COUNT_RX_SHORTS,
+	},
+	[OCELOT_STAT_RX_FRAGMENTS] = {
+		.name = "rx_fragments",
+		.reg = SYS_COUNT_RX_FRAGMENTS,
+	},
+	[OCELOT_STAT_RX_JABBERS] = {
+		.name = "rx_jabbers",
+		.reg = SYS_COUNT_RX_JABBERS,
+	},
+	[OCELOT_STAT_RX_CRC_ALIGN_ERRS] = {
+		.name = "rx_crc_align_errs",
+		.reg = SYS_COUNT_RX_CRC_ALIGN_ERRS,
+	},
+	[OCELOT_STAT_RX_SYM_ERRS] = {
+		.name = "rx_sym_errs",
+		.reg = SYS_COUNT_RX_SYM_ERRS,
+	},
+	[OCELOT_STAT_RX_64] = {
+		.name = "rx_frames_below_65_octets",
+		.reg = SYS_COUNT_RX_64,
+	},
+	[OCELOT_STAT_RX_65_127] = {
+		.name = "rx_frames_65_to_127_octets",
+		.reg = SYS_COUNT_RX_65_127,
+	},
+	[OCELOT_STAT_RX_128_255] = {
+		.name = "rx_frames_128_to_255_octets",
+		.reg = SYS_COUNT_RX_128_255,
+	},
+	[OCELOT_STAT_RX_256_511] = {
+		.name = "rx_frames_256_to_511_octets",
+		.reg = SYS_COUNT_RX_256_511,
+	},
+	[OCELOT_STAT_RX_512_1023] = {
+		.name = "rx_frames_512_to_1023_octets",
+		.reg = SYS_COUNT_RX_512_1023,
+	},
+	[OCELOT_STAT_RX_1024_1526] = {
+		.name = "rx_frames_1024_to_1526_octets",
+		.reg = SYS_COUNT_RX_1024_1526,
+	},
+	[OCELOT_STAT_RX_1527_MAX] = {
+		.name = "rx_frames_over_1526_octets",
+		.reg = SYS_COUNT_RX_1527_MAX,
+	},
+	[OCELOT_STAT_RX_PAUSE] = {
+		.name = "rx_pause",
+		.reg = SYS_COUNT_RX_PAUSE,
+	},
+	[OCELOT_STAT_RX_CONTROL] = {
+		.name = "rx_control",
+		.reg = SYS_COUNT_RX_CONTROL,
+	},
+	[OCELOT_STAT_RX_LONGS] = {
+		.name = "rx_longs",
+		.reg = SYS_COUNT_RX_LONGS,
+	},
+	[OCELOT_STAT_RX_CLASSIFIED_DROPS] = {
+		.name = "rx_classified_drops",
+		.reg = SYS_COUNT_RX_CLASSIFIED_DROPS,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_0] = {
+		.name = "rx_red_prio_0",
+		.reg = SYS_COUNT_RX_RED_PRIO_0,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_1] = {
+		.name = "rx_red_prio_1",
+		.reg = SYS_COUNT_RX_RED_PRIO_1,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_2] = {
+		.name = "rx_red_prio_2",
+		.reg = SYS_COUNT_RX_RED_PRIO_2,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_3] = {
+		.name = "rx_red_prio_3",
+		.reg = SYS_COUNT_RX_RED_PRIO_3,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_4] = {
+		.name = "rx_red_prio_4",
+		.reg = SYS_COUNT_RX_RED_PRIO_4,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_5] = {
+		.name = "rx_red_prio_5",
+		.reg = SYS_COUNT_RX_RED_PRIO_5,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_6] = {
+		.name = "rx_red_prio_6",
+		.reg = SYS_COUNT_RX_RED_PRIO_6,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_7] = {
+		.name = "rx_red_prio_7",
+		.reg = SYS_COUNT_RX_RED_PRIO_7,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_0] = {
+		.name = "rx_yellow_prio_0",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_1] = {
+		.name = "rx_yellow_prio_1",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_2] = {
+		.name = "rx_yellow_prio_2",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_3] = {
+		.name = "rx_yellow_prio_3",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_4] = {
+		.name = "rx_yellow_prio_4",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_5] = {
+		.name = "rx_yellow_prio_5",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_6] = {
+		.name = "rx_yellow_prio_6",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_7] = {
+		.name = "rx_yellow_prio_7",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_0] = {
+		.name = "rx_green_prio_0",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_1] = {
+		.name = "rx_green_prio_1",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_2] = {
+		.name = "rx_green_prio_2",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_3] = {
+		.name = "rx_green_prio_3",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_4] = {
+		.name = "rx_green_prio_4",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_5] = {
+		.name = "rx_green_prio_5",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_6] = {
+		.name = "rx_green_prio_6",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_7] = {
+		.name = "rx_green_prio_7",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_7,
+	},
+	[OCELOT_STAT_TX_OCTETS] = {
+		.name = "tx_octets",
+		.reg = SYS_COUNT_TX_OCTETS,
+	},
+	[OCELOT_STAT_TX_UNICAST] = {
+		.name = "tx_unicast",
+		.reg = SYS_COUNT_TX_UNICAST,
+	},
+	[OCELOT_STAT_TX_MULTICAST] = {
+		.name = "tx_multicast",
+		.reg = SYS_COUNT_TX_MULTICAST,
+	},
+	[OCELOT_STAT_TX_BROADCAST] = {
+		.name = "tx_broadcast",
+		.reg = SYS_COUNT_TX_BROADCAST,
+	},
+	[OCELOT_STAT_TX_COLLISION] = {
+		.name = "tx_collision",
+		.reg = SYS_COUNT_TX_COLLISION,
+	},
+	[OCELOT_STAT_TX_DROPS] = {
+		.name = "tx_drops",
+		.reg = SYS_COUNT_TX_DROPS,
+	},
+	[OCELOT_STAT_TX_PAUSE] = {
+		.name = "tx_pause",
+		.reg = SYS_COUNT_TX_PAUSE,
+	},
+	[OCELOT_STAT_TX_64] = {
+		.name = "tx_frames_below_65_octets",
+		.reg = SYS_COUNT_TX_64,
+	},
+	[OCELOT_STAT_TX_65_127] = {
+		.name = "tx_frames_65_to_127_octets",
+		.reg = SYS_COUNT_TX_65_127,
+	},
+	[OCELOT_STAT_TX_128_255] = {
+		.name = "tx_frames_128_255_octets",
+		.reg = SYS_COUNT_TX_128_255,
+	},
+	[OCELOT_STAT_TX_256_511] = {
+		.name = "tx_frames_256_511_octets",
+		.reg = SYS_COUNT_TX_256_511,
+	},
+	[OCELOT_STAT_TX_512_1023] = {
+		.name = "tx_frames_512_1023_octets",
+		.reg = SYS_COUNT_TX_512_1023,
+	},
+	[OCELOT_STAT_TX_1024_1526] = {
+		.name = "tx_frames_1024_1526_octets",
+		.reg = SYS_COUNT_TX_1024_1526,
+	},
+	[OCELOT_STAT_TX_1527_MAX] = {
+		.name = "tx_frames_over_1526_octets",
+		.reg = SYS_COUNT_TX_1527_MAX,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_0] = {
+		.name = "tx_yellow_prio_0",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_1] = {
+		.name = "tx_yellow_prio_1",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_2] = {
+		.name = "tx_yellow_prio_2",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_3] = {
+		.name = "tx_yellow_prio_3",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_4] = {
+		.name = "tx_yellow_prio_4",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_5] = {
+		.name = "tx_yellow_prio_5",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_6] = {
+		.name = "tx_yellow_prio_6",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_7] = {
+		.name = "tx_yellow_prio_7",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_0] = {
+		.name = "tx_green_prio_0",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_1] = {
+		.name = "tx_green_prio_1",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_2] = {
+		.name = "tx_green_prio_2",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_3] = {
+		.name = "tx_green_prio_3",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_4] = {
+		.name = "tx_green_prio_4",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_5] = {
+		.name = "tx_green_prio_5",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_6] = {
+		.name = "tx_green_prio_6",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_7] = {
+		.name = "tx_green_prio_7",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_7,
+	},
+	[OCELOT_STAT_TX_AGED] = {
+		.name = "tx_aged",
+		.reg = SYS_COUNT_TX_AGING,
+	},
+	[OCELOT_STAT_DROP_LOCAL] = {
+		.name = "drop_local",
+		.reg = SYS_COUNT_DROP_LOCAL,
+	},
+	[OCELOT_STAT_DROP_TAIL] = {
+		.name = "drop_tail",
+		.reg = SYS_COUNT_DROP_TAIL,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_0] = {
+		.name = "drop_yellow_prio_0",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_1] = {
+		.name = "drop_yellow_prio_1",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_2] = {
+		.name = "drop_yellow_prio_2",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_3] = {
+		.name = "drop_yellow_prio_3",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_4] = {
+		.name = "drop_yellow_prio_4",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_5] = {
+		.name = "drop_yellow_prio_5",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_6] = {
+		.name = "drop_yellow_prio_6",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_7] = {
+		.name = "drop_yellow_prio_7",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_0] = {
+		.name = "drop_green_prio_0",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_1] = {
+		.name = "drop_green_prio_1",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_2] = {
+		.name = "drop_green_prio_2",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_3] = {
+		.name = "drop_green_prio_3",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_4] = {
+		.name = "drop_green_prio_4",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_5] = {
+		.name = "drop_green_prio_5",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_6] = {
+		.name = "drop_green_prio_6",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_7] = {
+		.name = "drop_green_prio_7",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_7,
+	},
 };
 
 static const struct vcap_field vsc9953_vcap_es0_keys[] = {
diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index 1d3e7782a71f..c181346388a4 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -1889,9 +1889,9 @@ qca8k_sw_probe(struct mdio_device *mdiodev)
 	if (!priv)
 		return -ENOMEM;
 
-	priv->info = of_device_get_match_data(priv->dev);
 	priv->bus = mdiodev->bus;
 	priv->dev = &mdiodev->dev;
+	priv->info = of_device_get_match_data(priv->dev);
 
 	priv->reset_gpio = devm_gpiod_get_optional(priv->dev, "reset",
 						   GPIOD_ASIS);
diff --git a/drivers/net/dsa/sja1105/sja1105_devlink.c b/drivers/net/dsa/sja1105/sja1105_devlink.c
index 0569ff066634..10c6fea1227f 100644
--- a/drivers/net/dsa/sja1105/sja1105_devlink.c
+++ b/drivers/net/dsa/sja1105/sja1105_devlink.c
@@ -93,7 +93,7 @@ static int sja1105_setup_devlink_regions(struct dsa_switch *ds)
 
 		region = dsa_devlink_region_create(ds, ops, 1, size);
 		if (IS_ERR(region)) {
-			while (i-- >= 0)
+			while (--i >= 0)
 				dsa_devlink_region_destroy(priv->regions[i]);
 			return PTR_ERR(region);
 		}
diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c
index 3887ed33c5fe..fa622639d640 100644
--- a/drivers/net/dsa/xrs700x/xrs700x.c
+++ b/drivers/net/dsa/xrs700x/xrs700x.c
@@ -109,6 +109,7 @@ static void xrs700x_read_port_counters(struct xrs700x *priv, int port)
 {
 	struct xrs700x_port *p = &priv->ports[port];
 	struct rtnl_link_stats64 stats;
+	unsigned long flags;
 	int i;
 
 	memset(&stats, 0, sizeof(stats));
@@ -138,9 +139,9 @@ static void xrs700x_read_port_counters(struct xrs700x *priv, int port)
 	 */
 	stats.rx_packets += stats.multicast;
 
-	u64_stats_update_begin(&p->syncp);
+	flags = u64_stats_update_begin_irqsave(&p->syncp);
 	p->stats64 = stats;
-	u64_stats_update_end(&p->syncp);
+	u64_stats_update_end_irqrestore(&p->syncp, flags);
 
 	mutex_unlock(&p->mib_mutex);
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index 88595863d8bc..8a0af371e7dc 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -94,11 +94,8 @@ static int aq_ndev_close(struct net_device *ndev)
 	int err = 0;
 
 	err = aq_nic_stop(aq_nic);
-	if (err < 0)
-		goto err_exit;
 	aq_nic_deinit(aq_nic, true);
 
-err_exit:
 	return err;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 7071604f9984..02808513ffe4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -13844,7 +13844,7 @@ static void bnx2x_check_kr2_wa(struct link_params *params,
 
 	/* Once KR2 was disabled, wait 5 seconds before checking KR2 recovery
 	 * Since some switches tend to reinit the AN process and clear the
-	 * the advertised BP/NP after ~2 seconds causing the KR2 to be disabled
+	 * advertised BP/NP after ~2 seconds causing the KR2 to be disabled
 	 * and recovered many times
 	 */
 	if (vars->check_kr2_recovery_cnt > 0) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index ba0f1ffac507..96da0ba3d507 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -659,7 +659,6 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 
 	for (i = 0; i < nr_pkts; i++) {
 		struct bnxt_sw_tx_bd *tx_buf;
-		bool compl_deferred = false;
 		struct sk_buff *skb;
 		int j, last;
 
@@ -668,6 +667,8 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 		skb = tx_buf->skb;
 		tx_buf->skb = NULL;
 
+		tx_bytes += skb->len;
+
 		if (tx_buf->is_push) {
 			tx_buf->is_push = 0;
 			goto next_tx_int;
@@ -688,8 +689,9 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 		}
 		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) {
 			if (bp->flags & BNXT_FLAG_CHIP_P5) {
+				/* PTP worker takes ownership of the skb */
 				if (!bnxt_get_tx_ts_p5(bp, skb))
-					compl_deferred = true;
+					skb = NULL;
 				else
 					atomic_inc(&bp->ptp_cfg->tx_avail);
 			}
@@ -698,9 +700,7 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 next_tx_int:
 		cons = NEXT_TX(cons);
 
-		tx_bytes += skb->len;
-		if (!compl_deferred)
-			dev_kfree_skb_any(skb);
+		dev_kfree_skb_any(skb);
 	}
 
 	netdev_tx_completed_queue(txq, nr_pkts, tx_bytes);
@@ -11178,10 +11178,7 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev,
 	if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp))
 		features &= ~NETIF_F_NTUPLE;
 
-	if (bp->flags & BNXT_FLAG_NO_AGG_RINGS)
-		features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW);
-
-	if (!(bp->flags & BNXT_FLAG_TPA))
+	if ((bp->flags & BNXT_FLAG_NO_AGG_RINGS) || bp->xdp_prog)
 		features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW);
 
 	if (!(features & NETIF_F_GRO))
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 075c6206325c..b1b17f911300 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2130,6 +2130,7 @@ struct bnxt {
 #define BNXT_DUMP_CRASH		1
 
 	struct bpf_prog		*xdp_prog;
+	u8			xdp_has_frags;
 
 	struct bnxt_ptp_cfg	*ptp_cfg;
 	u8			ptp_all_rx_tstamp;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 059f96f7a96f..a36803e79e92 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -1306,6 +1306,7 @@ int bnxt_dl_register(struct bnxt *bp)
 	if (rc)
 		goto err_dl_port_unreg;
 
+	devlink_set_features(dl, DEVLINK_F_RELOAD);
 out:
 	devlink_register(dl);
 	return 0;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 7f3c0875b6f5..8e316367f6ce 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -317,9 +317,9 @@ void bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp)
 
 	if (!(bp->fw_cap & BNXT_FW_CAP_RX_ALL_PKT_TS) && (ptp->tstamp_filters &
 	    (PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_ENABLE |
-	     PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_DISABLE))) {
+	     PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_DISABLE))) {
 		ptp->tstamp_filters &= ~(PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_ENABLE |
-					 PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_DISABLE);
+					 PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_DISABLE);
 		netdev_warn(bp->dev, "Unsupported FW for all RX pkts timestamp filter\n");
 	}
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 730febd19330..a4cba7cb2783 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -623,7 +623,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 		hw_resc->max_stat_ctxs -= le16_to_cpu(req->min_stat_ctx) * n;
 		hw_resc->max_vnics -= le16_to_cpu(req->min_vnics) * n;
 		if (bp->flags & BNXT_FLAG_CHIP_P5)
-			hw_resc->max_irqs -= vf_msix * n;
+			hw_resc->max_nqs -= vf_msix;
 
 		rc = pf->active_vfs;
 	}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index f53387ed0167..c3065ec0a479 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -181,6 +181,7 @@ void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 			struct xdp_buff *xdp)
 {
 	struct bnxt_sw_rx_bd *rx_buf;
+	u32 buflen = PAGE_SIZE;
 	struct pci_dev *pdev;
 	dma_addr_t mapping;
 	u32 offset;
@@ -192,7 +193,10 @@ void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	mapping = rx_buf->mapping - bp->rx_dma_offset;
 	dma_sync_single_for_cpu(&pdev->dev, mapping + offset, *len, bp->rx_dir);
 
-	xdp_init_buff(xdp, BNXT_PAGE_MODE_BUF_SIZE + offset, &rxr->xdp_rxq);
+	if (bp->xdp_has_frags)
+		buflen = BNXT_PAGE_MODE_BUF_SIZE + offset;
+
+	xdp_init_buff(xdp, buflen, &rxr->xdp_rxq);
 	xdp_prepare_buff(xdp, *data_ptr - offset, offset, *len, false);
 }
 
@@ -397,8 +401,10 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 		netdev_warn(dev, "ethtool rx/tx channels must be combined to support XDP.\n");
 		return -EOPNOTSUPP;
 	}
-	if (prog)
+	if (prog) {
 		tx_xdp = bp->rx_nr_rings;
+		bp->xdp_has_frags = prog->aux->xdp_has_frags;
+	}
 
 	tc = netdev_get_num_tc(dev);
 	if (!tc)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index db1e9d810b41..89889d8150da 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -18076,16 +18076,20 @@ static void tg3_shutdown(struct pci_dev *pdev)
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct tg3 *tp = netdev_priv(dev);
 
+	tg3_reset_task_cancel(tp);
+
 	rtnl_lock();
+
 	netif_device_detach(dev);
 
 	if (netif_running(dev))
 		dev_close(dev);
 
-	if (system_state == SYSTEM_POWER_OFF)
-		tg3_power_down(tp);
+	tg3_power_down(tp);
 
 	rtnl_unlock();
+
+	pci_disable_device(pdev);
 }
 
 /**
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 66c7d08d376a..a2897549f9c4 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -5109,6 +5109,7 @@ static int __maybe_unused macb_suspend(struct device *dev)
 	if (!(bp->wol & MACB_WOL_ENABLED)) {
 		rtnl_lock();
 		phylink_stop(bp->phylink);
+		phy_exit(bp->sgmii_phy);
 		rtnl_unlock();
 		spin_lock_irqsave(&bp->lock, flags);
 		macb_reset_hw(bp);
@@ -5198,6 +5199,9 @@ static int __maybe_unused macb_resume(struct device *dev)
 	macb_set_rx_mode(netdev);
 	macb_restore_features(bp);
 	rtnl_lock();
+	if (!device_may_wakeup(&bp->dev->dev))
+		phy_init(bp->sgmii_phy);
+
 	phylink_start(bp->phylink);
 	rtnl_unlock();
 
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c
index 84604aff53ce..89256b866840 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c
@@ -243,7 +243,7 @@ static int cxgb_ulp_iscsi_ctl(struct adapter *adapter, unsigned int req,
 
 		/*
 		 * on rx, the iscsi pdu has to be < rx page size and the
-		 * the max rx data length programmed in TP
+		 * max rx data length programmed in TP
 		 */
 		val = min(adapter->params.tp.rx_pg_size,
 			  ((t3_read_reg(adapter, A_TP_PARA_REG2)) >>
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index a7f291c89702..557c591a6ce3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -14,6 +14,7 @@
 #include "cudbg_entity.h"
 #include "cudbg_lib.h"
 #include "cudbg_zlib.h"
+#include "cxgb4_tc_mqprio.h"
 
 static const u32 t6_tp_pio_array[][IREG_NUM_ELEM] = {
 	{0x7e40, 0x7e44, 0x020, 28}, /* t6_tp_pio_regs_20_to_3b */
@@ -3458,7 +3459,7 @@ int cudbg_collect_qdesc(struct cudbg_init *pdbg_init,
 			for (i = 0; i < utxq->ntxq; i++)
 				QDESC_GET_TXQ(&utxq->uldtxq[i].q,
 					      cudbg_uld_txq_to_qtype(j),
-					      out_unlock);
+					      out_unlock_uld);
 		}
 	}
 
@@ -3475,7 +3476,7 @@ int cudbg_collect_qdesc(struct cudbg_init *pdbg_init,
 			for (i = 0; i < urxq->nrxq; i++)
 				QDESC_GET_RXQ(&urxq->uldrxq[i].rspq,
 					      cudbg_uld_rxq_to_qtype(j),
-					      out_unlock);
+					      out_unlock_uld);
 		}
 
 		/* ULD FLQ */
@@ -3487,7 +3488,7 @@ int cudbg_collect_qdesc(struct cudbg_init *pdbg_init,
 			for (i = 0; i < urxq->nrxq; i++)
 				QDESC_GET_FLQ(&urxq->uldrxq[i].fl,
 					      cudbg_uld_flq_to_qtype(j),
-					      out_unlock);
+					      out_unlock_uld);
 		}
 
 		/* ULD CIQ */
@@ -3500,29 +3501,34 @@ int cudbg_collect_qdesc(struct cudbg_init *pdbg_init,
 			for (i = 0; i < urxq->nciq; i++)
 				QDESC_GET_RXQ(&urxq->uldrxq[base + i].rspq,
 					      cudbg_uld_ciq_to_qtype(j),
-					      out_unlock);
+					      out_unlock_uld);
 		}
 	}
+	mutex_unlock(&uld_mutex);
+
+	if (!padap->tc_mqprio)
+		goto out;
 
+	mutex_lock(&padap->tc_mqprio->mqprio_mutex);
 	/* ETHOFLD TXQ */
 	if (s->eohw_txq)
 		for (i = 0; i < s->eoqsets; i++)
 			QDESC_GET_TXQ(&s->eohw_txq[i].q,
-				      CUDBG_QTYPE_ETHOFLD_TXQ, out);
+				      CUDBG_QTYPE_ETHOFLD_TXQ, out_unlock_mqprio);
 
 	/* ETHOFLD RXQ and FLQ */
 	if (s->eohw_rxq) {
 		for (i = 0; i < s->eoqsets; i++)
 			QDESC_GET_RXQ(&s->eohw_rxq[i].rspq,
-				      CUDBG_QTYPE_ETHOFLD_RXQ, out);
+				      CUDBG_QTYPE_ETHOFLD_RXQ, out_unlock_mqprio);
 
 		for (i = 0; i < s->eoqsets; i++)
 			QDESC_GET_FLQ(&s->eohw_rxq[i].fl,
-				      CUDBG_QTYPE_ETHOFLD_FLQ, out);
+				      CUDBG_QTYPE_ETHOFLD_FLQ, out_unlock_mqprio);
 	}
 
-out_unlock:
-	mutex_unlock(&uld_mutex);
+out_unlock_mqprio:
+	mutex_unlock(&padap->tc_mqprio->mqprio_mutex);
 
 out:
 	qdesc_info->qdesc_entry_size = sizeof(*qdesc_entry);
@@ -3559,6 +3565,10 @@ out_free:
 #undef QDESC_GET
 
 	return rc;
+
+out_unlock_uld:
+	mutex_unlock(&uld_mutex);
+	goto out;
 }
 
 int cudbg_collect_flash(struct cudbg_init *pdbg_init,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index 26433a62d7f0..fed5f93bf620 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -497,7 +497,7 @@ struct cpl_t5_pass_accept_rpl {
 	__be32 opt2;
 	__be64 opt0;
 	__be32 iss;
-	__be32 rsvd[3];
+	__be32 rsvd;
 };
 
 struct cpl_act_open_req {
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 9e6de2f968fa..6dae768671e3 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -1919,7 +1919,7 @@ static void gmac_get_stats64(struct net_device *netdev,
 
 	/* Racing with RX NAPI */
 	do {
-		start = u64_stats_fetch_begin(&port->rx_stats_syncp);
+		start = u64_stats_fetch_begin_irq(&port->rx_stats_syncp);
 
 		stats->rx_packets = port->stats.rx_packets;
 		stats->rx_bytes = port->stats.rx_bytes;
@@ -1931,11 +1931,11 @@ static void gmac_get_stats64(struct net_device *netdev,
 		stats->rx_crc_errors = port->stats.rx_crc_errors;
 		stats->rx_frame_errors = port->stats.rx_frame_errors;
 
-	} while (u64_stats_fetch_retry(&port->rx_stats_syncp, start));
+	} while (u64_stats_fetch_retry_irq(&port->rx_stats_syncp, start));
 
 	/* Racing with MIB and TX completion interrupts */
 	do {
-		start = u64_stats_fetch_begin(&port->ir_stats_syncp);
+		start = u64_stats_fetch_begin_irq(&port->ir_stats_syncp);
 
 		stats->tx_errors = port->stats.tx_errors;
 		stats->tx_packets = port->stats.tx_packets;
@@ -1945,15 +1945,15 @@ static void gmac_get_stats64(struct net_device *netdev,
 		stats->rx_missed_errors = port->stats.rx_missed_errors;
 		stats->rx_fifo_errors = port->stats.rx_fifo_errors;
 
-	} while (u64_stats_fetch_retry(&port->ir_stats_syncp, start));
+	} while (u64_stats_fetch_retry_irq(&port->ir_stats_syncp, start));
 
 	/* Racing with hard_start_xmit */
 	do {
-		start = u64_stats_fetch_begin(&port->tx_stats_syncp);
+		start = u64_stats_fetch_begin_irq(&port->tx_stats_syncp);
 
 		stats->tx_dropped = port->stats.tx_dropped;
 
-	} while (u64_stats_fetch_retry(&port->tx_stats_syncp, start));
+	} while (u64_stats_fetch_retry_irq(&port->tx_stats_syncp, start));
 
 	stats->rx_dropped += stats->rx_missed_errors;
 }
@@ -2031,18 +2031,18 @@ static void gmac_get_ethtool_stats(struct net_device *netdev,
 	/* Racing with MIB interrupt */
 	do {
 		p = values;
-		start = u64_stats_fetch_begin(&port->ir_stats_syncp);
+		start = u64_stats_fetch_begin_irq(&port->ir_stats_syncp);
 
 		for (i = 0; i < RX_STATS_NUM; i++)
 			*p++ = port->hw_stats[i];
 
-	} while (u64_stats_fetch_retry(&port->ir_stats_syncp, start));
+	} while (u64_stats_fetch_retry_irq(&port->ir_stats_syncp, start));
 	values = p;
 
 	/* Racing with RX NAPI */
 	do {
 		p = values;
-		start = u64_stats_fetch_begin(&port->rx_stats_syncp);
+		start = u64_stats_fetch_begin_irq(&port->rx_stats_syncp);
 
 		for (i = 0; i < RX_STATUS_NUM; i++)
 			*p++ = port->rx_stats[i];
@@ -2050,13 +2050,13 @@ static void gmac_get_ethtool_stats(struct net_device *netdev,
 			*p++ = port->rx_csum_stats[i];
 		*p++ = port->rx_napi_exits;
 
-	} while (u64_stats_fetch_retry(&port->rx_stats_syncp, start));
+	} while (u64_stats_fetch_retry_irq(&port->rx_stats_syncp, start));
 	values = p;
 
 	/* Racing with TX start_xmit */
 	do {
 		p = values;
-		start = u64_stats_fetch_begin(&port->tx_stats_syncp);
+		start = u64_stats_fetch_begin_irq(&port->tx_stats_syncp);
 
 		for (i = 0; i < TX_MAX_FRAGS; i++) {
 			*values++ = port->tx_frag_stats[i];
@@ -2065,7 +2065,7 @@ static void gmac_get_ethtool_stats(struct net_device *netdev,
 		*values++ = port->tx_frags_linearized;
 		*values++ = port->tx_hw_csummed;
 
-	} while (u64_stats_fetch_retry(&port->tx_stats_syncp, start));
+	} while (u64_stats_fetch_retry_irq(&port->tx_stats_syncp, start));
 }
 
 static int gmac_get_ksettings(struct net_device *netdev,
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 45634579adb6..a770bab4d1ed 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2886,6 +2886,7 @@ static void dpaa_adjust_link(struct net_device *net_dev)
 
 /* The Aquantia PHYs are capable of performing rate adaptation */
 #define PHY_VEND_AQUANTIA	0x03a1b400
+#define PHY_VEND_AQUANTIA2	0x31c31c00
 
 static int dpaa_phy_init(struct net_device *net_dev)
 {
@@ -2893,6 +2894,7 @@ static int dpaa_phy_init(struct net_device *net_dev)
 	struct mac_device *mac_dev;
 	struct phy_device *phy_dev;
 	struct dpaa_priv *priv;
+	u32 phy_vendor;
 
 	priv = netdev_priv(net_dev);
 	mac_dev = priv->mac_dev;
@@ -2905,9 +2907,11 @@ static int dpaa_phy_init(struct net_device *net_dev)
 		return -ENODEV;
 	}
 
+	phy_vendor = phy_dev->drv->phy_id & GENMASK(31, 10);
 	/* Unless the PHY is capable of rate adaptation */
 	if (mac_dev->phy_if != PHY_INTERFACE_MODE_XGMII ||
-	    ((phy_dev->drv->phy_id & GENMASK(31, 10)) != PHY_VEND_AQUANTIA)) {
+	    (phy_vendor != PHY_VEND_AQUANTIA &&
+	     phy_vendor != PHY_VEND_AQUANTIA2)) {
 		/* remove any features not supported by the controller */
 		ethtool_convert_legacy_u32_to_link_mode(mask,
 							mac_dev->if_support);
diff --git a/drivers/net/ethernet/freescale/enetc/Makefile b/drivers/net/ethernet/freescale/enetc/Makefile
index a139f2e9d59f..e0e8dfd13793 100644
--- a/drivers/net/ethernet/freescale/enetc/Makefile
+++ b/drivers/net/ethernet/freescale/enetc/Makefile
@@ -9,7 +9,6 @@ fsl-enetc-$(CONFIG_FSL_ENETC_QOS) += enetc_qos.o
 
 obj-$(CONFIG_FSL_ENETC_VF) += fsl-enetc-vf.o
 fsl-enetc-vf-y := enetc_vf.o $(common-objs)
-fsl-enetc-vf-$(CONFIG_FSL_ENETC_QOS) += enetc_qos.o
 
 obj-$(CONFIG_FSL_ENETC_IERB) += fsl-enetc-ierb.o
 fsl-enetc-ierb-y := enetc_ierb.o
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 4470a4a3e4c3..9f5b921039bd 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -2432,7 +2432,7 @@ int enetc_close(struct net_device *ndev)
 	return 0;
 }
 
-static int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data)
+int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	struct tc_mqprio_qopt *mqprio = type_data;
@@ -2486,25 +2486,6 @@ static int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data)
 	return 0;
 }
 
-int enetc_setup_tc(struct net_device *ndev, enum tc_setup_type type,
-		   void *type_data)
-{
-	switch (type) {
-	case TC_SETUP_QDISC_MQPRIO:
-		return enetc_setup_tc_mqprio(ndev, type_data);
-	case TC_SETUP_QDISC_TAPRIO:
-		return enetc_setup_tc_taprio(ndev, type_data);
-	case TC_SETUP_QDISC_CBS:
-		return enetc_setup_tc_cbs(ndev, type_data);
-	case TC_SETUP_QDISC_ETF:
-		return enetc_setup_tc_txtime(ndev, type_data);
-	case TC_SETUP_BLOCK:
-		return enetc_setup_tc_psfp(ndev, type_data);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
 static int enetc_setup_xdp_prog(struct net_device *dev, struct bpf_prog *prog,
 				struct netlink_ext_ack *extack)
 {
@@ -2600,29 +2581,6 @@ static int enetc_set_rss(struct net_device *ndev, int en)
 	return 0;
 }
 
-static int enetc_set_psfp(struct net_device *ndev, int en)
-{
-	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-	int err;
-
-	if (en) {
-		err = enetc_psfp_enable(priv);
-		if (err)
-			return err;
-
-		priv->active_offloads |= ENETC_F_QCI;
-		return 0;
-	}
-
-	err = enetc_psfp_disable(priv);
-	if (err)
-		return err;
-
-	priv->active_offloads &= ~ENETC_F_QCI;
-
-	return 0;
-}
-
 static void enetc_enable_rxvlan(struct net_device *ndev, bool en)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
@@ -2641,11 +2599,9 @@ static void enetc_enable_txvlan(struct net_device *ndev, bool en)
 		enetc_bdr_enable_txvlan(&priv->si->hw, i, en);
 }
 
-int enetc_set_features(struct net_device *ndev,
-		       netdev_features_t features)
+void enetc_set_features(struct net_device *ndev, netdev_features_t features)
 {
 	netdev_features_t changed = ndev->features ^ features;
-	int err = 0;
 
 	if (changed & NETIF_F_RXHASH)
 		enetc_set_rss(ndev, !!(features & NETIF_F_RXHASH));
@@ -2657,11 +2613,6 @@ int enetc_set_features(struct net_device *ndev,
 	if (changed & NETIF_F_HW_VLAN_CTAG_TX)
 		enetc_enable_txvlan(ndev,
 				    !!(features & NETIF_F_HW_VLAN_CTAG_TX));
-
-	if (changed & NETIF_F_HW_TC)
-		err = enetc_set_psfp(ndev, !!(features & NETIF_F_HW_TC));
-
-	return err;
 }
 
 #ifdef CONFIG_FSL_ENETC_PTP_CLOCK
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 29922c20531f..2cfe6944ebd3 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -393,11 +393,9 @@ void enetc_start(struct net_device *ndev);
 void enetc_stop(struct net_device *ndev);
 netdev_tx_t enetc_xmit(struct sk_buff *skb, struct net_device *ndev);
 struct net_device_stats *enetc_get_stats(struct net_device *ndev);
-int enetc_set_features(struct net_device *ndev,
-		       netdev_features_t features);
+void enetc_set_features(struct net_device *ndev, netdev_features_t features);
 int enetc_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd);
-int enetc_setup_tc(struct net_device *ndev, enum tc_setup_type type,
-		   void *type_data);
+int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data);
 int enetc_setup_bpf(struct net_device *dev, struct netdev_bpf *xdp);
 int enetc_xdp_xmit(struct net_device *ndev, int num_frames,
 		   struct xdp_frame **frames, u32 flags);
@@ -465,6 +463,7 @@ int enetc_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 int enetc_setup_tc_psfp(struct net_device *ndev, void *type_data);
 int enetc_psfp_init(struct enetc_ndev_priv *priv);
 int enetc_psfp_clean(struct enetc_ndev_priv *priv);
+int enetc_set_psfp(struct net_device *ndev, bool en);
 
 static inline void enetc_get_max_cap(struct enetc_ndev_priv *priv)
 {
@@ -540,4 +539,9 @@ static inline int enetc_psfp_disable(struct enetc_ndev_priv *priv)
 {
 	return 0;
 }
+
+static inline int enetc_set_psfp(struct net_device *ndev, bool en)
+{
+	return 0;
+}
 #endif
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index c4a0e836d4f0..bb7750222691 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -709,6 +709,13 @@ static int enetc_pf_set_features(struct net_device *ndev,
 {
 	netdev_features_t changed = ndev->features ^ features;
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	int err;
+
+	if (changed & NETIF_F_HW_TC) {
+		err = enetc_set_psfp(ndev, !!(features & NETIF_F_HW_TC));
+		if (err)
+			return err;
+	}
 
 	if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) {
 		struct enetc_pf *pf = enetc_si_priv(priv->si);
@@ -722,7 +729,28 @@ static int enetc_pf_set_features(struct net_device *ndev,
 	if (changed & NETIF_F_LOOPBACK)
 		enetc_set_loopback(ndev, !!(features & NETIF_F_LOOPBACK));
 
-	return enetc_set_features(ndev, features);
+	enetc_set_features(ndev, features);
+
+	return 0;
+}
+
+static int enetc_pf_setup_tc(struct net_device *ndev, enum tc_setup_type type,
+			     void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_QDISC_MQPRIO:
+		return enetc_setup_tc_mqprio(ndev, type_data);
+	case TC_SETUP_QDISC_TAPRIO:
+		return enetc_setup_tc_taprio(ndev, type_data);
+	case TC_SETUP_QDISC_CBS:
+		return enetc_setup_tc_cbs(ndev, type_data);
+	case TC_SETUP_QDISC_ETF:
+		return enetc_setup_tc_txtime(ndev, type_data);
+	case TC_SETUP_BLOCK:
+		return enetc_setup_tc_psfp(ndev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 static const struct net_device_ops enetc_ndev_ops = {
@@ -739,7 +767,7 @@ static const struct net_device_ops enetc_ndev_ops = {
 	.ndo_set_vf_spoofchk	= enetc_pf_set_vf_spoofchk,
 	.ndo_set_features	= enetc_pf_set_features,
 	.ndo_eth_ioctl		= enetc_ioctl,
-	.ndo_setup_tc		= enetc_setup_tc,
+	.ndo_setup_tc		= enetc_pf_setup_tc,
 	.ndo_bpf		= enetc_setup_bpf,
 	.ndo_xdp_xmit		= enetc_xdp_xmit,
 };
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
index 582a663ed0ba..f8a2f02ce22d 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c
@@ -1517,6 +1517,29 @@ int enetc_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
+int enetc_set_psfp(struct net_device *ndev, bool en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	int err;
+
+	if (en) {
+		err = enetc_psfp_enable(priv);
+		if (err)
+			return err;
+
+		priv->active_offloads |= ENETC_F_QCI;
+		return 0;
+	}
+
+	err = enetc_psfp_disable(priv);
+	if (err)
+		return err;
+
+	priv->active_offloads &= ~ENETC_F_QCI;
+
+	return 0;
+}
+
 int enetc_psfp_init(struct enetc_ndev_priv *priv)
 {
 	if (epsfp.psfp_sfi_bitmap)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
index 17924305afa2..dfcaac302e24 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
@@ -88,7 +88,20 @@ static int enetc_vf_set_mac_addr(struct net_device *ndev, void *addr)
 static int enetc_vf_set_features(struct net_device *ndev,
 				 netdev_features_t features)
 {
-	return enetc_set_features(ndev, features);
+	enetc_set_features(ndev, features);
+
+	return 0;
+}
+
+static int enetc_vf_setup_tc(struct net_device *ndev, enum tc_setup_type type,
+			     void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_QDISC_MQPRIO:
+		return enetc_setup_tc_mqprio(ndev, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 /* Probing/ Init */
@@ -100,7 +113,7 @@ static const struct net_device_ops enetc_ndev_ops = {
 	.ndo_set_mac_address	= enetc_vf_set_mac_addr,
 	.ndo_set_features	= enetc_vf_set_features,
 	.ndo_eth_ioctl		= enetc_ioctl,
-	.ndo_setup_tc		= enetc_setup_tc,
+	.ndo_setup_tc		= enetc_vf_setup_tc,
 };
 
 static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index ed7301b69169..a5fed00cb971 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -16,6 +16,7 @@
 
 #include <linux/clocksource.h>
 #include <linux/net_tstamp.h>
+#include <linux/pm_qos.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/timecounter.h>
 
@@ -498,6 +499,9 @@ struct bufdesc_ex {
 /* i.MX8MQ SoC integration mix wakeup interrupt signal into "int2" interrupt line. */
 #define FEC_QUIRK_WAKEUP_FROM_INT2	(1 << 22)
 
+/* i.MX6Q adds pm_qos support */
+#define FEC_QUIRK_HAS_PMQOS			BIT(23)
+
 struct bufdesc_prop {
 	int qid;
 	/* Address of Rx and Tx buffers */
@@ -608,6 +612,7 @@ struct fec_enet_private {
 	struct delayed_work time_keep;
 	struct regulator *reg_phy;
 	struct fec_stop_mode_gpr stop_gpr;
+	struct pm_qos_request pm_qos_req;
 
 	unsigned int tx_align;
 	unsigned int rx_align;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index e8e2aa1e7f01..92c55e1a5507 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -111,7 +111,8 @@ static const struct fec_devinfo fec_imx6q_info = {
 	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
 		  FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
 		  FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 |
-		  FEC_QUIRK_HAS_RACC | FEC_QUIRK_CLEAR_SETUP_MII,
+		  FEC_QUIRK_HAS_RACC | FEC_QUIRK_CLEAR_SETUP_MII |
+		  FEC_QUIRK_HAS_PMQOS,
 };
 
 static const struct fec_devinfo fec_mvf600_info = {
@@ -3210,6 +3211,9 @@ fec_enet_open(struct net_device *ndev)
 	if (fep->quirks & FEC_QUIRK_ERR006687)
 		imx6q_cpuidle_fec_irqs_used();
 
+	if (fep->quirks & FEC_QUIRK_HAS_PMQOS)
+		cpu_latency_qos_add_request(&fep->pm_qos_req, 0);
+
 	napi_enable(&fep->napi);
 	phy_start(ndev->phydev);
 	netif_tx_start_all_queues(ndev);
@@ -3251,6 +3255,9 @@ fec_enet_close(struct net_device *ndev)
 	fec_enet_update_ethtool_stats(ndev);
 
 	fec_enet_clk_enable(ndev, false);
+	if (fep->quirks & FEC_QUIRK_HAS_PMQOS)
+		cpu_latency_qos_remove_request(&fep->pm_qos_req);
+
 	pinctrl_pm_select_sleep_state(&fep->pdev->dev);
 	pm_runtime_mark_last_busy(&fep->pdev->dev);
 	pm_runtime_put_autosuspend(&fep->pdev->dev);
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 7d49c28215f3..3dc3c0b626c2 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -135,11 +135,7 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
 		 * NSEC_PER_SEC - ts.tv_nsec. Add the remaining nanoseconds
 		 * to current timer would be next second.
 		 */
-		tempval = readl(fep->hwp + FEC_ATIME_CTRL);
-		tempval |= FEC_T_CTRL_CAPTURE;
-		writel(tempval, fep->hwp + FEC_ATIME_CTRL);
-
-		tempval = readl(fep->hwp + FEC_ATIME);
+		tempval = fep->cc.read(&fep->cc);
 		/* Convert the ptp local counter to 1588 timestamp */
 		ns = timecounter_cyc2time(&fep->tc, tempval);
 		ts = ns_to_timespec64(ns);
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h
index 53b7e95213a8..671f51135c26 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h
+++ b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h
@@ -206,9 +206,9 @@ struct funeth_rxq {
 
 #define FUN_QSTAT_READ(q, seq, stats_copy) \
 	do { \
-		seq = u64_stats_fetch_begin(&(q)->syncp); \
+		seq = u64_stats_fetch_begin_irq(&(q)->syncp); \
 		stats_copy = (q)->stats; \
-	} while (u64_stats_fetch_retry(&(q)->syncp, (seq)))
+	} while (u64_stats_fetch_retry_irq(&(q)->syncp, (seq)))
 
 #define FUN_INT_NAME_LEN (IFNAMSIZ + 16)
 
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index 50b384910c83..7b9a2d9d9624 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -177,14 +177,14 @@ gve_get_ethtool_stats(struct net_device *netdev,
 				struct gve_rx_ring *rx = &priv->rx[ring];
 
 				start =
-				  u64_stats_fetch_begin(&priv->rx[ring].statss);
+				  u64_stats_fetch_begin_irq(&priv->rx[ring].statss);
 				tmp_rx_pkts = rx->rpackets;
 				tmp_rx_bytes = rx->rbytes;
 				tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail;
 				tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail;
 				tmp_rx_desc_err_dropped_pkt =
 					rx->rx_desc_err_dropped_pkt;
-			} while (u64_stats_fetch_retry(&priv->rx[ring].statss,
+			} while (u64_stats_fetch_retry_irq(&priv->rx[ring].statss,
 						       start));
 			rx_pkts += tmp_rx_pkts;
 			rx_bytes += tmp_rx_bytes;
@@ -198,10 +198,10 @@ gve_get_ethtool_stats(struct net_device *netdev,
 		if (priv->tx) {
 			do {
 				start =
-				  u64_stats_fetch_begin(&priv->tx[ring].statss);
+				  u64_stats_fetch_begin_irq(&priv->tx[ring].statss);
 				tmp_tx_pkts = priv->tx[ring].pkt_done;
 				tmp_tx_bytes = priv->tx[ring].bytes_done;
-			} while (u64_stats_fetch_retry(&priv->tx[ring].statss,
+			} while (u64_stats_fetch_retry_irq(&priv->tx[ring].statss,
 						       start));
 			tx_pkts += tmp_tx_pkts;
 			tx_bytes += tmp_tx_bytes;
@@ -259,13 +259,13 @@ gve_get_ethtool_stats(struct net_device *netdev,
 			data[i++] = rx->fill_cnt - rx->cnt;
 			do {
 				start =
-				  u64_stats_fetch_begin(&priv->rx[ring].statss);
+				  u64_stats_fetch_begin_irq(&priv->rx[ring].statss);
 				tmp_rx_bytes = rx->rbytes;
 				tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail;
 				tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail;
 				tmp_rx_desc_err_dropped_pkt =
 					rx->rx_desc_err_dropped_pkt;
-			} while (u64_stats_fetch_retry(&priv->rx[ring].statss,
+			} while (u64_stats_fetch_retry_irq(&priv->rx[ring].statss,
 						       start));
 			data[i++] = tmp_rx_bytes;
 			data[i++] = rx->rx_cont_packet_cnt;
@@ -331,9 +331,9 @@ gve_get_ethtool_stats(struct net_device *netdev,
 			}
 			do {
 				start =
-				  u64_stats_fetch_begin(&priv->tx[ring].statss);
+				  u64_stats_fetch_begin_irq(&priv->tx[ring].statss);
 				tmp_tx_bytes = tx->bytes_done;
-			} while (u64_stats_fetch_retry(&priv->tx[ring].statss,
+			} while (u64_stats_fetch_retry_irq(&priv->tx[ring].statss,
 						       start));
 			data[i++] = tmp_tx_bytes;
 			data[i++] = tx->wake_queue;
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 6cafee55efc3..044db3ebb071 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -51,10 +51,10 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s)
 		for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) {
 			do {
 				start =
-				  u64_stats_fetch_begin(&priv->rx[ring].statss);
+				  u64_stats_fetch_begin_irq(&priv->rx[ring].statss);
 				packets = priv->rx[ring].rpackets;
 				bytes = priv->rx[ring].rbytes;
-			} while (u64_stats_fetch_retry(&priv->rx[ring].statss,
+			} while (u64_stats_fetch_retry_irq(&priv->rx[ring].statss,
 						       start));
 			s->rx_packets += packets;
 			s->rx_bytes += bytes;
@@ -64,10 +64,10 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s)
 		for (ring = 0; ring < priv->tx_cfg.num_queues; ring++) {
 			do {
 				start =
-				  u64_stats_fetch_begin(&priv->tx[ring].statss);
+				  u64_stats_fetch_begin_irq(&priv->tx[ring].statss);
 				packets = priv->tx[ring].pkt_done;
 				bytes = priv->tx[ring].bytes_done;
-			} while (u64_stats_fetch_retry(&priv->tx[ring].statss,
+			} while (u64_stats_fetch_retry_irq(&priv->tx[ring].statss,
 						       start));
 			s->tx_packets += packets;
 			s->tx_bytes += bytes;
@@ -1274,9 +1274,9 @@ void gve_handle_report_stats(struct gve_priv *priv)
 			}
 
 			do {
-				start = u64_stats_fetch_begin(&priv->tx[idx].statss);
+				start = u64_stats_fetch_begin_irq(&priv->tx[idx].statss);
 				tx_bytes = priv->tx[idx].bytes_done;
-			} while (u64_stats_fetch_retry(&priv->tx[idx].statss, start));
+			} while (u64_stats_fetch_retry_irq(&priv->tx[idx].statss, start));
 			stats[stats_idx++] = (struct stats) {
 				.stat_name = cpu_to_be32(TX_WAKE_CNT),
 				.value = cpu_to_be64(priv->tx[idx].wake_queue),
diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index 8c939628e2d8..2e6461b0ea8b 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -157,7 +157,7 @@ static int gve_alloc_page_dqo(struct gve_priv *priv,
 	int err;
 
 	err = gve_alloc_page(priv, &priv->pdev->dev, &buf_state->page_info.page,
-			     &buf_state->addr, DMA_FROM_DEVICE, GFP_KERNEL);
+			     &buf_state->addr, DMA_FROM_DEVICE, GFP_ATOMIC);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index a866bea65110..e5828a658caf 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -74,14 +74,14 @@ void hinic_rxq_get_stats(struct hinic_rxq *rxq, struct hinic_rxq_stats *stats)
 	unsigned int start;
 
 	do {
-		start = u64_stats_fetch_begin(&rxq_stats->syncp);
+		start = u64_stats_fetch_begin_irq(&rxq_stats->syncp);
 		stats->pkts = rxq_stats->pkts;
 		stats->bytes = rxq_stats->bytes;
 		stats->errors = rxq_stats->csum_errors +
 				rxq_stats->other_errors;
 		stats->csum_errors = rxq_stats->csum_errors;
 		stats->other_errors = rxq_stats->other_errors;
-	} while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
+	} while (u64_stats_fetch_retry_irq(&rxq_stats->syncp, start));
 }
 
 /**
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index 5051cdff2384..3b6c7b585737 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -99,14 +99,14 @@ void hinic_txq_get_stats(struct hinic_txq *txq, struct hinic_txq_stats *stats)
 	unsigned int start;
 
 	do {
-		start = u64_stats_fetch_begin(&txq_stats->syncp);
+		start = u64_stats_fetch_begin_irq(&txq_stats->syncp);
 		stats->pkts    = txq_stats->pkts;
 		stats->bytes   = txq_stats->bytes;
 		stats->tx_busy = txq_stats->tx_busy;
 		stats->tx_wake = txq_stats->tx_wake;
 		stats->tx_dropped = txq_stats->tx_dropped;
 		stats->big_frags_pkts = txq_stats->big_frags_pkts;
-	} while (u64_stats_fetch_retry(&txq_stats->syncp, start));
+	} while (u64_stats_fetch_retry_irq(&txq_stats->syncp, start));
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index ea2bb0140a6e..10d7a982a5b9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -177,6 +177,10 @@ void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset)
 			"Cannot locate client instance close routine\n");
 		return;
 	}
+	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) {
+		dev_dbg(&pf->pdev->dev, "Client is not open, abort close\n");
+		return;
+	}
 	cdev->client->ops->close(&cdev->lan_info, cdev->client, reset);
 	clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state);
 	i40e_client_release_qvlist(&cdev->lan_info);
@@ -429,7 +433,6 @@ void i40e_client_subtask(struct i40e_pf *pf)
 				/* Remove failed client instance */
 				clear_bit(__I40E_CLIENT_INSTANCE_OPENED,
 					  &cdev->state);
-				i40e_client_del_instance(pf);
 				return;
 			}
 		}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 156e92c43780..e9cd0fa6a0d2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -4485,7 +4485,7 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi,
 				    (struct in6_addr *)&ipv6_full_mask))
 			new_mask |= I40E_L3_V6_DST_MASK;
 		else if (ipv6_addr_any((struct in6_addr *)
-				       &usr_ip6_spec->ip6src))
+				       &usr_ip6_spec->ip6dst))
 			new_mask &= ~I40E_L3_V6_DST_MASK;
 		else
 			return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index b36bf9c3e1e4..e3d9804aeb25 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -384,7 +384,9 @@ static void i40e_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 		set_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state);
 		break;
 	default:
-		netdev_err(netdev, "tx_timeout recovery unsuccessful\n");
+		netdev_err(netdev, "tx_timeout recovery unsuccessful, device is in non-recoverable state.\n");
+		set_bit(__I40E_DOWN_REQUESTED, pf->state);
+		set_bit(__I40E_VSI_DOWN_REQUESTED, vsi->state);
 		break;
 	}
 
@@ -5907,6 +5909,26 @@ static int i40e_get_link_speed(struct i40e_vsi *vsi)
 }
 
 /**
+ * i40e_bw_bytes_to_mbits - Convert max_tx_rate from bytes to mbits
+ * @vsi: Pointer to vsi structure
+ * @max_tx_rate: max TX rate in bytes to be converted into Mbits
+ *
+ * Helper function to convert units before send to set BW limit
+ **/
+static u64 i40e_bw_bytes_to_mbits(struct i40e_vsi *vsi, u64 max_tx_rate)
+{
+	if (max_tx_rate < I40E_BW_MBPS_DIVISOR) {
+		dev_warn(&vsi->back->pdev->dev,
+			 "Setting max tx rate to minimum usable value of 50Mbps.\n");
+		max_tx_rate = I40E_BW_CREDIT_DIVISOR;
+	} else {
+		do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR);
+	}
+
+	return max_tx_rate;
+}
+
+/**
  * i40e_set_bw_limit - setup BW limit for Tx traffic based on max_tx_rate
  * @vsi: VSI to be configured
  * @seid: seid of the channel/VSI
@@ -5928,10 +5950,10 @@ int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate)
 			max_tx_rate, seid);
 		return -EINVAL;
 	}
-	if (max_tx_rate && max_tx_rate < 50) {
+	if (max_tx_rate && max_tx_rate < I40E_BW_CREDIT_DIVISOR) {
 		dev_warn(&pf->pdev->dev,
 			 "Setting max tx rate to minimum usable value of 50Mbps.\n");
-		max_tx_rate = 50;
+		max_tx_rate = I40E_BW_CREDIT_DIVISOR;
 	}
 
 	/* Tx rate credits are in values of 50Mbps, 0 is disabled */
@@ -6657,6 +6679,9 @@ static int i40e_configure_queue_channels(struct i40e_vsi *vsi)
 			vsi->tc_seid_map[i] = ch->seid;
 		}
 	}
+
+	/* reset to reconfigure TX queue contexts */
+	i40e_do_reset(vsi->back, I40E_PF_RESET_FLAG, true);
 	return ret;
 
 err_free:
@@ -8219,9 +8244,9 @@ config_tc:
 
 	if (i40e_is_tc_mqprio_enabled(pf)) {
 		if (vsi->mqprio_qopt.max_rate[0]) {
-			u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0];
+			u64 max_tx_rate = i40e_bw_bytes_to_mbits(vsi,
+						  vsi->mqprio_qopt.max_rate[0]);
 
-			do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR);
 			ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate);
 			if (!ret) {
 				u64 credits = max_tx_rate;
@@ -10966,10 +10991,10 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 	}
 
 	if (vsi->mqprio_qopt.max_rate[0]) {
-		u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0];
+		u64 max_tx_rate = i40e_bw_bytes_to_mbits(vsi,
+						  vsi->mqprio_qopt.max_rate[0]);
 		u64 credits = 0;
 
-		do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR);
 		ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate);
 		if (ret)
 			goto end_unlock;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index f6ba97a0166e..69e67eb6aea7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -3203,11 +3203,13 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 
 	protocol = vlan_get_protocol(skb);
 
-	if (eth_p_mpls(protocol))
+	if (eth_p_mpls(protocol)) {
 		ip.hdr = skb_inner_network_header(skb);
-	else
+		l4.hdr = skb_checksum_start(skb);
+	} else {
 		ip.hdr = skb_network_header(skb);
-	l4.hdr = skb_checksum_start(skb);
+		l4.hdr = skb_transport_header(skb);
+	}
 
 	/* set the tx_flags to indicate the IP protocol type. this is
 	 * required so that checksum header computation below is accurate.
@@ -3686,7 +3688,8 @@ u16 i40e_lan_select_queue(struct net_device *netdev,
 	u8 prio;
 
 	/* is DCB enabled at all? */
-	if (vsi->tc_config.numtc == 1)
+	if (vsi->tc_config.numtc == 1 ||
+	    i40e_is_tc_mqprio_enabled(vsi->back))
 		return netdev_pick_tx(netdev, skb, sb_dev);
 
 	prio = skb->priority;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 4f184c50f6e8..7e9f6a69eb10 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -2039,6 +2039,25 @@ static void i40e_del_qch(struct i40e_vf *vf)
 }
 
 /**
+ * i40e_vc_get_max_frame_size
+ * @vf: pointer to the VF
+ *
+ * Max frame size is determined based on the current port's max frame size and
+ * whether a port VLAN is configured on this VF. The VF is not aware whether
+ * it's in a port VLAN so the PF needs to account for this in max frame size
+ * checks and sending the max frame size to the VF.
+ **/
+static u16 i40e_vc_get_max_frame_size(struct i40e_vf *vf)
+{
+	u16 max_frame_size = vf->pf->hw.phy.link_info.max_frame_size;
+
+	if (vf->port_vlan_id)
+		max_frame_size -= VLAN_HLEN;
+
+	return max_frame_size;
+}
+
+/**
  * i40e_vc_get_vf_resources_msg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
@@ -2139,6 +2158,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 	vfres->max_vectors = pf->hw.func_caps.num_msix_vectors_vf;
 	vfres->rss_key_size = I40E_HKEY_ARRAY_SIZE;
 	vfres->rss_lut_size = I40E_VF_HLUT_ARRAY_SIZE;
+	vfres->max_mtu = i40e_vc_get_max_frame_size(vf);
 
 	if (vf->lan_vsi_idx) {
 		vfres->vsi_res[0].vsi_id = vf->lan_vsi_id;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adminq.c b/drivers/net/ethernet/intel/iavf/iavf_adminq.c
index cd4e6a22d0f9..9ffbd24d83cb 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_adminq.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_adminq.c
@@ -324,6 +324,7 @@ static enum iavf_status iavf_config_arq_regs(struct iavf_hw *hw)
 static enum iavf_status iavf_init_asq(struct iavf_hw *hw)
 {
 	enum iavf_status ret_code = 0;
+	int i;
 
 	if (hw->aq.asq.count > 0) {
 		/* queue already initialized */
@@ -354,12 +355,17 @@ static enum iavf_status iavf_init_asq(struct iavf_hw *hw)
 	/* initialize base registers */
 	ret_code = iavf_config_asq_regs(hw);
 	if (ret_code)
-		goto init_adminq_free_rings;
+		goto init_free_asq_bufs;
 
 	/* success! */
 	hw->aq.asq.count = hw->aq.num_asq_entries;
 	goto init_adminq_exit;
 
+init_free_asq_bufs:
+	for (i = 0; i < hw->aq.num_asq_entries; i++)
+		iavf_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]);
+	iavf_free_virt_mem(hw, &hw->aq.asq.dma_head);
+
 init_adminq_free_rings:
 	iavf_free_adminq_asq(hw);
 
@@ -383,6 +389,7 @@ init_adminq_exit:
 static enum iavf_status iavf_init_arq(struct iavf_hw *hw)
 {
 	enum iavf_status ret_code = 0;
+	int i;
 
 	if (hw->aq.arq.count > 0) {
 		/* queue already initialized */
@@ -413,12 +420,16 @@ static enum iavf_status iavf_init_arq(struct iavf_hw *hw)
 	/* initialize base registers */
 	ret_code = iavf_config_arq_regs(hw);
 	if (ret_code)
-		goto init_adminq_free_rings;
+		goto init_free_arq_bufs;
 
 	/* success! */
 	hw->aq.arq.count = hw->aq.num_arq_entries;
 	goto init_adminq_exit;
 
+init_free_arq_bufs:
+	for (i = 0; i < hw->aq.num_arq_entries; i++)
+		iavf_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]);
+	iavf_free_virt_mem(hw, &hw->aq.arq.dma_head);
 init_adminq_free_rings:
 	iavf_free_adminq_arq(hw);
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 45d097a164ad..0c89f16bf1e2 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -1077,7 +1077,6 @@ static int iavf_set_mac(struct net_device *netdev, void *p)
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	struct sockaddr *addr = p;
-	bool handle_mac = iavf_is_mac_set_handled(netdev, addr->sa_data);
 	int ret;
 
 	if (!is_valid_ether_addr(addr->sa_data))
@@ -1094,10 +1093,9 @@ static int iavf_set_mac(struct net_device *netdev, void *p)
 		return 0;
 	}
 
-	if (handle_mac)
-		goto done;
-
-	ret = wait_event_interruptible_timeout(adapter->vc_waitqueue, false, msecs_to_jiffies(2500));
+	ret = wait_event_interruptible_timeout(adapter->vc_waitqueue,
+					       iavf_is_mac_set_handled(netdev, addr->sa_data),
+					       msecs_to_jiffies(2500));
 
 	/* If ret < 0 then it means wait was interrupted.
 	 * If ret == 0 then it means we got a timeout.
@@ -1111,7 +1109,6 @@ static int iavf_set_mac(struct net_device *netdev, void *p)
 	if (!ret)
 		return -EAGAIN;
 
-done:
 	if (!ether_addr_equal(netdev->dev_addr, addr->sa_data))
 		return -EACCES;
 
@@ -2367,7 +2364,7 @@ static void iavf_init_get_resources(struct iavf_adapter *adapter)
 	err = iavf_get_vf_config(adapter);
 	if (err == -EALREADY) {
 		err = iavf_send_vf_config_msg(adapter);
-		goto err_alloc;
+		goto err;
 	} else if (err == -EINVAL) {
 		/* We only get -EINVAL if the device is in a very bad
 		 * state or if we've been disabled for previous bad
@@ -2877,6 +2874,11 @@ static void iavf_reset_task(struct work_struct *work)
 	int i = 0, err;
 	bool running;
 
+	/* Detach interface to avoid subsequent NDO callbacks */
+	rtnl_lock();
+	netif_device_detach(netdev);
+	rtnl_unlock();
+
 	/* When device is being removed it doesn't make sense to run the reset
 	 * task, just return in such a case.
 	 */
@@ -2884,7 +2886,7 @@ static void iavf_reset_task(struct work_struct *work)
 		if (adapter->state != __IAVF_REMOVE)
 			queue_work(iavf_wq, &adapter->reset_task);
 
-		return;
+		goto reset_finish;
 	}
 
 	while (!mutex_trylock(&adapter->client_lock))
@@ -2954,7 +2956,6 @@ continue_reset:
 
 	if (running) {
 		netif_carrier_off(netdev);
-		netif_tx_stop_all_queues(netdev);
 		adapter->link_up = false;
 		iavf_napi_disable_all(adapter);
 	}
@@ -3084,14 +3085,21 @@ continue_reset:
 	mutex_unlock(&adapter->client_lock);
 	mutex_unlock(&adapter->crit_lock);
 
-	return;
+	goto reset_finish;
 reset_err:
+	if (running) {
+		set_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
+		iavf_free_traffic_irqs(adapter);
+	}
+	iavf_disable_vf(adapter);
+
 	mutex_unlock(&adapter->client_lock);
 	mutex_unlock(&adapter->crit_lock);
-	if (running)
-		iavf_change_state(adapter, __IAVF_RUNNING);
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
-	iavf_close(netdev);
+reset_finish:
+	rtnl_lock();
+	netif_device_attach(netdev);
+	rtnl_unlock();
 }
 
 /**
@@ -4085,8 +4093,17 @@ static int iavf_open(struct net_device *netdev)
 		return -EIO;
 	}
 
-	while (!mutex_trylock(&adapter->crit_lock))
+	while (!mutex_trylock(&adapter->crit_lock)) {
+		/* If we are in __IAVF_INIT_CONFIG_ADAPTER state the crit_lock
+		 * is already taken and iavf_open is called from an upper
+		 * device's notifier reacting on NETDEV_REGISTER event.
+		 * We have to leave here to avoid dead lock.
+		 */
+		if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER)
+			return -EBUSY;
+
 		usleep_range(500, 1000);
+	}
 
 	if (adapter->state != __IAVF_DOWN) {
 		err = -EBUSY;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 06d18797d25a..18b6a702a1d6 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -114,8 +114,11 @@ u32 iavf_get_tx_pending(struct iavf_ring *ring, bool in_sw)
 {
 	u32 head, tail;
 
+	/* underlying hardware might not allow access and/or always return
+	 * 0 for the head/tail registers so just use the cached values
+	 */
 	head = ring->next_to_clean;
-	tail = readl(ring->tail);
+	tail = ring->next_to_use;
 
 	if (head != tail)
 		return (head < tail) ?
@@ -1390,7 +1393,7 @@ static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring,
 #endif
 	struct sk_buff *skb;
 
-	if (!rx_buffer)
+	if (!rx_buffer || !size)
 		return NULL;
 	/* prefetch first cache line of first page */
 	va = page_address(rx_buffer->page) + rx_buffer->page_offset;
@@ -1548,7 +1551,7 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
 			rx_ring->rx_stats.alloc_buff_failed++;
-			if (rx_buffer)
+			if (rx_buffer && size)
 				rx_buffer->pagecnt_bias++;
 			break;
 		}
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 15ee85dc33bd..5a9e6563923e 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -269,11 +269,14 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter)
 void iavf_configure_queues(struct iavf_adapter *adapter)
 {
 	struct virtchnl_vsi_queue_config_info *vqci;
-	struct virtchnl_queue_pair_info *vqpi;
+	int i, max_frame = adapter->vf_res->max_mtu;
 	int pairs = adapter->num_active_queues;
-	int i, max_frame = IAVF_MAX_RXBUFFER;
+	struct virtchnl_queue_pair_info *vqpi;
 	size_t len;
 
+	if (max_frame > IAVF_MAX_RXBUFFER || !max_frame)
+		max_frame = IAVF_MAX_RXBUFFER;
+
 	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
 		dev_err(&adapter->pdev->dev, "Cannot configure queues, command %d pending\n",
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index cc5b85afd437..841fa149c407 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -684,8 +684,8 @@ static inline void ice_set_ring_xdp(struct ice_tx_ring *ring)
  * ice_xsk_pool - get XSK buffer pool bound to a ring
  * @ring: Rx ring to use
  *
- * Returns a pointer to xdp_umem structure if there is a buffer pool present,
- * NULL otherwise.
+ * Returns a pointer to xsk_buff_pool structure if there is a buffer pool
+ * present, NULL otherwise.
  */
 static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring)
 {
@@ -699,23 +699,33 @@ static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring)
 }
 
 /**
- * ice_tx_xsk_pool - get XSK buffer pool bound to a ring
- * @ring: Tx ring to use
+ * ice_tx_xsk_pool - assign XSK buff pool to XDP ring
+ * @vsi: pointer to VSI
+ * @qid: index of a queue to look at XSK buff pool presence
  *
- * Returns a pointer to xdp_umem structure if there is a buffer pool present,
- * NULL otherwise. Tx equivalent of ice_xsk_pool.
+ * Sets XSK buff pool pointer on XDP ring.
+ *
+ * XDP ring is picked from Rx ring, whereas Rx ring is picked based on provided
+ * queue id. Reason for doing so is that queue vectors might have assigned more
+ * than one XDP ring, e.g. when user reduced the queue count on netdev; Rx ring
+ * carries a pointer to one of these XDP rings for its own purposes, such as
+ * handling XDP_TX action, therefore we can piggyback here on the
+ * rx_ring->xdp_ring assignment that was done during XDP rings initialization.
  */
-static inline struct xsk_buff_pool *ice_tx_xsk_pool(struct ice_tx_ring *ring)
+static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid)
 {
-	struct ice_vsi *vsi = ring->vsi;
-	u16 qid;
+	struct ice_tx_ring *ring;
 
-	qid = ring->q_index - vsi->alloc_txq;
+	ring = vsi->rx_rings[qid]->xdp_ring;
+	if (!ring)
+		return;
 
-	if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps))
-		return NULL;
+	if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) {
+		ring->xsk_pool = NULL;
+		return;
+	}
 
-	return xsk_get_pool_from_qid(vsi->netdev, qid);
+	ring->xsk_pool = xsk_get_pool_from_qid(vsi->netdev, qid);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 136d7911adb4..1e3243808178 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -7,18 +7,6 @@
 #include "ice_dcb_lib.h"
 #include "ice_sriov.h"
 
-static bool ice_alloc_rx_buf_zc(struct ice_rx_ring *rx_ring)
-{
-	rx_ring->xdp_buf = kcalloc(rx_ring->count, sizeof(*rx_ring->xdp_buf), GFP_KERNEL);
-	return !!rx_ring->xdp_buf;
-}
-
-static bool ice_alloc_rx_buf(struct ice_rx_ring *rx_ring)
-{
-	rx_ring->rx_buf = kcalloc(rx_ring->count, sizeof(*rx_ring->rx_buf), GFP_KERNEL);
-	return !!rx_ring->rx_buf;
-}
-
 /**
  * __ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI
  * @qs_cfg: gathered variables needed for PF->VSI queues assignment
@@ -519,11 +507,8 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 					 ring->q_index, ring->q_vector->napi.napi_id);
 
-		kfree(ring->rx_buf);
 		ring->xsk_pool = ice_xsk_pool(ring);
 		if (ring->xsk_pool) {
-			if (!ice_alloc_rx_buf_zc(ring))
-				return -ENOMEM;
 			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
 
 			ring->rx_buf_len =
@@ -538,8 +523,6 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 				 ring->q_index);
 		} else {
-			if (!ice_alloc_rx_buf(ring))
-				return -ENOMEM;
 			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
 				/* coverity[check_return] */
 				xdp_rxq_info_reg(&ring->xdp_rxq,
diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c
index 85a94483c2ed..40e678cfb507 100644
--- a/drivers/net/ethernet/intel/ice/ice_fltr.c
+++ b/drivers/net/ethernet/intel/ice/ice_fltr.c
@@ -62,7 +62,7 @@ ice_fltr_set_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi,
 	int result;
 
 	result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false);
-	if (result)
+	if (result && result != -EEXIST)
 		dev_err(ice_pf_to_dev(pf),
 			"Error setting promisc mode on VSI %i (rc=%d)\n",
 			vsi->vsi_num, result);
@@ -86,7 +86,7 @@ ice_fltr_clear_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi,
 	int result;
 
 	result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true);
-	if (result)
+	if (result && result != -EEXIST)
 		dev_err(ice_pf_to_dev(pf),
 			"Error clearing promisc mode on VSI %i (rc=%d)\n",
 			vsi->vsi_num, result);
@@ -109,7 +109,7 @@ ice_fltr_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
 	int result;
 
 	result = ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid);
-	if (result)
+	if (result && result != -EEXIST)
 		dev_err(ice_pf_to_dev(pf),
 			"Error clearing promisc mode on VSI %i for VID %u (rc=%d)\n",
 			ice_get_hw_vsi_num(hw, vsi_handle), vid, result);
@@ -132,7 +132,7 @@ ice_fltr_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
 	int result;
 
 	result = ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid);
-	if (result)
+	if (result && result != -EEXIST)
 		dev_err(ice_pf_to_dev(pf),
 			"Error setting promisc mode on VSI %i for VID %u (rc=%d)\n",
 			ice_get_hw_vsi_num(hw, vsi_handle), vid, result);
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index a830f7f9aed0..58d483e2f539 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -914,7 +914,7 @@ static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt)
  */
 static int ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 {
-	u16 offset = 0, qmap = 0, tx_count = 0, pow = 0;
+	u16 offset = 0, qmap = 0, tx_count = 0, rx_count = 0, pow = 0;
 	u16 num_txq_per_tc, num_rxq_per_tc;
 	u16 qcount_tx = vsi->alloc_txq;
 	u16 qcount_rx = vsi->alloc_rxq;
@@ -981,23 +981,25 @@ static int ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 	 * at least 1)
 	 */
 	if (offset)
-		vsi->num_rxq = offset;
+		rx_count = offset;
 	else
-		vsi->num_rxq = num_rxq_per_tc;
+		rx_count = num_rxq_per_tc;
 
-	if (vsi->num_rxq > vsi->alloc_rxq) {
+	if (rx_count > vsi->alloc_rxq) {
 		dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Rx queues (%u), than were allocated (%u)!\n",
-			vsi->num_rxq, vsi->alloc_rxq);
+			rx_count, vsi->alloc_rxq);
 		return -EINVAL;
 	}
 
-	vsi->num_txq = tx_count;
-	if (vsi->num_txq > vsi->alloc_txq) {
+	if (tx_count > vsi->alloc_txq) {
 		dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Tx queues (%u), than were allocated (%u)!\n",
-			vsi->num_txq, vsi->alloc_txq);
+			tx_count, vsi->alloc_txq);
 		return -EINVAL;
 	}
 
+	vsi->num_txq = tx_count;
+	vsi->num_rxq = rx_count;
+
 	if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) {
 		dev_dbg(ice_pf_to_dev(vsi->back), "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n");
 		/* since there is a chance that num_rxq could have been changed
@@ -1986,8 +1988,8 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi)
 	if (ret)
 		return ret;
 
-	ice_for_each_xdp_txq(vsi, i)
-		vsi->xdp_rings[i]->xsk_pool = ice_tx_xsk_pool(vsi->xdp_rings[i]);
+	ice_for_each_rxq(vsi, i)
+		ice_tx_xsk_pool(vsi, i);
 
 	return ret;
 }
@@ -3181,7 +3183,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi)
 
 	pf = vsi->back;
 	vtype = vsi->type;
-	if (WARN_ON(vtype == ICE_VSI_VF) && !vsi->vf)
+	if (WARN_ON(vtype == ICE_VSI_VF && !vsi->vf))
 		return -EINVAL;
 
 	ice_vsi_init_vlan_ops(vsi);
@@ -3490,6 +3492,7 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt,
 	u16 pow, offset = 0, qcount_tx = 0, qcount_rx = 0, qmap;
 	u16 tc0_offset = vsi->mqprio_qopt.qopt.offset[0];
 	int tc0_qcount = vsi->mqprio_qopt.qopt.count[0];
+	u16 new_txq, new_rxq;
 	u8 netdev_tc = 0;
 	int i;
 
@@ -3530,21 +3533,24 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt,
 		}
 	}
 
-	/* Set actual Tx/Rx queue pairs */
-	vsi->num_txq = offset + qcount_tx;
-	if (vsi->num_txq > vsi->alloc_txq) {
+	new_txq = offset + qcount_tx;
+	if (new_txq > vsi->alloc_txq) {
 		dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Tx queues (%u), than were allocated (%u)!\n",
-			vsi->num_txq, vsi->alloc_txq);
+			new_txq, vsi->alloc_txq);
 		return -EINVAL;
 	}
 
-	vsi->num_rxq = offset + qcount_rx;
-	if (vsi->num_rxq > vsi->alloc_rxq) {
+	new_rxq = offset + qcount_rx;
+	if (new_rxq > vsi->alloc_rxq) {
 		dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Rx queues (%u), than were allocated (%u)!\n",
-			vsi->num_rxq, vsi->alloc_rxq);
+			new_rxq, vsi->alloc_rxq);
 		return -EINVAL;
 	}
 
+	/* Set actual Tx/Rx queue pairs */
+	vsi->num_txq = new_txq;
+	vsi->num_rxq = new_rxq;
+
 	/* Setup queue TC[0].qmap for given VSI context */
 	ctxt->info.tc_mapping[0] = cpu_to_le16(qmap);
 	ctxt->info.q_mapping[0] = cpu_to_le16(vsi->rxq_map[0]);
@@ -3576,6 +3582,7 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc)
 {
 	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
 	struct ice_pf *pf = vsi->back;
+	struct ice_tc_cfg old_tc_cfg;
 	struct ice_vsi_ctx *ctx;
 	struct device *dev;
 	int i, ret = 0;
@@ -3600,6 +3607,7 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc)
 			max_txqs[i] = vsi->num_txq;
 	}
 
+	memcpy(&old_tc_cfg, &vsi->tc_cfg, sizeof(old_tc_cfg));
 	vsi->tc_cfg.ena_tc = ena_tc;
 	vsi->tc_cfg.numtc = num_tc;
 
@@ -3616,8 +3624,10 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc)
 	else
 		ret = ice_vsi_setup_q_map(vsi, ctx);
 
-	if (ret)
+	if (ret) {
+		memcpy(&vsi->tc_cfg, &old_tc_cfg, sizeof(vsi->tc_cfg));
 		goto out;
+	}
 
 	/* must to indicate which section of VSI context are being modified */
 	ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_RXQ_MAP_VALID);
@@ -4062,7 +4072,11 @@ int ice_vsi_del_vlan_zero(struct ice_vsi *vsi)
 	if (err && err != -EEXIST)
 		return err;
 
-	return 0;
+	/* when deleting the last VLAN filter, make sure to disable the VLAN
+	 * promisc mode so the filter isn't left by accident
+	 */
+	return ice_clear_vsi_promisc(&vsi->back->hw, vsi->idx,
+				    ICE_MCAST_VLAN_PROMISC_BITS, 0);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index eb40526ee179..e109cb93886b 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -267,8 +267,10 @@ static int ice_set_promisc(struct ice_vsi *vsi, u8 promisc_m)
 		status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx,
 						  promisc_m, 0);
 	}
+	if (status && status != -EEXIST)
+		return status;
 
-	return status;
+	return 0;
 }
 
 /**
@@ -2397,8 +2399,6 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset)
 		return -EBUSY;
 	}
 
-	ice_unplug_aux_dev(pf);
-
 	switch (reset) {
 	case ICE_RESET_PFR:
 		set_bit(ICE_PFR_REQ, pf->state);
@@ -2579,7 +2579,6 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi)
 		if (ice_setup_tx_ring(xdp_ring))
 			goto free_xdp_rings;
 		ice_set_ring_xdp(xdp_ring);
-		xdp_ring->xsk_pool = ice_tx_xsk_pool(xdp_ring);
 		spin_lock_init(&xdp_ring->tx_lock);
 		for (j = 0; j < xdp_ring->count; j++) {
 			tx_desc = ICE_TX_DESC(xdp_ring, j);
@@ -2587,13 +2586,6 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi)
 		}
 	}
 
-	ice_for_each_rxq(vsi, i) {
-		if (static_key_enabled(&ice_xdp_locking_key))
-			vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i % vsi->num_xdp_txq];
-		else
-			vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i];
-	}
-
 	return 0;
 
 free_xdp_rings:
@@ -2683,6 +2675,23 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog)
 		xdp_rings_rem -= xdp_rings_per_v;
 	}
 
+	ice_for_each_rxq(vsi, i) {
+		if (static_key_enabled(&ice_xdp_locking_key)) {
+			vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i % vsi->num_xdp_txq];
+		} else {
+			struct ice_q_vector *q_vector = vsi->rx_rings[i]->q_vector;
+			struct ice_tx_ring *ring;
+
+			ice_for_each_tx_ring(ring, q_vector->tx) {
+				if (ice_ring_is_xdp(ring)) {
+					vsi->rx_rings[i]->xdp_ring = ring;
+					break;
+				}
+			}
+		}
+		ice_tx_xsk_pool(vsi, i);
+	}
+
 	/* omit the scheduler update if in reset path; XDP queues will be
 	 * taken into account at the end of ice_vsi_rebuild, where
 	 * ice_cfg_vsi_lan is being called
@@ -2887,10 +2896,18 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 			if (xdp_ring_err)
 				NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed");
 		}
+		/* reallocate Rx queues that are used for zero-copy */
+		xdp_ring_err = ice_realloc_zc_buf(vsi, true);
+		if (xdp_ring_err)
+			NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed");
 	} else if (ice_is_xdp_ena_vsi(vsi) && !prog) {
 		xdp_ring_err = ice_destroy_xdp_rings(vsi);
 		if (xdp_ring_err)
 			NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed");
+		/* reallocate Rx queues that were used for zero-copy */
+		xdp_ring_err = ice_realloc_zc_buf(vsi, false);
+		if (xdp_ring_err)
+			NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Rx resources failed");
 	} else {
 		/* safe to call even when prog == vsi->xdp_prog as
 		 * dev_xdp_install in net/core/dev.c incremented prog's
@@ -3573,6 +3590,14 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid)
 	while (test_and_set_bit(ICE_CFG_BUSY, vsi->state))
 		usleep_range(1000, 2000);
 
+	ret = ice_clear_vsi_promisc(&vsi->back->hw, vsi->idx,
+				    ICE_MCAST_VLAN_PROMISC_BITS, vid);
+	if (ret) {
+		netdev_err(netdev, "Error clearing multicast promiscuous mode on VSI %i\n",
+			   vsi->vsi_num);
+		vsi->current_netdev_flags |= IFF_ALLMULTI;
+	}
+
 	vlan_ops = ice_get_compat_vsi_vlan_ops(vsi);
 
 	/* Make sure VLAN delete is successful before updating VLAN
@@ -3886,7 +3911,7 @@ static int ice_init_pf(struct ice_pf *pf)
 
 	pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL);
 	if (!pf->avail_rxqs) {
-		devm_kfree(ice_pf_to_dev(pf), pf->avail_txqs);
+		bitmap_free(pf->avail_txqs);
 		pf->avail_txqs = NULL;
 		return -ENOMEM;
 	}
@@ -6624,7 +6649,7 @@ static void ice_napi_disable_all(struct ice_vsi *vsi)
  */
 int ice_down(struct ice_vsi *vsi)
 {
-	int i, tx_err, rx_err, link_err = 0, vlan_err = 0;
+	int i, tx_err, rx_err, vlan_err = 0;
 
 	WARN_ON(!test_bit(ICE_VSI_DOWN, vsi->state));
 
@@ -6658,20 +6683,13 @@ int ice_down(struct ice_vsi *vsi)
 
 	ice_napi_disable_all(vsi);
 
-	if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) {
-		link_err = ice_force_phys_link_state(vsi, false);
-		if (link_err)
-			netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n",
-				   vsi->vsi_num, link_err);
-	}
-
 	ice_for_each_txq(vsi, i)
 		ice_clean_tx_ring(vsi->tx_rings[i]);
 
 	ice_for_each_rxq(vsi, i)
 		ice_clean_rx_ring(vsi->rx_rings[i]);
 
-	if (tx_err || rx_err || link_err || vlan_err) {
+	if (tx_err || rx_err || vlan_err) {
 		netdev_err(vsi->netdev, "Failed to close VSI 0x%04X on switch 0x%04X\n",
 			   vsi->vsi_num, vsi->vsw->sw_id);
 		return -EIO;
@@ -6833,6 +6851,8 @@ int ice_vsi_open(struct ice_vsi *vsi)
 	if (err)
 		goto err_setup_rx;
 
+	ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc);
+
 	if (vsi->type == ICE_VSI_PF) {
 		/* Notify the stack of the actual queue counts. */
 		err = netif_set_real_num_tx_queues(vsi->netdev, vsi->num_txq);
@@ -8865,6 +8885,16 @@ int ice_stop(struct net_device *netdev)
 		return -EBUSY;
 	}
 
+	if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) {
+		int link_err = ice_force_phys_link_state(vsi, false);
+
+		if (link_err) {
+			netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n",
+				   vsi->vsi_num, link_err);
+			return -EIO;
+		}
+	}
+
 	ice_vsi_close(vsi);
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 262e553e3b58..3808034f7e7e 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -4445,6 +4445,13 @@ ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
 		goto free_fltr_list;
 
 	list_for_each_entry(list_itr, &vsi_list_head, list_entry) {
+		/* Avoid enabling or disabling VLAN zero twice when in double
+		 * VLAN mode
+		 */
+		if (ice_is_dvm_ena(hw) &&
+		    list_itr->fltr_info.l_data.vlan.tpid == 0)
+			continue;
+
 		vlan_id = list_itr->fltr_info.l_data.vlan.vlan_id;
 		if (rm_vlan_promisc)
 			status = ice_clear_vsi_promisc(hw, vsi_handle,
@@ -4452,7 +4459,7 @@ ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
 		else
 			status = ice_set_vsi_promisc(hw, vsi_handle,
 						     promisc_mask, vlan_id);
-		if (status)
+		if (status && status != -EEXIST)
 			break;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 836dce840712..dd2285d4bef4 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -610,7 +610,7 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	if (test_bit(ICE_VSI_DOWN, vsi->state))
 		return -ENETDOWN;
 
-	if (!ice_is_xdp_ena_vsi(vsi) || queue_index >= vsi->num_xdp_txq)
+	if (!ice_is_xdp_ena_vsi(vsi))
 		return -ENXIO;
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
@@ -621,6 +621,9 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		xdp_ring = vsi->xdp_rings[queue_index];
 		spin_lock(&xdp_ring->tx_lock);
 	} else {
+		/* Generally, should not happen */
+		if (unlikely(queue_index >= vsi->num_xdp_txq))
+			return -ENXIO;
 		xdp_ring = vsi->xdp_rings[queue_index];
 	}
 
@@ -1464,7 +1467,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 		bool wd;
 
 		if (tx_ring->xsk_pool)
-			wd = ice_xmit_zc(tx_ring, ICE_DESC_UNUSED(tx_ring), budget);
+			wd = ice_xmit_zc(tx_ring);
 		else if (ice_ring_is_xdp(tx_ring))
 			wd = true;
 		else
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index 8fd7c3e37f5e..0abeed092de1 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -571,8 +571,10 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags)
 
 	if (ice_is_vf_disabled(vf)) {
 		vsi = ice_get_vf_vsi(vf);
-		if (WARN_ON(!vsi))
+		if (!vsi) {
+			dev_dbg(dev, "VF is already removed\n");
 			return -EINVAL;
+		}
 		ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id);
 		ice_vsi_stop_all_rx_rings(vsi);
 		dev_dbg(dev, "VF is already disabled, there is no need for resetting it, telling VM, all is fine %d\n",
@@ -762,13 +764,16 @@ static int ice_cfg_mac_antispoof(struct ice_vsi *vsi, bool enable)
 static int ice_vsi_ena_spoofchk(struct ice_vsi *vsi)
 {
 	struct ice_vsi_vlan_ops *vlan_ops;
-	int err;
+	int err = 0;
 
 	vlan_ops = ice_get_compat_vsi_vlan_ops(vsi);
 
-	err = vlan_ops->ena_tx_filtering(vsi);
-	if (err)
-		return err;
+	/* Allow VF with VLAN 0 only to send all tagged traffic */
+	if (vsi->type != ICE_VSI_VF || ice_vsi_has_non_zero_vlans(vsi)) {
+		err = vlan_ops->ena_tx_filtering(vsi);
+		if (err)
+			return err;
+	}
 
 	return ice_cfg_mac_antispoof(vsi, true);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 094e3c97a1ea..2b4c791b6cba 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -2288,6 +2288,15 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
 
 			/* Enable VLAN filtering on first non-zero VLAN */
 			if (!vlan_promisc && vid && !ice_is_dvm_ena(&pf->hw)) {
+				if (vf->spoofchk) {
+					status = vsi->inner_vlan_ops.ena_tx_filtering(vsi);
+					if (status) {
+						v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+						dev_err(dev, "Enable VLAN anti-spoofing on VLAN ID: %d failed error-%d\n",
+							vid, status);
+						goto error_param;
+					}
+				}
 				if (vsi->inner_vlan_ops.ena_rx_filtering(vsi)) {
 					v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 					dev_err(dev, "Enable VLAN pruning on VLAN ID: %d failed error-%d\n",
@@ -2333,8 +2342,10 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
 			}
 
 			/* Disable VLAN filtering when only VLAN 0 is left */
-			if (!ice_vsi_has_non_zero_vlans(vsi))
+			if (!ice_vsi_has_non_zero_vlans(vsi)) {
+				vsi->inner_vlan_ops.dis_tx_filtering(vsi);
 				vsi->inner_vlan_ops.dis_rx_filtering(vsi);
+			}
 
 			if (vlan_promisc)
 				ice_vf_dis_vlan_promisc(vsi, &vlan);
@@ -2838,6 +2849,13 @@ ice_vc_del_vlans(struct ice_vf *vf, struct ice_vsi *vsi,
 
 			if (vlan_promisc)
 				ice_vf_dis_vlan_promisc(vsi, &vlan);
+
+			/* Disable VLAN filtering when only VLAN 0 is left */
+			if (!ice_vsi_has_non_zero_vlans(vsi) && ice_is_dvm_ena(&vsi->back->hw)) {
+				err = vsi->outer_vlan_ops.dis_tx_filtering(vsi);
+				if (err)
+					return err;
+			}
 		}
 
 		vc_vlan = &vlan_fltr->inner;
@@ -2853,8 +2871,17 @@ ice_vc_del_vlans(struct ice_vf *vf, struct ice_vsi *vsi,
 			/* no support for VLAN promiscuous on inner VLAN unless
 			 * we are in Single VLAN Mode (SVM)
 			 */
-			if (!ice_is_dvm_ena(&vsi->back->hw) && vlan_promisc)
-				ice_vf_dis_vlan_promisc(vsi, &vlan);
+			if (!ice_is_dvm_ena(&vsi->back->hw)) {
+				if (vlan_promisc)
+					ice_vf_dis_vlan_promisc(vsi, &vlan);
+
+				/* Disable VLAN filtering when only VLAN 0 is left */
+				if (!ice_vsi_has_non_zero_vlans(vsi)) {
+					err = vsi->inner_vlan_ops.dis_tx_filtering(vsi);
+					if (err)
+						return err;
+				}
+			}
 		}
 	}
 
@@ -2931,6 +2958,13 @@ ice_vc_add_vlans(struct ice_vf *vf, struct ice_vsi *vsi,
 				if (err)
 					return err;
 			}
+
+			/* Enable VLAN filtering on first non-zero VLAN */
+			if (vf->spoofchk && vlan.vid && ice_is_dvm_ena(&vsi->back->hw)) {
+				err = vsi->outer_vlan_ops.ena_tx_filtering(vsi);
+				if (err)
+					return err;
+			}
 		}
 
 		vc_vlan = &vlan_fltr->inner;
@@ -2946,10 +2980,19 @@ ice_vc_add_vlans(struct ice_vf *vf, struct ice_vsi *vsi,
 			/* no support for VLAN promiscuous on inner VLAN unless
 			 * we are in Single VLAN Mode (SVM)
 			 */
-			if (!ice_is_dvm_ena(&vsi->back->hw) && vlan_promisc) {
-				err = ice_vf_ena_vlan_promisc(vsi, &vlan);
-				if (err)
-					return err;
+			if (!ice_is_dvm_ena(&vsi->back->hw)) {
+				if (vlan_promisc) {
+					err = ice_vf_ena_vlan_promisc(vsi, &vlan);
+					if (err)
+						return err;
+				}
+
+				/* Enable VLAN filtering on first non-zero VLAN */
+				if (vf->spoofchk && vlan.vid) {
+					err = vsi->inner_vlan_ops.ena_tx_filtering(vsi);
+					if (err)
+						return err;
+				}
 			}
 		}
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 49ba8bfdbf04..056c904b83cc 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -192,6 +192,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 	err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true);
 	if (err)
 		return err;
+	ice_clean_rx_ring(rx_ring);
 
 	ice_qvec_toggle_napi(vsi, q_vector, false);
 	ice_qp_clean_rings(vsi, q_idx);
@@ -243,7 +244,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
 		if (err)
 			goto free_buf;
 		ice_set_ring_xdp(xdp_ring);
-		xdp_ring->xsk_pool = ice_tx_xsk_pool(xdp_ring);
+		ice_tx_xsk_pool(vsi, q_idx);
 	}
 
 	err = ice_vsi_cfg_rxq(rx_ring);
@@ -317,6 +318,62 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 }
 
 /**
+ * ice_realloc_rx_xdp_bufs - reallocate for either XSK or normal buffer
+ * @rx_ring: Rx ring
+ * @pool_present: is pool for XSK present
+ *
+ * Try allocating memory and return ENOMEM, if failed to allocate.
+ * If allocation was successful, substitute buffer with allocated one.
+ * Returns 0 on success, negative on failure
+ */
+static int
+ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present)
+{
+	size_t elem_size = pool_present ? sizeof(*rx_ring->xdp_buf) :
+					  sizeof(*rx_ring->rx_buf);
+	void *sw_ring = kcalloc(rx_ring->count, elem_size, GFP_KERNEL);
+
+	if (!sw_ring)
+		return -ENOMEM;
+
+	if (pool_present) {
+		kfree(rx_ring->rx_buf);
+		rx_ring->rx_buf = NULL;
+		rx_ring->xdp_buf = sw_ring;
+	} else {
+		kfree(rx_ring->xdp_buf);
+		rx_ring->xdp_buf = NULL;
+		rx_ring->rx_buf = sw_ring;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_realloc_zc_buf - reallocate XDP ZC queue pairs
+ * @vsi: Current VSI
+ * @zc: is zero copy set
+ *
+ * Reallocate buffer for rx_rings that might be used by XSK.
+ * XDP requires more memory, than rx_buf provides.
+ * Returns 0 on success, negative on failure
+ */
+int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc)
+{
+	struct ice_rx_ring *rx_ring;
+	unsigned long q;
+
+	for_each_set_bit(q, vsi->af_xdp_zc_qps,
+			 max_t(int, vsi->alloc_txq, vsi->alloc_rxq)) {
+		rx_ring = vsi->rx_rings[q];
+		if (ice_realloc_rx_xdp_bufs(rx_ring, zc))
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/**
  * ice_xsk_pool_setup - enable/disable a buffer pool region depending on its state
  * @vsi: Current VSI
  * @pool: buffer pool to enable/associate to a ring, NULL to disable
@@ -329,9 +386,8 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 	bool if_running, pool_present = !!pool;
 	int ret = 0, pool_failure = 0;
 
-	if (!is_power_of_2(vsi->rx_rings[qid]->count) ||
-	    !is_power_of_2(vsi->tx_rings[qid]->count)) {
-		netdev_err(vsi->netdev, "Please align ring sizes to power of 2\n");
+	if (qid >= vsi->num_rxq || qid >= vsi->num_txq) {
+		netdev_err(vsi->netdev, "Please use queue id in scope of combined queues count\n");
 		pool_failure = -EINVAL;
 		goto failure;
 	}
@@ -339,11 +395,17 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 	if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi);
 
 	if (if_running) {
+		struct ice_rx_ring *rx_ring = vsi->rx_rings[qid];
+
 		ret = ice_qp_dis(vsi, qid);
 		if (ret) {
 			netdev_err(vsi->netdev, "ice_qp_dis error = %d\n", ret);
 			goto xsk_pool_if_up;
 		}
+
+		ret = ice_realloc_rx_xdp_bufs(rx_ring, pool_present);
+		if (ret)
+			goto xsk_pool_if_up;
 	}
 
 	pool_failure = pool_present ? ice_xsk_pool_enable(vsi, pool, qid) :
@@ -353,7 +415,7 @@ xsk_pool_if_up:
 	if (if_running) {
 		ret = ice_qp_ena(vsi, qid);
 		if (!ret && pool_present)
-			napi_schedule(&vsi->xdp_rings[qid]->q_vector->napi);
+			napi_schedule(&vsi->rx_rings[qid]->xdp_ring->q_vector->napi);
 		else if (ret)
 			netdev_err(vsi->netdev, "ice_qp_ena error = %d\n", ret);
 	}
@@ -465,11 +527,10 @@ exit:
 bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 {
 	u16 rx_thresh = ICE_RING_QUARTER(rx_ring);
-	u16 batched, leftover, i, tail_bumps;
+	u16 leftover, i, tail_bumps;
 
-	batched = ALIGN_DOWN(count, rx_thresh);
-	tail_bumps = batched / rx_thresh;
-	leftover = count & (rx_thresh - 1);
+	tail_bumps = count / rx_thresh;
+	leftover = count - (tail_bumps * rx_thresh);
 
 	for (i = 0; i < tail_bumps; i++)
 		if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh))
@@ -719,69 +780,57 @@ ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf)
 }
 
 /**
- * ice_clean_xdp_irq_zc - Reclaim resources after transmit completes on XDP ring
- * @xdp_ring: XDP ring to clean
- * @napi_budget: amount of descriptors that NAPI allows us to clean
- *
- * Returns count of cleaned descriptors
+ * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ
+ * @xdp_ring: XDP Tx ring
  */
-static u16 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring, int napi_budget)
+static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
 {
-	u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
-	int budget = napi_budget / tx_thresh;
-	u16 next_dd = xdp_ring->next_dd;
-	u16 ntc, cleared_dds = 0;
-
-	do {
-		struct ice_tx_desc *next_dd_desc;
-		u16 desc_cnt = xdp_ring->count;
-		struct ice_tx_buf *tx_buf;
-		u32 xsk_frames;
-		u16 i;
-
-		next_dd_desc = ICE_TX_DESC(xdp_ring, next_dd);
-		if (!(next_dd_desc->cmd_type_offset_bsz &
-		    cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)))
-			break;
+	u16 ntc = xdp_ring->next_to_clean;
+	struct ice_tx_desc *tx_desc;
+	u16 cnt = xdp_ring->count;
+	struct ice_tx_buf *tx_buf;
+	u16 xsk_frames = 0;
+	u16 last_rs;
+	int i;
 
-		cleared_dds++;
-		xsk_frames = 0;
-		if (likely(!xdp_ring->xdp_tx_active)) {
-			xsk_frames = tx_thresh;
-			goto skip;
-		}
+	last_rs = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : cnt - 1;
+	tx_desc = ICE_TX_DESC(xdp_ring, last_rs);
+	if ((tx_desc->cmd_type_offset_bsz &
+	    cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) {
+		if (last_rs >= ntc)
+			xsk_frames = last_rs - ntc + 1;
+		else
+			xsk_frames = last_rs + cnt - ntc + 1;
+	}
 
-		ntc = xdp_ring->next_to_clean;
+	if (!xsk_frames)
+		return;
 
-		for (i = 0; i < tx_thresh; i++) {
-			tx_buf = &xdp_ring->tx_buf[ntc];
+	if (likely(!xdp_ring->xdp_tx_active))
+		goto skip;
 
-			if (tx_buf->raw_buf) {
-				ice_clean_xdp_tx_buf(xdp_ring, tx_buf);
-				tx_buf->raw_buf = NULL;
-			} else {
-				xsk_frames++;
-			}
+	ntc = xdp_ring->next_to_clean;
+	for (i = 0; i < xsk_frames; i++) {
+		tx_buf = &xdp_ring->tx_buf[ntc];
 
-			ntc++;
-			if (ntc >= xdp_ring->count)
-				ntc = 0;
+		if (tx_buf->raw_buf) {
+			ice_clean_xdp_tx_buf(xdp_ring, tx_buf);
+			tx_buf->raw_buf = NULL;
+		} else {
+			xsk_frames++;
 		}
+
+		ntc++;
+		if (ntc >= xdp_ring->count)
+			ntc = 0;
+	}
 skip:
-		xdp_ring->next_to_clean += tx_thresh;
-		if (xdp_ring->next_to_clean >= desc_cnt)
-			xdp_ring->next_to_clean -= desc_cnt;
-		if (xsk_frames)
-			xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
-		next_dd_desc->cmd_type_offset_bsz = 0;
-		next_dd = next_dd + tx_thresh;
-		if (next_dd >= desc_cnt)
-			next_dd = tx_thresh - 1;
-	} while (--budget);
-
-	xdp_ring->next_dd = next_dd;
-
-	return cleared_dds * tx_thresh;
+	tx_desc->cmd_type_offset_bsz = 0;
+	xdp_ring->next_to_clean += xsk_frames;
+	if (xdp_ring->next_to_clean >= cnt)
+		xdp_ring->next_to_clean -= cnt;
+	if (xsk_frames)
+		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
 }
 
 /**
@@ -816,7 +865,6 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
 static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
 			       unsigned int *total_bytes)
 {
-	u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
 	u16 ntu = xdp_ring->next_to_use;
 	struct ice_tx_desc *tx_desc;
 	u32 i;
@@ -836,13 +884,6 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
 	}
 
 	xdp_ring->next_to_use = ntu;
-
-	if (xdp_ring->next_to_use > xdp_ring->next_rs) {
-		tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs);
-		tx_desc->cmd_type_offset_bsz |=
-			cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S);
-		xdp_ring->next_rs += tx_thresh;
-	}
 }
 
 /**
@@ -855,7 +896,6 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
 static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
 				u32 nb_pkts, unsigned int *total_bytes)
 {
-	u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
 	u32 batched, leftover, i;
 
 	batched = ALIGN_DOWN(nb_pkts, PKTS_PER_BATCH);
@@ -864,54 +904,54 @@ static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *d
 		ice_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes);
 	for (; i < batched + leftover; i++)
 		ice_xmit_pkt(xdp_ring, &descs[i], total_bytes);
+}
 
-	if (xdp_ring->next_to_use > xdp_ring->next_rs) {
-		struct ice_tx_desc *tx_desc;
+/**
+ * ice_set_rs_bit - set RS bit on last produced descriptor (one behind current NTU)
+ * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ */
+static void ice_set_rs_bit(struct ice_tx_ring *xdp_ring)
+{
+	u16 ntu = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : xdp_ring->count - 1;
+	struct ice_tx_desc *tx_desc;
 
-		tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs);
-		tx_desc->cmd_type_offset_bsz |=
-			cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S);
-		xdp_ring->next_rs += tx_thresh;
-	}
+	tx_desc = ICE_TX_DESC(xdp_ring, ntu);
+	tx_desc->cmd_type_offset_bsz |=
+		cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S);
 }
 
 /**
  * ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring
  * @xdp_ring: XDP ring to produce the HW Tx descriptors on
- * @budget: number of free descriptors on HW Tx ring that can be used
- * @napi_budget: amount of descriptors that NAPI allows us to clean
  *
  * Returns true if there is no more work that needs to be done, false otherwise
  */
-bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, u32 budget, int napi_budget)
+bool ice_xmit_zc(struct ice_tx_ring *xdp_ring)
 {
 	struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs;
-	u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
 	u32 nb_pkts, nb_processed = 0;
 	unsigned int total_bytes = 0;
+	int budget;
+
+	ice_clean_xdp_irq_zc(xdp_ring);
 
-	if (budget < tx_thresh)
-		budget += ice_clean_xdp_irq_zc(xdp_ring, napi_budget);
+	budget = ICE_DESC_UNUSED(xdp_ring);
+	budget = min_t(u16, budget, ICE_RING_QUARTER(xdp_ring));
 
 	nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget);
 	if (!nb_pkts)
 		return true;
 
 	if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) {
-		struct ice_tx_desc *tx_desc;
-
 		nb_processed = xdp_ring->count - xdp_ring->next_to_use;
 		ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes);
-		tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs);
-		tx_desc->cmd_type_offset_bsz |=
-			cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S);
-		xdp_ring->next_rs = tx_thresh - 1;
 		xdp_ring->next_to_use = 0;
 	}
 
 	ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed,
 			    &total_bytes);
 
+	ice_set_rs_bit(xdp_ring);
 	ice_xdp_ring_update_tail(xdp_ring);
 	ice_update_tx_ring_stats(xdp_ring, nb_pkts, total_bytes);
 
@@ -944,13 +984,13 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
 	if (!ice_is_xdp_ena_vsi(vsi))
 		return -EINVAL;
 
-	if (queue_id >= vsi->num_txq)
+	if (queue_id >= vsi->num_txq || queue_id >= vsi->num_rxq)
 		return -EINVAL;
 
-	if (!vsi->xdp_rings[queue_id]->xsk_pool)
-		return -EINVAL;
+	ring = vsi->rx_rings[queue_id]->xdp_ring;
 
-	ring = vsi->xdp_rings[queue_id];
+	if (!ring->xsk_pool)
+		return -EINVAL;
 
 	/* The idea here is that if NAPI is running, mark a miss, so
 	 * it will run again. If not, trigger an interrupt and
@@ -989,14 +1029,16 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi)
  */
 void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring)
 {
-	u16 count_mask = rx_ring->count - 1;
 	u16 ntc = rx_ring->next_to_clean;
 	u16 ntu = rx_ring->next_to_use;
 
-	for ( ; ntc != ntu; ntc = (ntc + 1) & count_mask) {
+	while (ntc != ntu) {
 		struct xdp_buff *xdp = *ice_xdp_buf(rx_ring, ntc);
 
 		xsk_buff_free(xdp);
+		ntc++;
+		if (ntc >= rx_ring->count)
+			ntc = 0;
 	}
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h
index 21faec8e97db..6fa181f080ef 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.h
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.h
@@ -26,12 +26,10 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count);
 bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi);
 void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring);
 void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring);
-bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, u32 budget, int napi_budget);
+bool ice_xmit_zc(struct ice_tx_ring *xdp_ring);
+int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc);
 #else
-static inline bool
-ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring,
-	    u32 __always_unused budget,
-	    int __always_unused napi_budget)
+static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring)
 {
 	return false;
 }
@@ -72,5 +70,12 @@ ice_xsk_wakeup(struct net_device __always_unused *netdev,
 
 static inline void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) { }
 static inline void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring) { }
+
+static inline int
+ice_realloc_zc_buf(struct ice_vsi __always_unused *vsi,
+		   bool __always_unused zc)
+{
+	return 0;
+}
 #endif /* CONFIG_XDP_SOCKETS */
 #endif /* !_ICE_XSK_H_ */
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 2d3daf022651..015b78144114 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -664,6 +664,8 @@ struct igb_adapter {
 	struct igb_mac_addr *mac_table;
 	struct vf_mac_filter vf_macs;
 	struct vf_mac_filter *vf_mac_list;
+	/* lock for VF resources */
+	spinlock_t vfs_lock;
 };
 
 /* flags controlling PTP/1588 function */
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index d8b836a85cc3..2796e81d2726 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -3637,6 +3637,7 @@ static int igb_disable_sriov(struct pci_dev *pdev)
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	unsigned long flags;
 
 	/* reclaim resources allocated to VFs */
 	if (adapter->vf_data) {
@@ -3649,12 +3650,13 @@ static int igb_disable_sriov(struct pci_dev *pdev)
 			pci_disable_sriov(pdev);
 			msleep(500);
 		}
-
+		spin_lock_irqsave(&adapter->vfs_lock, flags);
 		kfree(adapter->vf_mac_list);
 		adapter->vf_mac_list = NULL;
 		kfree(adapter->vf_data);
 		adapter->vf_data = NULL;
 		adapter->vfs_allocated_count = 0;
+		spin_unlock_irqrestore(&adapter->vfs_lock, flags);
 		wr32(E1000_IOVCTL, E1000_IOVCTL_REUSE_VFQ);
 		wrfl();
 		msleep(100);
@@ -3814,7 +3816,9 @@ static void igb_remove(struct pci_dev *pdev)
 	igb_release_hw_control(adapter);
 
 #ifdef CONFIG_PCI_IOV
+	rtnl_lock();
 	igb_disable_sriov(pdev);
+	rtnl_unlock();
 #endif
 
 	unregister_netdev(netdev);
@@ -3974,6 +3978,9 @@ static int igb_sw_init(struct igb_adapter *adapter)
 
 	spin_lock_init(&adapter->nfc_lock);
 	spin_lock_init(&adapter->stats64_lock);
+
+	/* init spinlock to avoid concurrency of VF resources */
+	spin_lock_init(&adapter->vfs_lock);
 #ifdef CONFIG_PCI_IOV
 	switch (hw->mac.type) {
 	case e1000_82576:
@@ -7958,8 +7965,10 @@ unlock:
 static void igb_msg_task(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
+	unsigned long flags;
 	u32 vf;
 
+	spin_lock_irqsave(&adapter->vfs_lock, flags);
 	for (vf = 0; vf < adapter->vfs_allocated_count; vf++) {
 		/* process any reset requests */
 		if (!igb_check_for_rst(hw, vf))
@@ -7973,6 +7982,7 @@ static void igb_msg_task(struct igb_adapter *adapter)
 		if (!igb_check_for_ack(hw, vf))
 			igb_rcv_ack_from_vf(adapter, vf);
 	}
+	spin_unlock_irqrestore(&adapter->vfs_lock, flags);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index 9f06896a049b..f8605f57bd06 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -1214,7 +1214,6 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
 	struct cyclecounter cc;
 	unsigned long flags;
 	u32 incval = 0;
-	u32 tsauxc = 0;
 	u32 fuse0 = 0;
 
 	/* For some of the boards below this mask is technically incorrect.
@@ -1249,18 +1248,6 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_x550em_a:
 	case ixgbe_mac_X550:
 		cc.read = ixgbe_ptp_read_X550;
-
-		/* enable SYSTIME counter */
-		IXGBE_WRITE_REG(hw, IXGBE_SYSTIMR, 0);
-		IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0);
-		IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0);
-		tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC);
-		IXGBE_WRITE_REG(hw, IXGBE_TSAUXC,
-				tsauxc & ~IXGBE_TSAUXC_DISABLE_SYSTIME);
-		IXGBE_WRITE_REG(hw, IXGBE_TSIM, IXGBE_TSIM_TXTS);
-		IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_TIMESYNC);
-
-		IXGBE_WRITE_FLUSH(hw);
 		break;
 	case ixgbe_mac_X540:
 		cc.read = ixgbe_ptp_read_82599;
@@ -1293,6 +1280,50 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
 }
 
 /**
+ * ixgbe_ptp_init_systime - Initialize SYSTIME registers
+ * @adapter: the ixgbe private board structure
+ *
+ * Initialize and start the SYSTIME registers.
+ */
+static void ixgbe_ptp_init_systime(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 tsauxc;
+
+	switch (hw->mac.type) {
+	case ixgbe_mac_X550EM_x:
+	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_X550:
+		tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC);
+
+		/* Reset SYSTIME registers to 0 */
+		IXGBE_WRITE_REG(hw, IXGBE_SYSTIMR, 0);
+		IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0);
+		IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0);
+
+		/* Reset interrupt settings */
+		IXGBE_WRITE_REG(hw, IXGBE_TSIM, IXGBE_TSIM_TXTS);
+		IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_TIMESYNC);
+
+		/* Activate the SYSTIME counter */
+		IXGBE_WRITE_REG(hw, IXGBE_TSAUXC,
+				tsauxc & ~IXGBE_TSAUXC_DISABLE_SYSTIME);
+		break;
+	case ixgbe_mac_X540:
+	case ixgbe_mac_82599EB:
+		/* Reset SYSTIME registers to 0 */
+		IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0);
+		IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0);
+		break;
+	default:
+		/* Other devices aren't supported */
+		return;
+	};
+
+	IXGBE_WRITE_FLUSH(hw);
+}
+
+/**
  * ixgbe_ptp_reset
  * @adapter: the ixgbe private board structure
  *
@@ -1318,6 +1349,8 @@ void ixgbe_ptp_reset(struct ixgbe_adapter *adapter)
 
 	ixgbe_ptp_start_cyclecounter(adapter);
 
+	ixgbe_ptp_init_systime(adapter);
+
 	spin_lock_irqsave(&adapter->tmreg_lock, flags);
 	timecounter_init(&adapter->hw_tc, &adapter->hw_cc,
 			 ktime_to_ns(ktime_get_real()));
diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 5edb68a8aab1..57f27cc7724e 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -193,6 +193,7 @@ static int xrx200_alloc_buf(struct xrx200_chan *ch, void *(*alloc)(unsigned int
 
 	ch->rx_buff[ch->dma.desc] = alloc(priv->rx_skb_size);
 	if (!ch->rx_buff[ch->dma.desc]) {
+		ch->rx_buff[ch->dma.desc] = buf;
 		ret = -ENOMEM;
 		goto skip;
 	}
@@ -239,6 +240,12 @@ static int xrx200_hw_receive(struct xrx200_chan *ch)
 	}
 
 	skb = build_skb(buf, priv->rx_skb_size);
+	if (!skb) {
+		skb_free_frag(buf);
+		net_dev->stats.rx_dropped++;
+		return -ENOMEM;
+	}
+
 	skb_reserve(skb, NET_SKB_PAD);
 	skb_put(skb, len);
 
@@ -288,7 +295,7 @@ static int xrx200_poll_rx(struct napi_struct *napi, int budget)
 			if (ret == XRX200_DMA_PACKET_IN_PROGRESS)
 				continue;
 			if (ret != XRX200_DMA_PACKET_COMPLETE)
-				return ret;
+				break;
 			rx++;
 		} else {
 			break;
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c
index ede3e53b9790..a895862b4821 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_main.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c
@@ -368,6 +368,7 @@ static int prestera_port_sfp_bind(struct prestera_port *port)
 	if (!sw->np)
 		return 0;
 
+	of_node_get(sw->np);
 	ports = of_find_node_by_name(sw->np, "ports");
 
 	for_each_child_of_node(ports, node) {
@@ -417,6 +418,7 @@ static int prestera_port_sfp_bind(struct prestera_port *port)
 	}
 
 out:
+	of_node_put(node);
 	of_node_put(ports);
 	return err;
 }
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
index f538a749ebd4..59470d99f522 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
@@ -872,6 +872,7 @@ static void prestera_pci_remove(struct pci_dev *pdev)
 static const struct pci_device_id prestera_pci_devices[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0xC804) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0xC80C) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0xCC1E) },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, prestera_pci_devices);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index d9426b01f462..b344632beadd 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1458,7 +1458,7 @@ static void mtk_update_rx_cpu_idx(struct mtk_eth *eth)
 
 static bool mtk_page_pool_enabled(struct mtk_eth *eth)
 {
-	return !eth->hwlro;
+	return MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2);
 }
 
 static struct page_pool *mtk_create_page_pool(struct mtk_eth *eth,
@@ -1732,7 +1732,7 @@ static u32 mtk_xdp_run(struct mtk_eth *eth, struct mtk_rx_ring *ring,
 	case XDP_TX: {
 		struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
 
-		if (mtk_xdp_submit_frame(eth, xdpf, dev, false)) {
+		if (!xdpf || mtk_xdp_submit_frame(eth, xdpf, dev, false)) {
 			count = &hw_stats->xdp_stats.rx_xdp_tx_errors;
 			act = XDP_DROP;
 			break;
@@ -1891,10 +1891,19 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 		skb->dev = netdev;
 		bytes += skb->len;
 
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+			hash = trxd.rxd5 & MTK_RXD5_FOE_ENTRY;
+			if (hash != MTK_RXD5_FOE_ENTRY)
+				skb_set_hash(skb, jhash_1word(hash, 0),
+					     PKT_HASH_TYPE_L4);
 			rxdcsum = &trxd.rxd3;
-		else
+		} else {
+			hash = trxd.rxd4 & MTK_RXD4_FOE_ENTRY;
+			if (hash != MTK_RXD4_FOE_ENTRY)
+				skb_set_hash(skb, jhash_1word(hash, 0),
+					     PKT_HASH_TYPE_L4);
 			rxdcsum = &trxd.rxd4;
+		}
 
 		if (*rxdcsum & eth->soc->txrx.rx_dma_l4_valid)
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -1902,16 +1911,9 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 			skb_checksum_none_assert(skb);
 		skb->protocol = eth_type_trans(skb, netdev);
 
-		hash = trxd.rxd4 & MTK_RXD4_FOE_ENTRY;
-		if (hash != MTK_RXD4_FOE_ENTRY) {
-			hash = jhash_1word(hash, 0);
-			skb_set_hash(skb, hash, PKT_HASH_TYPE_L4);
-		}
-
 		reason = FIELD_GET(MTK_RXD4_PPE_CPU_REASON, trxd.rxd4);
 		if (reason == MTK_PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED)
-			mtk_ppe_check_skb(eth->ppe, skb,
-					  trxd.rxd4 & MTK_RXD4_FOE_ENTRY);
+			mtk_ppe_check_skb(eth->ppe, skb, hash);
 
 		if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) {
 			if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 7405c97cda66..0f9668a4079d 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -314,8 +314,13 @@
 #define RX_DMA_L4_VALID_PDMA	BIT(30)		/* when PDMA is used */
 #define RX_DMA_SPECIAL_TAG	BIT(22)
 
-#define RX_DMA_GET_SPORT(x)	(((x) >> 19) & 0xf)
-#define RX_DMA_GET_SPORT_V2(x)	(((x) >> 26) & 0x7)
+/* PDMA descriptor rxd5 */
+#define MTK_RXD5_FOE_ENTRY	GENMASK(14, 0)
+#define MTK_RXD5_PPE_CPU_REASON	GENMASK(22, 18)
+#define MTK_RXD5_SRC_PORT	GENMASK(29, 26)
+
+#define RX_DMA_GET_SPORT(x)	(((x) >> 19) & 0x7)
+#define RX_DMA_GET_SPORT_V2(x)	(((x) >> 26) & 0xf)
 
 /* PDMA V2 descriptor rxd3 */
 #define RX_DMA_VTAG_V2		BIT(0)
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c
index dab8f3f771f8..cfe804bc8d20 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe.c
@@ -412,7 +412,7 @@ __mtk_foe_entry_clear(struct mtk_ppe *ppe, struct mtk_flow_entry *entry)
 	if (entry->hash != 0xffff) {
 		ppe->foe_table[entry->hash].ib1 &= ~MTK_FOE_IB1_STATE;
 		ppe->foe_table[entry->hash].ib1 |= FIELD_PREP(MTK_FOE_IB1_STATE,
-							      MTK_FOE_STATE_BIND);
+							      MTK_FOE_STATE_UNBIND);
 		dma_wmb();
 	}
 	entry->hash = 0xffff;
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.h b/drivers/net/ethernet/mediatek/mtk_ppe.h
index 1f5cf1c9a947..69ffce04d630 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe.h
+++ b/drivers/net/ethernet/mediatek/mtk_ppe.h
@@ -293,6 +293,9 @@ mtk_ppe_check_skb(struct mtk_ppe *ppe, struct sk_buff *skb, u16 hash)
 	if (!ppe)
 		return;
 
+	if (hash > MTK_PPE_HASH_MASK)
+		return;
+
 	now = (u16)jiffies;
 	diff = now - ppe->foe_check_time[hash];
 	if (diff < HZ / 10)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c
index 37522352e4b2..c8e5ca65bb6e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c
@@ -79,6 +79,10 @@ tc_act_police_offload(struct mlx5e_priv *priv,
 	struct mlx5e_flow_meter_handle *meter;
 	int err = 0;
 
+	err = mlx5e_policer_validate(&fl_act->action, act, fl_act->extack);
+	if (err)
+		return err;
+
 	err = fill_meter_params_from_act(act, &params);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 0aef69527226..3a1f76eac542 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -246,7 +246,7 @@ static void mlx5e_tls_priv_tx_cleanup(struct mlx5e_ktls_offload_context_tx *priv
 static void mlx5e_tls_priv_tx_list_cleanup(struct mlx5_core_dev *mdev,
 					   struct list_head *list, int size)
 {
-	struct mlx5e_ktls_offload_context_tx *obj;
+	struct mlx5e_ktls_offload_context_tx *obj, *n;
 	struct mlx5e_async_ctx *bulk_async;
 	int i;
 
@@ -255,7 +255,7 @@ static void mlx5e_tls_priv_tx_list_cleanup(struct mlx5_core_dev *mdev,
 		return;
 
 	i = 0;
-	list_for_each_entry(obj, list, list_node) {
+	list_for_each_entry_safe(obj, n, list, list_node) {
 		mlx5e_tls_priv_tx_cleanup(obj, &bulk_async[i]);
 		i++;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index e2a9b9be5c1f..e0ce5a233d0b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -1395,10 +1395,11 @@ struct mlx5e_flow_steering *mlx5e_fs_init(const struct mlx5e_profile *profile,
 	}
 
 	return fs;
-err_free_fs:
-	kvfree(fs);
+
 err_free_vlan:
 	mlx5e_fs_vlan_free(fs);
+err_free_fs:
+	kvfree(fs);
 err:
 	return NULL;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d858667736a3..02eb2f0fa2ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3682,7 +3682,9 @@ static int set_feature_hw_tc(struct net_device *netdev, bool enable)
 	int err = 0;
 
 #if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
-	if (!enable && mlx5e_tc_num_filters(priv, MLX5_TC_FLAG(NIC_OFFLOAD))) {
+	int tc_flag = mlx5e_is_uplink_rep(priv) ? MLX5_TC_FLAG(ESW_OFFLOAD) :
+						  MLX5_TC_FLAG(NIC_OFFLOAD);
+	if (!enable && mlx5e_tc_num_filters(priv, tc_flag)) {
 		netdev_err(netdev,
 			   "Active offloaded tc filters, can't turn hw_tc_offload off\n");
 		return -EINVAL;
@@ -4769,14 +4771,6 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
 
-	/* HW LRO */
-	if (MLX5_CAP_ETH(mdev, lro_cap) &&
-	    params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
-		/* No XSK params: checking the availability of striding RQ in general. */
-		if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
-			params->packet_merge.type = slow_pci_heuristic(mdev) ?
-				MLX5E_PACKET_MERGE_NONE : MLX5E_PACKET_MERGE_LRO;
-	}
 	params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
 
 	/* CQ moderation params */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 4c1599de652c..759f7d3c2cfd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -662,6 +662,8 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 
 	params->mqprio.num_tc       = 1;
 	params->tunneled_offload_en = false;
+	if (rep->vport != MLX5_VPORT_UPLINK)
+		params->vlan_strip_disable = true;
 
 	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
 }
@@ -696,6 +698,13 @@ static int mlx5e_init_rep(struct mlx5_core_dev *mdev,
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
+	priv->fs = mlx5e_fs_init(priv->profile, mdev,
+				 !test_bit(MLX5E_STATE_DESTROYING, &priv->state));
+	if (!priv->fs) {
+		netdev_err(priv->netdev, "FS allocation failed\n");
+		return -ENOMEM;
+	}
+
 	mlx5e_build_rep_params(netdev);
 	mlx5e_timestamp_init(priv);
 
@@ -708,12 +717,21 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev,
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	int err;
 
+	priv->fs = mlx5e_fs_init(priv->profile, mdev,
+				 !test_bit(MLX5E_STATE_DESTROYING, &priv->state));
+	if (!priv->fs) {
+		netdev_err(priv->netdev, "FS allocation failed\n");
+		return -ENOMEM;
+	}
+
 	err = mlx5e_ipsec_init(priv);
 	if (err)
 		mlx5_core_err(mdev, "Uplink rep IPsec initialization failed, %d\n", err);
 
 	mlx5e_vxlan_set_netdev_info(priv);
-	return mlx5e_init_rep(mdev, netdev);
+	mlx5e_build_rep_params(netdev);
+	mlx5e_timestamp_init(priv);
+	return 0;
 }
 
 static void mlx5e_cleanup_rep(struct mlx5e_priv *priv)
@@ -836,13 +854,6 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
-	priv->fs = mlx5e_fs_init(priv->profile, mdev,
-				 !test_bit(MLX5E_STATE_DESTROYING, &priv->state));
-	if (!priv->fs) {
-		netdev_err(priv->netdev, "FS allocation failed\n");
-		return -ENOMEM;
-	}
-
 	priv->rx_res = mlx5e_rx_res_alloc();
 	if (!priv->rx_res) {
 		err = -ENOMEM;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index ed73132129aa..a9f4c652f859 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -427,7 +427,8 @@ esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *f
 		dest[dest_idx].vport.vhca_id =
 			MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id);
 		dest[dest_idx].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
-		if (mlx5_lag_mpesw_is_activated(esw->dev))
+		if (dest[dest_idx].vport.num == MLX5_VPORT_UPLINK &&
+		    mlx5_lag_mpesw_is_activated(esw->dev))
 			dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_UPLINK;
 	}
 	if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP) {
@@ -3115,8 +3116,10 @@ esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, const u32 *out)
 
 		err = mlx5_eswitch_load_vf_vports(esw, new_num_vfs,
 						  MLX5_VPORT_UC_ADDR_CHANGE);
-		if (err)
+		if (err) {
+			devl_unlock(devlink);
 			return;
+		}
 	}
 	esw->esw_funcs.num_vfs = new_num_vfs;
 	devl_unlock(devlink);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 0f34e3c80d1f..065102278cb8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1067,30 +1067,32 @@ static void mlx5_ldev_add_netdev(struct mlx5_lag *ldev,
 				 struct net_device *netdev)
 {
 	unsigned int fn = mlx5_get_dev_index(dev);
+	unsigned long flags;
 
 	if (fn >= ldev->ports)
 		return;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev->pf[fn].netdev = netdev;
 	ldev->tracker.netdev_state[fn].link_up = 0;
 	ldev->tracker.netdev_state[fn].tx_enabled = 0;
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 }
 
 static void mlx5_ldev_remove_netdev(struct mlx5_lag *ldev,
 				    struct net_device *netdev)
 {
+	unsigned long flags;
 	int i;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	for (i = 0; i < ldev->ports; i++) {
 		if (ldev->pf[i].netdev == netdev) {
 			ldev->pf[i].netdev = NULL;
 			break;
 		}
 	}
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 }
 
 static void mlx5_ldev_add_mdev(struct mlx5_lag *ldev,
@@ -1234,7 +1236,7 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev,
 	mlx5_ldev_add_netdev(ldev, dev, netdev);
 
 	for (i = 0; i < ldev->ports; i++)
-		if (!ldev->pf[i].dev)
+		if (!ldev->pf[i].netdev)
 			break;
 
 	if (i >= ldev->ports)
@@ -1246,12 +1248,13 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev,
 bool mlx5_lag_is_roce(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	bool res;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	res  = ldev && __mlx5_lag_is_roce(ldev);
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 
 	return res;
 }
@@ -1260,12 +1263,13 @@ EXPORT_SYMBOL(mlx5_lag_is_roce);
 bool mlx5_lag_is_active(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	bool res;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	res  = ldev && __mlx5_lag_is_active(ldev);
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 
 	return res;
 }
@@ -1274,13 +1278,14 @@ EXPORT_SYMBOL(mlx5_lag_is_active);
 bool mlx5_lag_is_master(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	bool res;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	res = ldev && __mlx5_lag_is_active(ldev) &&
 		dev == ldev->pf[MLX5_LAG_P1].dev;
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 
 	return res;
 }
@@ -1289,12 +1294,13 @@ EXPORT_SYMBOL(mlx5_lag_is_master);
 bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	bool res;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	res  = ldev && __mlx5_lag_is_sriov(ldev);
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 
 	return res;
 }
@@ -1303,13 +1309,14 @@ EXPORT_SYMBOL(mlx5_lag_is_sriov);
 bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	bool res;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	res = ldev && __mlx5_lag_is_sriov(ldev) &&
 	      test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags);
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 
 	return res;
 }
@@ -1352,9 +1359,10 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
 {
 	struct net_device *ndev = NULL;
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	int i;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 
 	if (!(ldev && __mlx5_lag_is_roce(ldev)))
@@ -1373,7 +1381,7 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
 		dev_hold(ndev);
 
 unlock:
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 
 	return ndev;
 }
@@ -1383,10 +1391,11 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
 			   struct net_device *slave)
 {
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	u8 port = 0;
 	int i;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	if (!(ldev && __mlx5_lag_is_roce(ldev)))
 		goto unlock;
@@ -1401,7 +1410,7 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
 	port = ldev->v2p_map[port * ldev->buckets];
 
 unlock:
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 	return port;
 }
 EXPORT_SYMBOL(mlx5_lag_get_slave_port);
@@ -1422,8 +1431,9 @@ struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_dev *peer_dev = NULL;
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	if (!ldev)
 		goto unlock;
@@ -1433,7 +1443,7 @@ struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev)
 			   ldev->pf[MLX5_LAG_P1].dev;
 
 unlock:
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 	return peer_dev;
 }
 EXPORT_SYMBOL(mlx5_lag_get_peer_mdev);
@@ -1446,6 +1456,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 	int outlen = MLX5_ST_SZ_BYTES(query_cong_statistics_out);
 	struct mlx5_core_dev **mdev;
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	int num_ports;
 	int ret, i, j;
 	void *out;
@@ -1462,7 +1473,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 
 	memset(values, 0, sizeof(*values) * num_counters);
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	if (ldev && __mlx5_lag_is_active(ldev)) {
 		num_ports = ldev->ports;
@@ -1472,7 +1483,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 		num_ports = 1;
 		mdev[MLX5_LAG_P1] = dev;
 	}
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 
 	for (i = 0; i < num_ports; ++i) {
 		u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = {};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index bec8d6d0b5f6..89b2d9cea33f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -494,6 +494,24 @@ static int max_uc_list_get_devlink_param(struct mlx5_core_dev *dev)
 	return err;
 }
 
+bool mlx5_is_roce_on(struct mlx5_core_dev *dev)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	union devlink_param_value val;
+	int err;
+
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
+						 &val);
+
+	if (!err)
+		return val.vbool;
+
+	mlx5_core_dbg(dev, "Failed to get param. err = %d\n", err);
+	return MLX5_CAP_GEN(dev, roce);
+}
+EXPORT_SYMBOL(mlx5_is_roce_on);
+
 static int handle_hca_cap_2(struct mlx5_core_dev *dev, void *set_ctx)
 {
 	void *set_hca_cap;
@@ -597,7 +615,8 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 			 MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix));
 
 	if (MLX5_CAP_GEN(dev, roce_rw_supported))
-		MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev));
+		MLX5_SET(cmd_hca_cap, set_hca_cap, roce,
+			 mlx5_is_roce_on(dev));
 
 	max_uc_list = max_uc_list_get_devlink_param(dev);
 	if (max_uc_list > 0)
@@ -623,7 +642,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
  */
 static bool is_roce_fw_disabled(struct mlx5_core_dev *dev)
 {
-	return (MLX5_CAP_GEN(dev, roce_rw_supported) && !mlx5_is_roce_init_enabled(dev)) ||
+	return (MLX5_CAP_GEN(dev, roce_rw_supported) && !mlx5_is_roce_on(dev)) ||
 		(!MLX5_CAP_GEN(dev, roce_rw_supported) && !MLX5_CAP_GEN(dev, roce));
 }
 
@@ -1530,7 +1549,9 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	memcpy(&dev->profile, &profile[profile_idx], sizeof(dev->profile));
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
+	lockdep_register_key(&dev->lock_key);
 	mutex_init(&dev->intf_state_mutex);
+	lockdep_set_class(&dev->intf_state_mutex, &dev->lock_key);
 
 	mutex_init(&priv->bfregs.reg_head.lock);
 	mutex_init(&priv->bfregs.wc_head.lock);
@@ -1597,6 +1618,7 @@ err_timeout_init:
 	mutex_destroy(&priv->bfregs.wc_head.lock);
 	mutex_destroy(&priv->bfregs.reg_head.lock);
 	mutex_destroy(&dev->intf_state_mutex);
+	lockdep_unregister_key(&dev->lock_key);
 	return err;
 }
 
@@ -1618,6 +1640,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 	mutex_destroy(&priv->bfregs.wc_head.lock);
 	mutex_destroy(&priv->bfregs.reg_head.lock);
 	mutex_destroy(&dev->intf_state_mutex);
+	lockdep_unregister_key(&dev->lock_key);
 }
 
 static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index ec76a8b1acc1..60596357bfc7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -376,8 +376,8 @@ retry:
 			goto out_dropped;
 		}
 	}
+	err = mlx5_cmd_check(dev, err, in, out);
 	if (err) {
-		err = mlx5_cmd_check(dev, err, in, out);
 		mlx5_core_warn(dev, "func_id 0x%x, npages %d, err %d\n",
 			       func_id, npages, err);
 		goto out_dropped;
@@ -524,10 +524,13 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
 		dev->priv.reclaim_pages_discard += npages;
 	}
 	/* if triggered by FW event and failed by FW then ignore */
-	if (event && err == -EREMOTEIO)
+	if (event && err == -EREMOTEIO) {
 		err = 0;
+		goto out_free;
+	}
+
+	err = mlx5_cmd_check(dev, err, in, out);
 	if (err) {
-		err = mlx5_cmd_check(dev, err, in, out);
 		mlx5_core_err(dev, "failed reclaiming pages: err %d\n", err);
 		goto out_free;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index ee2e1b7c1310..c0e6c487c63c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -159,11 +159,11 @@ static int mlx5_sriov_enable(struct pci_dev *pdev, int num_vfs)
 
 	devl_lock(devlink);
 	err = mlx5_device_enable_sriov(dev, num_vfs);
+	devl_unlock(devlink);
 	if (err) {
 		mlx5_core_warn(dev, "mlx5_device_enable_sriov failed : %d\n", err);
 		return err;
 	}
-	devl_unlock(devlink);
 
 	err = pci_enable_sriov(pdev, num_vfs);
 	if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h
index 5fdf9b7179f5..5a1027b07215 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h
@@ -75,6 +75,7 @@ struct mlxbf_gige {
 	struct net_device *netdev;
 	struct platform_device *pdev;
 	void __iomem *mdio_io;
+	void __iomem *clk_io;
 	struct mii_bus *mdiobus;
 	spinlock_t lock;      /* for packet processing indices */
 	u16 rx_q_entries;
@@ -137,7 +138,8 @@ enum mlxbf_gige_res {
 	MLXBF_GIGE_RES_MDIO9,
 	MLXBF_GIGE_RES_GPIO0,
 	MLXBF_GIGE_RES_LLU,
-	MLXBF_GIGE_RES_PLU
+	MLXBF_GIGE_RES_PLU,
+	MLXBF_GIGE_RES_CLK
 };
 
 /* Version of register data returned by mlxbf_gige_get_regs() */
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c
index 2e6c1b7af096..aa780b1614a3 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c
@@ -22,10 +22,23 @@
 #include <linux/property.h>
 
 #include "mlxbf_gige.h"
+#include "mlxbf_gige_regs.h"
 
 #define MLXBF_GIGE_MDIO_GW_OFFSET	0x0
 #define MLXBF_GIGE_MDIO_CFG_OFFSET	0x4
 
+#define MLXBF_GIGE_MDIO_FREQ_REFERENCE 156250000ULL
+#define MLXBF_GIGE_MDIO_COREPLL_CONST  16384ULL
+#define MLXBF_GIGE_MDC_CLK_NS          400
+#define MLXBF_GIGE_MDIO_PLL_I1CLK_REG1 0x4
+#define MLXBF_GIGE_MDIO_PLL_I1CLK_REG2 0x8
+#define MLXBF_GIGE_MDIO_CORE_F_SHIFT   0
+#define MLXBF_GIGE_MDIO_CORE_F_MASK    GENMASK(25, 0)
+#define MLXBF_GIGE_MDIO_CORE_R_SHIFT   26
+#define MLXBF_GIGE_MDIO_CORE_R_MASK    GENMASK(31, 26)
+#define MLXBF_GIGE_MDIO_CORE_OD_SHIFT  0
+#define MLXBF_GIGE_MDIO_CORE_OD_MASK   GENMASK(3, 0)
+
 /* Support clause 22 */
 #define MLXBF_GIGE_MDIO_CL22_ST1	0x1
 #define MLXBF_GIGE_MDIO_CL22_WRITE	0x1
@@ -50,27 +63,76 @@
 #define MLXBF_GIGE_MDIO_CFG_MDIO_IN_SAMP_MASK		GENMASK(23, 16)
 #define MLXBF_GIGE_MDIO_CFG_MDIO_OUT_SAMP_MASK		GENMASK(31, 24)
 
+#define MLXBF_GIGE_MDIO_CFG_VAL (FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_MODE_MASK, 1) | \
+				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO3_3_MASK, 1) | \
+				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_FULL_DRIVE_MASK, 1) | \
+				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_IN_SAMP_MASK, 6) | \
+				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_OUT_SAMP_MASK, 13))
+
+#define MLXBF_GIGE_BF2_COREPLL_ADDR 0x02800c30
+#define MLXBF_GIGE_BF2_COREPLL_SIZE 0x0000000c
+
+static struct resource corepll_params[] = {
+	[MLXBF_GIGE_VERSION_BF2] = {
+		.start = MLXBF_GIGE_BF2_COREPLL_ADDR,
+		.end = MLXBF_GIGE_BF2_COREPLL_ADDR + MLXBF_GIGE_BF2_COREPLL_SIZE - 1,
+		.name = "COREPLL_RES"
+	},
+};
+
+/* Returns core clock i1clk in Hz */
+static u64 calculate_i1clk(struct mlxbf_gige *priv)
+{
+	u8 core_od, core_r;
+	u64 freq_output;
+	u32 reg1, reg2;
+	u32 core_f;
+
+	reg1 = readl(priv->clk_io + MLXBF_GIGE_MDIO_PLL_I1CLK_REG1);
+	reg2 = readl(priv->clk_io + MLXBF_GIGE_MDIO_PLL_I1CLK_REG2);
+
+	core_f = (reg1 & MLXBF_GIGE_MDIO_CORE_F_MASK) >>
+		MLXBF_GIGE_MDIO_CORE_F_SHIFT;
+	core_r = (reg1 & MLXBF_GIGE_MDIO_CORE_R_MASK) >>
+		MLXBF_GIGE_MDIO_CORE_R_SHIFT;
+	core_od = (reg2 & MLXBF_GIGE_MDIO_CORE_OD_MASK) >>
+		MLXBF_GIGE_MDIO_CORE_OD_SHIFT;
+
+	/* Compute PLL output frequency as follow:
+	 *
+	 *                                     CORE_F / 16384
+	 * freq_output = freq_reference * ----------------------------
+	 *                              (CORE_R + 1) * (CORE_OD + 1)
+	 */
+	freq_output = div_u64((MLXBF_GIGE_MDIO_FREQ_REFERENCE * core_f),
+			      MLXBF_GIGE_MDIO_COREPLL_CONST);
+	freq_output = div_u64(freq_output, (core_r + 1) * (core_od + 1));
+
+	return freq_output;
+}
+
 /* Formula for encoding the MDIO period. The encoded value is
  * passed to the MDIO config register.
  *
- * mdc_clk = 2*(val + 1)*i1clk
+ * mdc_clk = 2*(val + 1)*(core clock in sec)
  *
- * 400 ns = 2*(val + 1)*(((1/430)*1000) ns)
+ * i1clk is in Hz:
+ * 400 ns = 2*(val + 1)*(1/i1clk)
  *
- * val = (((400 * 430 / 1000) / 2) - 1)
+ * val = (((400/10^9) / (1/i1clk) / 2) - 1)
+ * val = (400/2 * i1clk)/10^9 - 1
  */
-#define MLXBF_GIGE_I1CLK_MHZ		430
-#define MLXBF_GIGE_MDC_CLK_NS		400
+static u8 mdio_period_map(struct mlxbf_gige *priv)
+{
+	u8 mdio_period;
+	u64 i1clk;
 
-#define MLXBF_GIGE_MDIO_PERIOD	(((MLXBF_GIGE_MDC_CLK_NS * MLXBF_GIGE_I1CLK_MHZ / 1000) / 2) - 1)
+	i1clk = calculate_i1clk(priv);
 
-#define MLXBF_GIGE_MDIO_CFG_VAL (FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_MODE_MASK, 1) | \
-				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO3_3_MASK, 1) | \
-				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_FULL_DRIVE_MASK, 1) | \
-				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDC_PERIOD_MASK, \
-					    MLXBF_GIGE_MDIO_PERIOD) | \
-				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_IN_SAMP_MASK, 6) | \
-				 FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_OUT_SAMP_MASK, 13))
+	mdio_period = div_u64((MLXBF_GIGE_MDC_CLK_NS >> 1) * i1clk, 1000000000) - 1;
+
+	return mdio_period;
+}
 
 static u32 mlxbf_gige_mdio_create_cmd(u16 data, int phy_add,
 				      int phy_reg, u32 opcode)
@@ -117,6 +179,9 @@ static int mlxbf_gige_mdio_read(struct mii_bus *bus, int phy_add, int phy_reg)
 	/* Only return ad bits of the gw register */
 	ret &= MLXBF_GIGE_MDIO_GW_AD_MASK;
 
+	/* The MDIO lock is set on read. To release it, clear gw register */
+	writel(0, priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET);
+
 	return ret;
 }
 
@@ -124,9 +189,9 @@ static int mlxbf_gige_mdio_write(struct mii_bus *bus, int phy_add,
 				 int phy_reg, u16 val)
 {
 	struct mlxbf_gige *priv = bus->priv;
+	u32 temp;
 	u32 cmd;
 	int ret;
-	u32 temp;
 
 	if (phy_reg & MII_ADDR_C45)
 		return -EOPNOTSUPP;
@@ -141,21 +206,50 @@ static int mlxbf_gige_mdio_write(struct mii_bus *bus, int phy_add,
 					temp, !(temp & MLXBF_GIGE_MDIO_GW_BUSY_MASK),
 					5, 1000000);
 
+	/* The MDIO lock is set on read. To release it, clear gw register */
+	writel(0, priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET);
+
 	return ret;
 }
 
+static void mlxbf_gige_mdio_cfg(struct mlxbf_gige *priv)
+{
+	u8 mdio_period;
+	u32 val;
+
+	mdio_period = mdio_period_map(priv);
+
+	val = MLXBF_GIGE_MDIO_CFG_VAL;
+	val |= FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDC_PERIOD_MASK, mdio_period);
+	writel(val, priv->mdio_io + MLXBF_GIGE_MDIO_CFG_OFFSET);
+}
+
 int mlxbf_gige_mdio_probe(struct platform_device *pdev, struct mlxbf_gige *priv)
 {
 	struct device *dev = &pdev->dev;
+	struct resource *res;
 	int ret;
 
 	priv->mdio_io = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MDIO9);
 	if (IS_ERR(priv->mdio_io))
 		return PTR_ERR(priv->mdio_io);
 
-	/* Configure mdio parameters */
-	writel(MLXBF_GIGE_MDIO_CFG_VAL,
-	       priv->mdio_io + MLXBF_GIGE_MDIO_CFG_OFFSET);
+	/* clk resource shared with other drivers so cannot use
+	 * devm_platform_ioremap_resource
+	 */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_CLK);
+	if (!res) {
+		/* For backward compatibility with older ACPI tables, also keep
+		 * CLK resource internal to the driver.
+		 */
+		res = &corepll_params[MLXBF_GIGE_VERSION_BF2];
+	}
+
+	priv->clk_io = devm_ioremap(dev, res->start, resource_size(res));
+	if (!priv->clk_io)
+		return -ENOMEM;
+
+	mlxbf_gige_mdio_cfg(priv);
 
 	priv->mdiobus = devm_mdiobus_alloc(dev);
 	if (!priv->mdiobus) {
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h
index 5fb33c9294bf..7be3a793984d 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h
@@ -8,6 +8,8 @@
 #ifndef __MLXBF_GIGE_REGS_H__
 #define __MLXBF_GIGE_REGS_H__
 
+#define MLXBF_GIGE_VERSION                            0x0000
+#define MLXBF_GIGE_VERSION_BF2                        0x0
 #define MLXBF_GIGE_STATUS                             0x0010
 #define MLXBF_GIGE_STATUS_READY                       BIT(0)
 #define MLXBF_GIGE_INT_STATUS                         0x0028
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 3548fe1df7c8..987fe5c9d5a3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -21,7 +21,6 @@
 #define MLXSW_THERMAL_ASIC_TEMP_HOT	105000	/* 105C */
 #define MLXSW_THERMAL_HYSTERESIS_TEMP	5000	/* 5C */
 #define MLXSW_THERMAL_MODULE_TEMP_SHIFT	(MLXSW_THERMAL_HYSTERESIS_TEMP * 2)
-#define MLXSW_THERMAL_TEMP_SCORE_MAX	GENMASK(31, 0)
 #define MLXSW_THERMAL_MAX_STATE	10
 #define MLXSW_THERMAL_MIN_STATE	2
 #define MLXSW_THERMAL_MAX_DUTY	255
@@ -101,8 +100,6 @@ struct mlxsw_thermal {
 	struct thermal_cooling_device *cdevs[MLXSW_MFCR_PWMS_MAX];
 	u8 cooling_levels[MLXSW_THERMAL_MAX_STATE + 1];
 	struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
-	unsigned int tz_highest_score;
-	struct thermal_zone_device *tz_highest_dev;
 	struct mlxsw_thermal_area line_cards[];
 };
 
@@ -193,34 +190,6 @@ mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core,
 	return 0;
 }
 
-static void mlxsw_thermal_tz_score_update(struct mlxsw_thermal *thermal,
-					  struct thermal_zone_device *tzdev,
-					  struct mlxsw_thermal_trip *trips,
-					  int temp)
-{
-	struct mlxsw_thermal_trip *trip = trips;
-	unsigned int score, delta, i, shift = 1;
-
-	/* Calculate thermal zone score, if temperature is above the hot
-	 * threshold score is set to MLXSW_THERMAL_TEMP_SCORE_MAX.
-	 */
-	score = MLXSW_THERMAL_TEMP_SCORE_MAX;
-	for (i = MLXSW_THERMAL_TEMP_TRIP_NORM; i < MLXSW_THERMAL_NUM_TRIPS;
-	     i++, trip++) {
-		if (temp < trip->temp) {
-			delta = DIV_ROUND_CLOSEST(temp, trip->temp - temp);
-			score = delta * shift;
-			break;
-		}
-		shift *= 256;
-	}
-
-	if (score > thermal->tz_highest_score) {
-		thermal->tz_highest_score = score;
-		thermal->tz_highest_dev = tzdev;
-	}
-}
-
 static int mlxsw_thermal_bind(struct thermal_zone_device *tzdev,
 			      struct thermal_cooling_device *cdev)
 {
@@ -286,9 +255,6 @@ static int mlxsw_thermal_get_temp(struct thermal_zone_device *tzdev,
 		return err;
 	}
 	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL, NULL, NULL);
-	if (temp > 0)
-		mlxsw_thermal_tz_score_update(thermal, tzdev, thermal->trips,
-					      temp);
 
 	*p_temp = temp;
 	return 0;
@@ -349,21 +315,6 @@ static int mlxsw_thermal_set_trip_hyst(struct thermal_zone_device *tzdev,
 	return 0;
 }
 
-static int mlxsw_thermal_trend_get(struct thermal_zone_device *tzdev,
-				   int trip, enum thermal_trend *trend)
-{
-	struct mlxsw_thermal *thermal = tzdev->devdata;
-
-	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
-		return -EINVAL;
-
-	if (tzdev == thermal->tz_highest_dev)
-		return 1;
-
-	*trend = THERMAL_TREND_STABLE;
-	return 0;
-}
-
 static struct thermal_zone_params mlxsw_thermal_params = {
 	.no_hwmon = true,
 };
@@ -377,7 +328,6 @@ static struct thermal_zone_device_ops mlxsw_thermal_ops = {
 	.set_trip_temp	= mlxsw_thermal_set_trip_temp,
 	.get_trip_hyst	= mlxsw_thermal_get_trip_hyst,
 	.set_trip_hyst	= mlxsw_thermal_set_trip_hyst,
-	.get_trend	= mlxsw_thermal_trend_get,
 };
 
 static int mlxsw_thermal_module_bind(struct thermal_zone_device *tzdev,
@@ -463,7 +413,6 @@ static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
 	int temp, crit_temp, emerg_temp;
 	struct device *dev;
 	u16 sensor_index;
-	int err;
 
 	dev = thermal->bus_info->dev;
 	sensor_index = MLXSW_REG_MTMP_MODULE_INDEX_MIN + tz->module;
@@ -479,10 +428,8 @@ static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
 		return 0;
 
 	/* Update trip points. */
-	err = mlxsw_thermal_module_trips_update(dev, thermal->core, tz,
-						crit_temp, emerg_temp);
-	if (!err && temp > 0)
-		mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
+	mlxsw_thermal_module_trips_update(dev, thermal->core, tz,
+					  crit_temp, emerg_temp);
 
 	return 0;
 }
@@ -546,22 +493,6 @@ mlxsw_thermal_module_trip_hyst_set(struct thermal_zone_device *tzdev, int trip,
 	return 0;
 }
 
-static int mlxsw_thermal_module_trend_get(struct thermal_zone_device *tzdev,
-					  int trip, enum thermal_trend *trend)
-{
-	struct mlxsw_thermal_module *tz = tzdev->devdata;
-	struct mlxsw_thermal *thermal = tz->parent;
-
-	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
-		return -EINVAL;
-
-	if (tzdev == thermal->tz_highest_dev)
-		return 1;
-
-	*trend = THERMAL_TREND_STABLE;
-	return 0;
-}
-
 static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
 	.bind		= mlxsw_thermal_module_bind,
 	.unbind		= mlxsw_thermal_module_unbind,
@@ -571,7 +502,6 @@ static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
 	.set_trip_temp	= mlxsw_thermal_module_trip_temp_set,
 	.get_trip_hyst	= mlxsw_thermal_module_trip_hyst_get,
 	.set_trip_hyst	= mlxsw_thermal_module_trip_hyst_set,
-	.get_trend	= mlxsw_thermal_module_trend_get,
 };
 
 static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
@@ -592,8 +522,6 @@ static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
 		return err;
 
 	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL, NULL, NULL);
-	if (temp > 0)
-		mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
 
 	*p_temp = temp;
 	return 0;
@@ -608,7 +536,6 @@ static struct thermal_zone_device_ops mlxsw_thermal_gearbox_ops = {
 	.set_trip_temp	= mlxsw_thermal_module_trip_temp_set,
 	.get_trip_hyst	= mlxsw_thermal_module_trip_hyst_get,
 	.set_trip_hyst	= mlxsw_thermal_module_trip_hyst_set,
-	.get_trend	= mlxsw_thermal_module_trend_get,
 };
 
 static int mlxsw_thermal_get_max_state(struct thermal_cooling_device *cdev,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 1e240cdd9cbd..30c7b0e15721 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1897,9 +1897,9 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u16 local_port)
 
 	cancel_delayed_work_sync(&mlxsw_sp_port->periodic_hw_stats.update_dw);
 	cancel_delayed_work_sync(&mlxsw_sp_port->ptp.shaper_dw);
-	mlxsw_sp_port_ptp_clear(mlxsw_sp_port);
 	mlxsw_core_port_clear(mlxsw_sp->core, local_port, mlxsw_sp);
 	unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
+	mlxsw_sp_port_ptp_clear(mlxsw_sp_port);
 	mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, true, true);
 	mlxsw_sp->ports[local_port] = NULL;
 	mlxsw_sp_port_vlan_flush(mlxsw_sp_port, true);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
index 2e0b704b8a31..7b01b9c20722 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
@@ -46,6 +46,7 @@ struct mlxsw_sp2_ptp_state {
 					  * enabled.
 					  */
 	struct hwtstamp_config config;
+	struct mutex lock; /* Protects 'config' and HW configuration. */
 };
 
 struct mlxsw_sp1_ptp_key {
@@ -1374,6 +1375,7 @@ struct mlxsw_sp_ptp_state *mlxsw_sp2_ptp_init(struct mlxsw_sp *mlxsw_sp)
 		goto err_ptp_traps_set;
 
 	refcount_set(&ptp_state->ptp_port_enabled_ref, 0);
+	mutex_init(&ptp_state->lock);
 	return &ptp_state->common;
 
 err_ptp_traps_set:
@@ -1388,6 +1390,7 @@ void mlxsw_sp2_ptp_fini(struct mlxsw_sp_ptp_state *ptp_state_common)
 
 	ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp);
 
+	mutex_destroy(&ptp_state->lock);
 	mlxsw_sp_ptp_traps_unset(mlxsw_sp);
 	kfree(ptp_state);
 }
@@ -1461,7 +1464,10 @@ int mlxsw_sp2_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp_port->mlxsw_sp);
 
+	mutex_lock(&ptp_state->lock);
 	*config = ptp_state->config;
+	mutex_unlock(&ptp_state->lock);
+
 	return 0;
 }
 
@@ -1523,6 +1529,9 @@ mlxsw_sp2_ptp_get_message_types(const struct hwtstamp_config *config,
 		return -EINVAL;
 	}
 
+	if ((ing_types && !egr_types) || (!ing_types && egr_types))
+		return -EINVAL;
+
 	*p_ing_types = ing_types;
 	*p_egr_types = egr_types;
 	return 0;
@@ -1574,8 +1583,6 @@ static int mlxsw_sp2_ptp_configure_port(struct mlxsw_sp_port *mlxsw_sp_port,
 	struct mlxsw_sp2_ptp_state *ptp_state;
 	int err;
 
-	ASSERT_RTNL();
-
 	ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp_port->mlxsw_sp);
 
 	if (refcount_inc_not_zero(&ptp_state->ptp_port_enabled_ref))
@@ -1597,8 +1604,6 @@ static int mlxsw_sp2_ptp_deconfigure_port(struct mlxsw_sp_port *mlxsw_sp_port,
 	struct mlxsw_sp2_ptp_state *ptp_state;
 	int err;
 
-	ASSERT_RTNL();
-
 	ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp_port->mlxsw_sp);
 
 	if (!refcount_dec_and_test(&ptp_state->ptp_port_enabled_ref))
@@ -1618,16 +1623,20 @@ err_ptp_disable:
 int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 			       struct hwtstamp_config *config)
 {
+	struct mlxsw_sp2_ptp_state *ptp_state;
 	enum hwtstamp_rx_filters rx_filter;
 	struct hwtstamp_config new_config;
 	u16 new_ing_types, new_egr_types;
 	bool ptp_enabled;
 	int err;
 
+	ptp_state = mlxsw_sp2_ptp_state(mlxsw_sp_port->mlxsw_sp);
+	mutex_lock(&ptp_state->lock);
+
 	err = mlxsw_sp2_ptp_get_message_types(config, &new_ing_types,
 					      &new_egr_types, &rx_filter);
 	if (err)
-		return err;
+		goto err_get_message_types;
 
 	new_config.flags = config->flags;
 	new_config.tx_type = config->tx_type;
@@ -1640,11 +1649,11 @@ int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 		err = mlxsw_sp2_ptp_configure_port(mlxsw_sp_port, new_ing_types,
 						   new_egr_types, new_config);
 		if (err)
-			return err;
+			goto err_configure_port;
 	} else if (!new_ing_types && !new_egr_types && ptp_enabled) {
 		err = mlxsw_sp2_ptp_deconfigure_port(mlxsw_sp_port, new_config);
 		if (err)
-			return err;
+			goto err_deconfigure_port;
 	}
 
 	mlxsw_sp_port->ptp.ing_types = new_ing_types;
@@ -1652,8 +1661,15 @@ int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	/* Notify the ioctl caller what we are actually timestamping. */
 	config->rx_filter = rx_filter;
+	mutex_unlock(&ptp_state->lock);
 
 	return 0;
+
+err_deconfigure_port:
+err_configure_port:
+err_get_message_types:
+	mutex_unlock(&ptp_state->lock);
+	return err;
 }
 
 int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
index 2d1628fdefc1..a8b88230959a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
@@ -171,10 +171,11 @@ static inline void mlxsw_sp1_get_stats(struct mlxsw_sp_port *mlxsw_sp_port,
 {
 }
 
-int mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-				 struct mlxsw_sp_port *mlxsw_sp_port,
-				 struct sk_buff *skb,
-				 const struct mlxsw_tx_info *tx_info)
+static inline int
+mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
+			     struct mlxsw_sp_port *mlxsw_sp_port,
+			     struct sk_buff *skb,
+			     const struct mlxsw_tx_info *tx_info)
 {
 	return -EOPNOTSUPP;
 }
@@ -231,10 +232,11 @@ static inline int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
 	return mlxsw_sp_ptp_get_ts_info_noptp(info);
 }
 
-int mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
-				  struct mlxsw_sp_port *mlxsw_sp_port,
-				  struct sk_buff *skb,
-				  const struct mlxsw_tx_info *tx_info)
+static inline int
+mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
+			      struct mlxsw_sp_port *mlxsw_sp_port,
+			      struct sk_buff *skb,
+			      const struct mlxsw_tx_info *tx_info)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 39904dacf4f0..b3472fb94617 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -423,7 +423,8 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev,
 
 	parms = mlxsw_sp_ipip_netdev_parms4(to_dev);
 	ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp,
-			    0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0);
+			    0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0,
+			    0);
 
 	rt = ip_route_output_key(tun->net, &fl4);
 	if (IS_ERR(rt))
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index 6dea7f8c1481..51f8a0816377 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -425,7 +425,8 @@ static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx)
 	lan966x_ifh_get_src_port(skb->data, &src_port);
 	lan966x_ifh_get_timestamp(skb->data, &timestamp);
 
-	WARN_ON(src_port >= lan966x->num_phys_ports);
+	if (WARN_ON(src_port >= lan966x->num_phys_ports))
+		goto free_skb;
 
 	skb->dev = lan966x->ports[src_port]->dev;
 	skb_pull(skb, IFH_LEN * sizeof(u32));
@@ -449,6 +450,8 @@ static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx)
 
 	return skb;
 
+free_skb:
+	kfree_skb(skb);
 unmap_page:
 	dma_unmap_page(lan966x->dev, (dma_addr_t)db->dataptr,
 		       FDMA_DCB_STATUS_BLOCKL(db->status),
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index 1d6e3b641b2e..d928b75f3780 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -710,7 +710,7 @@ static void lan966x_cleanup_ports(struct lan966x *lan966x)
 	disable_irq(lan966x->xtr_irq);
 	lan966x->xtr_irq = -ENXIO;
 
-	if (lan966x->ana_irq) {
+	if (lan966x->ana_irq > 0) {
 		disable_irq(lan966x->ana_irq);
 		lan966x->ana_irq = -ENXIO;
 	}
@@ -718,10 +718,10 @@ static void lan966x_cleanup_ports(struct lan966x *lan966x)
 	if (lan966x->fdma)
 		devm_free_irq(lan966x->dev, lan966x->fdma_irq, lan966x);
 
-	if (lan966x->ptp_irq)
+	if (lan966x->ptp_irq > 0)
 		devm_free_irq(lan966x->dev, lan966x->ptp_irq, lan966x);
 
-	if (lan966x->ptp_ext_irq)
+	if (lan966x->ptp_ext_irq > 0)
 		devm_free_irq(lan966x->dev, lan966x->ptp_ext_irq, lan966x);
 }
 
@@ -1049,7 +1049,7 @@ static int lan966x_probe(struct platform_device *pdev)
 	}
 
 	lan966x->ana_irq = platform_get_irq_byname(pdev, "ana");
-	if (lan966x->ana_irq) {
+	if (lan966x->ana_irq > 0) {
 		err = devm_request_threaded_irq(&pdev->dev, lan966x->ana_irq, NULL,
 						lan966x_ana_irq_handler, IRQF_ONESHOT,
 						"ana irq", lan966x);
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
index 304f84aadc36..21844beba72d 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
@@ -113,6 +113,8 @@ static void sparx5_xtr_grp(struct sparx5 *sparx5, u8 grp, bool byte_swap)
 			/* This assumes STATUS_WORD_POS == 1, Status
 			 * just after last data
 			 */
+			if (!byte_swap)
+				val = ntohl((__force __be32)val);
 			byte_cnt -= (4 - XTR_VALID_BYTES(val));
 			eof_flag = true;
 			break;
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 5f9240182351..a6f99b4344d9 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -397,6 +397,11 @@ static void mana_gd_process_eq_events(void *arg)
 			break;
 		}
 
+		/* Per GDMA spec, rmb is necessary after checking owner_bits, before
+		 * reading eqe.
+		 */
+		rmb();
+
 		mana_gd_process_eqe(eq);
 
 		eq->head++;
@@ -1134,6 +1139,11 @@ static int mana_gd_read_cqe(struct gdma_queue *cq, struct gdma_comp *comp)
 	if (WARN_ON_ONCE(owner_bits != new_bits))
 		return -1;
 
+	/* Per GDMA spec, rmb is necessary after checking owner_bits, before
+	 * reading completion info
+	 */
+	rmb();
+
 	comp->wq_num = cqe->cqe_info.wq_num;
 	comp->is_sq = cqe->cqe_info.is_sq;
 	memcpy(comp->cqe_data, cqe->cqe_data, GDMA_COMP_DATA_SIZE);
@@ -1465,10 +1475,6 @@ static void mana_gd_shutdown(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 }
 
-#ifndef PCI_VENDOR_ID_MICROSOFT
-#define PCI_VENDOR_ID_MICROSOFT 0x1414
-#endif
-
 static const struct pci_device_id mana_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_MICROSOFT, MANA_PF_DEVICE_ID) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MICROSOFT, MANA_VF_DEVICE_ID) },
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index a3214a762e4b..9e57d23e57bf 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -62,9 +62,6 @@ static int moxart_set_mac_address(struct net_device *ndev, void *addr)
 {
 	struct sockaddr *address = addr;
 
-	if (!is_valid_ether_addr(address->sa_data))
-		return -EADDRNOTAVAIL;
-
 	eth_hw_addr_set(ndev, address->sa_data);
 	moxart_update_mac_address(ndev);
 
@@ -74,11 +71,6 @@ static int moxart_set_mac_address(struct net_device *ndev, void *addr)
 static void moxart_mac_free_memory(struct net_device *ndev)
 {
 	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
-	int i;
-
-	for (i = 0; i < RX_DESC_NUM; i++)
-		dma_unmap_single(&ndev->dev, priv->rx_mapping[i],
-				 priv->rx_buf_size, DMA_FROM_DEVICE);
 
 	if (priv->tx_desc_base)
 		dma_free_coherent(&priv->pdev->dev,
@@ -147,11 +139,11 @@ static void moxart_mac_setup_desc_ring(struct net_device *ndev)
 		       desc + RX_REG_OFFSET_DESC1);
 
 		priv->rx_buf[i] = priv->rx_buf_base + priv->rx_buf_size * i;
-		priv->rx_mapping[i] = dma_map_single(&ndev->dev,
+		priv->rx_mapping[i] = dma_map_single(&priv->pdev->dev,
 						     priv->rx_buf[i],
 						     priv->rx_buf_size,
 						     DMA_FROM_DEVICE);
-		if (dma_mapping_error(&ndev->dev, priv->rx_mapping[i]))
+		if (dma_mapping_error(&priv->pdev->dev, priv->rx_mapping[i]))
 			netdev_err(ndev, "DMA mapping error\n");
 
 		moxart_desc_write(priv->rx_mapping[i],
@@ -172,9 +164,6 @@ static int moxart_mac_open(struct net_device *ndev)
 {
 	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
 
-	if (!is_valid_ether_addr(ndev->dev_addr))
-		return -EADDRNOTAVAIL;
-
 	napi_enable(&priv->napi);
 
 	moxart_mac_reset(ndev);
@@ -193,6 +182,7 @@ static int moxart_mac_open(struct net_device *ndev)
 static int moxart_mac_stop(struct net_device *ndev)
 {
 	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
+	int i;
 
 	napi_disable(&priv->napi);
 
@@ -204,6 +194,11 @@ static int moxart_mac_stop(struct net_device *ndev)
 	/* disable all functions */
 	writel(0, priv->base + REG_MAC_CTRL);
 
+	/* unmap areas mapped in moxart_mac_setup_desc_ring() */
+	for (i = 0; i < RX_DESC_NUM; i++)
+		dma_unmap_single(&priv->pdev->dev, priv->rx_mapping[i],
+				 priv->rx_buf_size, DMA_FROM_DEVICE);
+
 	return 0;
 }
 
@@ -240,7 +235,7 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget)
 		if (len > RX_BUF_SIZE)
 			len = RX_BUF_SIZE;
 
-		dma_sync_single_for_cpu(&ndev->dev,
+		dma_sync_single_for_cpu(&priv->pdev->dev,
 					priv->rx_mapping[rx_head],
 					priv->rx_buf_size, DMA_FROM_DEVICE);
 		skb = netdev_alloc_skb_ip_align(ndev, len);
@@ -294,7 +289,7 @@ static void moxart_tx_finished(struct net_device *ndev)
 	unsigned int tx_tail = priv->tx_tail;
 
 	while (tx_tail != tx_head) {
-		dma_unmap_single(&ndev->dev, priv->tx_mapping[tx_tail],
+		dma_unmap_single(&priv->pdev->dev, priv->tx_mapping[tx_tail],
 				 priv->tx_len[tx_tail], DMA_TO_DEVICE);
 
 		ndev->stats.tx_packets++;
@@ -358,9 +353,9 @@ static netdev_tx_t moxart_mac_start_xmit(struct sk_buff *skb,
 
 	len = skb->len > TX_BUF_SIZE ? TX_BUF_SIZE : skb->len;
 
-	priv->tx_mapping[tx_head] = dma_map_single(&ndev->dev, skb->data,
+	priv->tx_mapping[tx_head] = dma_map_single(&priv->pdev->dev, skb->data,
 						   len, DMA_TO_DEVICE);
-	if (dma_mapping_error(&ndev->dev, priv->tx_mapping[tx_head])) {
+	if (dma_mapping_error(&priv->pdev->dev, priv->tx_mapping[tx_head])) {
 		netdev_err(ndev, "DMA mapping error\n");
 		goto out_unlock;
 	}
@@ -379,7 +374,7 @@ static netdev_tx_t moxart_mac_start_xmit(struct sk_buff *skb,
 		len = ETH_ZLEN;
 	}
 
-	dma_sync_single_for_device(&ndev->dev, priv->tx_mapping[tx_head],
+	dma_sync_single_for_device(&priv->pdev->dev, priv->tx_mapping[tx_head],
 				   priv->tx_buf_size, DMA_TO_DEVICE);
 
 	txdes1 = TX_DESC1_LTS | TX_DESC1_FTS | (len & TX_DESC1_BUF_SIZE_MASK);
@@ -488,12 +483,19 @@ static int moxart_mac_probe(struct platform_device *pdev)
 	}
 	ndev->base_addr = res->start;
 
+	ret = platform_get_ethdev_address(p_dev, ndev);
+	if (ret == -EPROBE_DEFER)
+		goto init_fail;
+	if (ret)
+		eth_hw_addr_random(ndev);
+	moxart_update_mac_address(ndev);
+
 	spin_lock_init(&priv->txlock);
 
 	priv->tx_buf_size = TX_BUF_SIZE;
 	priv->rx_buf_size = RX_BUF_SIZE;
 
-	priv->tx_desc_base = dma_alloc_coherent(&pdev->dev, TX_REG_DESC_SIZE *
+	priv->tx_desc_base = dma_alloc_coherent(p_dev, TX_REG_DESC_SIZE *
 						TX_DESC_NUM, &priv->tx_base,
 						GFP_DMA | GFP_KERNEL);
 	if (!priv->tx_desc_base) {
@@ -501,7 +503,7 @@ static int moxart_mac_probe(struct platform_device *pdev)
 		goto init_fail;
 	}
 
-	priv->rx_desc_base = dma_alloc_coherent(&pdev->dev, RX_REG_DESC_SIZE *
+	priv->rx_desc_base = dma_alloc_coherent(p_dev, RX_REG_DESC_SIZE *
 						RX_DESC_NUM, &priv->rx_base,
 						GFP_DMA | GFP_KERNEL);
 	if (!priv->rx_desc_base) {
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index d4649e4ee0e7..8f8005bc6eea 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -290,6 +290,13 @@ static int ocelot_port_num_untagged_vlans(struct ocelot *ocelot, int port)
 		if (!(vlan->portmask & BIT(port)))
 			continue;
 
+		/* Ignore the VLAN added by ocelot_add_vlan_unaware_pvid(),
+		 * because this is never active in hardware at the same time as
+		 * the bridge VLANs, which only matter in VLAN-aware mode.
+		 */
+		if (vlan->vid >= OCELOT_RSV_VLAN_RANGE_START)
+			continue;
+
 		if (vlan->untagged & BIT(port))
 			num_untagged++;
 	}
@@ -1860,16 +1867,20 @@ void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data)
 	if (sset != ETH_SS_STATS)
 		return;
 
-	for (i = 0; i < ocelot->num_stats; i++)
+	for (i = 0; i < OCELOT_NUM_STATS; i++) {
+		if (ocelot->stats_layout[i].name[0] == '\0')
+			continue;
+
 		memcpy(data + i * ETH_GSTRING_LEN, ocelot->stats_layout[i].name,
 		       ETH_GSTRING_LEN);
+	}
 }
 EXPORT_SYMBOL(ocelot_get_strings);
 
 /* Caller must hold &ocelot->stats_lock */
 static int ocelot_port_update_stats(struct ocelot *ocelot, int port)
 {
-	unsigned int idx = port * ocelot->num_stats;
+	unsigned int idx = port * OCELOT_NUM_STATS;
 	struct ocelot_stats_region *region;
 	int err, j;
 
@@ -1877,9 +1888,8 @@ static int ocelot_port_update_stats(struct ocelot *ocelot, int port)
 	ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(port), SYS_STAT_CFG);
 
 	list_for_each_entry(region, &ocelot->stats_regions, node) {
-		err = ocelot_bulk_read_rix(ocelot, SYS_COUNT_RX_OCTETS,
-					   region->offset, region->buf,
-					   region->count);
+		err = ocelot_bulk_read(ocelot, region->base, region->buf,
+				       region->count);
 		if (err)
 			return err;
 
@@ -1906,13 +1916,13 @@ static void ocelot_check_stats_work(struct work_struct *work)
 					     stats_work);
 	int i, err;
 
-	mutex_lock(&ocelot->stats_lock);
+	spin_lock(&ocelot->stats_lock);
 	for (i = 0; i < ocelot->num_phys_ports; i++) {
 		err = ocelot_port_update_stats(ocelot, i);
 		if (err)
 			break;
 	}
-	mutex_unlock(&ocelot->stats_lock);
+	spin_unlock(&ocelot->stats_lock);
 
 	if (err)
 		dev_err(ocelot->dev, "Error %d updating ethtool stats\n",  err);
@@ -1925,16 +1935,22 @@ void ocelot_get_ethtool_stats(struct ocelot *ocelot, int port, u64 *data)
 {
 	int i, err;
 
-	mutex_lock(&ocelot->stats_lock);
+	spin_lock(&ocelot->stats_lock);
 
 	/* check and update now */
 	err = ocelot_port_update_stats(ocelot, port);
 
-	/* Copy all counters */
-	for (i = 0; i < ocelot->num_stats; i++)
-		*data++ = ocelot->stats[port * ocelot->num_stats + i];
+	/* Copy all supported counters */
+	for (i = 0; i < OCELOT_NUM_STATS; i++) {
+		int index = port * OCELOT_NUM_STATS + i;
 
-	mutex_unlock(&ocelot->stats_lock);
+		if (ocelot->stats_layout[i].name[0] == '\0')
+			continue;
+
+		*data++ = ocelot->stats[index];
+	}
+
+	spin_unlock(&ocelot->stats_lock);
 
 	if (err)
 		dev_err(ocelot->dev, "Error %d updating ethtool stats\n", err);
@@ -1943,10 +1959,16 @@ EXPORT_SYMBOL(ocelot_get_ethtool_stats);
 
 int ocelot_get_sset_count(struct ocelot *ocelot, int port, int sset)
 {
+	int i, num_stats = 0;
+
 	if (sset != ETH_SS_STATS)
 		return -EOPNOTSUPP;
 
-	return ocelot->num_stats;
+	for (i = 0; i < OCELOT_NUM_STATS; i++)
+		if (ocelot->stats_layout[i].name[0] != '\0')
+			num_stats++;
+
+	return num_stats;
 }
 EXPORT_SYMBOL(ocelot_get_sset_count);
 
@@ -1958,8 +1980,11 @@ static int ocelot_prepare_stats_regions(struct ocelot *ocelot)
 
 	INIT_LIST_HEAD(&ocelot->stats_regions);
 
-	for (i = 0; i < ocelot->num_stats; i++) {
-		if (region && ocelot->stats_layout[i].offset == last + 1) {
+	for (i = 0; i < OCELOT_NUM_STATS; i++) {
+		if (ocelot->stats_layout[i].name[0] == '\0')
+			continue;
+
+		if (region && ocelot->stats_layout[i].reg == last + 4) {
 			region->count++;
 		} else {
 			region = devm_kzalloc(ocelot->dev, sizeof(*region),
@@ -1967,12 +1992,12 @@ static int ocelot_prepare_stats_regions(struct ocelot *ocelot)
 			if (!region)
 				return -ENOMEM;
 
-			region->offset = ocelot->stats_layout[i].offset;
+			region->base = ocelot->stats_layout[i].reg;
 			region->count = 1;
 			list_add_tail(&region->node, &ocelot->stats_regions);
 		}
 
-		last = ocelot->stats_layout[i].offset;
+		last = ocelot->stats_layout[i].reg;
 	}
 
 	list_for_each_entry(region, &ocelot->stats_regions, node) {
@@ -3340,7 +3365,6 @@ static void ocelot_detect_features(struct ocelot *ocelot)
 
 int ocelot_init(struct ocelot *ocelot)
 {
-	const struct ocelot_stat_layout *stat;
 	char queue_name[32];
 	int i, ret;
 	u32 port;
@@ -3353,17 +3377,13 @@ int ocelot_init(struct ocelot *ocelot)
 		}
 	}
 
-	ocelot->num_stats = 0;
-	for_each_stat(ocelot, stat)
-		ocelot->num_stats++;
-
 	ocelot->stats = devm_kcalloc(ocelot->dev,
-				     ocelot->num_phys_ports * ocelot->num_stats,
+				     ocelot->num_phys_ports * OCELOT_NUM_STATS,
 				     sizeof(u64), GFP_KERNEL);
 	if (!ocelot->stats)
 		return -ENOMEM;
 
-	mutex_init(&ocelot->stats_lock);
+	spin_lock_init(&ocelot->stats_lock);
 	mutex_init(&ocelot->ptp_lock);
 	mutex_init(&ocelot->mact_lock);
 	mutex_init(&ocelot->fwd_domain_lock);
@@ -3511,7 +3531,6 @@ void ocelot_deinit(struct ocelot *ocelot)
 	cancel_delayed_work(&ocelot->stats_work);
 	destroy_workqueue(ocelot->stats_queue);
 	destroy_workqueue(ocelot->owq);
-	mutex_destroy(&ocelot->stats_lock);
 }
 EXPORT_SYMBOL(ocelot_deinit);
 
diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c
index 5e6136e80282..330d30841cdc 100644
--- a/drivers/net/ethernet/mscc/ocelot_net.c
+++ b/drivers/net/ethernet/mscc/ocelot_net.c
@@ -725,37 +725,42 @@ static void ocelot_get_stats64(struct net_device *dev,
 	struct ocelot_port_private *priv = netdev_priv(dev);
 	struct ocelot *ocelot = priv->port.ocelot;
 	int port = priv->port.index;
+	u64 *s;
 
-	/* Configure the port to read the stats from */
-	ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(port),
-		     SYS_STAT_CFG);
+	spin_lock(&ocelot->stats_lock);
+
+	s = &ocelot->stats[port * OCELOT_NUM_STATS];
 
 	/* Get Rx stats */
-	stats->rx_bytes = ocelot_read(ocelot, SYS_COUNT_RX_OCTETS);
-	stats->rx_packets = ocelot_read(ocelot, SYS_COUNT_RX_SHORTS) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_FRAGMENTS) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_JABBERS) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_LONGS) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_64) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_65_127) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_128_255) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_256_1023) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_1024_1526) +
-			    ocelot_read(ocelot, SYS_COUNT_RX_1527_MAX);
-	stats->multicast = ocelot_read(ocelot, SYS_COUNT_RX_MULTICAST);
+	stats->rx_bytes = s[OCELOT_STAT_RX_OCTETS];
+	stats->rx_packets = s[OCELOT_STAT_RX_SHORTS] +
+			    s[OCELOT_STAT_RX_FRAGMENTS] +
+			    s[OCELOT_STAT_RX_JABBERS] +
+			    s[OCELOT_STAT_RX_LONGS] +
+			    s[OCELOT_STAT_RX_64] +
+			    s[OCELOT_STAT_RX_65_127] +
+			    s[OCELOT_STAT_RX_128_255] +
+			    s[OCELOT_STAT_RX_256_511] +
+			    s[OCELOT_STAT_RX_512_1023] +
+			    s[OCELOT_STAT_RX_1024_1526] +
+			    s[OCELOT_STAT_RX_1527_MAX];
+	stats->multicast = s[OCELOT_STAT_RX_MULTICAST];
 	stats->rx_dropped = dev->stats.rx_dropped;
 
 	/* Get Tx stats */
-	stats->tx_bytes = ocelot_read(ocelot, SYS_COUNT_TX_OCTETS);
-	stats->tx_packets = ocelot_read(ocelot, SYS_COUNT_TX_64) +
-			    ocelot_read(ocelot, SYS_COUNT_TX_65_127) +
-			    ocelot_read(ocelot, SYS_COUNT_TX_128_511) +
-			    ocelot_read(ocelot, SYS_COUNT_TX_512_1023) +
-			    ocelot_read(ocelot, SYS_COUNT_TX_1024_1526) +
-			    ocelot_read(ocelot, SYS_COUNT_TX_1527_MAX);
-	stats->tx_dropped = ocelot_read(ocelot, SYS_COUNT_TX_DROPS) +
-			    ocelot_read(ocelot, SYS_COUNT_TX_AGING);
-	stats->collisions = ocelot_read(ocelot, SYS_COUNT_TX_COLLISION);
+	stats->tx_bytes = s[OCELOT_STAT_TX_OCTETS];
+	stats->tx_packets = s[OCELOT_STAT_TX_64] +
+			    s[OCELOT_STAT_TX_65_127] +
+			    s[OCELOT_STAT_TX_128_255] +
+			    s[OCELOT_STAT_TX_256_511] +
+			    s[OCELOT_STAT_TX_512_1023] +
+			    s[OCELOT_STAT_TX_1024_1526] +
+			    s[OCELOT_STAT_TX_1527_MAX];
+	stats->tx_dropped = s[OCELOT_STAT_TX_DROPS] +
+			    s[OCELOT_STAT_TX_AGED];
+	stats->collisions = s[OCELOT_STAT_TX_COLLISION];
+
+	spin_unlock(&ocelot->stats_lock);
 }
 
 static int ocelot_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index 961f803aca19..9c488953f541 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -96,101 +96,379 @@ static const struct reg_field ocelot_regfields[REGFIELD_MAX] = {
 	[SYS_PAUSE_CFG_PAUSE_ENA] = REG_FIELD_ID(SYS_PAUSE_CFG, 0, 1, 12, 4),
 };
 
-static const struct ocelot_stat_layout ocelot_stats_layout[] = {
-	{ .name = "rx_octets", .offset = 0x00, },
-	{ .name = "rx_unicast", .offset = 0x01, },
-	{ .name = "rx_multicast", .offset = 0x02, },
-	{ .name = "rx_broadcast", .offset = 0x03, },
-	{ .name = "rx_shorts", .offset = 0x04, },
-	{ .name = "rx_fragments", .offset = 0x05, },
-	{ .name = "rx_jabbers", .offset = 0x06, },
-	{ .name = "rx_crc_align_errs", .offset = 0x07, },
-	{ .name = "rx_sym_errs", .offset = 0x08, },
-	{ .name = "rx_frames_below_65_octets", .offset = 0x09, },
-	{ .name = "rx_frames_65_to_127_octets", .offset = 0x0A, },
-	{ .name = "rx_frames_128_to_255_octets", .offset = 0x0B, },
-	{ .name = "rx_frames_256_to_511_octets", .offset = 0x0C, },
-	{ .name = "rx_frames_512_to_1023_octets", .offset = 0x0D, },
-	{ .name = "rx_frames_1024_to_1526_octets", .offset = 0x0E, },
-	{ .name = "rx_frames_over_1526_octets", .offset = 0x0F, },
-	{ .name = "rx_pause", .offset = 0x10, },
-	{ .name = "rx_control", .offset = 0x11, },
-	{ .name = "rx_longs", .offset = 0x12, },
-	{ .name = "rx_classified_drops", .offset = 0x13, },
-	{ .name = "rx_red_prio_0", .offset = 0x14, },
-	{ .name = "rx_red_prio_1", .offset = 0x15, },
-	{ .name = "rx_red_prio_2", .offset = 0x16, },
-	{ .name = "rx_red_prio_3", .offset = 0x17, },
-	{ .name = "rx_red_prio_4", .offset = 0x18, },
-	{ .name = "rx_red_prio_5", .offset = 0x19, },
-	{ .name = "rx_red_prio_6", .offset = 0x1A, },
-	{ .name = "rx_red_prio_7", .offset = 0x1B, },
-	{ .name = "rx_yellow_prio_0", .offset = 0x1C, },
-	{ .name = "rx_yellow_prio_1", .offset = 0x1D, },
-	{ .name = "rx_yellow_prio_2", .offset = 0x1E, },
-	{ .name = "rx_yellow_prio_3", .offset = 0x1F, },
-	{ .name = "rx_yellow_prio_4", .offset = 0x20, },
-	{ .name = "rx_yellow_prio_5", .offset = 0x21, },
-	{ .name = "rx_yellow_prio_6", .offset = 0x22, },
-	{ .name = "rx_yellow_prio_7", .offset = 0x23, },
-	{ .name = "rx_green_prio_0", .offset = 0x24, },
-	{ .name = "rx_green_prio_1", .offset = 0x25, },
-	{ .name = "rx_green_prio_2", .offset = 0x26, },
-	{ .name = "rx_green_prio_3", .offset = 0x27, },
-	{ .name = "rx_green_prio_4", .offset = 0x28, },
-	{ .name = "rx_green_prio_5", .offset = 0x29, },
-	{ .name = "rx_green_prio_6", .offset = 0x2A, },
-	{ .name = "rx_green_prio_7", .offset = 0x2B, },
-	{ .name = "tx_octets", .offset = 0x40, },
-	{ .name = "tx_unicast", .offset = 0x41, },
-	{ .name = "tx_multicast", .offset = 0x42, },
-	{ .name = "tx_broadcast", .offset = 0x43, },
-	{ .name = "tx_collision", .offset = 0x44, },
-	{ .name = "tx_drops", .offset = 0x45, },
-	{ .name = "tx_pause", .offset = 0x46, },
-	{ .name = "tx_frames_below_65_octets", .offset = 0x47, },
-	{ .name = "tx_frames_65_to_127_octets", .offset = 0x48, },
-	{ .name = "tx_frames_128_255_octets", .offset = 0x49, },
-	{ .name = "tx_frames_256_511_octets", .offset = 0x4A, },
-	{ .name = "tx_frames_512_1023_octets", .offset = 0x4B, },
-	{ .name = "tx_frames_1024_1526_octets", .offset = 0x4C, },
-	{ .name = "tx_frames_over_1526_octets", .offset = 0x4D, },
-	{ .name = "tx_yellow_prio_0", .offset = 0x4E, },
-	{ .name = "tx_yellow_prio_1", .offset = 0x4F, },
-	{ .name = "tx_yellow_prio_2", .offset = 0x50, },
-	{ .name = "tx_yellow_prio_3", .offset = 0x51, },
-	{ .name = "tx_yellow_prio_4", .offset = 0x52, },
-	{ .name = "tx_yellow_prio_5", .offset = 0x53, },
-	{ .name = "tx_yellow_prio_6", .offset = 0x54, },
-	{ .name = "tx_yellow_prio_7", .offset = 0x55, },
-	{ .name = "tx_green_prio_0", .offset = 0x56, },
-	{ .name = "tx_green_prio_1", .offset = 0x57, },
-	{ .name = "tx_green_prio_2", .offset = 0x58, },
-	{ .name = "tx_green_prio_3", .offset = 0x59, },
-	{ .name = "tx_green_prio_4", .offset = 0x5A, },
-	{ .name = "tx_green_prio_5", .offset = 0x5B, },
-	{ .name = "tx_green_prio_6", .offset = 0x5C, },
-	{ .name = "tx_green_prio_7", .offset = 0x5D, },
-	{ .name = "tx_aged", .offset = 0x5E, },
-	{ .name = "drop_local", .offset = 0x80, },
-	{ .name = "drop_tail", .offset = 0x81, },
-	{ .name = "drop_yellow_prio_0", .offset = 0x82, },
-	{ .name = "drop_yellow_prio_1", .offset = 0x83, },
-	{ .name = "drop_yellow_prio_2", .offset = 0x84, },
-	{ .name = "drop_yellow_prio_3", .offset = 0x85, },
-	{ .name = "drop_yellow_prio_4", .offset = 0x86, },
-	{ .name = "drop_yellow_prio_5", .offset = 0x87, },
-	{ .name = "drop_yellow_prio_6", .offset = 0x88, },
-	{ .name = "drop_yellow_prio_7", .offset = 0x89, },
-	{ .name = "drop_green_prio_0", .offset = 0x8A, },
-	{ .name = "drop_green_prio_1", .offset = 0x8B, },
-	{ .name = "drop_green_prio_2", .offset = 0x8C, },
-	{ .name = "drop_green_prio_3", .offset = 0x8D, },
-	{ .name = "drop_green_prio_4", .offset = 0x8E, },
-	{ .name = "drop_green_prio_5", .offset = 0x8F, },
-	{ .name = "drop_green_prio_6", .offset = 0x90, },
-	{ .name = "drop_green_prio_7", .offset = 0x91, },
-	OCELOT_STAT_END
+static const struct ocelot_stat_layout ocelot_stats_layout[OCELOT_NUM_STATS] = {
+	[OCELOT_STAT_RX_OCTETS] = {
+		.name = "rx_octets",
+		.reg = SYS_COUNT_RX_OCTETS,
+	},
+	[OCELOT_STAT_RX_UNICAST] = {
+		.name = "rx_unicast",
+		.reg = SYS_COUNT_RX_UNICAST,
+	},
+	[OCELOT_STAT_RX_MULTICAST] = {
+		.name = "rx_multicast",
+		.reg = SYS_COUNT_RX_MULTICAST,
+	},
+	[OCELOT_STAT_RX_BROADCAST] = {
+		.name = "rx_broadcast",
+		.reg = SYS_COUNT_RX_BROADCAST,
+	},
+	[OCELOT_STAT_RX_SHORTS] = {
+		.name = "rx_shorts",
+		.reg = SYS_COUNT_RX_SHORTS,
+	},
+	[OCELOT_STAT_RX_FRAGMENTS] = {
+		.name = "rx_fragments",
+		.reg = SYS_COUNT_RX_FRAGMENTS,
+	},
+	[OCELOT_STAT_RX_JABBERS] = {
+		.name = "rx_jabbers",
+		.reg = SYS_COUNT_RX_JABBERS,
+	},
+	[OCELOT_STAT_RX_CRC_ALIGN_ERRS] = {
+		.name = "rx_crc_align_errs",
+		.reg = SYS_COUNT_RX_CRC_ALIGN_ERRS,
+	},
+	[OCELOT_STAT_RX_SYM_ERRS] = {
+		.name = "rx_sym_errs",
+		.reg = SYS_COUNT_RX_SYM_ERRS,
+	},
+	[OCELOT_STAT_RX_64] = {
+		.name = "rx_frames_below_65_octets",
+		.reg = SYS_COUNT_RX_64,
+	},
+	[OCELOT_STAT_RX_65_127] = {
+		.name = "rx_frames_65_to_127_octets",
+		.reg = SYS_COUNT_RX_65_127,
+	},
+	[OCELOT_STAT_RX_128_255] = {
+		.name = "rx_frames_128_to_255_octets",
+		.reg = SYS_COUNT_RX_128_255,
+	},
+	[OCELOT_STAT_RX_256_511] = {
+		.name = "rx_frames_256_to_511_octets",
+		.reg = SYS_COUNT_RX_256_511,
+	},
+	[OCELOT_STAT_RX_512_1023] = {
+		.name = "rx_frames_512_to_1023_octets",
+		.reg = SYS_COUNT_RX_512_1023,
+	},
+	[OCELOT_STAT_RX_1024_1526] = {
+		.name = "rx_frames_1024_to_1526_octets",
+		.reg = SYS_COUNT_RX_1024_1526,
+	},
+	[OCELOT_STAT_RX_1527_MAX] = {
+		.name = "rx_frames_over_1526_octets",
+		.reg = SYS_COUNT_RX_1527_MAX,
+	},
+	[OCELOT_STAT_RX_PAUSE] = {
+		.name = "rx_pause",
+		.reg = SYS_COUNT_RX_PAUSE,
+	},
+	[OCELOT_STAT_RX_CONTROL] = {
+		.name = "rx_control",
+		.reg = SYS_COUNT_RX_CONTROL,
+	},
+	[OCELOT_STAT_RX_LONGS] = {
+		.name = "rx_longs",
+		.reg = SYS_COUNT_RX_LONGS,
+	},
+	[OCELOT_STAT_RX_CLASSIFIED_DROPS] = {
+		.name = "rx_classified_drops",
+		.reg = SYS_COUNT_RX_CLASSIFIED_DROPS,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_0] = {
+		.name = "rx_red_prio_0",
+		.reg = SYS_COUNT_RX_RED_PRIO_0,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_1] = {
+		.name = "rx_red_prio_1",
+		.reg = SYS_COUNT_RX_RED_PRIO_1,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_2] = {
+		.name = "rx_red_prio_2",
+		.reg = SYS_COUNT_RX_RED_PRIO_2,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_3] = {
+		.name = "rx_red_prio_3",
+		.reg = SYS_COUNT_RX_RED_PRIO_3,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_4] = {
+		.name = "rx_red_prio_4",
+		.reg = SYS_COUNT_RX_RED_PRIO_4,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_5] = {
+		.name = "rx_red_prio_5",
+		.reg = SYS_COUNT_RX_RED_PRIO_5,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_6] = {
+		.name = "rx_red_prio_6",
+		.reg = SYS_COUNT_RX_RED_PRIO_6,
+	},
+	[OCELOT_STAT_RX_RED_PRIO_7] = {
+		.name = "rx_red_prio_7",
+		.reg = SYS_COUNT_RX_RED_PRIO_7,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_0] = {
+		.name = "rx_yellow_prio_0",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_1] = {
+		.name = "rx_yellow_prio_1",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_2] = {
+		.name = "rx_yellow_prio_2",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_3] = {
+		.name = "rx_yellow_prio_3",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_4] = {
+		.name = "rx_yellow_prio_4",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_5] = {
+		.name = "rx_yellow_prio_5",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_6] = {
+		.name = "rx_yellow_prio_6",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_RX_YELLOW_PRIO_7] = {
+		.name = "rx_yellow_prio_7",
+		.reg = SYS_COUNT_RX_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_0] = {
+		.name = "rx_green_prio_0",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_1] = {
+		.name = "rx_green_prio_1",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_2] = {
+		.name = "rx_green_prio_2",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_3] = {
+		.name = "rx_green_prio_3",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_4] = {
+		.name = "rx_green_prio_4",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_5] = {
+		.name = "rx_green_prio_5",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_6] = {
+		.name = "rx_green_prio_6",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_RX_GREEN_PRIO_7] = {
+		.name = "rx_green_prio_7",
+		.reg = SYS_COUNT_RX_GREEN_PRIO_7,
+	},
+	[OCELOT_STAT_TX_OCTETS] = {
+		.name = "tx_octets",
+		.reg = SYS_COUNT_TX_OCTETS,
+	},
+	[OCELOT_STAT_TX_UNICAST] = {
+		.name = "tx_unicast",
+		.reg = SYS_COUNT_TX_UNICAST,
+	},
+	[OCELOT_STAT_TX_MULTICAST] = {
+		.name = "tx_multicast",
+		.reg = SYS_COUNT_TX_MULTICAST,
+	},
+	[OCELOT_STAT_TX_BROADCAST] = {
+		.name = "tx_broadcast",
+		.reg = SYS_COUNT_TX_BROADCAST,
+	},
+	[OCELOT_STAT_TX_COLLISION] = {
+		.name = "tx_collision",
+		.reg = SYS_COUNT_TX_COLLISION,
+	},
+	[OCELOT_STAT_TX_DROPS] = {
+		.name = "tx_drops",
+		.reg = SYS_COUNT_TX_DROPS,
+	},
+	[OCELOT_STAT_TX_PAUSE] = {
+		.name = "tx_pause",
+		.reg = SYS_COUNT_TX_PAUSE,
+	},
+	[OCELOT_STAT_TX_64] = {
+		.name = "tx_frames_below_65_octets",
+		.reg = SYS_COUNT_TX_64,
+	},
+	[OCELOT_STAT_TX_65_127] = {
+		.name = "tx_frames_65_to_127_octets",
+		.reg = SYS_COUNT_TX_65_127,
+	},
+	[OCELOT_STAT_TX_128_255] = {
+		.name = "tx_frames_128_255_octets",
+		.reg = SYS_COUNT_TX_128_255,
+	},
+	[OCELOT_STAT_TX_256_511] = {
+		.name = "tx_frames_256_511_octets",
+		.reg = SYS_COUNT_TX_256_511,
+	},
+	[OCELOT_STAT_TX_512_1023] = {
+		.name = "tx_frames_512_1023_octets",
+		.reg = SYS_COUNT_TX_512_1023,
+	},
+	[OCELOT_STAT_TX_1024_1526] = {
+		.name = "tx_frames_1024_1526_octets",
+		.reg = SYS_COUNT_TX_1024_1526,
+	},
+	[OCELOT_STAT_TX_1527_MAX] = {
+		.name = "tx_frames_over_1526_octets",
+		.reg = SYS_COUNT_TX_1527_MAX,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_0] = {
+		.name = "tx_yellow_prio_0",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_1] = {
+		.name = "tx_yellow_prio_1",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_2] = {
+		.name = "tx_yellow_prio_2",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_3] = {
+		.name = "tx_yellow_prio_3",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_4] = {
+		.name = "tx_yellow_prio_4",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_5] = {
+		.name = "tx_yellow_prio_5",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_6] = {
+		.name = "tx_yellow_prio_6",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_TX_YELLOW_PRIO_7] = {
+		.name = "tx_yellow_prio_7",
+		.reg = SYS_COUNT_TX_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_0] = {
+		.name = "tx_green_prio_0",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_1] = {
+		.name = "tx_green_prio_1",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_2] = {
+		.name = "tx_green_prio_2",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_3] = {
+		.name = "tx_green_prio_3",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_4] = {
+		.name = "tx_green_prio_4",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_5] = {
+		.name = "tx_green_prio_5",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_6] = {
+		.name = "tx_green_prio_6",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_TX_GREEN_PRIO_7] = {
+		.name = "tx_green_prio_7",
+		.reg = SYS_COUNT_TX_GREEN_PRIO_7,
+	},
+	[OCELOT_STAT_TX_AGED] = {
+		.name = "tx_aged",
+		.reg = SYS_COUNT_TX_AGING,
+	},
+	[OCELOT_STAT_DROP_LOCAL] = {
+		.name = "drop_local",
+		.reg = SYS_COUNT_DROP_LOCAL,
+	},
+	[OCELOT_STAT_DROP_TAIL] = {
+		.name = "drop_tail",
+		.reg = SYS_COUNT_DROP_TAIL,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_0] = {
+		.name = "drop_yellow_prio_0",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_0,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_1] = {
+		.name = "drop_yellow_prio_1",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_1,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_2] = {
+		.name = "drop_yellow_prio_2",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_2,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_3] = {
+		.name = "drop_yellow_prio_3",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_3,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_4] = {
+		.name = "drop_yellow_prio_4",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_4,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_5] = {
+		.name = "drop_yellow_prio_5",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_5,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_6] = {
+		.name = "drop_yellow_prio_6",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_6,
+	},
+	[OCELOT_STAT_DROP_YELLOW_PRIO_7] = {
+		.name = "drop_yellow_prio_7",
+		.reg = SYS_COUNT_DROP_YELLOW_PRIO_7,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_0] = {
+		.name = "drop_green_prio_0",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_0,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_1] = {
+		.name = "drop_green_prio_1",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_1,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_2] = {
+		.name = "drop_green_prio_2",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_2,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_3] = {
+		.name = "drop_green_prio_3",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_3,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_4] = {
+		.name = "drop_green_prio_4",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_4,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_5] = {
+		.name = "drop_green_prio_5",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_5,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_6] = {
+		.name = "drop_green_prio_6",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_6,
+	},
+	[OCELOT_STAT_DROP_GREEN_PRIO_7] = {
+		.name = "drop_green_prio_7",
+		.reg = SYS_COUNT_DROP_GREEN_PRIO_7,
+	},
 };
 
 static void ocelot_pll5_init(struct ocelot *ocelot)
diff --git a/drivers/net/ethernet/mscc/vsc7514_regs.c b/drivers/net/ethernet/mscc/vsc7514_regs.c
index c2af4eb8ca5d..9cf82ecf191c 100644
--- a/drivers/net/ethernet/mscc/vsc7514_regs.c
+++ b/drivers/net/ethernet/mscc/vsc7514_regs.c
@@ -180,13 +180,38 @@ const u32 vsc7514_sys_regmap[] = {
 	REG(SYS_COUNT_RX_64,				0x000024),
 	REG(SYS_COUNT_RX_65_127,			0x000028),
 	REG(SYS_COUNT_RX_128_255,			0x00002c),
-	REG(SYS_COUNT_RX_256_1023,			0x000030),
-	REG(SYS_COUNT_RX_1024_1526,			0x000034),
-	REG(SYS_COUNT_RX_1527_MAX,			0x000038),
-	REG(SYS_COUNT_RX_PAUSE,				0x00003c),
-	REG(SYS_COUNT_RX_CONTROL,			0x000040),
-	REG(SYS_COUNT_RX_LONGS,				0x000044),
-	REG(SYS_COUNT_RX_CLASSIFIED_DROPS,		0x000048),
+	REG(SYS_COUNT_RX_256_511,			0x000030),
+	REG(SYS_COUNT_RX_512_1023,			0x000034),
+	REG(SYS_COUNT_RX_1024_1526,			0x000038),
+	REG(SYS_COUNT_RX_1527_MAX,			0x00003c),
+	REG(SYS_COUNT_RX_PAUSE,				0x000040),
+	REG(SYS_COUNT_RX_CONTROL,			0x000044),
+	REG(SYS_COUNT_RX_LONGS,				0x000048),
+	REG(SYS_COUNT_RX_CLASSIFIED_DROPS,		0x00004c),
+	REG(SYS_COUNT_RX_RED_PRIO_0,			0x000050),
+	REG(SYS_COUNT_RX_RED_PRIO_1,			0x000054),
+	REG(SYS_COUNT_RX_RED_PRIO_2,			0x000058),
+	REG(SYS_COUNT_RX_RED_PRIO_3,			0x00005c),
+	REG(SYS_COUNT_RX_RED_PRIO_4,			0x000060),
+	REG(SYS_COUNT_RX_RED_PRIO_5,			0x000064),
+	REG(SYS_COUNT_RX_RED_PRIO_6,			0x000068),
+	REG(SYS_COUNT_RX_RED_PRIO_7,			0x00006c),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_0,			0x000070),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_1,			0x000074),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_2,			0x000078),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_3,			0x00007c),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_4,			0x000080),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_5,			0x000084),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_6,			0x000088),
+	REG(SYS_COUNT_RX_YELLOW_PRIO_7,			0x00008c),
+	REG(SYS_COUNT_RX_GREEN_PRIO_0,			0x000090),
+	REG(SYS_COUNT_RX_GREEN_PRIO_1,			0x000094),
+	REG(SYS_COUNT_RX_GREEN_PRIO_2,			0x000098),
+	REG(SYS_COUNT_RX_GREEN_PRIO_3,			0x00009c),
+	REG(SYS_COUNT_RX_GREEN_PRIO_4,			0x0000a0),
+	REG(SYS_COUNT_RX_GREEN_PRIO_5,			0x0000a4),
+	REG(SYS_COUNT_RX_GREEN_PRIO_6,			0x0000a8),
+	REG(SYS_COUNT_RX_GREEN_PRIO_7,			0x0000ac),
 	REG(SYS_COUNT_TX_OCTETS,			0x000100),
 	REG(SYS_COUNT_TX_UNICAST,			0x000104),
 	REG(SYS_COUNT_TX_MULTICAST,			0x000108),
@@ -196,11 +221,46 @@ const u32 vsc7514_sys_regmap[] = {
 	REG(SYS_COUNT_TX_PAUSE,				0x000118),
 	REG(SYS_COUNT_TX_64,				0x00011c),
 	REG(SYS_COUNT_TX_65_127,			0x000120),
-	REG(SYS_COUNT_TX_128_511,			0x000124),
-	REG(SYS_COUNT_TX_512_1023,			0x000128),
-	REG(SYS_COUNT_TX_1024_1526,			0x00012c),
-	REG(SYS_COUNT_TX_1527_MAX,			0x000130),
-	REG(SYS_COUNT_TX_AGING,				0x000170),
+	REG(SYS_COUNT_TX_128_255,			0x000124),
+	REG(SYS_COUNT_TX_256_511,			0x000128),
+	REG(SYS_COUNT_TX_512_1023,			0x00012c),
+	REG(SYS_COUNT_TX_1024_1526,			0x000130),
+	REG(SYS_COUNT_TX_1527_MAX,			0x000134),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_0,			0x000138),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_1,			0x00013c),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_2,			0x000140),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_3,			0x000144),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_4,			0x000148),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_5,			0x00014c),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_6,			0x000150),
+	REG(SYS_COUNT_TX_YELLOW_PRIO_7,			0x000154),
+	REG(SYS_COUNT_TX_GREEN_PRIO_0,			0x000158),
+	REG(SYS_COUNT_TX_GREEN_PRIO_1,			0x00015c),
+	REG(SYS_COUNT_TX_GREEN_PRIO_2,			0x000160),
+	REG(SYS_COUNT_TX_GREEN_PRIO_3,			0x000164),
+	REG(SYS_COUNT_TX_GREEN_PRIO_4,			0x000168),
+	REG(SYS_COUNT_TX_GREEN_PRIO_5,			0x00016c),
+	REG(SYS_COUNT_TX_GREEN_PRIO_6,			0x000170),
+	REG(SYS_COUNT_TX_GREEN_PRIO_7,			0x000174),
+	REG(SYS_COUNT_TX_AGING,				0x000178),
+	REG(SYS_COUNT_DROP_LOCAL,			0x000200),
+	REG(SYS_COUNT_DROP_TAIL,			0x000204),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_0,		0x000208),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_1,		0x00020c),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_2,		0x000210),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_3,		0x000214),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_4,		0x000218),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_5,		0x00021c),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_6,		0x000220),
+	REG(SYS_COUNT_DROP_YELLOW_PRIO_7,		0x000214),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_0,		0x000218),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_1,		0x00021c),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_2,		0x000220),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_3,		0x000224),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_4,		0x000228),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_5,		0x00022c),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_6,		0x000230),
+	REG(SYS_COUNT_DROP_GREEN_PRIO_7,		0x000234),
 	REG(SYS_RESET_CFG,				0x000508),
 	REG(SYS_CMID,					0x00050c),
 	REG(SYS_VLAN_ETYPE_CFG,				0x000510),
diff --git a/drivers/net/ethernet/netronome/nfp/flower/qos_conf.c b/drivers/net/ethernet/netronome/nfp/flower/qos_conf.c
index 4e5df9f2c372..7b92026e1a6f 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/qos_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/qos_conf.c
@@ -127,10 +127,11 @@ static int nfp_policer_validate(const struct flow_action *action,
 		return -EOPNOTSUPP;
 	}
 
-	if (act->police.notexceed.act_id != FLOW_ACTION_PIPE &&
+	if (act->police.notexceed.act_id != FLOW_ACTION_CONTINUE &&
+	    act->police.notexceed.act_id != FLOW_ACTION_PIPE &&
 	    act->police.notexceed.act_id != FLOW_ACTION_ACCEPT) {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "Offload not supported when conform action is not pipe or ok");
+				   "Offload not supported when conform action is not continue, pipe or ok");
 		return -EOPNOTSUPP;
 	}
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index cf4d6f1129fa..349a2b1a19a2 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1630,21 +1630,21 @@ static void nfp_net_stat64(struct net_device *netdev,
 		unsigned int start;
 
 		do {
-			start = u64_stats_fetch_begin(&r_vec->rx_sync);
+			start = u64_stats_fetch_begin_irq(&r_vec->rx_sync);
 			data[0] = r_vec->rx_pkts;
 			data[1] = r_vec->rx_bytes;
 			data[2] = r_vec->rx_drops;
-		} while (u64_stats_fetch_retry(&r_vec->rx_sync, start));
+		} while (u64_stats_fetch_retry_irq(&r_vec->rx_sync, start));
 		stats->rx_packets += data[0];
 		stats->rx_bytes += data[1];
 		stats->rx_dropped += data[2];
 
 		do {
-			start = u64_stats_fetch_begin(&r_vec->tx_sync);
+			start = u64_stats_fetch_begin_irq(&r_vec->tx_sync);
 			data[0] = r_vec->tx_pkts;
 			data[1] = r_vec->tx_bytes;
 			data[2] = r_vec->tx_errors;
-		} while (u64_stats_fetch_retry(&r_vec->tx_sync, start));
+		} while (u64_stats_fetch_retry_irq(&r_vec->tx_sync, start));
 		stats->tx_packets += data[0];
 		stats->tx_bytes += data[1];
 		stats->tx_errors += data[2];
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index eeb1455a4e5d..b1b1b648e40c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -649,7 +649,7 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data)
 		unsigned int start;
 
 		do {
-			start = u64_stats_fetch_begin(&nn->r_vecs[i].rx_sync);
+			start = u64_stats_fetch_begin_irq(&nn->r_vecs[i].rx_sync);
 			data[0] = nn->r_vecs[i].rx_pkts;
 			tmp[0] = nn->r_vecs[i].hw_csum_rx_ok;
 			tmp[1] = nn->r_vecs[i].hw_csum_rx_inner_ok;
@@ -657,10 +657,10 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data)
 			tmp[3] = nn->r_vecs[i].hw_csum_rx_error;
 			tmp[4] = nn->r_vecs[i].rx_replace_buf_alloc_fail;
 			tmp[5] = nn->r_vecs[i].hw_tls_rx;
-		} while (u64_stats_fetch_retry(&nn->r_vecs[i].rx_sync, start));
+		} while (u64_stats_fetch_retry_irq(&nn->r_vecs[i].rx_sync, start));
 
 		do {
-			start = u64_stats_fetch_begin(&nn->r_vecs[i].tx_sync);
+			start = u64_stats_fetch_begin_irq(&nn->r_vecs[i].tx_sync);
 			data[1] = nn->r_vecs[i].tx_pkts;
 			data[2] = nn->r_vecs[i].tx_busy;
 			tmp[6] = nn->r_vecs[i].hw_csum_tx;
@@ -670,7 +670,7 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data)
 			tmp[10] = nn->r_vecs[i].hw_tls_tx;
 			tmp[11] = nn->r_vecs[i].tls_tx_fallback;
 			tmp[12] = nn->r_vecs[i].tls_tx_no_fallback;
-		} while (u64_stats_fetch_retry(&nn->r_vecs[i].tx_sync, start));
+		} while (u64_stats_fetch_retry_irq(&nn->r_vecs[i].tx_sync, start));
 
 		data += NN_RVEC_PER_Q_STATS;
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
index edd300033735..4cc38799eabc 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
@@ -507,6 +507,7 @@ int nfp_eth_set_idmode(struct nfp_cpp *cpp, unsigned int idx, bool state)
 	if (nfp_nsp_get_abi_ver_minor(nsp) < 32) {
 		nfp_err(nfp_nsp_cpp(nsp),
 			"set id mode operation not supported, please update flash\n");
+		nfp_eth_config_cleanup_end(nsp);
 		return -EOPNOTSUPP;
 	}
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 1443f788ee37..0be79c516781 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -1564,8 +1564,67 @@ static int ionic_set_features(struct net_device *netdev,
 	return err;
 }
 
+static int ionic_set_attr_mac(struct ionic_lif *lif, u8 *mac)
+{
+	struct ionic_admin_ctx ctx = {
+		.work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
+		.cmd.lif_setattr = {
+			.opcode = IONIC_CMD_LIF_SETATTR,
+			.index = cpu_to_le16(lif->index),
+			.attr = IONIC_LIF_ATTR_MAC,
+		},
+	};
+
+	ether_addr_copy(ctx.cmd.lif_setattr.mac, mac);
+	return ionic_adminq_post_wait(lif, &ctx);
+}
+
+static int ionic_get_attr_mac(struct ionic_lif *lif, u8 *mac_addr)
+{
+	struct ionic_admin_ctx ctx = {
+		.work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
+		.cmd.lif_getattr = {
+			.opcode = IONIC_CMD_LIF_GETATTR,
+			.index = cpu_to_le16(lif->index),
+			.attr = IONIC_LIF_ATTR_MAC,
+		},
+	};
+	int err;
+
+	err = ionic_adminq_post_wait(lif, &ctx);
+	if (err)
+		return err;
+
+	ether_addr_copy(mac_addr, ctx.comp.lif_getattr.mac);
+	return 0;
+}
+
+static int ionic_program_mac(struct ionic_lif *lif, u8 *mac)
+{
+	u8  get_mac[ETH_ALEN];
+	int err;
+
+	err = ionic_set_attr_mac(lif, mac);
+	if (err)
+		return err;
+
+	err = ionic_get_attr_mac(lif, get_mac);
+	if (err)
+		return err;
+
+	/* To deal with older firmware that silently ignores the set attr mac:
+	 * doesn't actually change the mac and doesn't return an error, so we
+	 * do the get attr to verify whether or not the set actually happened
+	 */
+	if (!ether_addr_equal(get_mac, mac))
+		return 1;
+
+	return 0;
+}
+
 static int ionic_set_mac_address(struct net_device *netdev, void *sa)
 {
+	struct ionic_lif *lif = netdev_priv(netdev);
 	struct sockaddr *addr = sa;
 	u8 *mac;
 	int err;
@@ -1574,6 +1633,14 @@ static int ionic_set_mac_address(struct net_device *netdev, void *sa)
 	if (ether_addr_equal(netdev->dev_addr, mac))
 		return 0;
 
+	err = ionic_program_mac(lif, mac);
+	if (err < 0)
+		return err;
+
+	if (err > 0)
+		netdev_dbg(netdev, "%s: SET and GET ATTR Mac are not equal-due to old FW running\n",
+			   __func__);
+
 	err = eth_prepare_mac_addr_change(netdev, addr);
 	if (err)
 		return err;
@@ -2963,6 +3030,9 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif)
 
 	mutex_lock(&lif->queue_lock);
 
+	if (test_and_clear_bit(IONIC_LIF_F_BROKEN, lif->state))
+		dev_info(ionic->dev, "FW Up: clearing broken state\n");
+
 	err = ionic_qcqs_alloc(lif);
 	if (err)
 		goto err_unlock;
@@ -3169,6 +3239,7 @@ static int ionic_station_set(struct ionic_lif *lif)
 			.attr = IONIC_LIF_ATTR_MAC,
 		},
 	};
+	u8 mac_address[ETH_ALEN];
 	struct sockaddr addr;
 	int err;
 
@@ -3177,8 +3248,23 @@ static int ionic_station_set(struct ionic_lif *lif)
 		return err;
 	netdev_dbg(lif->netdev, "found initial MAC addr %pM\n",
 		   ctx.comp.lif_getattr.mac);
-	if (is_zero_ether_addr(ctx.comp.lif_getattr.mac))
-		return 0;
+	ether_addr_copy(mac_address, ctx.comp.lif_getattr.mac);
+
+	if (is_zero_ether_addr(mac_address)) {
+		eth_hw_addr_random(netdev);
+		netdev_dbg(netdev, "Random Mac generated: %pM\n", netdev->dev_addr);
+		ether_addr_copy(mac_address, netdev->dev_addr);
+
+		err = ionic_program_mac(lif, mac_address);
+		if (err < 0)
+			return err;
+
+		if (err > 0) {
+			netdev_dbg(netdev, "%s:SET/GET ATTR Mac are not same-due to old FW running\n",
+				   __func__);
+			return 0;
+		}
+	}
 
 	if (!is_zero_ether_addr(netdev->dev_addr)) {
 		/* If the netdev mac is non-zero and doesn't match the default
@@ -3186,12 +3272,11 @@ static int ionic_station_set(struct ionic_lif *lif)
 		 * likely here again after a fw-upgrade reset.  We need to be
 		 * sure the netdev mac is in our filter list.
 		 */
-		if (!ether_addr_equal(ctx.comp.lif_getattr.mac,
-				      netdev->dev_addr))
+		if (!ether_addr_equal(mac_address, netdev->dev_addr))
 			ionic_lif_addr_add(lif, netdev->dev_addr);
 	} else {
 		/* Update the netdev mac with the device's mac */
-		memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len);
+		ether_addr_copy(addr.sa_data, mac_address);
 		addr.sa_family = AF_INET;
 		err = eth_prepare_mac_addr_change(netdev, &addr);
 		if (err) {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index 4029b4e021f8..56f93b030551 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -474,8 +474,8 @@ try_again:
 				ionic_opcode_to_str(opcode), opcode,
 				ionic_error_to_str(err), err);
 
-			msleep(1000);
 			iowrite32(0, &idev->dev_cmd_regs->done);
+			msleep(1000);
 			iowrite32(1, &idev->dev_cmd_regs->doorbell);
 			goto try_again;
 		}
@@ -488,6 +488,8 @@ try_again:
 		return ionic_error_to_errno(err);
 	}
 
+	ionic_dev_cmd_clean(ionic);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index b357ac4c56c5..7e32b04eb0c7 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1449,6 +1449,8 @@ static int ravb_phy_init(struct net_device *ndev)
 		phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT);
 	}
 
+	/* Indicate that the MAC is responsible for managing PHY PM */
+	phydev->mac_managed_pm = true;
 	phy_attached_info(phydev);
 
 	return 0;
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 67ade78fb767..7fd8828d3a84 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -2029,6 +2029,8 @@ static int sh_eth_phy_init(struct net_device *ndev)
 	if (mdp->cd->register_type != SH_ETH_REG_GIGABIT)
 		phy_set_max_speed(phydev, SPEED_100);
 
+	/* Indicate that the MAC is responsible for managing PHY PM */
+	phydev->mac_managed_pm = true;
 	phy_attached_info(phydev);
 
 	return 0;
diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c
index bc70c6abd6a5..58cf7cc54f40 100644
--- a/drivers/net/ethernet/rocker/rocker_ofdpa.c
+++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c
@@ -1273,7 +1273,7 @@ static int ofdpa_port_ipv4_neigh(struct ofdpa_port *ofdpa_port,
 	bool removing;
 	int err = 0;
 
-	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
 	if (!entry)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index ee734b69150f..d1e1aa19a68e 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -4213,7 +4213,7 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
 	.ev_test_generate = efx_ef10_ev_test_generate,
 	.filter_table_probe = efx_ef10_filter_table_probe,
 	.filter_table_restore = efx_mcdi_filter_table_restore,
-	.filter_table_remove = efx_mcdi_filter_table_remove,
+	.filter_table_remove = efx_ef10_filter_table_remove,
 	.filter_update_rx_scatter = efx_mcdi_update_rx_scatter,
 	.filter_insert = efx_mcdi_filter_insert,
 	.filter_remove_safe = efx_mcdi_filter_remove_safe,
diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c
index 032b8c0bd788..5b4d661ab986 100644
--- a/drivers/net/ethernet/sfc/efx_channels.c
+++ b/drivers/net/ethernet/sfc/efx_channels.c
@@ -319,7 +319,7 @@ int efx_probe_interrupts(struct efx_nic *efx)
 		efx->n_channels = 1 + (efx_separate_tx_channels ? 1 : 0);
 		efx->n_rx_channels = 1;
 		efx->n_tx_channels = 1;
-		efx->tx_channel_offset = 1;
+		efx->tx_channel_offset = efx_separate_tx_channels ? 1 : 0;
 		efx->n_xdp_channels = 0;
 		efx->xdp_channel_offset = efx->n_channels;
 		efx->legacy_irq = efx->pci_dev->irq;
diff --git a/drivers/net/ethernet/sfc/siena/efx_channels.c b/drivers/net/ethernet/sfc/siena/efx_channels.c
index 017212a40df3..f54ebd007286 100644
--- a/drivers/net/ethernet/sfc/siena/efx_channels.c
+++ b/drivers/net/ethernet/sfc/siena/efx_channels.c
@@ -320,7 +320,7 @@ int efx_siena_probe_interrupts(struct efx_nic *efx)
 		efx->n_channels = 1 + (efx_siena_separate_tx_channels ? 1 : 0);
 		efx->n_rx_channels = 1;
 		efx->n_tx_channels = 1;
-		efx->tx_channel_offset = 1;
+		efx->tx_channel_offset = efx_siena_separate_tx_channels ? 1 : 0;
 		efx->n_xdp_channels = 0;
 		efx->xdp_channel_offset = efx->n_channels;
 		efx->legacy_irq = efx->pci_dev->irq;
diff --git a/drivers/net/ethernet/sfc/siena/tx.c b/drivers/net/ethernet/sfc/siena/tx.c
index e166dcb9b99c..91e87594ed1e 100644
--- a/drivers/net/ethernet/sfc/siena/tx.c
+++ b/drivers/net/ethernet/sfc/siena/tx.c
@@ -336,7 +336,7 @@ netdev_tx_t efx_siena_hard_start_xmit(struct sk_buff *skb,
 		 * previous packets out.
 		 */
 		if (!netdev_xmit_more())
-			efx_tx_send_pending(tx_queue->channel);
+			efx_tx_send_pending(efx_get_tx_channel(efx, index));
 		return NETDEV_TX_OK;
 	}
 
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index d12474042c84..c5f88f7a7a04 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -549,7 +549,7 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb,
 		 * previous packets out.
 		 */
 		if (!netdev_xmit_more())
-			efx_tx_send_pending(tx_queue->channel);
+			efx_tx_send_pending(efx_get_tx_channel(efx, index));
 		return NETDEV_TX_OK;
 	}
 
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 3bf20211cceb..3829c2805b16 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -1037,6 +1037,8 @@ static int smsc911x_mii_probe(struct net_device *dev)
 		return ret;
 	}
 
+	/* Indicate that the MAC is responsible for managing PHY PM */
+	phydev->mac_managed_pm = true;
 	phy_attached_info(phydev);
 
 	phy_set_max_speed(phydev, SPEED_100);
@@ -2587,6 +2589,8 @@ static int smsc911x_suspend(struct device *dev)
 	if (netif_running(ndev)) {
 		netif_stop_queue(ndev);
 		netif_device_detach(ndev);
+		if (!device_may_wakeup(dev))
+			phy_stop(ndev->phydev);
 	}
 
 	/* enable wake on LAN, energy detection and the external PME
@@ -2628,6 +2632,8 @@ static int smsc911x_resume(struct device *dev)
 	if (netif_running(ndev)) {
 		netif_device_attach(ndev);
 		netif_start_queue(ndev);
+		if (!device_may_wakeup(dev))
+			phy_start(ndev->phydev);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 52f9ed8db9c9..9af25be42401 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -1134,9 +1134,8 @@ static void intel_eth_pci_remove(struct pci_dev *pdev)
 
 	stmmac_dvr_remove(&pdev->dev);
 
+	clk_disable_unprepare(priv->plat->stmmac_clk);
 	clk_unregister_fixed_rate(priv->plat->stmmac_clk);
-
-	pcim_iounmap_regions(pdev, BIT(0));
 }
 
 static int __maybe_unused intel_eth_pci_suspend(struct device *dev)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index caa4bfc4c1d6..9b6138b11776 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -258,14 +258,18 @@ EXPORT_SYMBOL_GPL(stmmac_set_mac_addr);
 /* Enable disable MAC RX/TX */
 void stmmac_set_mac(void __iomem *ioaddr, bool enable)
 {
-	u32 value = readl(ioaddr + MAC_CTRL_REG);
+	u32 old_val, value;
+
+	old_val = readl(ioaddr + MAC_CTRL_REG);
+	value = old_val;
 
 	if (enable)
 		value |= MAC_ENABLE_RX | MAC_ENABLE_TX;
 	else
 		value &= ~(MAC_ENABLE_TX | MAC_ENABLE_RX);
 
-	writel(value, ioaddr + MAC_CTRL_REG);
+	if (value != old_val)
+		writel(value, ioaddr + MAC_CTRL_REG);
 }
 
 void stmmac_get_mac_addr(void __iomem *ioaddr, unsigned char *addr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 070b5ef165eb..9083159b93f1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -986,10 +986,10 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 			       bool tx_pause, bool rx_pause)
 {
 	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
-	u32 ctrl;
+	u32 old_ctrl, ctrl;
 
-	ctrl = readl(priv->ioaddr + MAC_CTRL_REG);
-	ctrl &= ~priv->hw->link.speed_mask;
+	old_ctrl = readl(priv->ioaddr + MAC_CTRL_REG);
+	ctrl = old_ctrl & ~priv->hw->link.speed_mask;
 
 	if (interface == PHY_INTERFACE_MODE_USXGMII) {
 		switch (speed) {
@@ -1064,7 +1064,8 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 	if (tx_pause && rx_pause)
 		stmmac_mac_flow_ctrl(priv, duplex);
 
-	writel(ctrl, priv->ioaddr + MAC_CTRL_REG);
+	if (ctrl != old_ctrl)
+		writel(ctrl, priv->ioaddr + MAC_CTRL_REG);
 
 	stmmac_mac_set(priv, priv->ioaddr, true);
 	if (phy && priv->dma_cap.eee) {
@@ -3800,6 +3801,15 @@ static int __stmmac_open(struct net_device *dev,
 
 	stmmac_reset_queues_param(priv);
 
+	if (priv->plat->serdes_powerup) {
+		ret = priv->plat->serdes_powerup(dev, priv->plat->bsp_priv);
+		if (ret < 0) {
+			netdev_err(priv->dev, "%s: Serdes powerup failed\n",
+				   __func__);
+			goto init_error;
+		}
+	}
+
 	ret = stmmac_hw_setup(dev, true);
 	if (ret < 0) {
 		netdev_err(priv->dev, "%s: Hw setup failed\n", __func__);
@@ -3903,6 +3913,10 @@ static int stmmac_release(struct net_device *dev)
 	/* Disable the MAC Rx/Tx */
 	stmmac_mac_set(priv, priv->ioaddr, false);
 
+	/* Powerdown Serdes if there is */
+	if (priv->plat->serdes_powerdown)
+		priv->plat->serdes_powerdown(dev, priv->plat->bsp_priv);
+
 	netif_carrier_off(dev);
 
 	stmmac_release_ptp(priv);
@@ -7292,14 +7306,6 @@ int stmmac_dvr_probe(struct device *device,
 		goto error_netdev_register;
 	}
 
-	if (priv->plat->serdes_powerup) {
-		ret = priv->plat->serdes_powerup(ndev,
-						 priv->plat->bsp_priv);
-
-		if (ret < 0)
-			goto error_serdes_powerup;
-	}
-
 #ifdef CONFIG_DEBUG_FS
 	stmmac_init_fs(ndev);
 #endif
@@ -7314,8 +7320,6 @@ int stmmac_dvr_probe(struct device *device,
 
 	return ret;
 
-error_serdes_powerup:
-	unregister_netdev(ndev);
 error_netdev_register:
 	phylink_destroy(priv->phylink);
 error_xpcs_setup:
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index 8594ee839628..88aa0d310aee 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -2020,9 +2020,9 @@ static void happy_meal_rx(struct happy_meal *hp, struct net_device *dev)
 
 			skb_reserve(copy_skb, 2);
 			skb_put(copy_skb, len);
-			dma_sync_single_for_cpu(hp->dma_dev, dma_addr, len, DMA_FROM_DEVICE);
+			dma_sync_single_for_cpu(hp->dma_dev, dma_addr, len + 2, DMA_FROM_DEVICE);
 			skb_copy_from_linear_data(skb, copy_skb->data, len);
-			dma_sync_single_for_device(hp->dma_dev, dma_addr, len, DMA_FROM_DEVICE);
+			dma_sync_single_for_device(hp->dma_dev, dma_addr, len + 2, DMA_FROM_DEVICE);
 			/* Reuse original ring buffer. */
 			hme_write_rxd(hp, this,
 				      (RXFLAG_OWN|((RX_BUF_ALLOC_SIZE-RX_OFFSET)<<16)),
diff --git a/drivers/net/fddi/skfp/h/hwmtm.h b/drivers/net/fddi/skfp/h/hwmtm.h
index 76c4a709d73d..e97db826cdd4 100644
--- a/drivers/net/fddi/skfp/h/hwmtm.h
+++ b/drivers/net/fddi/skfp/h/hwmtm.h
@@ -348,7 +348,7 @@ do {									\
  *		This macro is invoked by the OS-specific before it left the
  *		function mac_drv_rx_complete. This macro calls mac_drv_fill_rxd
  *		if the number of used RxDs is equal or lower than the
- *		the given low water mark.
+ *		given low water mark.
  *
  * para	low_water	low water mark of used RxD's
  *
diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c
index 74e845fa2e07..aa8f828a0ae7 100644
--- a/drivers/net/hippi/rrunner.c
+++ b/drivers/net/hippi/rrunner.c
@@ -213,6 +213,7 @@ static int rr_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		pci_iounmap(pdev, rrpriv->regs);
 	if (pdev)
 		pci_release_regions(pdev);
+	pci_disable_device(pdev);
  out2:
 	free_netdev(dev);
  out3:
diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c
index 6afdf1622944..5cf218c674a5 100644
--- a/drivers/net/ieee802154/adf7242.c
+++ b/drivers/net/ieee802154/adf7242.c
@@ -1310,10 +1310,11 @@ static void adf7242_remove(struct spi_device *spi)
 
 	debugfs_remove_recursive(lp->debugfs_root);
 
+	ieee802154_unregister_hw(lp->hw);
+
 	cancel_delayed_work_sync(&lp->work);
 	destroy_workqueue(lp->wqueue);
 
-	ieee802154_unregister_hw(lp->hw);
 	mutex_destroy(&lp->bmux);
 	ieee802154_free_hw(lp->hw);
 }
diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c
index 42c0b451088d..450b16ad40a4 100644
--- a/drivers/net/ieee802154/ca8210.c
+++ b/drivers/net/ieee802154/ca8210.c
@@ -2293,7 +2293,7 @@ static int ca8210_set_csma_params(
  * @retries:  Number of retries
  *
  * Sets the number of times to retry a transmission if no acknowledgment was
- * was received from the other end when one was requested.
+ * received from the other end when one was requested.
  *
  * Return: 0 or linux error code
  */
diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c
index 1e1f40f628a0..c69b87d3837d 100644
--- a/drivers/net/ieee802154/cc2520.c
+++ b/drivers/net/ieee802154/cc2520.c
@@ -504,6 +504,7 @@ cc2520_tx(struct ieee802154_hw *hw, struct sk_buff *skb)
 		goto err_tx;
 
 	if (status & CC2520_STATUS_TX_UNDERFLOW) {
+		rc = -EINVAL;
 		dev_err(&priv->spi->dev, "cc2520 tx underflow exception\n");
 		goto err_tx;
 	}
diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c
index 1e9eae208e44..53a1dbeaffa6 100644
--- a/drivers/net/ipa/ipa_mem.c
+++ b/drivers/net/ipa/ipa_mem.c
@@ -568,7 +568,7 @@ static int ipa_smem_init(struct ipa *ipa, u32 item, size_t size)
 	}
 
 	/* Align the address down and the size up to a page boundary */
-	addr = qcom_smem_virt_to_phys(virt) & PAGE_MASK;
+	addr = qcom_smem_virt_to_phys(virt);
 	phys = addr & PAGE_MASK;
 	size = PAGE_ALIGN(size + addr - phys);
 	iova = phys;	/* We just want a direct mapping */
diff --git a/drivers/net/ipa/ipa_qmi.c b/drivers/net/ipa/ipa_qmi.c
index ec010cf2e816..6f874f99b910 100644
--- a/drivers/net/ipa/ipa_qmi.c
+++ b/drivers/net/ipa/ipa_qmi.c
@@ -308,12 +308,12 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi)
 	mem = ipa_mem_find(ipa, IPA_MEM_V4_ROUTE);
 	req.v4_route_tbl_info_valid = 1;
 	req.v4_route_tbl_info.start = ipa->mem_offset + mem->offset;
-	req.v4_route_tbl_info.count = mem->size / sizeof(__le64);
+	req.v4_route_tbl_info.end = IPA_ROUTE_MODEM_COUNT - 1;
 
 	mem = ipa_mem_find(ipa, IPA_MEM_V6_ROUTE);
 	req.v6_route_tbl_info_valid = 1;
 	req.v6_route_tbl_info.start = ipa->mem_offset + mem->offset;
-	req.v6_route_tbl_info.count = mem->size / sizeof(__le64);
+	req.v6_route_tbl_info.end = IPA_ROUTE_MODEM_COUNT - 1;
 
 	mem = ipa_mem_find(ipa, IPA_MEM_V4_FILTER);
 	req.v4_filter_tbl_start_valid = 1;
@@ -352,7 +352,7 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi)
 		req.v4_hash_route_tbl_info_valid = 1;
 		req.v4_hash_route_tbl_info.start =
 				ipa->mem_offset + mem->offset;
-		req.v4_hash_route_tbl_info.count = mem->size / sizeof(__le64);
+		req.v4_hash_route_tbl_info.end = IPA_ROUTE_MODEM_COUNT - 1;
 	}
 
 	mem = ipa_mem_find(ipa, IPA_MEM_V6_ROUTE_HASHED);
@@ -360,7 +360,7 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi)
 		req.v6_hash_route_tbl_info_valid = 1;
 		req.v6_hash_route_tbl_info.start =
 			ipa->mem_offset + mem->offset;
-		req.v6_hash_route_tbl_info.count = mem->size / sizeof(__le64);
+		req.v6_hash_route_tbl_info.end = IPA_ROUTE_MODEM_COUNT - 1;
 	}
 
 	mem = ipa_mem_find(ipa, IPA_MEM_V4_FILTER_HASHED);
diff --git a/drivers/net/ipa/ipa_qmi_msg.c b/drivers/net/ipa/ipa_qmi_msg.c
index 6838e8065072..75d3fc0092e9 100644
--- a/drivers/net/ipa/ipa_qmi_msg.c
+++ b/drivers/net/ipa/ipa_qmi_msg.c
@@ -311,7 +311,7 @@ struct qmi_elem_info ipa_init_modem_driver_req_ei[] = {
 		.tlv_type	= 0x12,
 		.offset		= offsetof(struct ipa_init_modem_driver_req,
 					   v4_route_tbl_info),
-		.ei_array	= ipa_mem_array_ei,
+		.ei_array	= ipa_mem_bounds_ei,
 	},
 	{
 		.data_type	= QMI_OPT_FLAG,
@@ -332,7 +332,7 @@ struct qmi_elem_info ipa_init_modem_driver_req_ei[] = {
 		.tlv_type	= 0x13,
 		.offset		= offsetof(struct ipa_init_modem_driver_req,
 					   v6_route_tbl_info),
-		.ei_array	= ipa_mem_array_ei,
+		.ei_array	= ipa_mem_bounds_ei,
 	},
 	{
 		.data_type	= QMI_OPT_FLAG,
@@ -496,7 +496,7 @@ struct qmi_elem_info ipa_init_modem_driver_req_ei[] = {
 		.tlv_type	= 0x1b,
 		.offset		= offsetof(struct ipa_init_modem_driver_req,
 					   v4_hash_route_tbl_info),
-		.ei_array	= ipa_mem_array_ei,
+		.ei_array	= ipa_mem_bounds_ei,
 	},
 	{
 		.data_type	= QMI_OPT_FLAG,
@@ -517,7 +517,7 @@ struct qmi_elem_info ipa_init_modem_driver_req_ei[] = {
 		.tlv_type	= 0x1c,
 		.offset		= offsetof(struct ipa_init_modem_driver_req,
 					   v6_hash_route_tbl_info),
-		.ei_array	= ipa_mem_array_ei,
+		.ei_array	= ipa_mem_bounds_ei,
 	},
 	{
 		.data_type	= QMI_OPT_FLAG,
diff --git a/drivers/net/ipa/ipa_qmi_msg.h b/drivers/net/ipa/ipa_qmi_msg.h
index 495e85abe50b..9651aa59b596 100644
--- a/drivers/net/ipa/ipa_qmi_msg.h
+++ b/drivers/net/ipa/ipa_qmi_msg.h
@@ -86,9 +86,11 @@ enum ipa_platform_type {
 	IPA_QMI_PLATFORM_TYPE_MSM_QNX_V01	= 0x5,	/* QNX MSM */
 };
 
-/* This defines the start and end offset of a range of memory.  Both
- * fields are offsets relative to the start of IPA shared memory.
- * The end value is the last addressable byte *within* the range.
+/* This defines the start and end offset of a range of memory.  The start
+ * value is a byte offset relative to the start of IPA shared memory.  The
+ * end value is the last addressable unit *within* the range.  Typically
+ * the end value is in units of bytes, however it can also be a maximum
+ * array index value.
  */
 struct ipa_mem_bounds {
 	u32 start;
@@ -129,18 +131,19 @@ struct ipa_init_modem_driver_req {
 	u8			hdr_tbl_info_valid;
 	struct ipa_mem_bounds	hdr_tbl_info;
 
-	/* Routing table information.  These define the location and size of
-	 * non-hashable IPv4 and IPv6 filter tables.  The start values are
-	 * offsets relative to the start of IPA shared memory.
+	/* Routing table information.  These define the location and maximum
+	 * *index* (not byte) for the modem portion of non-hashable IPv4 and
+	 * IPv6 routing tables.  The start values are byte offsets relative
+	 * to the start of IPA shared memory.
 	 */
 	u8			v4_route_tbl_info_valid;
-	struct ipa_mem_array	v4_route_tbl_info;
+	struct ipa_mem_bounds	v4_route_tbl_info;
 	u8			v6_route_tbl_info_valid;
-	struct ipa_mem_array	v6_route_tbl_info;
+	struct ipa_mem_bounds	v6_route_tbl_info;
 
 	/* Filter table information.  These define the location of the
 	 * non-hashable IPv4 and IPv6 filter tables.  The start values are
-	 * offsets relative to the start of IPA shared memory.
+	 * byte offsets relative to the start of IPA shared memory.
 	 */
 	u8			v4_filter_tbl_start_valid;
 	u32			v4_filter_tbl_start;
@@ -181,18 +184,20 @@ struct ipa_init_modem_driver_req {
 	u8			zip_tbl_info_valid;
 	struct ipa_mem_bounds	zip_tbl_info;
 
-	/* Routing table information.  These define the location and size
-	 * of hashable IPv4 and IPv6 filter tables.  The start values are
-	 * offsets relative to the start of IPA shared memory.
+	/* Routing table information.  These define the location and maximum
+	 * *index* (not byte) for the modem portion of hashable IPv4 and IPv6
+	 * routing tables (if supported by hardware).  The start values are
+	 * byte offsets relative to the start of IPA shared memory.
 	 */
 	u8			v4_hash_route_tbl_info_valid;
-	struct ipa_mem_array	v4_hash_route_tbl_info;
+	struct ipa_mem_bounds	v4_hash_route_tbl_info;
 	u8			v6_hash_route_tbl_info_valid;
-	struct ipa_mem_array	v6_hash_route_tbl_info;
+	struct ipa_mem_bounds	v6_hash_route_tbl_info;
 
 	/* Filter table information.  These define the location and size
-	 * of hashable IPv4 and IPv6 filter tables.  The start values are
-	 * offsets relative to the start of IPA shared memory.
+	 * of hashable IPv4 and IPv6 filter tables (if supported by hardware).
+	 * The start values are byte offsets relative to the start of IPA
+	 * shared memory.
 	 */
 	u8			v4_hash_filter_tbl_start_valid;
 	u32			v4_hash_filter_tbl_start;
diff --git a/drivers/net/ipa/ipa_reg.h b/drivers/net/ipa/ipa_reg.h
index a5b355384d4a..6f35438cda89 100644
--- a/drivers/net/ipa/ipa_reg.h
+++ b/drivers/net/ipa/ipa_reg.h
@@ -48,7 +48,7 @@ struct ipa;
  *
  * The offset of registers related to resource types is computed by a macro
  * that is supplied a parameter "rt".  The "rt" represents a resource type,
- * which is is a member of the ipa_resource_type_src enumerated type for
+ * which is a member of the ipa_resource_type_src enumerated type for
  * source endpoint resources or the ipa_resource_type_dst enumerated type
  * for destination endpoint resources.
  *
diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c
index 2f5a58bfc529..69efe672ca52 100644
--- a/drivers/net/ipa/ipa_table.c
+++ b/drivers/net/ipa/ipa_table.c
@@ -108,8 +108,6 @@
 
 /* Assignment of route table entries to the modem and AP */
 #define IPA_ROUTE_MODEM_MIN		0
-#define IPA_ROUTE_MODEM_COUNT		8
-
 #define IPA_ROUTE_AP_MIN		IPA_ROUTE_MODEM_COUNT
 #define IPA_ROUTE_AP_COUNT \
 		(IPA_ROUTE_COUNT_MAX - IPA_ROUTE_MODEM_COUNT)
diff --git a/drivers/net/ipa/ipa_table.h b/drivers/net/ipa/ipa_table.h
index b6a9a0d79d68..1538e2e1732f 100644
--- a/drivers/net/ipa/ipa_table.h
+++ b/drivers/net/ipa/ipa_table.h
@@ -13,6 +13,9 @@ struct ipa;
 /* The maximum number of filter table entries (IPv4, IPv6; hashed or not) */
 #define IPA_FILTER_COUNT_MAX	14
 
+/* The number of route table entries allotted to the modem */
+#define IPA_ROUTE_MODEM_COUNT	8
+
 /* The maximum number of route table entries (IPv4, IPv6; hashed or not) */
 #define IPA_ROUTE_COUNT_MAX	15
 
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index dfeb5b392e64..bb1c298c1e78 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -495,7 +495,6 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb)
 
 static int ipvlan_process_outbound(struct sk_buff *skb)
 {
-	struct ethhdr *ethh = eth_hdr(skb);
 	int ret = NET_XMIT_DROP;
 
 	/* The ipvlan is a pseudo-L2 device, so the packets that we receive
@@ -505,6 +504,8 @@ static int ipvlan_process_outbound(struct sk_buff *skb)
 	if (skb_mac_header_was_set(skb)) {
 		/* In this mode we dont care about
 		 * multicast and broadcast traffic */
+		struct ethhdr *ethh = eth_hdr(skb);
+
 		if (is_multicast_ether_addr(ethh->h_dest)) {
 			pr_debug_ratelimited(
 				"Dropped {multi|broad}cast of type=[%x]\n",
@@ -589,7 +590,7 @@ out:
 static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev)
 {
 	const struct ipvl_dev *ipvlan = netdev_priv(dev);
-	struct ethhdr *eth = eth_hdr(skb);
+	struct ethhdr *eth = skb_eth_hdr(skb);
 	struct ipvl_addr *addr;
 	void *lyr3h;
 	int addr_type;
@@ -619,6 +620,7 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev)
 		return dev_forward_skb(ipvlan->phy_dev, skb);
 
 	} else if (is_multicast_ether_addr(eth->h_dest)) {
+		skb_reset_mac_header(skb);
 		ipvlan_skb_crossing_ns(skb, NULL);
 		ipvlan_multicast_enqueue(ipvlan->port, skb, true);
 		return NET_XMIT_SUCCESS;
diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
index ef02f2cf5ce1..cbabca167a07 100644
--- a/drivers/net/ipvlan/ipvtap.c
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -194,7 +194,7 @@ static struct notifier_block ipvtap_notifier_block __read_mostly = {
 	.notifier_call	= ipvtap_device_event,
 };
 
-static int ipvtap_init(void)
+static int __init ipvtap_init(void)
 {
 	int err;
 
@@ -228,7 +228,7 @@ out1:
 }
 module_init(ipvtap_init);
 
-static void ipvtap_exit(void)
+static void __exit ipvtap_exit(void)
 {
 	rtnl_link_unregister(&ipvtap_link_ops);
 	unregister_netdevice_notifier(&ipvtap_notifier_block);
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index ee6087e7b2bf..c6d271e5687e 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -462,11 +462,6 @@ static struct macsec_eth_header *macsec_ethhdr(struct sk_buff *skb)
 	return (struct macsec_eth_header *)skb_mac_header(skb);
 }
 
-static sci_t dev_to_sci(struct net_device *dev, __be16 port)
-{
-	return make_sci(dev->dev_addr, port);
-}
-
 static void __macsec_pn_wrapped(struct macsec_secy *secy,
 				struct macsec_tx_sa *tx_sa)
 {
@@ -3661,7 +3656,6 @@ static int macsec_set_mac_address(struct net_device *dev, void *p)
 
 out:
 	eth_hw_addr_set(dev, addr->sa_data);
-	macsec->secy.sci = dev_to_sci(dev, MACSEC_PORT_ES);
 
 	/* If h/w offloading is available, propagate to the device */
 	if (macsec_is_offloaded(macsec)) {
@@ -4000,6 +3994,11 @@ static bool sci_exists(struct net_device *dev, sci_t sci)
 	return false;
 }
 
+static sci_t dev_to_sci(struct net_device *dev, __be16 port)
+{
+	return make_sci(dev->dev_addr, port);
+}
+
 static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);
diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c
index 3e79c2c51929..1c1584fca632 100644
--- a/drivers/net/mdio/fwnode_mdio.c
+++ b/drivers/net/mdio/fwnode_mdio.c
@@ -47,7 +47,9 @@ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio,
 	 * just fall back to poll mode
 	 */
 	if (rc == -EPROBE_DEFER)
-		rc = -ENODEV;
+		rc = driver_deferred_probe_check_state(&phy->mdio.dev);
+	if (rc == -EPROBE_DEFER)
+		return rc;
 
 	if (rc > 0) {
 		phy->irq = rc;
diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c
index 9e3c815a070f..796e9c7857d0 100644
--- a/drivers/net/mdio/of_mdio.c
+++ b/drivers/net/mdio/of_mdio.c
@@ -231,6 +231,7 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 	return 0;
 
 unregister:
+	of_node_put(child);
 	mdiobus_unregister(mdio);
 	return rc;
 }
diff --git a/drivers/net/netdevsim/hwstats.c b/drivers/net/netdevsim/hwstats.c
index 605a38e16db0..0e58aa7f0374 100644
--- a/drivers/net/netdevsim/hwstats.c
+++ b/drivers/net/netdevsim/hwstats.c
@@ -433,11 +433,11 @@ int nsim_dev_hwstats_init(struct nsim_dev *nsim_dev)
 		goto err_remove_hwstats_recursive;
 	}
 
-	debugfs_create_file("enable_ifindex", 0600, hwstats->l3_ddir, hwstats,
+	debugfs_create_file("enable_ifindex", 0200, hwstats->l3_ddir, hwstats,
 			    &nsim_dev_hwstats_l3_enable_fops.fops);
-	debugfs_create_file("disable_ifindex", 0600, hwstats->l3_ddir, hwstats,
+	debugfs_create_file("disable_ifindex", 0200, hwstats->l3_ddir, hwstats,
 			    &nsim_dev_hwstats_l3_disable_fops.fops);
-	debugfs_create_file("fail_next_enable", 0600, hwstats->l3_ddir, hwstats,
+	debugfs_create_file("fail_next_enable", 0200, hwstats->l3_ddir, hwstats,
 			    &nsim_dev_hwstats_l3_fail_fops.fops);
 
 	INIT_DELAYED_WORK(&hwstats->traffic_dw,
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index e470e3398abc..9a1a5b203624 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -67,10 +67,10 @@ nsim_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	unsigned int start;
 
 	do {
-		start = u64_stats_fetch_begin(&ns->syncp);
+		start = u64_stats_fetch_begin_irq(&ns->syncp);
 		stats->tx_bytes = ns->tx_bytes;
 		stats->tx_packets = ns->tx_packets;
-	} while (u64_stats_fetch_retry(&ns->syncp, start));
+	} while (u64_stats_fetch_retry_irq(&ns->syncp, start));
 }
 
 static int
diff --git a/drivers/net/phy/aquantia_main.c b/drivers/net/phy/aquantia_main.c
index 8b7a46db30e0..7111e2e958e9 100644
--- a/drivers/net/phy/aquantia_main.c
+++ b/drivers/net/phy/aquantia_main.c
@@ -91,6 +91,9 @@
 #define VEND1_GLOBAL_FW_ID_MAJOR		GENMASK(15, 8)
 #define VEND1_GLOBAL_FW_ID_MINOR		GENMASK(7, 0)
 
+#define VEND1_GLOBAL_GEN_STAT2			0xc831
+#define VEND1_GLOBAL_GEN_STAT2_OP_IN_PROG	BIT(15)
+
 #define VEND1_GLOBAL_RSVD_STAT1			0xc885
 #define VEND1_GLOBAL_RSVD_STAT1_FW_BUILD_ID	GENMASK(7, 4)
 #define VEND1_GLOBAL_RSVD_STAT1_PROV_ID		GENMASK(3, 0)
@@ -125,6 +128,12 @@
 #define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL2	BIT(1)
 #define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL3	BIT(0)
 
+/* Sleep and timeout for checking if the Processor-Intensive
+ * MDIO operation is finished
+ */
+#define AQR107_OP_IN_PROG_SLEEP		1000
+#define AQR107_OP_IN_PROG_TIMEOUT	100000
+
 struct aqr107_hw_stat {
 	const char *name;
 	int reg;
@@ -597,16 +606,52 @@ static void aqr107_link_change_notify(struct phy_device *phydev)
 		phydev_info(phydev, "Aquantia 1000Base-T2 mode active\n");
 }
 
+static int aqr107_wait_processor_intensive_op(struct phy_device *phydev)
+{
+	int val, err;
+
+	/* The datasheet notes to wait at least 1ms after issuing a
+	 * processor intensive operation before checking.
+	 * We cannot use the 'sleep_before_read' parameter of read_poll_timeout
+	 * because that just determines the maximum time slept, not the minimum.
+	 */
+	usleep_range(1000, 5000);
+
+	err = phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1,
+					VEND1_GLOBAL_GEN_STAT2, val,
+					!(val & VEND1_GLOBAL_GEN_STAT2_OP_IN_PROG),
+					AQR107_OP_IN_PROG_SLEEP,
+					AQR107_OP_IN_PROG_TIMEOUT, false);
+	if (err) {
+		phydev_err(phydev, "timeout: processor-intensive MDIO operation\n");
+		return err;
+	}
+
+	return 0;
+}
+
 static int aqr107_suspend(struct phy_device *phydev)
 {
-	return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, MDIO_CTRL1,
-				MDIO_CTRL1_LPOWER);
+	int err;
+
+	err = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, MDIO_CTRL1,
+			       MDIO_CTRL1_LPOWER);
+	if (err)
+		return err;
+
+	return aqr107_wait_processor_intensive_op(phydev);
 }
 
 static int aqr107_resume(struct phy_device *phydev)
 {
-	return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, MDIO_CTRL1,
-				  MDIO_CTRL1_LPOWER);
+	int err;
+
+	err = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, MDIO_CTRL1,
+				 MDIO_CTRL1_LPOWER);
+	if (err)
+		return err;
+
+	return aqr107_wait_processor_intensive_op(phydev);
 }
 
 static int aqr107_probe(struct phy_device *phydev)
diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c
index 73f7962a37d3..c49062ad72c6 100644
--- a/drivers/net/phy/meson-gxl.c
+++ b/drivers/net/phy/meson-gxl.c
@@ -243,13 +243,7 @@ static irqreturn_t meson_gxl_handle_interrupt(struct phy_device *phydev)
 	    irq_status == INTSRC_ENERGY_DETECT)
 		return IRQ_HANDLED;
 
-	/* Give PHY some time before MAC starts sending data. This works
-	 * around an issue where network doesn't come up properly.
-	 */
-	if (!(irq_status & INTSRC_LINK_DOWN))
-		phy_queue_state_machine(phydev, msecs_to_jiffies(100));
-	else
-		phy_trigger_machine(phydev);
+	phy_trigger_machine(phydev);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index e78d0bf69bc3..38234d7e14c5 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -2679,16 +2679,19 @@ static int lan8804_config_init(struct phy_device *phydev)
 static irqreturn_t lan8814_handle_interrupt(struct phy_device *phydev)
 {
 	int irq_status, tsu_irq_status;
+	int ret = IRQ_NONE;
 
 	irq_status = phy_read(phydev, LAN8814_INTS);
-	if (irq_status > 0 && (irq_status & LAN8814_INT_LINK))
-		phy_trigger_machine(phydev);
-
 	if (irq_status < 0) {
 		phy_error(phydev);
 		return IRQ_NONE;
 	}
 
+	if (irq_status & LAN8814_INT_LINK) {
+		phy_trigger_machine(phydev);
+		ret = IRQ_HANDLED;
+	}
+
 	while (1) {
 		tsu_irq_status = lanphy_read_page_reg(phydev, 4,
 						      LAN8814_INTR_STS_REG);
@@ -2697,12 +2700,15 @@ static irqreturn_t lan8814_handle_interrupt(struct phy_device *phydev)
 		    (tsu_irq_status & (LAN8814_INTR_STS_REG_1588_TSU0_ |
 				       LAN8814_INTR_STS_REG_1588_TSU1_ |
 				       LAN8814_INTR_STS_REG_1588_TSU2_ |
-				       LAN8814_INTR_STS_REG_1588_TSU3_)))
+				       LAN8814_INTR_STS_REG_1588_TSU3_))) {
 			lan8814_handle_ptp_interrupt(phydev);
-		else
+			ret = IRQ_HANDLED;
+		} else {
 			break;
+		}
 	}
-	return IRQ_HANDLED;
+
+	return ret;
 }
 
 static int lan8814_ack_interrupt(struct phy_device *phydev)
@@ -2873,12 +2879,18 @@ static int lan8814_config_init(struct phy_device *phydev)
 	return 0;
 }
 
+/* It is expected that there will not be any 'lan8814_take_coma_mode'
+ * function called in suspend. Because the GPIO line can be shared, so if one of
+ * the phys goes back in coma mode, then all the other PHYs will go, which is
+ * wrong.
+ */
 static int lan8814_release_coma_mode(struct phy_device *phydev)
 {
 	struct gpio_desc *gpiod;
 
 	gpiod = devm_gpiod_get_optional(&phydev->mdio.dev, "coma-mode",
-					GPIOD_OUT_HIGH_OPEN_DRAIN);
+					GPIOD_OUT_HIGH_OPEN_DRAIN |
+					GPIOD_FLAGS_BIT_NONEXCLUSIVE);
 	if (IS_ERR(gpiod))
 		return PTR_ERR(gpiod);
 
diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c
index d4c93d59bc53..8569a545e0a3 100644
--- a/drivers/net/phy/microchip_t1.c
+++ b/drivers/net/phy/microchip_t1.c
@@ -28,12 +28,16 @@
 
 /* Interrupt Source Register */
 #define LAN87XX_INTERRUPT_SOURCE                (0x18)
+#define LAN87XX_INTERRUPT_SOURCE_2              (0x08)
 
 /* Interrupt Mask Register */
 #define LAN87XX_INTERRUPT_MASK                  (0x19)
 #define LAN87XX_MASK_LINK_UP                    (0x0004)
 #define LAN87XX_MASK_LINK_DOWN                  (0x0002)
 
+#define LAN87XX_INTERRUPT_MASK_2                (0x09)
+#define LAN87XX_MASK_COMM_RDY			BIT(10)
+
 /* MISC Control 1 Register */
 #define LAN87XX_CTRL_1                          (0x11)
 #define LAN87XX_MASK_RGMII_TXC_DLY_EN           (0x4000)
@@ -424,17 +428,55 @@ static int lan87xx_phy_config_intr(struct phy_device *phydev)
 	int rc, val = 0;
 
 	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
-		/* unmask all source and clear them before enable */
-		rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, 0x7FFF);
+		/* clear all interrupt */
+		rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, val);
+		if (rc < 0)
+			return rc;
+
 		rc = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE);
-		val = LAN87XX_MASK_LINK_UP | LAN87XX_MASK_LINK_DOWN;
+		if (rc < 0)
+			return rc;
+
+		rc = access_ereg(phydev, PHYACC_ATTR_MODE_WRITE,
+				 PHYACC_ATTR_BANK_MISC,
+				 LAN87XX_INTERRUPT_MASK_2, val);
+		if (rc < 0)
+			return rc;
+
+		rc = access_ereg(phydev, PHYACC_ATTR_MODE_READ,
+				 PHYACC_ATTR_BANK_MISC,
+				 LAN87XX_INTERRUPT_SOURCE_2, 0);
+		if (rc < 0)
+			return rc;
+
+		/* enable link down and comm ready interrupt */
+		val = LAN87XX_MASK_LINK_DOWN;
 		rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, val);
+		if (rc < 0)
+			return rc;
+
+		val = LAN87XX_MASK_COMM_RDY;
+		rc = access_ereg(phydev, PHYACC_ATTR_MODE_WRITE,
+				 PHYACC_ATTR_BANK_MISC,
+				 LAN87XX_INTERRUPT_MASK_2, val);
 	} else {
 		rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, val);
-		if (rc)
+		if (rc < 0)
 			return rc;
 
 		rc = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE);
+		if (rc < 0)
+			return rc;
+
+		rc = access_ereg(phydev, PHYACC_ATTR_MODE_WRITE,
+				 PHYACC_ATTR_BANK_MISC,
+				 LAN87XX_INTERRUPT_MASK_2, val);
+		if (rc < 0)
+			return rc;
+
+		rc = access_ereg(phydev, PHYACC_ATTR_MODE_READ,
+				 PHYACC_ATTR_BANK_MISC,
+				 LAN87XX_INTERRUPT_SOURCE_2, 0);
 	}
 
 	return rc < 0 ? rc : 0;
@@ -444,6 +486,14 @@ static irqreturn_t lan87xx_handle_interrupt(struct phy_device *phydev)
 {
 	int irq_status;
 
+	irq_status  = access_ereg(phydev, PHYACC_ATTR_MODE_READ,
+				  PHYACC_ATTR_BANK_MISC,
+				  LAN87XX_INTERRUPT_SOURCE_2, 0);
+	if (irq_status < 0) {
+		phy_error(phydev);
+		return IRQ_NONE;
+	}
+
 	irq_status = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE);
 	if (irq_status < 0) {
 		phy_error(phydev);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 0c6efd792690..4df8c337221b 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -316,11 +316,13 @@ static __maybe_unused int mdio_bus_phy_resume(struct device *dev)
 
 	phydev->suspended_by_mdio_bus = 0;
 
-	/* If we managed to get here with the PHY state machine in a state other
-	 * than PHY_HALTED this is an indication that something went wrong and
-	 * we should most likely be using MAC managed PM and we are not.
+	/* If we managed to get here with the PHY state machine in a state
+	 * neither PHY_HALTED, PHY_READY nor PHY_UP, this is an indication
+	 * that something went wrong and we should most likely be using
+	 * MAC managed PM, but we are not.
 	 */
-	WARN_ON(phydev->state != PHY_HALTED && !phydev->mac_managed_pm);
+	WARN_ON(phydev->state != PHY_HALTED && phydev->state != PHY_READY &&
+		phydev->state != PHY_UP);
 
 	ret = phy_init_hw(phydev);
 	if (ret < 0)
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index aac133a1e27a..154a3c0a6dfd 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1275,10 +1275,12 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 		}
 	}
 
-	netif_addr_lock_bh(dev);
-	dev_uc_sync_multiple(port_dev, dev);
-	dev_mc_sync_multiple(port_dev, dev);
-	netif_addr_unlock_bh(dev);
+	if (dev->flags & IFF_UP) {
+		netif_addr_lock_bh(dev);
+		dev_uc_sync_multiple(port_dev, dev);
+		dev_mc_sync_multiple(port_dev, dev);
+		netif_addr_unlock_bh(dev);
+	}
 
 	port->index = -1;
 	list_add_tail_rcu(&port->list, &team->port_list);
@@ -1349,8 +1351,10 @@ static int team_port_del(struct team *team, struct net_device *port_dev)
 	netdev_rx_handler_unregister(port_dev);
 	team_port_disable_netpoll(port);
 	vlan_vids_del_by_dev(port_dev, dev);
-	dev_uc_unsync(port_dev, dev);
-	dev_mc_unsync(port_dev, dev);
+	if (dev->flags & IFF_UP) {
+		dev_uc_unsync(port_dev, dev);
+		dev_mc_unsync(port_dev, dev);
+	}
 	dev_close(port_dev);
 	team_port_leave(team, port);
 
@@ -1700,6 +1704,14 @@ static int team_open(struct net_device *dev)
 
 static int team_close(struct net_device *dev)
 {
+	struct team *team = netdev_priv(dev);
+	struct team_port *port;
+
+	list_for_each_entry(port, &team->port_list, list) {
+		dev_uc_unsync(port->dev, dev);
+		dev_mc_unsync(port->dev, dev);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 259b2b84b2b3..db736b944016 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2828,7 +2828,10 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		rcu_assign_pointer(tfile->tun, tun);
 	}
 
-	netif_carrier_on(tun->dev);
+	if (ifr->ifr_flags & IFF_NO_CARRIER)
+		netif_carrier_off(tun->dev);
+	else
+		netif_carrier_on(tun->dev);
 
 	/* Make sure persistent devices do not get stuck in
 	 * xoff state.
@@ -3056,8 +3059,8 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		 * This is needed because we never checked for invalid flags on
 		 * TUNSETIFF.
 		 */
-		return put_user(IFF_TUN | IFF_TAP | TUN_FEATURES,
-				(unsigned int __user*)argp);
+		return put_user(IFF_TUN | IFF_TAP | IFF_NO_CARRIER |
+				TUN_FEATURES, (unsigned int __user*)argp);
 	} else if (cmd == TUNSETQUEUE) {
 		return tun_set_queue(file, &ifr);
 	} else if (cmd == SIOCGSKNS) {
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 2de09ad5bac0..e11f70911acc 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -777,6 +777,13 @@ static const struct usb_device_id	products[] = {
 },
 #endif
 
+/* Lenovo ThinkPad OneLink+ Dock (based on Realtek RTL8153) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x3054, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* ThinkPad USB-C Dock (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x3062, USB_CLASS_COMM,
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 709e3c59e340..26c34a7c21bd 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1087,6 +1087,7 @@ static const struct usb_device_id products[] = {
 	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0512)},	/* Quectel EG12/EM12 */
 	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0620)},	/* Quectel EM160R-GL */
 	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0800)},	/* Quectel RM500Q-GL */
+	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0801)},	/* Quectel RM520N */
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
@@ -1401,6 +1402,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81b3, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
+	{QMI_FIXED_INTF(0x413c, 0x81c2, 8)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81cc, 8)},	/* Dell Wireless 5816e */
 	{QMI_FIXED_INTF(0x413c, 0x81d7, 0)},	/* Dell Wireless 5821e */
 	{QMI_FIXED_INTF(0x413c, 0x81d7, 1)},	/* Dell Wireless 5821e preproduction config */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 0f6efaabaa32..688905ea0a6d 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -770,6 +770,7 @@ enum rtl8152_flags {
 	RX_EPROTO,
 };
 
+#define DEVICE_ID_THINKPAD_ONELINK_PLUS_DOCK		0x3054
 #define DEVICE_ID_THINKPAD_THUNDERBOLT3_DOCK_GEN2	0x3082
 #define DEVICE_ID_THINKPAD_USB_C_DONGLE			0x720c
 #define DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2		0xa387
@@ -5906,6 +5907,11 @@ static void r8153_enter_oob(struct r8152 *tp)
 	ocp_data &= ~NOW_IS_OOB;
 	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
 
+	/* RX FIFO settings for OOB */
+	ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL0, RXFIFO_THR1_OOB);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL1, RXFIFO_THR2_OOB);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL2, RXFIFO_THR3_OOB);
+
 	rtl_disable(tp);
 	rtl_reset_bmu(tp);
 
@@ -6431,21 +6437,8 @@ static void r8156_fc_parameter(struct r8152 *tp)
 	u32 pause_on = tp->fc_pause_on ? tp->fc_pause_on : fc_pause_on_auto(tp);
 	u32 pause_off = tp->fc_pause_off ? tp->fc_pause_off : fc_pause_off_auto(tp);
 
-	switch (tp->version) {
-	case RTL_VER_10:
-	case RTL_VER_11:
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 8);
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 8);
-		break;
-	case RTL_VER_12:
-	case RTL_VER_13:
-	case RTL_VER_15:
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 16);
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 16);
-		break;
-	default:
-		break;
-	}
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 16);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 16);
 }
 
 static void rtl8156_change_mtu(struct r8152 *tp)
@@ -6557,6 +6550,11 @@ static void rtl8156_down(struct r8152 *tp)
 	ocp_data &= ~NOW_IS_OOB;
 	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
 
+	/* RX FIFO settings for OOB */
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RXFIFO_FULL, 64 / 16);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, 1024 / 16);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, 4096 / 16);
+
 	rtl_disable(tp);
 	rtl_reset_bmu(tp);
 
@@ -9584,6 +9582,7 @@ static bool rtl8152_supports_lenovo_macpassthru(struct usb_device *udev)
 
 	if (vendor_id == VENDOR_ID_LENOVO) {
 		switch (product_id) {
+		case DEVICE_ID_THINKPAD_ONELINK_PLUS_DOCK:
 		case DEVICE_ID_THINKPAD_THUNDERBOLT3_DOCK_GEN2:
 		case DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2:
 		case DEVICE_ID_THINKPAD_USB_C_DOCK_GEN3:
@@ -9831,6 +9830,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927),
 	REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101),
 	REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x304f),
+	REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x3054),
 	REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x3062),
 	REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x3069),
 	REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x3082),
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index aaa89b4cfd50..e368b0780753 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1598,6 +1598,7 @@ void usbnet_disconnect (struct usb_interface *intf)
 	struct usbnet		*dev;
 	struct usb_device	*xdev;
 	struct net_device	*net;
+	struct urb		*urb;
 
 	dev = usb_get_intfdata(intf);
 	usb_set_intfdata(intf, NULL);
@@ -1614,7 +1615,11 @@ void usbnet_disconnect (struct usb_interface *intf)
 	net = dev->net;
 	unregister_netdev (net);
 
-	usb_scuttle_anchored_urbs(&dev->deferred);
+	while ((urb = usb_get_from_anchor(&dev->deferred))) {
+		dev_kfree_skb(urb->context);
+		kfree(urb->sg);
+		usb_free_urb(urb);
+	}
 
 	if (dev->driver_info->unbind)
 		dev->driver_info->unbind(dev, intf);
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d934774e9733..9cce7dec7366 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1211,7 +1211,7 @@ static void virtio_skb_set_hash(const struct virtio_net_hdr_v1_hash *hdr_hash,
 	if (!hdr_hash || !skb)
 		return;
 
-	switch ((int)hdr_hash->hash_report) {
+	switch (__le16_to_cpu(hdr_hash->hash_report)) {
 	case VIRTIO_NET_HASH_REPORT_TCPv4:
 	case VIRTIO_NET_HASH_REPORT_UDPv4:
 	case VIRTIO_NET_HASH_REPORT_TCPv6:
@@ -1229,7 +1229,7 @@ static void virtio_skb_set_hash(const struct virtio_net_hdr_v1_hash *hdr_hash,
 	default:
 		rss_hash_type = PKT_HASH_TYPE_NONE;
 	}
-	skb_set_hash(skb, (unsigned int)hdr_hash->hash_value, rss_hash_type);
+	skb_set_hash(skb, __le32_to_cpu(hdr_hash->hash_value), rss_hash_type);
 }
 
 static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
@@ -3432,29 +3432,6 @@ static unsigned int mergeable_min_buf_len(struct virtnet_info *vi, struct virtqu
 		   (unsigned int)GOOD_PACKET_LEN);
 }
 
-static void virtnet_config_sizes(struct virtnet_info *vi, u32 *sizes)
-{
-	u32 i, rx_size, tx_size;
-
-	if (vi->speed == SPEED_UNKNOWN || vi->speed < SPEED_10000) {
-		rx_size = 1024;
-		tx_size = 1024;
-
-	} else if (vi->speed < SPEED_40000) {
-		rx_size = 1024 * 4;
-		tx_size = 1024 * 4;
-
-	} else {
-		rx_size = 1024 * 8;
-		tx_size = 1024 * 8;
-	}
-
-	for (i = 0; i < vi->max_queue_pairs; i++) {
-		sizes[rxq2vq(i)] = rx_size;
-		sizes[txq2vq(i)] = tx_size;
-	}
-}
-
 static int virtnet_find_vqs(struct virtnet_info *vi)
 {
 	vq_callback_t **callbacks;
@@ -3462,7 +3439,6 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 	int ret = -ENOMEM;
 	int i, total_vqs;
 	const char **names;
-	u32 *sizes;
 	bool *ctx;
 
 	/* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by
@@ -3490,15 +3466,10 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 		ctx = NULL;
 	}
 
-	sizes = kmalloc_array(total_vqs, sizeof(*sizes), GFP_KERNEL);
-	if (!sizes)
-		goto err_sizes;
-
 	/* Parameters for control virtqueue, if any */
 	if (vi->has_cvq) {
 		callbacks[total_vqs - 1] = NULL;
 		names[total_vqs - 1] = "control";
-		sizes[total_vqs - 1] = 64;
 	}
 
 	/* Allocate/initialize parameters for send/receive virtqueues */
@@ -3513,10 +3484,8 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 			ctx[rxq2vq(i)] = true;
 	}
 
-	virtnet_config_sizes(vi, sizes);
-
-	ret = virtio_find_vqs_ctx_size(vi->vdev, total_vqs, vqs, callbacks,
-				       names, sizes, ctx, NULL);
+	ret = virtio_find_vqs_ctx(vi->vdev, total_vqs, vqs, callbacks,
+				  names, ctx, NULL);
 	if (ret)
 		goto err_find;
 
@@ -3536,8 +3505,6 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 
 
 err_find:
-	kfree(sizes);
-err_sizes:
 	kfree(ctx);
 err_ctx:
 	kfree(names);
@@ -3897,9 +3864,6 @@ static int virtnet_probe(struct virtio_device *vdev)
 		vi->curr_queue_pairs = num_online_cpus();
 	vi->max_queue_pairs = max_queue_pairs;
 
-	virtnet_init_settings(dev);
-	virtnet_update_settings(vi);
-
 	/* Allocate/initialize the rx/tx queues, and invoke find_vqs */
 	err = init_vqs(vi);
 	if (err)
@@ -3912,6 +3876,8 @@ static int virtnet_probe(struct virtio_device *vdev)
 	netif_set_real_num_tx_queues(dev, vi->curr_queue_pairs);
 	netif_set_real_num_rx_queues(dev, vi->curr_queue_pairs);
 
+	virtnet_init_settings(dev);
+
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_STANDBY)) {
 		vi->failover = net_failover_create(vi->dev);
 		if (IS_ERR(vi->failover)) {
diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c
index d0f3b6d7f408..5c804bcabfe6 100644
--- a/drivers/net/wireguard/netlink.c
+++ b/drivers/net/wireguard/netlink.c
@@ -436,14 +436,13 @@ static int set_peer(struct wg_device *wg, struct nlattr **attrs)
 	if (attrs[WGPEER_A_ENDPOINT]) {
 		struct sockaddr *addr = nla_data(attrs[WGPEER_A_ENDPOINT]);
 		size_t len = nla_len(attrs[WGPEER_A_ENDPOINT]);
+		struct endpoint endpoint = { { { 0 } } };
 
-		if ((len == sizeof(struct sockaddr_in) &&
-		     addr->sa_family == AF_INET) ||
-		    (len == sizeof(struct sockaddr_in6) &&
-		     addr->sa_family == AF_INET6)) {
-			struct endpoint endpoint = { { { 0 } } };
-
-			memcpy(&endpoint.addr, addr, len);
+		if (len == sizeof(struct sockaddr_in) && addr->sa_family == AF_INET) {
+			endpoint.addr4 = *(struct sockaddr_in *)addr;
+			wg_socket_set_peer_endpoint(peer, &endpoint);
+		} else if (len == sizeof(struct sockaddr_in6) && addr->sa_family == AF_INET6) {
+			endpoint.addr6 = *(struct sockaddr_in6 *)addr;
 			wg_socket_set_peer_endpoint(peer, &endpoint);
 		}
 	}
diff --git a/drivers/net/wireguard/selftest/ratelimiter.c b/drivers/net/wireguard/selftest/ratelimiter.c
index ba87d294604f..d4bb40a695ab 100644
--- a/drivers/net/wireguard/selftest/ratelimiter.c
+++ b/drivers/net/wireguard/selftest/ratelimiter.c
@@ -6,29 +6,28 @@
 #ifdef DEBUG
 
 #include <linux/jiffies.h>
-#include <linux/hrtimer.h>
 
 static const struct {
 	bool result;
-	u64 nsec_to_sleep_before;
+	unsigned int msec_to_sleep_before;
 } expected_results[] __initconst = {
 	[0 ... PACKETS_BURSTABLE - 1] = { true, 0 },
 	[PACKETS_BURSTABLE] = { false, 0 },
-	[PACKETS_BURSTABLE + 1] = { true, NSEC_PER_SEC / PACKETS_PER_SECOND },
+	[PACKETS_BURSTABLE + 1] = { true, MSEC_PER_SEC / PACKETS_PER_SECOND },
 	[PACKETS_BURSTABLE + 2] = { false, 0 },
-	[PACKETS_BURSTABLE + 3] = { true, (NSEC_PER_SEC / PACKETS_PER_SECOND) * 2 },
+	[PACKETS_BURSTABLE + 3] = { true, (MSEC_PER_SEC / PACKETS_PER_SECOND) * 2 },
 	[PACKETS_BURSTABLE + 4] = { true, 0 },
 	[PACKETS_BURSTABLE + 5] = { false, 0 }
 };
 
 static __init unsigned int maximum_jiffies_at_index(int index)
 {
-	u64 total_nsecs = 2 * NSEC_PER_SEC / PACKETS_PER_SECOND / 3;
+	unsigned int total_msecs = 2 * MSEC_PER_SEC / PACKETS_PER_SECOND / 3;
 	int i;
 
 	for (i = 0; i <= index; ++i)
-		total_nsecs += expected_results[i].nsec_to_sleep_before;
-	return nsecs_to_jiffies(total_nsecs);
+		total_msecs += expected_results[i].msec_to_sleep_before;
+	return msecs_to_jiffies(total_msecs);
 }
 
 static __init int timings_test(struct sk_buff *skb4, struct iphdr *hdr4,
@@ -43,12 +42,8 @@ static __init int timings_test(struct sk_buff *skb4, struct iphdr *hdr4,
 	loop_start_time = jiffies;
 
 	for (i = 0; i < ARRAY_SIZE(expected_results); ++i) {
-		if (expected_results[i].nsec_to_sleep_before) {
-			ktime_t timeout = ktime_add(ktime_add_ns(ktime_get_coarse_boottime(), TICK_NSEC * 4 / 3),
-						    ns_to_ktime(expected_results[i].nsec_to_sleep_before));
-			set_current_state(TASK_UNINTERRUPTIBLE);
-			schedule_hrtimeout_range_clock(&timeout, 0, HRTIMER_MODE_ABS, CLOCK_BOOTTIME);
-		}
+		if (expected_results[i].msec_to_sleep_before)
+			msleep(expected_results[i].msec_to_sleep_before);
 
 		if (time_is_before_jiffies(loop_start_time +
 					   maximum_jiffies_at_index(i)))
@@ -132,7 +127,7 @@ bool __init wg_ratelimiter_selftest(void)
 	if (IS_ENABLED(CONFIG_KASAN) || IS_ENABLED(CONFIG_UBSAN))
 		return true;
 
-	BUILD_BUG_ON(NSEC_PER_SEC % PACKETS_PER_SECOND != 0);
+	BUILD_BUG_ON(MSEC_PER_SEC % PACKETS_PER_SECOND != 0);
 
 	if (wg_ratelimiter_init())
 		goto out;
@@ -172,7 +167,7 @@ bool __init wg_ratelimiter_selftest(void)
 	++test;
 #endif
 
-	for (trials = TRIALS_BEFORE_GIVING_UP;;) {
+	for (trials = TRIALS_BEFORE_GIVING_UP; IS_ENABLED(DEBUG_RATELIMITER_TIMINGS);) {
 		int test_count = 0, ret;
 
 		ret = timings_test(skb4, hdr4, skb6, hdr6, &test_count);
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-rs.c b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
index c62f299b9e0a..d8a5dbf89a02 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-rs.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
@@ -2403,7 +2403,7 @@ il4965_rs_fill_link_cmd(struct il_priv *il, struct il_lq_sta *lq_sta,
 		/* Repeat initial/next rate.
 		 * For legacy IL_NUMBER_TRY == 1, this loop will not execute.
 		 * For HT IL_HT_NUMBER_TRY == 3, this executes twice. */
-		while (repeat_rate > 0) {
+		while (repeat_rate > 0 && idx < (LINK_QUAL_MAX_RETRY_NUM - 1)) {
 			if (is_legacy(tbl_type.lq_type)) {
 				if (ant_toggle_cnt < NUM_TRY_BEFORE_ANT_TOGGLE)
 					ant_toggle_cnt++;
@@ -2422,8 +2422,6 @@ il4965_rs_fill_link_cmd(struct il_priv *il, struct il_lq_sta *lq_sta,
 			    cpu_to_le32(new_rate);
 			repeat_rate--;
 			idx++;
-			if (idx >= LINK_QUAL_MAX_RETRY_NUM)
-				goto out;
 		}
 
 		il4965_rs_get_tbl_info_from_mcs(new_rate, lq_sta->band,
@@ -2468,7 +2466,6 @@ il4965_rs_fill_link_cmd(struct il_priv *il, struct il_lq_sta *lq_sta,
 		repeat_rate--;
 	}
 
-out:
 	lq_cmd->agg_params.agg_frame_cnt_limit = LINK_QUAL_AGG_FRAME_LIMIT_DEF;
 	lq_cmd->agg_params.agg_dis_start_th = LINK_QUAL_AGG_DISABLE_START_DEF;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig
index a647a406b87b..b20409f8c13a 100644
--- a/drivers/net/wireless/intel/iwlwifi/Kconfig
+++ b/drivers/net/wireless/intel/iwlwifi/Kconfig
@@ -140,6 +140,7 @@ config IWLMEI
 	depends on INTEL_MEI
 	depends on PM
 	depends on CFG80211
+	depends on BROKEN
 	help
 	  Enables the iwlmei kernel module.
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 5eb28f8ee87e..11536f115198 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1833,8 +1833,8 @@ static void iwl_mvm_parse_ppe(struct iwl_mvm *mvm,
 	* If nss < MAX: we can set zeros in other streams
 	*/
 	if (nss > MAX_HE_SUPP_NSS) {
-		IWL_INFO(mvm, "Got NSS = %d - trimming to %d\n", nss,
-			 MAX_HE_SUPP_NSS);
+		IWL_DEBUG_INFO(mvm, "Got NSS = %d - trimming to %d\n", nss,
+			       MAX_HE_SUPP_NSS);
 		nss = MAX_HE_SUPP_NSS;
 	}
 
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 6e55f153ff26..1f301a5fb396 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -5060,6 +5060,10 @@ static int hwsim_virtio_handle_cmd(struct sk_buff *skb)
 
 	nlh = nlmsg_hdr(skb);
 	gnlh = nlmsg_data(nlh);
+
+	if (skb->len < nlh->nlmsg_len)
+		return -EINVAL;
+
 	err = genlmsg_parse(nlh, &hwsim_genl_family, tb, HWSIM_ATTR_MAX,
 			    hwsim_genl_policy, NULL);
 	if (err) {
@@ -5102,7 +5106,8 @@ static void hwsim_virtio_rx_work(struct work_struct *work)
 	spin_unlock_irqrestore(&hwsim_virtio_lock, flags);
 
 	skb->data = skb->head;
-	skb_set_tail_pointer(skb, len);
+	skb_reset_tail_pointer(skb);
+	skb_put(skb, len);
 	hwsim_virtio_handle_cmd(skb);
 
 	spin_lock_irqsave(&hwsim_virtio_lock, flags);
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 253cbc1956d1..6de13d641438 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -267,7 +267,8 @@ static void mt76_init_stream_cap(struct mt76_phy *phy,
 	}
 	vht_cap->vht_mcs.rx_mcs_map = cpu_to_le16(mcs_map);
 	vht_cap->vht_mcs.tx_mcs_map = cpu_to_le16(mcs_map);
-	vht_cap->vht_mcs.tx_highest |=
+	if (ieee80211_hw_check(phy->hw, SUPPORTS_VHT_EXT_NSS_BW))
+		vht_cap->vht_mcs.tx_highest |=
 				cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
index ad6c7d632eed..d6aae60c440d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
@@ -1088,7 +1088,7 @@ u32 mt7615_mac_get_sta_tid_sn(struct mt7615_dev *dev, int wcid, u8 tid)
 	offset %= 32;
 
 	val = mt76_rr(dev, addr);
-	val >>= (tid % 32);
+	val >>= offset;
 
 	if (offset > 20) {
 		addr += 4;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
index e1800674089a..576a0149251b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
@@ -261,7 +261,7 @@ int mt7921e_mac_reset(struct mt7921_dev *dev)
 
 	err = mt7921e_driver_own(dev);
 	if (err)
-		return err;
+		goto out;
 
 	err = mt7921_run_firmware(dev);
 	if (err)
diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.h b/drivers/net/wireless/microchip/wilc1000/netdev.h
index 43c085c74b7a..bb1a315a7b7e 100644
--- a/drivers/net/wireless/microchip/wilc1000/netdev.h
+++ b/drivers/net/wireless/microchip/wilc1000/netdev.h
@@ -245,6 +245,7 @@ struct wilc {
 	u8 *rx_buffer;
 	u32 rx_buffer_offset;
 	u8 *tx_buffer;
+	u32 *vmm_table;
 
 	struct txq_handle txq[NQUEUES];
 	int txq_entries;
diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index 600cc57e9da2..7390f94cd4ca 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -28,6 +28,7 @@ struct wilc_sdio {
 	u32 block_size;
 	bool isinit;
 	int has_thrpt_enh3;
+	u8 *cmd53_buf;
 };
 
 struct sdio_cmd52 {
@@ -47,6 +48,7 @@ struct sdio_cmd53 {
 	u32 count:		9;
 	u8 *buffer;
 	u32 block_size;
+	bool use_global_buf;
 };
 
 static const struct wilc_hif_func wilc_hif_sdio;
@@ -91,6 +93,8 @@ static int wilc_sdio_cmd53(struct wilc *wilc, struct sdio_cmd53 *cmd)
 {
 	struct sdio_func *func = container_of(wilc->dev, struct sdio_func, dev);
 	int size, ret;
+	struct wilc_sdio *sdio_priv = wilc->bus_data;
+	u8 *buf = cmd->buffer;
 
 	sdio_claim_host(func);
 
@@ -101,12 +105,23 @@ static int wilc_sdio_cmd53(struct wilc *wilc, struct sdio_cmd53 *cmd)
 	else
 		size = cmd->count;
 
+	if (cmd->use_global_buf) {
+		if (size > sizeof(u32))
+			return -EINVAL;
+
+		buf = sdio_priv->cmd53_buf;
+	}
+
 	if (cmd->read_write) {  /* write */
-		ret = sdio_memcpy_toio(func, cmd->address,
-				       (void *)cmd->buffer, size);
+		if (cmd->use_global_buf)
+			memcpy(buf, cmd->buffer, size);
+
+		ret = sdio_memcpy_toio(func, cmd->address, buf, size);
 	} else {        /* read */
-		ret = sdio_memcpy_fromio(func, (void *)cmd->buffer,
-					 cmd->address,  size);
+		ret = sdio_memcpy_fromio(func, buf, cmd->address, size);
+
+		if (cmd->use_global_buf)
+			memcpy(cmd->buffer, buf, size);
 	}
 
 	sdio_release_host(func);
@@ -128,6 +143,12 @@ static int wilc_sdio_probe(struct sdio_func *func,
 	if (!sdio_priv)
 		return -ENOMEM;
 
+	sdio_priv->cmd53_buf = kzalloc(sizeof(u32), GFP_KERNEL);
+	if (!sdio_priv->cmd53_buf) {
+		ret = -ENOMEM;
+		goto free;
+	}
+
 	ret = wilc_cfg80211_init(&wilc, &func->dev, WILC_HIF_SDIO,
 				 &wilc_hif_sdio);
 	if (ret)
@@ -161,6 +182,7 @@ dispose_irq:
 	irq_dispose_mapping(wilc->dev_irq_num);
 	wilc_netdev_cleanup(wilc);
 free:
+	kfree(sdio_priv->cmd53_buf);
 	kfree(sdio_priv);
 	return ret;
 }
@@ -172,6 +194,7 @@ static void wilc_sdio_remove(struct sdio_func *func)
 
 	clk_disable_unprepare(wilc->rtc_clk);
 	wilc_netdev_cleanup(wilc);
+	kfree(sdio_priv->cmd53_buf);
 	kfree(sdio_priv);
 }
 
@@ -375,8 +398,9 @@ static int wilc_sdio_write_reg(struct wilc *wilc, u32 addr, u32 data)
 		cmd.address = WILC_SDIO_FBR_DATA_REG;
 		cmd.block_mode = 0;
 		cmd.increment = 1;
-		cmd.count = 4;
+		cmd.count = sizeof(u32);
 		cmd.buffer = (u8 *)&data;
+		cmd.use_global_buf = true;
 		cmd.block_size = sdio_priv->block_size;
 		ret = wilc_sdio_cmd53(wilc, &cmd);
 		if (ret)
@@ -414,6 +438,7 @@ static int wilc_sdio_write(struct wilc *wilc, u32 addr, u8 *buf, u32 size)
 	nblk = size / block_size;
 	nleft = size % block_size;
 
+	cmd.use_global_buf = false;
 	if (nblk > 0) {
 		cmd.block_mode = 1;
 		cmd.increment = 1;
@@ -492,8 +517,9 @@ static int wilc_sdio_read_reg(struct wilc *wilc, u32 addr, u32 *data)
 		cmd.address = WILC_SDIO_FBR_DATA_REG;
 		cmd.block_mode = 0;
 		cmd.increment = 1;
-		cmd.count = 4;
+		cmd.count = sizeof(u32);
 		cmd.buffer = (u8 *)data;
+		cmd.use_global_buf = true;
 
 		cmd.block_size = sdio_priv->block_size;
 		ret = wilc_sdio_cmd53(wilc, &cmd);
@@ -535,6 +561,7 @@ static int wilc_sdio_read(struct wilc *wilc, u32 addr, u8 *buf, u32 size)
 	nblk = size / block_size;
 	nleft = size % block_size;
 
+	cmd.use_global_buf = false;
 	if (nblk > 0) {
 		cmd.block_mode = 1;
 		cmd.increment = 1;
diff --git a/drivers/net/wireless/microchip/wilc1000/wlan.c b/drivers/net/wireless/microchip/wilc1000/wlan.c
index 947d9a0a494e..58bbf50081e4 100644
--- a/drivers/net/wireless/microchip/wilc1000/wlan.c
+++ b/drivers/net/wireless/microchip/wilc1000/wlan.c
@@ -714,7 +714,7 @@ int wilc_wlan_handle_txq(struct wilc *wilc, u32 *txq_count)
 	int ret = 0;
 	int counter;
 	int timeout;
-	u32 vmm_table[WILC_VMM_TBL_SIZE];
+	u32 *vmm_table = wilc->vmm_table;
 	u8 ac_pkt_num_to_chip[NQUEUES] = {0, 0, 0, 0};
 	const struct wilc_hif_func *func;
 	int srcu_idx;
@@ -1252,6 +1252,8 @@ void wilc_wlan_cleanup(struct net_device *dev)
 	while ((rqe = wilc_wlan_rxq_remove(wilc)))
 		kfree(rqe);
 
+	kfree(wilc->vmm_table);
+	wilc->vmm_table = NULL;
 	kfree(wilc->rx_buffer);
 	wilc->rx_buffer = NULL;
 	kfree(wilc->tx_buffer);
@@ -1489,6 +1491,14 @@ int wilc_wlan_init(struct net_device *dev)
 			goto fail;
 	}
 
+	if (!wilc->vmm_table)
+		wilc->vmm_table = kzalloc(WILC_VMM_TBL_SIZE, GFP_KERNEL);
+
+	if (!wilc->vmm_table) {
+		ret = -ENOBUFS;
+		goto fail;
+	}
+
 	if (!wilc->tx_buffer)
 		wilc->tx_buffer = kmalloc(WILC_TX_BUFF_SIZE, GFP_KERNEL);
 
@@ -1513,7 +1523,8 @@ int wilc_wlan_init(struct net_device *dev)
 	return 0;
 
 fail:
-
+	kfree(wilc->vmm_table);
+	wilc->vmm_table = NULL;
 	kfree(wilc->rx_buffer);
 	wilc->rx_buffer = NULL;
 	kfree(wilc->tx_buffer);
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 990360d75cb6..e85b3c5d4acc 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -256,7 +256,6 @@ static void backend_disconnect(struct backend_info *be)
 		unsigned int queue_index;
 
 		xen_unregister_watchers(vif);
-		xenbus_rm(XBT_NIL, be->dev->nodename, "hotplug-status");
 #ifdef CONFIG_DEBUG_FS
 		xenvif_debugfs_delif(vif);
 #endif /* CONFIG_DEBUG_FS */
@@ -984,6 +983,7 @@ static int netback_remove(struct xenbus_device *dev)
 	struct backend_info *be = dev_get_drvdata(&dev->dev);
 
 	unregister_hotplug_status_watch(be);
+	xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status");
 	if (be->vif) {
 		kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE);
 		backend_disconnect(be);
diff --git a/drivers/nfc/pn533/uart.c b/drivers/nfc/pn533/uart.c
index 2caf997f9bc9..07596bf5f7d6 100644
--- a/drivers/nfc/pn533/uart.c
+++ b/drivers/nfc/pn533/uart.c
@@ -310,6 +310,7 @@ static void pn532_uart_remove(struct serdev_device *serdev)
 	pn53x_unregister_nfc(pn532->priv);
 	serdev_device_close(serdev);
 	pn53x_common_clean(pn532->priv);
+	del_timer_sync(&pn532->cmd_timeout);
 	kfree_skb(pn532->recv_skb);
 	kfree(pn532);
 }
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index bf4f5c09d9b1..bbe5099c836d 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -1712,8 +1712,6 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region,
 	res->flags = IORESOURCE_MEM;
 
 	for (i = 0; i < nd_region->ndr_mappings; i++) {
-		uuid_t uuid;
-
 		nsl_get_uuid(ndd, nd_label, &uuid);
 		if (has_uuid_at_pos(nd_region, &uuid, cookie, i))
 			continue;
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 7e88cd242380..96e6e9a5f235 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -45,7 +45,7 @@ static struct nd_region *to_region(struct pmem_device *pmem)
 	return to_nd_region(to_dev(pmem)->parent);
 }
 
-static phys_addr_t to_phys(struct pmem_device *pmem, phys_addr_t offset)
+static phys_addr_t pmem_to_phys(struct pmem_device *pmem, phys_addr_t offset)
 {
 	return pmem->phys_addr + offset;
 }
@@ -63,7 +63,7 @@ static phys_addr_t to_offset(struct pmem_device *pmem, sector_t sector)
 static void pmem_mkpage_present(struct pmem_device *pmem, phys_addr_t offset,
 		unsigned int len)
 {
-	phys_addr_t phys = to_phys(pmem, offset);
+	phys_addr_t phys = pmem_to_phys(pmem, offset);
 	unsigned long pfn_start, pfn_end, pfn;
 
 	/* only pmem in the linear map supports HWPoison */
@@ -97,7 +97,7 @@ static void pmem_clear_bb(struct pmem_device *pmem, sector_t sector, long blks)
 static long __pmem_clear_poison(struct pmem_device *pmem,
 		phys_addr_t offset, unsigned int len)
 {
-	phys_addr_t phys = to_phys(pmem, offset);
+	phys_addr_t phys = pmem_to_phys(pmem, offset);
 	long cleared = nvdimm_clear_poison(to_dev(pmem), phys, len);
 
 	if (cleared > 0) {
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index af367b22871b..8d5a7ae19844 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2162,14 +2162,14 @@ static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new,
 
 static int nvme_pr_clear(struct block_device *bdev, u64 key)
 {
-	u32 cdw10 = 1 | (key ? 1 << 3 : 0);
+	u32 cdw10 = 1 | (key ? 0 : 1 << 3);
 
-	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_register);
+	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
 }
 
 static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
 {
-	u32 cdw10 = nvme_pr_type(type) << 8 | (key ? 1 << 3 : 0);
+	u32 cdw10 = nvme_pr_type(type) << 8 | (key ? 0 : 1 << 3);
 
 	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
 }
@@ -4703,6 +4703,8 @@ static void nvme_fw_act_work(struct work_struct *work)
 	nvme_start_queues(ctrl);
 	/* read FW slot information to clear the AER */
 	nvme_get_fw_slot_info(ctrl);
+
+	queue_work(nvme_wq, &ctrl->async_event_work);
 }
 
 static u32 nvme_aer_type(u32 result)
@@ -4715,9 +4717,10 @@ static u32 nvme_aer_subtype(u32 result)
 	return (result & 0xff00) >> 8;
 }
 
-static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
+static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 {
 	u32 aer_notice_type = nvme_aer_subtype(result);
+	bool requeue = true;
 
 	trace_nvme_async_event(ctrl, aer_notice_type);
 
@@ -4734,6 +4737,7 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 		 */
 		if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) {
 			nvme_auth_stop(ctrl);
+			requeue = false;
 			queue_work(nvme_wq, &ctrl->fw_act_work);
 		}
 		break;
@@ -4750,6 +4754,7 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 	default:
 		dev_warn(ctrl->device, "async event result %08x\n", result);
 	}
+	return requeue;
 }
 
 static void nvme_handle_aer_persistent_error(struct nvme_ctrl *ctrl)
@@ -4765,13 +4770,14 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 	u32 result = le32_to_cpu(res->u32);
 	u32 aer_type = nvme_aer_type(result);
 	u32 aer_subtype = nvme_aer_subtype(result);
+	bool requeue = true;
 
 	if (le16_to_cpu(status) >> 1 != NVME_SC_SUCCESS)
 		return;
 
 	switch (aer_type) {
 	case NVME_AER_NOTICE:
-		nvme_handle_aen_notice(ctrl, result);
+		requeue = nvme_handle_aen_notice(ctrl, result);
 		break;
 	case NVME_AER_ERROR:
 		/*
@@ -4792,7 +4798,9 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 	default:
 		break;
 	}
-	queue_work(nvme_wq, &ctrl->async_event_work);
+
+	if (requeue)
+		queue_work(nvme_wq, &ctrl->async_event_work);
 }
 EXPORT_SYMBOL_GPL(nvme_complete_async_event);
 
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 3a1c37f32f30..67d3335e9cc8 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3470,6 +3470,10 @@ static const struct pci_device_id nvme_id_table[] = {
 	{ PCI_DEVICE(0x1987, 0x5016),	/* Phison E16 */
 		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN |
 				NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x1987, 0x5019),  /* phison E19 */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x1987, 0x5021),   /* Phison E21 */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1b4b, 0x1092),	/* Lexar 256 GB SSD */
 		.driver_data = NVME_QUIRK_NO_NS_DESC_LIST |
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
@@ -3517,6 +3521,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
 	{ PCI_DEVICE(0xc0a9, 0x540a),   /* Crucial P2 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x1d97, 0x2263), /* Lexar NM610 */
+		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061),
 		.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065),
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 044da18c06f5..d5871fd6f769 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -121,7 +121,6 @@ struct nvme_tcp_queue {
 	struct mutex		send_mutex;
 	struct llist_head	req_list;
 	struct list_head	send_list;
-	bool			more_requests;
 
 	/* recv state */
 	void			*pdu;
@@ -320,7 +319,7 @@ static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue)
 static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
 {
 	return !list_empty(&queue->send_list) ||
-		!llist_empty(&queue->req_list) || queue->more_requests;
+		!llist_empty(&queue->req_list);
 }
 
 static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
@@ -339,9 +338,7 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
 	 */
 	if (queue->io_cpu == raw_smp_processor_id() &&
 	    sync && empty && mutex_trylock(&queue->send_mutex)) {
-		queue->more_requests = !last;
 		nvme_tcp_send_all(queue);
-		queue->more_requests = false;
 		mutex_unlock(&queue->send_mutex);
 	}
 
@@ -1229,7 +1226,7 @@ static void nvme_tcp_io_work(struct work_struct *w)
 		else if (unlikely(result < 0))
 			return;
 
-		if (!pending)
+		if (!pending || !queue->rd_enabled)
 			return;
 
 	} while (!time_after(jiffies, deadline)); /* quota is exhausted */
diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c
index cf690df34775..c4113b43dbfe 100644
--- a/drivers/nvme/target/auth.c
+++ b/drivers/nvme/target/auth.c
@@ -196,6 +196,7 @@ int nvmet_setup_auth(struct nvmet_ctrl *ctrl)
 	if (IS_ERR(ctrl->ctrl_key)) {
 		ret = PTR_ERR(ctrl->ctrl_key);
 		ctrl->ctrl_key = NULL;
+		goto out_free_hash;
 	}
 	pr_debug("%s: using ctrl hash %s key %*ph\n", __func__,
 		 ctrl->ctrl_key->hash > 0 ?
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index a1345790005f..7f4083cf953a 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -735,6 +735,8 @@ static void nvmet_set_error(struct nvmet_req *req, u16 status)
 
 static void __nvmet_req_complete(struct nvmet_req *req, u16 status)
 {
+	struct nvmet_ns *ns = req->ns;
+
 	if (!req->sq->sqhd_disabled)
 		nvmet_update_sq_head(req);
 	req->cqe->sq_id = cpu_to_le16(req->sq->qid);
@@ -745,9 +747,9 @@ static void __nvmet_req_complete(struct nvmet_req *req, u16 status)
 
 	trace_nvmet_req_complete(req);
 
-	if (req->ns)
-		nvmet_put_namespace(req->ns);
 	req->ops->queue_response(req);
+	if (ns)
+		nvmet_put_namespace(ns);
 }
 
 void nvmet_req_complete(struct nvmet_req *req, u16 status)
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index dc3b4dc8fe08..a3694a32f6d5 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1506,6 +1506,9 @@ static void nvmet_tcp_state_change(struct sock *sk)
 		goto done;
 
 	switch (sk->sk_state) {
+	case TCP_FIN_WAIT2:
+	case TCP_LAST_ACK:
+		break;
 	case TCP_FIN_WAIT1:
 	case TCP_CLOSE_WAIT:
 	case TCP_CLOSE:
diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c
index c7ef69f29fe4..835bfda86fcf 100644
--- a/drivers/nvme/target/zns.c
+++ b/drivers/nvme/target/zns.c
@@ -100,6 +100,7 @@ void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req)
 	struct nvme_id_ns_zns *id_zns;
 	u64 zsze;
 	u16 status;
+	u32 mar, mor;
 
 	if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) {
 		req->error_loc = offsetof(struct nvme_identify, nsid);
@@ -130,8 +131,20 @@ void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req)
 	zsze = (bdev_zone_sectors(req->ns->bdev) << 9) >>
 					req->ns->blksize_shift;
 	id_zns->lbafe[0].zsze = cpu_to_le64(zsze);
-	id_zns->mor = cpu_to_le32(bdev_max_open_zones(req->ns->bdev));
-	id_zns->mar = cpu_to_le32(bdev_max_active_zones(req->ns->bdev));
+
+	mor = bdev_max_open_zones(req->ns->bdev);
+	if (!mor)
+		mor = U32_MAX;
+	else
+		mor--;
+	id_zns->mor = cpu_to_le32(mor);
+
+	mar = bdev_max_active_zones(req->ns->bdev);
+	if (!mar)
+		mar = U32_MAX;
+	else
+		mar--;
+	id_zns->mar = cpu_to_le32(mar);
 
 done:
 	status = nvmet_copy_to_sgl(req, 0, id_zns, sizeof(*id_zns));
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 7bc92923104c..1c573e7a60bc 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -314,7 +314,7 @@ static int unflatten_dt_nodes(const void *blob,
 	for (offset = 0;
 	     offset >= 0 && depth >= initial_depth;
 	     offset = fdt_next_node(blob, offset, &depth)) {
-		if (WARN_ON_ONCE(depth >= FDT_MAX_DEPTH))
+		if (WARN_ON_ONCE(depth >= FDT_MAX_DEPTH - 1))
 			continue;
 
 		if (!IS_ENABLED(CONFIG_OF_KOBJ) &&
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 77d1ba3a4154..e87567dbe99f 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -873,7 +873,7 @@ int dev_pm_opp_config_clks_simple(struct device *dev,
 		}
 	}
 
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_config_clks_simple);
 
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index 9be007c9420f..a66386043aa6 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -268,7 +268,7 @@ static int ioc_count;
 *   Each bit can represent a number of pages.
 *   LSbs represent lower addresses (IOVA's).
 *
-*   This was was copied from sba_iommu.c. Don't try to unify
+*   This was copied from sba_iommu.c. Don't try to unify
 *   the two resource managers unless a way to have different
 *   allocation policies is also adjusted. We'd like to avoid
 *   I/O TLB thrashing by having resource allocation policy
@@ -1380,15 +1380,17 @@ ccio_init_resource(struct resource *res, char *name, void __iomem *ioaddr)
 	}
 }
 
-static void __init ccio_init_resources(struct ioc *ioc)
+static int __init ccio_init_resources(struct ioc *ioc)
 {
 	struct resource *res = ioc->mmio_region;
 	char *name = kmalloc(14, GFP_KERNEL);
-
+	if (unlikely(!name))
+		return -ENOMEM;
 	snprintf(name, 14, "GSC Bus [%d/]", ioc->hw_path);
 
 	ccio_init_resource(res, name, &ioc->ioc_regs->io_io_low);
 	ccio_init_resource(res + 1, name, &ioc->ioc_regs->io_io_low_hv);
+	return 0;
 }
 
 static int new_ioc_area(struct resource *res, unsigned long size,
@@ -1543,7 +1545,11 @@ static int __init ccio_probe(struct parisc_device *dev)
 		return -ENOMEM;
 	}
 	ccio_ioc_init(ioc);
-	ccio_init_resources(ioc);
+	if (ccio_init_resources(ioc)) {
+		iounmap(ioc->ioc_regs);
+		kfree(ioc);
+		return -ENOMEM;
+	}
 	hppa_dma_ops = &ccio_ops;
 
 	hba = kzalloc(sizeof(*hba), GFP_KERNEL);
diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c
index 3a8c98615634..bdef7a8d6ab8 100644
--- a/drivers/parisc/iosapic.c
+++ b/drivers/parisc/iosapic.c
@@ -221,16 +221,7 @@ static size_t irt_num_entry;
 
 static struct irt_entry *iosapic_alloc_irt(int num_entries)
 {
-	unsigned long a;
-
-	/* The IRT needs to be 8-byte aligned for the PDC call. 
-	 * Normally kmalloc would guarantee larger alignment, but
-	 * if CONFIG_DEBUG_SLAB is enabled, then we can get only
-	 * 4-byte alignment on 32-bit kernels
-	 */
-	a = (unsigned long)kmalloc(sizeof(struct irt_entry) * num_entries + 8, GFP_KERNEL);
-	a = (a + 7UL) & ~7UL;
-	return (struct irt_entry *)a;
+	return kcalloc(num_entries, sizeof(struct irt_entry), GFP_KERNEL);
 }
 
 /**
diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c
index 1e4a5663d011..d4be9d2ee74d 100644
--- a/drivers/parisc/led.c
+++ b/drivers/parisc/led.c
@@ -646,7 +646,7 @@ int lcd_print( const char *str )
 		cancel_delayed_work_sync(&led_task);
 
 	/* copy display string to buffer for procfs */
-	strlcpy(lcd_text, str, sizeof(lcd_text));
+	strscpy(lcd_text, str, sizeof(lcd_text));
 
 	/* Set LCD Cursor to 1st character */
 	gsc_writeb(lcd_info.reset_cmd1, LCD_CMD_REG);
diff --git a/drivers/peci/controller/peci-aspeed.c b/drivers/peci/controller/peci-aspeed.c
index 1925ddc13f00..731c5d8f75c6 100644
--- a/drivers/peci/controller/peci-aspeed.c
+++ b/drivers/peci/controller/peci-aspeed.c
@@ -523,7 +523,7 @@ static int aspeed_peci_probe(struct platform_device *pdev)
 		return PTR_ERR(priv->base);
 
 	priv->irq = platform_get_irq(pdev, 0);
-	if (!priv->irq)
+	if (priv->irq < 0)
 		return priv->irq;
 
 	ret = devm_request_irq(&pdev->dev, priv->irq, aspeed_peci_irq_handler,
diff --git a/drivers/peci/cpu.c b/drivers/peci/cpu.c
index 68eb61c65d34..de4a7b3e5966 100644
--- a/drivers/peci/cpu.c
+++ b/drivers/peci/cpu.c
@@ -188,8 +188,6 @@ static void adev_release(struct device *dev)
 {
 	struct auxiliary_device *adev = to_auxiliary_dev(dev);
 
-	auxiliary_device_uninit(adev);
-
 	kfree(adev->name);
 	kfree(adev);
 }
@@ -234,6 +232,7 @@ static void unregister_adev(void *_adev)
 	struct auxiliary_device *adev = _adev;
 
 	auxiliary_device_delete(adev);
+	auxiliary_device_uninit(adev);
 }
 
 static int devm_adev_add(struct device *dev, int idx)
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index 80d8309652a4..b80a9b74662b 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -36,7 +36,7 @@
 #define CMN_CI_CHILD_COUNT		GENMASK_ULL(15, 0)
 #define CMN_CI_CHILD_PTR_OFFSET		GENMASK_ULL(31, 16)
 
-#define CMN_CHILD_NODE_ADDR		GENMASK(27, 0)
+#define CMN_CHILD_NODE_ADDR		GENMASK(29, 0)
 #define CMN_CHILD_NODE_EXTERNAL		BIT(31)
 
 #define CMN_MAX_DIMENSION		12
diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c
index a36698a90d2f..4a15c86f45ef 100644
--- a/drivers/perf/arm_dsu_pmu.c
+++ b/drivers/perf/arm_dsu_pmu.c
@@ -639,6 +639,7 @@ static int dsu_pmu_dt_get_cpus(struct device *dev, cpumask_t *mask)
 static int dsu_pmu_acpi_get_cpus(struct device *dev, cpumask_t *mask)
 {
 #ifdef CONFIG_ACPI
+	struct acpi_device *parent_adev = acpi_dev_parent(ACPI_COMPANION(dev));
 	int cpu;
 
 	/*
@@ -653,8 +654,7 @@ static int dsu_pmu_acpi_get_cpus(struct device *dev, cpumask_t *mask)
 			continue;
 
 		acpi_dev = ACPI_COMPANION(cpu_dev);
-		if (acpi_dev &&
-			acpi_dev->parent == ACPI_COMPANION(dev)->parent)
+		if (acpi_dev && acpi_dev_parent(acpi_dev) == parent_adev)
 			cpumask_set_cpu(cpu, mask);
 	}
 #endif
diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c
index 513de1f54e2d..933b96e243b8 100644
--- a/drivers/perf/arm_pmu_platform.c
+++ b/drivers/perf/arm_pmu_platform.c
@@ -117,7 +117,7 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 
 	if (num_irqs == 1) {
 		int irq = platform_get_irq(pdev, 0);
-		if (irq && irq_is_percpu_devid(irq))
+		if ((irq > 0) && irq_is_percpu_devid(irq))
 			return pmu_parse_percpu_irq(pmu, irq);
 	}
 
diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c
index 30234c261b05..aaca6db7d8f6 100644
--- a/drivers/perf/qcom_l2_pmu.c
+++ b/drivers/perf/qcom_l2_pmu.c
@@ -840,16 +840,16 @@ static int l2_cache_pmu_probe_cluster(struct device *dev, void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev->parent);
 	struct platform_device *sdev = to_platform_device(dev);
-	struct acpi_device *adev = ACPI_COMPANION(dev);
 	struct l2cache_pmu *l2cache_pmu = data;
 	struct cluster_pmu *cluster;
-	unsigned long fw_cluster_id;
+	u64 fw_cluster_id;
 	int err;
 	int irq;
 
-	if (!adev || kstrtoul(adev->pnp.unique_id, 10, &fw_cluster_id) < 0) {
+	err = acpi_dev_uid_to_integer(ACPI_COMPANION(dev), &fw_cluster_id);
+	if (err) {
 		dev_err(&pdev->dev, "unable to read ACPI uid\n");
-		return -ENODEV;
+		return err;
 	}
 
 	cluster = devm_kzalloc(&pdev->dev, sizeof(*cluster), GFP_KERNEL);
@@ -879,7 +879,7 @@ static int l2_cache_pmu_probe_cluster(struct device *dev, void *data)
 	}
 
 	dev_info(&pdev->dev,
-		"Registered L2 cache PMU cluster %ld\n", fw_cluster_id);
+		 "Registered L2 cache PMU cluster %lld\n", fw_cluster_id);
 
 	spin_lock_init(&cluster->pmu_lock);
 
diff --git a/drivers/perf/qcom_l3_pmu.c b/drivers/perf/qcom_l3_pmu.c
index 1ff2ff6582bf..346311a05460 100644
--- a/drivers/perf/qcom_l3_pmu.c
+++ b/drivers/perf/qcom_l3_pmu.c
@@ -742,7 +742,8 @@ static int qcom_l3_cache_pmu_probe(struct platform_device *pdev)
 
 	l3pmu = devm_kzalloc(&pdev->dev, sizeof(*l3pmu), GFP_KERNEL);
 	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "l3cache_%s_%s",
-		      acpi_dev->parent->pnp.unique_id, acpi_dev->pnp.unique_id);
+		      acpi_dev_parent(acpi_dev)->pnp.unique_id,
+		      acpi_dev->pnp.unique_id);
 	if (!l3pmu || !name)
 		return -ENOMEM;
 
diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c
index 342778782359..2c20b0de8cb0 100644
--- a/drivers/perf/riscv_pmu_legacy.c
+++ b/drivers/perf/riscv_pmu_legacy.c
@@ -72,7 +72,7 @@ static void pmu_legacy_ctr_start(struct perf_event *event, u64 ival)
 	local64_set(&hwc->prev_count, initial_val);
 }
 
-/**
+/*
  * This is just a simple implementation to allow legacy implementations
  * compatible with new RISC-V PMU driver framework.
  * This driver only allows reading two counters i.e CYCLE & INSTRET.
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 6f6681bbfd36..8de4ca2fef21 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -473,7 +473,7 @@ static int pmu_sbi_get_ctrinfo(int nctr)
 	if (!pmu_ctr_list)
 		return -ENOMEM;
 
-	for (i = 0; i <= nctr; i++) {
+	for (i = 0; i < nctr; i++) {
 		ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_GET_INFO, i, 0, 0, 0, 0, 0);
 		if (ret.error)
 			/* The logical counter ids are not expected to be contiguous */
diff --git a/drivers/phy/marvell/phy-mvebu-a3700-comphy.c b/drivers/phy/marvell/phy-mvebu-a3700-comphy.c
index a4d7d9bd100d..67712c77d806 100644
--- a/drivers/phy/marvell/phy-mvebu-a3700-comphy.c
+++ b/drivers/phy/marvell/phy-mvebu-a3700-comphy.c
@@ -274,7 +274,6 @@ struct mvebu_a3700_comphy_lane {
 	int submode;
 	bool invert_tx;
 	bool invert_rx;
-	bool needs_reset;
 };
 
 struct gbe_phy_init_data_fix {
@@ -1097,40 +1096,12 @@ mvebu_a3700_comphy_pcie_power_off(struct mvebu_a3700_comphy_lane *lane)
 			    0x0, PU_PLL_BIT | PU_RX_BIT | PU_TX_BIT);
 }
 
-static int mvebu_a3700_comphy_reset(struct phy *phy)
+static void mvebu_a3700_comphy_usb3_power_off(struct mvebu_a3700_comphy_lane *lane)
 {
-	struct mvebu_a3700_comphy_lane *lane = phy_get_drvdata(phy);
-	u16 mask, data;
-
-	dev_dbg(lane->dev, "resetting lane %d\n", lane->id);
-
-	/* COMPHY reset for internal logic */
-	comphy_lane_reg_set(lane, COMPHY_SFT_RESET,
-			    SFT_RST_NO_REG, SFT_RST_NO_REG);
-
-	/* COMPHY register reset (cleared automatically) */
-	comphy_lane_reg_set(lane, COMPHY_SFT_RESET, SFT_RST, SFT_RST);
-
-	/* PIPE soft and register reset */
-	data = PIPE_SOFT_RESET | PIPE_REG_RESET;
-	mask = data;
-	comphy_lane_reg_set(lane, COMPHY_PIPE_RST_CLK_CTRL, data, mask);
-
-	/* Release PIPE register reset */
-	comphy_lane_reg_set(lane, COMPHY_PIPE_RST_CLK_CTRL,
-			    0x0, PIPE_REG_RESET);
-
-	/* Reset SB configuration register (only for lanes 0 and 1) */
-	if (lane->id == 0 || lane->id == 1) {
-		u32 mask, data;
-
-		data = PIN_RESET_CORE_BIT | PIN_RESET_COMPHY_BIT |
-		       PIN_PU_PLL_BIT | PIN_PU_RX_BIT | PIN_PU_TX_BIT;
-		mask = data | PIN_PU_IVREF_BIT | PIN_TX_IDLE_BIT;
-		comphy_periph_reg_set(lane, COMPHY_PHY_CFG1, data, mask);
-	}
-
-	return 0;
+	/*
+	 * The USB3 MAC sets the USB3 PHY to low state, so we do not
+	 * need to power off USB3 PHY again.
+	 */
 }
 
 static bool mvebu_a3700_comphy_check_mode(int lane,
@@ -1171,10 +1142,6 @@ static int mvebu_a3700_comphy_set_mode(struct phy *phy, enum phy_mode mode,
 	    (lane->mode != mode || lane->submode != submode))
 		return -EBUSY;
 
-	/* If changing mode, ensure reset is called */
-	if (lane->mode != PHY_MODE_INVALID && lane->mode != mode)
-		lane->needs_reset = true;
-
 	/* Just remember the mode, ->power_on() will do the real setup */
 	lane->mode = mode;
 	lane->submode = submode;
@@ -1185,7 +1152,6 @@ static int mvebu_a3700_comphy_set_mode(struct phy *phy, enum phy_mode mode,
 static int mvebu_a3700_comphy_power_on(struct phy *phy)
 {
 	struct mvebu_a3700_comphy_lane *lane = phy_get_drvdata(phy);
-	int ret;
 
 	if (!mvebu_a3700_comphy_check_mode(lane->id, lane->mode,
 					   lane->submode)) {
@@ -1193,14 +1159,6 @@ static int mvebu_a3700_comphy_power_on(struct phy *phy)
 		return -EINVAL;
 	}
 
-	if (lane->needs_reset) {
-		ret = mvebu_a3700_comphy_reset(phy);
-		if (ret)
-			return ret;
-
-		lane->needs_reset = false;
-	}
-
 	switch (lane->mode) {
 	case PHY_MODE_USB_HOST_SS:
 		dev_dbg(lane->dev, "set lane %d to USB3 host mode\n", lane->id);
@@ -1224,38 +1182,28 @@ static int mvebu_a3700_comphy_power_off(struct phy *phy)
 {
 	struct mvebu_a3700_comphy_lane *lane = phy_get_drvdata(phy);
 
-	switch (lane->mode) {
-	case PHY_MODE_USB_HOST_SS:
-		/*
-		 * The USB3 MAC sets the USB3 PHY to low state, so we do not
-		 * need to power off USB3 PHY again.
-		 */
-		break;
-
-	case PHY_MODE_SATA:
-		mvebu_a3700_comphy_sata_power_off(lane);
-		break;
-
-	case PHY_MODE_ETHERNET:
+	switch (lane->id) {
+	case 0:
+		mvebu_a3700_comphy_usb3_power_off(lane);
 		mvebu_a3700_comphy_ethernet_power_off(lane);
-		break;
-
-	case PHY_MODE_PCIE:
+		return 0;
+	case 1:
 		mvebu_a3700_comphy_pcie_power_off(lane);
-		break;
-
+		mvebu_a3700_comphy_ethernet_power_off(lane);
+		return 0;
+	case 2:
+		mvebu_a3700_comphy_usb3_power_off(lane);
+		mvebu_a3700_comphy_sata_power_off(lane);
+		return 0;
 	default:
 		dev_err(lane->dev, "invalid COMPHY mode\n");
 		return -EINVAL;
 	}
-
-	return 0;
 }
 
 static const struct phy_ops mvebu_a3700_comphy_ops = {
 	.power_on	= mvebu_a3700_comphy_power_on,
 	.power_off	= mvebu_a3700_comphy_power_off,
-	.reset		= mvebu_a3700_comphy_reset,
 	.set_mode	= mvebu_a3700_comphy_set_mode,
 	.owner		= THIS_MODULE,
 };
@@ -1393,8 +1341,7 @@ static int mvebu_a3700_comphy_probe(struct platform_device *pdev)
 		 * To avoid relying on the bootloader/firmware configuration,
 		 * power off all comphys.
 		 */
-		mvebu_a3700_comphy_reset(phy);
-		lane->needs_reset = false;
+		mvebu_a3700_comphy_power_off(phy);
 	}
 
 	provider = devm_of_phy_provider_register(&pdev->dev,
diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c
index c5fd154990c8..c7df8c5fe585 100644
--- a/drivers/pinctrl/pinctrl-ocelot.c
+++ b/drivers/pinctrl/pinctrl-ocelot.c
@@ -331,6 +331,7 @@ struct ocelot_pinctrl {
 	const struct ocelot_pincfg_data *pincfg_data;
 	struct ocelot_pmx_func func[FUNC_MAX];
 	u8 stride;
+	struct workqueue_struct *wq;
 };
 
 struct ocelot_match_data {
@@ -338,6 +339,11 @@ struct ocelot_match_data {
 	struct ocelot_pincfg_data pincfg_data;
 };
 
+struct ocelot_irq_work {
+	struct work_struct irq_work;
+	struct irq_desc *irq_desc;
+};
+
 #define LUTON_P(p, f0, f1)						\
 static struct ocelot_pin_caps luton_pin_##p = {				\
 	.pin = p,							\
@@ -1813,6 +1819,75 @@ static void ocelot_irq_mask(struct irq_data *data)
 	gpiochip_disable_irq(chip, gpio);
 }
 
+static void ocelot_irq_work(struct work_struct *work)
+{
+	struct ocelot_irq_work *w = container_of(work, struct ocelot_irq_work, irq_work);
+	struct irq_chip *parent_chip = irq_desc_get_chip(w->irq_desc);
+	struct gpio_chip *chip = irq_desc_get_chip_data(w->irq_desc);
+	struct irq_data *data = irq_desc_get_irq_data(w->irq_desc);
+	unsigned int gpio = irqd_to_hwirq(data);
+
+	local_irq_disable();
+	chained_irq_enter(parent_chip, w->irq_desc);
+	generic_handle_domain_irq(chip->irq.domain, gpio);
+	chained_irq_exit(parent_chip, w->irq_desc);
+	local_irq_enable();
+
+	kfree(w);
+}
+
+static void ocelot_irq_unmask_level(struct irq_data *data)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
+	struct ocelot_pinctrl *info = gpiochip_get_data(chip);
+	struct irq_desc *desc = irq_data_to_desc(data);
+	unsigned int gpio = irqd_to_hwirq(data);
+	unsigned int bit = BIT(gpio % 32);
+	bool ack = false, active = false;
+	u8 trigger_level;
+	int val;
+
+	trigger_level = irqd_get_trigger_type(data);
+
+	/* Check if the interrupt line is still active. */
+	regmap_read(info->map, REG(OCELOT_GPIO_IN, info, gpio), &val);
+	if ((!(val & bit) && trigger_level == IRQ_TYPE_LEVEL_LOW) ||
+	      (val & bit && trigger_level == IRQ_TYPE_LEVEL_HIGH))
+		active = true;
+
+	/*
+	 * Check if the interrupt controller has seen any changes in the
+	 * interrupt line.
+	 */
+	regmap_read(info->map, REG(OCELOT_GPIO_INTR, info, gpio), &val);
+	if (val & bit)
+		ack = true;
+
+	/* Enable the interrupt now */
+	gpiochip_enable_irq(chip, gpio);
+	regmap_update_bits(info->map, REG(OCELOT_GPIO_INTR_ENA, info, gpio),
+			   bit, bit);
+
+	/*
+	 * In case the interrupt line is still active and the interrupt
+	 * controller has not seen any changes in the interrupt line, then it
+	 * means that there happen another interrupt while the line was active.
+	 * So we missed that one, so we need to kick the interrupt again
+	 * handler.
+	 */
+	if (active && !ack) {
+		struct ocelot_irq_work *work;
+
+		work = kmalloc(sizeof(*work), GFP_ATOMIC);
+		if (!work)
+			return;
+
+		work->irq_desc = desc;
+		INIT_WORK(&work->irq_work, ocelot_irq_work);
+		queue_work(info->wq, &work->irq_work);
+	}
+}
+
 static void ocelot_irq_unmask(struct irq_data *data)
 {
 	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
@@ -1836,13 +1911,12 @@ static void ocelot_irq_ack(struct irq_data *data)
 
 static int ocelot_irq_set_type(struct irq_data *data, unsigned int type);
 
-static struct irq_chip ocelot_eoi_irqchip = {
+static struct irq_chip ocelot_level_irqchip = {
 	.name		= "gpio",
 	.irq_mask	= ocelot_irq_mask,
-	.irq_eoi	= ocelot_irq_ack,
-	.irq_unmask	= ocelot_irq_unmask,
-	.flags          = IRQCHIP_EOI_THREADED | IRQCHIP_EOI_IF_HANDLED |
-			  IRQCHIP_IMMUTABLE,
+	.irq_ack	= ocelot_irq_ack,
+	.irq_unmask	= ocelot_irq_unmask_level,
+	.flags		= IRQCHIP_IMMUTABLE,
 	.irq_set_type	= ocelot_irq_set_type,
 	GPIOCHIP_IRQ_RESOURCE_HELPERS
 };
@@ -1859,14 +1933,9 @@ static struct irq_chip ocelot_irqchip = {
 
 static int ocelot_irq_set_type(struct irq_data *data, unsigned int type)
 {
-	type &= IRQ_TYPE_SENSE_MASK;
-
-	if (!(type & (IRQ_TYPE_EDGE_BOTH | IRQ_TYPE_LEVEL_HIGH)))
-		return -EINVAL;
-
-	if (type & IRQ_TYPE_LEVEL_HIGH)
-		irq_set_chip_handler_name_locked(data, &ocelot_eoi_irqchip,
-						 handle_fasteoi_irq, NULL);
+	if (type & (IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_LEVEL_LOW))
+		irq_set_chip_handler_name_locked(data, &ocelot_level_irqchip,
+						 handle_level_irq, NULL);
 	if (type & IRQ_TYPE_EDGE_BOTH)
 		irq_set_chip_handler_name_locked(data, &ocelot_irqchip,
 						 handle_edge_irq, NULL);
@@ -1996,6 +2065,10 @@ static int ocelot_pinctrl_probe(struct platform_device *pdev)
 	if (!info->desc)
 		return -ENOMEM;
 
+	info->wq = alloc_ordered_workqueue("ocelot_ordered", 0);
+	if (!info->wq)
+		return -ENOMEM;
+
 	info->pincfg_data = &data->pincfg_data;
 
 	reset = devm_reset_control_get_optional_shared(dev, "switch");
@@ -2018,7 +2091,7 @@ static int ocelot_pinctrl_probe(struct platform_device *pdev)
 		dev_err(dev, "Failed to create regmap\n");
 		return PTR_ERR(info->map);
 	}
-	dev_set_drvdata(dev, info->map);
+	dev_set_drvdata(dev, info);
 	info->dev = dev;
 
 	/* Pinconf registers */
@@ -2043,6 +2116,15 @@ static int ocelot_pinctrl_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static int ocelot_pinctrl_remove(struct platform_device *pdev)
+{
+	struct ocelot_pinctrl *info = platform_get_drvdata(pdev);
+
+	destroy_workqueue(info->wq);
+
+	return 0;
+}
+
 static struct platform_driver ocelot_pinctrl_driver = {
 	.driver = {
 		.name = "pinctrl-ocelot",
@@ -2050,6 +2132,7 @@ static struct platform_driver ocelot_pinctrl_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = ocelot_pinctrl_probe,
+	.remove = ocelot_pinctrl_remove,
 };
 module_platform_driver(ocelot_pinctrl_driver);
 MODULE_LICENSE("Dual MIT/GPL");
diff --git a/drivers/pinctrl/qcom/pinctrl-sc8180x.c b/drivers/pinctrl/qcom/pinctrl-sc8180x.c
index 6bec7f143134..704a99d2f93c 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc8180x.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc8180x.c
@@ -530,10 +530,10 @@ DECLARE_MSM_GPIO_PINS(187);
 DECLARE_MSM_GPIO_PINS(188);
 DECLARE_MSM_GPIO_PINS(189);
 
-static const unsigned int sdc2_clk_pins[] = { 190 };
-static const unsigned int sdc2_cmd_pins[] = { 191 };
-static const unsigned int sdc2_data_pins[] = { 192 };
-static const unsigned int ufs_reset_pins[] = { 193 };
+static const unsigned int ufs_reset_pins[] = { 190 };
+static const unsigned int sdc2_clk_pins[] = { 191 };
+static const unsigned int sdc2_cmd_pins[] = { 192 };
+static const unsigned int sdc2_data_pins[] = { 193 };
 
 enum sc8180x_functions {
 	msm_mux_adsp_ext,
@@ -1582,7 +1582,7 @@ static const int sc8180x_acpi_reserved_gpios[] = {
 static const struct msm_gpio_wakeirq_map sc8180x_pdc_map[] = {
 	{ 3, 31 }, { 5, 32 }, { 8, 33 }, { 9, 34 }, { 10, 100 }, { 12, 104 },
 	{ 24, 37 }, { 26, 38 }, { 27, 41 }, { 28, 42 }, { 30, 39 }, { 36, 43 },
-	{ 37, 43 }, { 38, 45 }, { 39, 118 }, { 39, 125 }, { 41, 47 },
+	{ 37, 44 }, { 38, 45 }, { 39, 118 }, { 39, 125 }, { 41, 47 },
 	{ 42, 48 }, { 46, 50 }, { 47, 49 }, { 48, 51 }, { 49, 53 }, { 50, 52 },
 	{ 51, 116 }, { 51, 123 }, { 53, 54 }, { 54, 55 }, { 55, 56 },
 	{ 56, 57 }, { 58, 58 }, { 60, 60 }, { 68, 62 }, { 70, 63 }, { 76, 86 },
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun50i-a100-r.c b/drivers/pinctrl/sunxi/pinctrl-sun50i-a100-r.c
index afc1f5df7545..b82ad135bf2a 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sun50i-a100-r.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sun50i-a100-r.c
@@ -99,7 +99,7 @@ MODULE_DEVICE_TABLE(of, a100_r_pinctrl_match);
 static struct platform_driver a100_r_pinctrl_driver = {
 	.probe	= a100_r_pinctrl_probe,
 	.driver	= {
-		.name		= "sun50iw10p1-r-pinctrl",
+		.name		= "sun50i-a100-r-pinctrl",
 		.of_match_table	= a100_r_pinctrl_match,
 	},
 };
diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c
index 8be13d416f48..1ae3c56b66b0 100644
--- a/drivers/platform/mellanox/mlxbf-tmfifo.c
+++ b/drivers/platform/mellanox/mlxbf-tmfifo.c
@@ -928,7 +928,6 @@ static int mlxbf_tmfifo_virtio_find_vqs(struct virtio_device *vdev,
 					struct virtqueue *vqs[],
 					vq_callback_t *callbacks[],
 					const char * const names[],
-					u32 sizes[],
 					const bool *ctx,
 					struct irq_affinity *desc)
 {
diff --git a/drivers/platform/mellanox/mlxreg-lc.c b/drivers/platform/mellanox/mlxreg-lc.c
index 55834ccb4ac7..1e071df4c9f5 100644
--- a/drivers/platform/mellanox/mlxreg-lc.c
+++ b/drivers/platform/mellanox/mlxreg-lc.c
@@ -460,8 +460,6 @@ static int mlxreg_lc_power_on_off(struct mlxreg_lc *mlxreg_lc, u8 action)
 	u32 regval;
 	int err;
 
-	mutex_lock(&mlxreg_lc->lock);
-
 	err = regmap_read(mlxreg_lc->par_regmap, mlxreg_lc->data->reg_pwr, &regval);
 	if (err)
 		goto regmap_read_fail;
@@ -474,7 +472,6 @@ static int mlxreg_lc_power_on_off(struct mlxreg_lc *mlxreg_lc, u8 action)
 	err = regmap_write(mlxreg_lc->par_regmap, mlxreg_lc->data->reg_pwr, regval);
 
 regmap_read_fail:
-	mutex_unlock(&mlxreg_lc->lock);
 	return err;
 }
 
@@ -491,8 +488,6 @@ static int mlxreg_lc_enable_disable(struct mlxreg_lc *mlxreg_lc, bool action)
 	 * line card which is already has been enabled. Disabling does not affect the disabled line
 	 * card.
 	 */
-	mutex_lock(&mlxreg_lc->lock);
-
 	err = regmap_read(mlxreg_lc->par_regmap, mlxreg_lc->data->reg_ena, &regval);
 	if (err)
 		goto regmap_read_fail;
@@ -505,7 +500,6 @@ static int mlxreg_lc_enable_disable(struct mlxreg_lc *mlxreg_lc, bool action)
 	err = regmap_write(mlxreg_lc->par_regmap, mlxreg_lc->data->reg_ena, regval);
 
 regmap_read_fail:
-	mutex_unlock(&mlxreg_lc->lock);
 	return err;
 }
 
@@ -538,6 +532,15 @@ mlxreg_lc_sn4800_c16_config_init(struct mlxreg_lc *mlxreg_lc, void *regmap,
 static void
 mlxreg_lc_state_update(struct mlxreg_lc *mlxreg_lc, enum mlxreg_lc_state state, u8 action)
 {
+	if (action)
+		mlxreg_lc->state |= state;
+	else
+		mlxreg_lc->state &= ~state;
+}
+
+static void
+mlxreg_lc_state_update_locked(struct mlxreg_lc *mlxreg_lc, enum mlxreg_lc_state state, u8 action)
+{
 	mutex_lock(&mlxreg_lc->lock);
 
 	if (action)
@@ -560,8 +563,11 @@ static int mlxreg_lc_event_handler(void *handle, enum mlxreg_hotplug_kind kind,
 	dev_info(mlxreg_lc->dev, "linecard#%d state %d event kind %d action %d\n",
 		 mlxreg_lc->data->slot, mlxreg_lc->state, kind, action);
 
-	if (!(mlxreg_lc->state & MLXREG_LC_INITIALIZED))
+	mutex_lock(&mlxreg_lc->lock);
+	if (!(mlxreg_lc->state & MLXREG_LC_INITIALIZED)) {
+		mutex_unlock(&mlxreg_lc->lock);
 		return 0;
+	}
 
 	switch (kind) {
 	case MLXREG_HOTPLUG_LC_SYNCED:
@@ -574,7 +580,7 @@ static int mlxreg_lc_event_handler(void *handle, enum mlxreg_hotplug_kind kind,
 		if (!(mlxreg_lc->state & MLXREG_LC_POWERED) && action) {
 			err = mlxreg_lc_power_on_off(mlxreg_lc, 1);
 			if (err)
-				return err;
+				goto mlxreg_lc_power_on_off_fail;
 		}
 		/* In case line card is configured - enable it. */
 		if (mlxreg_lc->state & MLXREG_LC_CONFIGURED && action)
@@ -588,12 +594,13 @@ static int mlxreg_lc_event_handler(void *handle, enum mlxreg_hotplug_kind kind,
 				/* In case line card is configured - enable it. */
 				if (mlxreg_lc->state & MLXREG_LC_CONFIGURED)
 					err = mlxreg_lc_enable_disable(mlxreg_lc, 1);
+				mutex_unlock(&mlxreg_lc->lock);
 				return err;
 			}
 			err = mlxreg_lc_create_static_devices(mlxreg_lc, mlxreg_lc->main_devs,
 							      mlxreg_lc->main_devs_num);
 			if (err)
-				return err;
+				goto mlxreg_lc_create_static_devices_fail;
 
 			/* In case line card is already in ready state - enable it. */
 			if (mlxreg_lc->state & MLXREG_LC_CONFIGURED)
@@ -620,6 +627,10 @@ static int mlxreg_lc_event_handler(void *handle, enum mlxreg_hotplug_kind kind,
 		break;
 	}
 
+mlxreg_lc_power_on_off_fail:
+mlxreg_lc_create_static_devices_fail:
+	mutex_unlock(&mlxreg_lc->lock);
+
 	return err;
 }
 
@@ -665,7 +676,7 @@ static int mlxreg_lc_completion_notify(void *handle, struct i2c_adapter *parent,
 		if (err)
 			goto mlxreg_lc_create_static_devices_failed;
 
-		mlxreg_lc_state_update(mlxreg_lc, MLXREG_LC_POWERED, 1);
+		mlxreg_lc_state_update_locked(mlxreg_lc, MLXREG_LC_POWERED, 1);
 	}
 
 	/* Verify if line card is synchronized. */
@@ -676,7 +687,7 @@ static int mlxreg_lc_completion_notify(void *handle, struct i2c_adapter *parent,
 	/* Power on line card if necessary. */
 	if (regval & mlxreg_lc->data->mask) {
 		mlxreg_lc->state |= MLXREG_LC_SYNCED;
-		mlxreg_lc_state_update(mlxreg_lc, MLXREG_LC_SYNCED, 1);
+		mlxreg_lc_state_update_locked(mlxreg_lc, MLXREG_LC_SYNCED, 1);
 		if (mlxreg_lc->state & ~MLXREG_LC_POWERED) {
 			err = mlxreg_lc_power_on_off(mlxreg_lc, 1);
 			if (err)
@@ -684,7 +695,7 @@ static int mlxreg_lc_completion_notify(void *handle, struct i2c_adapter *parent,
 		}
 	}
 
-	mlxreg_lc_state_update(mlxreg_lc, MLXREG_LC_INITIALIZED, 1);
+	mlxreg_lc_state_update_locked(mlxreg_lc, MLXREG_LC_INITIALIZED, 1);
 
 	return 0;
 
@@ -814,10 +825,9 @@ static int mlxreg_lc_probe(struct platform_device *pdev)
 
 	mutex_init(&mlxreg_lc->lock);
 	/* Set event notification callback. */
-	if (data->notifier) {
-		data->notifier->user_handler = mlxreg_lc_event_handler;
-		data->notifier->handle = mlxreg_lc;
-	}
+	data->notifier->user_handler = mlxreg_lc_event_handler;
+	data->notifier->handle = mlxreg_lc;
+
 	data->hpdev.adapter = i2c_get_adapter(data->hpdev.nr);
 	if (!data->hpdev.adapter) {
 		dev_err(&pdev->dev, "Failed to get adapter for bus %d\n",
@@ -863,7 +873,6 @@ static int mlxreg_lc_probe(struct platform_device *pdev)
 	if (err) {
 		dev_err(&pdev->dev, "Failed to sync regmap for client %s at bus %d at addr 0x%02x\n",
 			data->hpdev.brdinfo->type, data->hpdev.nr, data->hpdev.brdinfo->addr);
-		err = PTR_ERR(regmap);
 		goto regcache_sync_fail;
 	}
 
@@ -878,16 +887,14 @@ static int mlxreg_lc_probe(struct platform_device *pdev)
 	if (err)
 		goto mlxreg_lc_config_init_fail;
 
-	return err;
+	return 0;
 
 mlxreg_lc_config_init_fail:
 regcache_sync_fail:
 regmap_write_fail:
 devm_regmap_init_i2c_fail:
-	if (data->hpdev.client) {
-		i2c_unregister_device(data->hpdev.client);
-		data->hpdev.client = NULL;
-	}
+	i2c_unregister_device(data->hpdev.client);
+	data->hpdev.client = NULL;
 i2c_new_device_fail:
 	i2c_put_adapter(data->hpdev.adapter);
 	data->hpdev.adapter = NULL;
@@ -905,6 +912,8 @@ static int mlxreg_lc_remove(struct platform_device *pdev)
 	struct mlxreg_core_data *data = dev_get_platdata(&pdev->dev);
 	struct mlxreg_lc *mlxreg_lc = platform_get_drvdata(pdev);
 
+	mlxreg_lc_state_update_locked(mlxreg_lc, MLXREG_LC_INITIALIZED, 0);
+
 	/*
 	 * Probing and removing are invoked by hotplug events raised upon line card insertion and
 	 * removing. If probing procedure fails all data is cleared. However, hotplug event still
diff --git a/drivers/platform/surface/surface_aggregator_registry.c b/drivers/platform/surface/surface_aggregator_registry.c
index d5655f6a4a41..585911020cea 100644
--- a/drivers/platform/surface/surface_aggregator_registry.c
+++ b/drivers/platform/surface/surface_aggregator_registry.c
@@ -86,38 +86,38 @@ static const struct software_node ssam_node_bas_dtx = {
 	.parent = &ssam_node_root,
 };
 
-/* HID keyboard (TID1). */
-static const struct software_node ssam_node_hid_tid1_keyboard = {
+/* HID keyboard (SAM, TID=1). */
+static const struct software_node ssam_node_hid_sam_keyboard = {
 	.name = "ssam:01:15:01:01:00",
 	.parent = &ssam_node_root,
 };
 
-/* HID pen stash (TID1; pen taken / stashed away evens). */
-static const struct software_node ssam_node_hid_tid1_penstash = {
+/* HID pen stash (SAM, TID=1; pen taken / stashed away evens). */
+static const struct software_node ssam_node_hid_sam_penstash = {
 	.name = "ssam:01:15:01:02:00",
 	.parent = &ssam_node_root,
 };
 
-/* HID touchpad (TID1). */
-static const struct software_node ssam_node_hid_tid1_touchpad = {
+/* HID touchpad (SAM, TID=1). */
+static const struct software_node ssam_node_hid_sam_touchpad = {
 	.name = "ssam:01:15:01:03:00",
 	.parent = &ssam_node_root,
 };
 
-/* HID device instance 6 (TID1, unknown HID device). */
-static const struct software_node ssam_node_hid_tid1_iid6 = {
+/* HID device instance 6 (SAM, TID=1, HID sensor collection). */
+static const struct software_node ssam_node_hid_sam_sensors = {
 	.name = "ssam:01:15:01:06:00",
 	.parent = &ssam_node_root,
 };
 
-/* HID device instance 7 (TID1, unknown HID device). */
-static const struct software_node ssam_node_hid_tid1_iid7 = {
+/* HID device instance 7 (SAM, TID=1, UCM UCSI HID client). */
+static const struct software_node ssam_node_hid_sam_ucm_ucsi = {
 	.name = "ssam:01:15:01:07:00",
 	.parent = &ssam_node_root,
 };
 
-/* HID system controls (TID1). */
-static const struct software_node ssam_node_hid_tid1_sysctrl = {
+/* HID system controls (SAM, TID=1). */
+static const struct software_node ssam_node_hid_sam_sysctrl = {
 	.name = "ssam:01:15:01:08:00",
 	.parent = &ssam_node_root,
 };
@@ -182,8 +182,8 @@ static const struct software_node ssam_node_hid_kip_touchpad = {
 	.parent = &ssam_node_hub_kip,
 };
 
-/* HID device instance 5 (KIP hub, unknown HID device). */
-static const struct software_node ssam_node_hid_kip_iid5 = {
+/* HID device instance 5 (KIP hub, type-cover firmware update). */
+static const struct software_node ssam_node_hid_kip_fwupd = {
 	.name = "ssam:01:15:02:05:00",
 	.parent = &ssam_node_hub_kip,
 };
@@ -241,12 +241,12 @@ static const struct software_node *ssam_node_group_sls[] = {
 	&ssam_node_bat_main,
 	&ssam_node_tmp_pprof,
 	&ssam_node_pos_tablet_switch,
-	&ssam_node_hid_tid1_keyboard,
-	&ssam_node_hid_tid1_penstash,
-	&ssam_node_hid_tid1_touchpad,
-	&ssam_node_hid_tid1_iid6,
-	&ssam_node_hid_tid1_iid7,
-	&ssam_node_hid_tid1_sysctrl,
+	&ssam_node_hid_sam_keyboard,
+	&ssam_node_hid_sam_penstash,
+	&ssam_node_hid_sam_touchpad,
+	&ssam_node_hid_sam_sensors,
+	&ssam_node_hid_sam_ucm_ucsi,
+	&ssam_node_hid_sam_sysctrl,
 	NULL,
 };
 
@@ -278,7 +278,9 @@ static const struct software_node *ssam_node_group_sp8[] = {
 	&ssam_node_hid_kip_keyboard,
 	&ssam_node_hid_kip_penstash,
 	&ssam_node_hid_kip_touchpad,
-	&ssam_node_hid_kip_iid5,
+	&ssam_node_hid_kip_fwupd,
+	&ssam_node_hid_sam_sensors,
+	&ssam_node_hid_sam_ucm_ucsi,
 	NULL,
 };
 
@@ -325,6 +327,9 @@ static const struct acpi_device_id ssam_platform_hub_match[] = {
 	/* Surface Laptop Go 1 */
 	{ "MSHW0118", (unsigned long)ssam_node_group_slg1 },
 
+	/* Surface Laptop Go 2 */
+	{ "MSHW0290", (unsigned long)ssam_node_group_slg1 },
+
 	/* Surface Laptop Studio */
 	{ "MSHW0123", (unsigned long)ssam_node_group_sls },
 
diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index e0230ea0cb7e..f1259d81d86d 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -99,6 +99,7 @@ static const struct key_entry acer_wmi_keymap[] __initconst = {
 	{KE_KEY, 0x22, {KEY_PROG2} },    /* Arcade */
 	{KE_KEY, 0x23, {KEY_PROG3} },    /* P_Key */
 	{KE_KEY, 0x24, {KEY_PROG4} },    /* Social networking_Key */
+	{KE_KEY, 0x27, {KEY_HELP} },
 	{KE_KEY, 0x29, {KEY_PROG3} },    /* P_Key for TM8372 */
 	{KE_IGNORE, 0x41, {KEY_MUTE} },
 	{KE_IGNORE, 0x42, {KEY_PREVIOUSSONG} },
@@ -112,7 +113,13 @@ static const struct key_entry acer_wmi_keymap[] __initconst = {
 	{KE_IGNORE, 0x48, {KEY_VOLUMEUP} },
 	{KE_IGNORE, 0x49, {KEY_VOLUMEDOWN} },
 	{KE_IGNORE, 0x4a, {KEY_VOLUMEDOWN} },
-	{KE_IGNORE, 0x61, {KEY_SWITCHVIDEOMODE} },
+	/*
+	 * 0x61 is KEY_SWITCHVIDEOMODE. Usually this is a duplicate input event
+	 * with the "Video Bus" input device events. But sometimes it is not
+	 * a dup. Map it to KEY_UNKNOWN instead of using KE_IGNORE so that
+	 * udev/hwdb can override it on systems where it is not a dup.
+	 */
+	{KE_KEY, 0x61, {KEY_UNKNOWN} },
 	{KE_IGNORE, 0x62, {KEY_BRIGHTNESSUP} },
 	{KE_IGNORE, 0x63, {KEY_BRIGHTNESSDOWN} },
 	{KE_KEY, 0x64, {KEY_SWITCHVIDEOMODE} },	/* Display Switch */
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 89b604e04d7f..eec7d0ed7cf2 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -107,7 +107,7 @@ module_param(fnlock_default, bool, 0444);
 #define WMI_EVENT_MASK			0xFFFF
 
 #define FAN_CURVE_POINTS		8
-#define FAN_CURVE_BUF_LEN		(FAN_CURVE_POINTS * 2)
+#define FAN_CURVE_BUF_LEN		32
 #define FAN_CURVE_DEV_CPU		0x00
 #define FAN_CURVE_DEV_GPU		0x01
 /* Mask to determine if setting temperature or percentage */
@@ -1118,7 +1118,7 @@ static int asus_wmi_led_init(struct asus_wmi *asus)
 	}
 
 	if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_MICMUTE_LED)) {
-		asus->micmute_led.name = "asus::micmute";
+		asus->micmute_led.name = "platform::micmute";
 		asus->micmute_led.max_brightness = 1;
 		asus->micmute_led.brightness = ledtrig_audio_get(LED_AUDIO_MICMUTE);
 		asus->micmute_led.brightness_set_blocking = micmute_led_set;
@@ -2233,8 +2233,10 @@ static int fan_curve_get_factory_default(struct asus_wmi *asus, u32 fan_dev)
 	curves = &asus->custom_fan_curves[fan_idx];
 	err = asus_wmi_evaluate_method_buf(asus->dsts_id, fan_dev, mode, buf,
 					   FAN_CURVE_BUF_LEN);
-	if (err)
+	if (err) {
+		pr_warn("%s (0x%08x) failed: %d\n", __func__, fan_dev, err);
 		return err;
+	}
 
 	fan_curve_copy_from_buf(curves, buf);
 	curves->device_id = fan_dev;
@@ -2252,9 +2254,6 @@ static int fan_curve_check_present(struct asus_wmi *asus, bool *available,
 
 	err = fan_curve_get_factory_default(asus, fan_dev);
 	if (err) {
-		pr_debug("fan_curve_get_factory_default(0x%08x) failed: %d\n",
-			 fan_dev, err);
-		/* Don't cause probe to fail on devices without fan-curves */
 		return 0;
 	}
 
diff --git a/drivers/platform/x86/intel/int3472/common.c b/drivers/platform/x86/intel/int3472/common.c
index 77cf058e4168..9db2bb0bbba4 100644
--- a/drivers/platform/x86/intel/int3472/common.c
+++ b/drivers/platform/x86/intel/int3472/common.c
@@ -62,7 +62,7 @@ int skl_int3472_get_sensor_adev_and_name(struct device *dev,
 	struct acpi_device *sensor;
 	int ret = 0;
 
-	sensor = acpi_dev_get_first_consumer_dev(adev);
+	sensor = acpi_dev_get_next_consumer_dev(adev, NULL);
 	if (!sensor) {
 		dev_err(dev, "INT3472 seems to have no dependents.\n");
 		return -ENODEV;
diff --git a/drivers/platform/x86/intel/int3472/tps68470.c b/drivers/platform/x86/intel/int3472/tps68470.c
index 22f61b47f9e5..49fc379fe680 100644
--- a/drivers/platform/x86/intel/int3472/tps68470.c
+++ b/drivers/platform/x86/intel/int3472/tps68470.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Author: Dan Scally <djrscally@gmail.com> */
 
+#include <linux/acpi.h>
 #include <linux/i2c.h>
 #include <linux/kernel.h>
 #include <linux/mfd/core.h>
@@ -95,20 +96,65 @@ static int skl_int3472_tps68470_calc_type(struct acpi_device *adev)
 	return DESIGNED_FOR_WINDOWS;
 }
 
+/*
+ * Return the size of the flexible array member, because we'll need that later
+ * on to pass .pdata_size to cells.
+ */
+static int
+skl_int3472_fill_clk_pdata(struct device *dev, struct tps68470_clk_platform_data **clk_pdata)
+{
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+	struct acpi_device *consumer;
+	unsigned int n_consumers = 0;
+	const char *sensor_name;
+	unsigned int i = 0;
+
+	for_each_acpi_consumer_dev(adev, consumer)
+		n_consumers++;
+
+	if (!n_consumers) {
+		dev_err(dev, "INT3472 seems to have no dependents\n");
+		return -ENODEV;
+	}
+
+	*clk_pdata = devm_kzalloc(dev, struct_size(*clk_pdata, consumers, n_consumers),
+				  GFP_KERNEL);
+	if (!*clk_pdata)
+		return -ENOMEM;
+
+	(*clk_pdata)->n_consumers = n_consumers;
+	i = 0;
+
+	for_each_acpi_consumer_dev(adev, consumer) {
+		sensor_name = devm_kasprintf(dev, GFP_KERNEL, I2C_DEV_NAME_FORMAT,
+					     acpi_dev_name(consumer));
+		if (!sensor_name)
+			return -ENOMEM;
+
+		(*clk_pdata)->consumers[i].consumer_dev_name = sensor_name;
+		i++;
+	}
+
+	acpi_dev_put(consumer);
+
+	return n_consumers;
+}
+
 static int skl_int3472_tps68470_probe(struct i2c_client *client)
 {
 	struct acpi_device *adev = ACPI_COMPANION(&client->dev);
 	const struct int3472_tps68470_board_data *board_data;
-	struct tps68470_clk_platform_data clk_pdata = {};
+	struct tps68470_clk_platform_data *clk_pdata;
 	struct mfd_cell *cells;
 	struct regmap *regmap;
+	int n_consumers;
 	int device_type;
 	int ret;
+	int i;
 
-	ret = skl_int3472_get_sensor_adev_and_name(&client->dev, NULL,
-						   &clk_pdata.consumer_dev_name);
-	if (ret)
-		return ret;
+	n_consumers = skl_int3472_fill_clk_pdata(&client->dev, &clk_pdata);
+	if (n_consumers < 0)
+		return n_consumers;
 
 	regmap = devm_regmap_init_i2c(client, &tps68470_regmap_config);
 	if (IS_ERR(regmap)) {
@@ -142,22 +188,25 @@ static int skl_int3472_tps68470_probe(struct i2c_client *client)
 		 * the clk + regulators must be ready when this happens.
 		 */
 		cells[0].name = "tps68470-clk";
-		cells[0].platform_data = &clk_pdata;
-		cells[0].pdata_size = sizeof(clk_pdata);
+		cells[0].platform_data = clk_pdata;
+		cells[0].pdata_size = struct_size(clk_pdata, consumers, n_consumers);
 		cells[1].name = "tps68470-regulator";
 		cells[1].platform_data = (void *)board_data->tps68470_regulator_pdata;
 		cells[1].pdata_size = sizeof(struct tps68470_regulator_platform_data);
 		cells[2].name = "tps68470-gpio";
 
-		gpiod_add_lookup_table(board_data->tps68470_gpio_lookup_table);
+		for (i = 0; i < board_data->n_gpiod_lookups; i++)
+			gpiod_add_lookup_table(board_data->tps68470_gpio_lookup_tables[i]);
 
 		ret = devm_mfd_add_devices(&client->dev, PLATFORM_DEVID_NONE,
 					   cells, TPS68470_WIN_MFD_CELL_COUNT,
 					   NULL, 0, NULL);
 		kfree(cells);
 
-		if (ret)
-			gpiod_remove_lookup_table(board_data->tps68470_gpio_lookup_table);
+		if (ret) {
+			for (i = 0; i < board_data->n_gpiod_lookups; i++)
+				gpiod_remove_lookup_table(board_data->tps68470_gpio_lookup_tables[i]);
+		}
 
 		break;
 	case DESIGNED_FOR_CHROMEOS:
@@ -181,10 +230,13 @@ static int skl_int3472_tps68470_probe(struct i2c_client *client)
 static int skl_int3472_tps68470_remove(struct i2c_client *client)
 {
 	const struct int3472_tps68470_board_data *board_data;
+	int i;
 
 	board_data = int3472_tps68470_get_board_data(dev_name(&client->dev));
-	if (board_data)
-		gpiod_remove_lookup_table(board_data->tps68470_gpio_lookup_table);
+	if (board_data) {
+		for (i = 0; i < board_data->n_gpiod_lookups; i++)
+			gpiod_remove_lookup_table(board_data->tps68470_gpio_lookup_tables[i]);
+	}
 
 	return 0;
 }
diff --git a/drivers/platform/x86/intel/int3472/tps68470.h b/drivers/platform/x86/intel/int3472/tps68470.h
index cfd33eb62740..35915e701593 100644
--- a/drivers/platform/x86/intel/int3472/tps68470.h
+++ b/drivers/platform/x86/intel/int3472/tps68470.h
@@ -16,8 +16,9 @@ struct tps68470_regulator_platform_data;
 
 struct int3472_tps68470_board_data {
 	const char *dev_name;
-	struct gpiod_lookup_table *tps68470_gpio_lookup_table;
 	const struct tps68470_regulator_platform_data *tps68470_regulator_pdata;
+	unsigned int n_gpiod_lookups;
+	struct gpiod_lookup_table *tps68470_gpio_lookup_tables[];
 };
 
 const struct int3472_tps68470_board_data *int3472_tps68470_get_board_data(const char *dev_name);
diff --git a/drivers/platform/x86/intel/int3472/tps68470_board_data.c b/drivers/platform/x86/intel/int3472/tps68470_board_data.c
index 525f09a3b5ff..309eab9c0558 100644
--- a/drivers/platform/x86/intel/int3472/tps68470_board_data.c
+++ b/drivers/platform/x86/intel/int3472/tps68470_board_data.c
@@ -30,6 +30,15 @@ static struct regulator_consumer_supply int347a_vcm_consumer_supplies[] = {
 static struct regulator_consumer_supply int347a_vsio_consumer_supplies[] = {
 	REGULATOR_SUPPLY("dovdd", "i2c-INT347A:00"),
 	REGULATOR_SUPPLY("vsio", "i2c-INT347A:00-VCM"),
+	REGULATOR_SUPPLY("vddd", "i2c-INT347E:00"),
+};
+
+static struct regulator_consumer_supply int347a_aux1_consumer_supplies[] = {
+	REGULATOR_SUPPLY("vdda", "i2c-INT347E:00"),
+};
+
+static struct regulator_consumer_supply int347a_aux2_consumer_supplies[] = {
+	REGULATOR_SUPPLY("vdddo", "i2c-INT347E:00"),
 };
 
 static const struct regulator_init_data surface_go_tps68470_core_reg_init_data = {
@@ -86,6 +95,28 @@ static const struct regulator_init_data surface_go_tps68470_vsio_reg_init_data =
 	.consumer_supplies = int347a_vsio_consumer_supplies,
 };
 
+static const struct regulator_init_data surface_go_tps68470_aux1_reg_init_data = {
+	.constraints = {
+		.min_uV = 2815200,
+		.max_uV = 2815200,
+		.apply_uV = 1,
+		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+	},
+	.num_consumer_supplies = ARRAY_SIZE(int347a_aux1_consumer_supplies),
+	.consumer_supplies = int347a_aux1_consumer_supplies,
+};
+
+static const struct regulator_init_data surface_go_tps68470_aux2_reg_init_data = {
+	.constraints = {
+		.min_uV = 1800600,
+		.max_uV = 1800600,
+		.apply_uV = 1,
+		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+	},
+	.num_consumer_supplies = ARRAY_SIZE(int347a_aux2_consumer_supplies),
+	.consumer_supplies = int347a_aux2_consumer_supplies,
+};
+
 static const struct tps68470_regulator_platform_data surface_go_tps68470_pdata = {
 	.reg_init_data = {
 		[TPS68470_CORE] = &surface_go_tps68470_core_reg_init_data,
@@ -93,10 +124,12 @@ static const struct tps68470_regulator_platform_data surface_go_tps68470_pdata =
 		[TPS68470_VCM]  = &surface_go_tps68470_vcm_reg_init_data,
 		[TPS68470_VIO] = &surface_go_tps68470_vio_reg_init_data,
 		[TPS68470_VSIO] = &surface_go_tps68470_vsio_reg_init_data,
+		[TPS68470_AUX1] = &surface_go_tps68470_aux1_reg_init_data,
+		[TPS68470_AUX2] = &surface_go_tps68470_aux2_reg_init_data,
 	},
 };
 
-static struct gpiod_lookup_table surface_go_tps68470_gpios = {
+static struct gpiod_lookup_table surface_go_int347a_gpios = {
 	.dev_id = "i2c-INT347A:00",
 	.table = {
 		GPIO_LOOKUP("tps68470-gpio", 9, "reset", GPIO_ACTIVE_LOW),
@@ -105,16 +138,31 @@ static struct gpiod_lookup_table surface_go_tps68470_gpios = {
 	}
 };
 
+static struct gpiod_lookup_table surface_go_int347e_gpios = {
+	.dev_id = "i2c-INT347E:00",
+	.table = {
+		GPIO_LOOKUP("tps68470-gpio", 5, "enable", GPIO_ACTIVE_HIGH),
+		{ }
+	}
+};
+
 static const struct int3472_tps68470_board_data surface_go_tps68470_board_data = {
 	.dev_name = "i2c-INT3472:05",
-	.tps68470_gpio_lookup_table = &surface_go_tps68470_gpios,
 	.tps68470_regulator_pdata = &surface_go_tps68470_pdata,
+	.n_gpiod_lookups = 2,
+	.tps68470_gpio_lookup_tables = {
+		&surface_go_int347a_gpios,
+		&surface_go_int347e_gpios,
+	},
 };
 
 static const struct int3472_tps68470_board_data surface_go3_tps68470_board_data = {
 	.dev_name = "i2c-INT3472:01",
-	.tps68470_gpio_lookup_table = &surface_go_tps68470_gpios,
 	.tps68470_regulator_pdata = &surface_go_tps68470_pdata,
+	.n_gpiod_lookups = 1,
+	.tps68470_gpio_lookup_tables = {
+		&surface_go_int347a_gpios
+	},
 };
 
 static const struct dmi_system_id int3472_tps68470_board_data_table[] = {
diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c
index fb2e141f3eb8..384d0962ae93 100644
--- a/drivers/platform/x86/p2sb.c
+++ b/drivers/platform/x86/p2sb.c
@@ -42,10 +42,24 @@ static int p2sb_get_devfn(unsigned int *devfn)
 	return 0;
 }
 
+/* Copy resource from the first BAR of the device in question */
 static int p2sb_read_bar0(struct pci_dev *pdev, struct resource *mem)
 {
-	/* Copy resource from the first BAR of the device in question */
-	*mem = pdev->resource[0];
+	struct resource *bar0 = &pdev->resource[0];
+
+	/* Make sure we have no dangling pointers in the output */
+	memset(mem, 0, sizeof(*mem));
+
+	/*
+	 * We copy only selected fields from the original resource.
+	 * Because a PCI device will be removed soon, we may not use
+	 * any allocated data, hence we may not copy any pointers.
+	 */
+	mem->start = bar0->start;
+	mem->end = bar0->end;
+	mem->flags = bar0->flags;
+	mem->desc = bar0->desc;
+
 	return 0;
 }
 
diff --git a/drivers/platform/x86/pmc_atom.c b/drivers/platform/x86/pmc_atom.c
index 154317e9910d..5c757c7f64de 100644
--- a/drivers/platform/x86/pmc_atom.c
+++ b/drivers/platform/x86/pmc_atom.c
@@ -232,7 +232,7 @@ static void pmc_power_off(void)
 	pm1_cnt_port = acpi_base_addr + PM1_CNT;
 
 	pm1_cnt_value = inl(pm1_cnt_port);
-	pm1_cnt_value &= SLEEP_TYPE_MASK;
+	pm1_cnt_value &= ~SLEEP_TYPE_MASK;
 	pm1_cnt_value |= SLEEP_TYPE_S5;
 	pm1_cnt_value |= SLEEP_ENABLE;
 
diff --git a/drivers/platform/x86/serial-multi-instantiate.c b/drivers/platform/x86/serial-multi-instantiate.c
index 67feed25c9db..5362f1a7b77c 100644
--- a/drivers/platform/x86/serial-multi-instantiate.c
+++ b/drivers/platform/x86/serial-multi-instantiate.c
@@ -328,6 +328,7 @@ static const struct acpi_device_id smi_acpi_ids[] = {
 	{ "INT3515", (unsigned long)&int3515_data },
 	/* Non-conforming _HID for Cirrus Logic already released */
 	{ "CLSA0100", (unsigned long)&cs35l41_hda },
+	{ "CLSA0101", (unsigned long)&cs35l41_hda },
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, smi_acpi_ids);
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 22d4e8633e30..2dbb9fc011a7 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -10592,10 +10592,9 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm)
 	/* Ensure initial values are correct */
 	dytc_profile_refresh();
 
-	/* Set AMT correctly now we know current profile */
-	if ((dytc_capabilities & BIT(DYTC_FC_PSC)) &&
-	    (dytc_capabilities & BIT(DYTC_FC_AMT)))
-	    dytc_control_amt(dytc_current_profile == PLATFORM_PROFILE_BALANCED);
+	/* Workaround for https://bugzilla.kernel.org/show_bug.cgi?id=216347 */
+	if (dytc_capabilities & BIT(DYTC_FC_PSC))
+		dytc_profile_set(NULL, PLATFORM_PROFILE_BALANCED);
 
 	return 0;
 }
diff --git a/drivers/platform/x86/x86-android-tablets.c b/drivers/platform/x86/x86-android-tablets.c
index 480375977435..4acd6fa8d43b 100644
--- a/drivers/platform/x86/x86-android-tablets.c
+++ b/drivers/platform/x86/x86-android-tablets.c
@@ -663,9 +663,23 @@ static const struct x86_i2c_client_info chuwi_hi8_i2c_clients[] __initconst = {
 	},
 };
 
+static int __init chuwi_hi8_init(void)
+{
+	/*
+	 * Avoid the acpi_unregister_gsi() call in x86_acpi_irq_helper_get()
+	 * breaking the touchscreen + logging various errors when the Windows
+	 * BIOS is used.
+	 */
+	if (acpi_dev_present("MSSL0001", NULL, 1))
+		return -ENODEV;
+
+	return 0;
+}
+
 static const struct x86_dev_info chuwi_hi8_info __initconst = {
 	.i2c_client_info = chuwi_hi8_i2c_clients,
 	.i2c_client_count = ARRAY_SIZE(chuwi_hi8_i2c_clients),
+	.init = chuwi_hi8_init,
 };
 
 #define CZC_EC_EXTRA_PORT	0x68
diff --git a/drivers/pnp/pnpbios/pnpbios.h b/drivers/pnp/pnpbios/pnpbios.h
index 2ce739ff9c1a..f3302006842e 100644
--- a/drivers/pnp/pnpbios/pnpbios.h
+++ b/drivers/pnp/pnpbios/pnpbios.h
@@ -153,7 +153,6 @@ extern int  pnpbios_dont_use_current_config;
 extern int pnpbios_parse_data_stream(struct pnp_dev *dev, struct pnp_bios_node * node);
 extern int pnpbios_read_resources_from_node(struct pnp_dev *dev, struct pnp_bios_node *node);
 extern int pnpbios_write_resources_to_node(struct pnp_dev *dev, struct pnp_bios_node *node);
-extern void pnpid32_to_pnpid(u32 id, char *str);
 
 extern void pnpbios_print_status(const char * module, u16 status);
 extern void pnpbios_calls_init(union pnp_bios_install_struct * header);
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 21d624f9f5fb..26d00b1853b4 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -994,6 +994,9 @@ static u64 rapl_compute_time_window_core(struct rapl_package *rp, u64 value,
 		y = value & 0x1f;
 		value = (1 << y) * (4 + f) * rp->time_unit / 4;
 	} else {
+		if (value < rp->time_unit)
+			return 0;
+
 		do_div(value, rp->time_unit);
 		y = ilog2(value);
 		f = div64_u64(4 * (value - (1 << y)), 1 << y);
@@ -1035,7 +1038,6 @@ static const struct rapl_defaults rapl_defaults_spr_server = {
 	.check_unit = rapl_check_unit_core,
 	.set_floor_freq = set_floor_freq_default,
 	.compute_time_window = rapl_compute_time_window_core,
-	.dram_domain_energy_unit = 15300,
 	.psys_domain_energy_unit = 1000000000,
 	.spr_psys_bits = true,
 };
@@ -1110,6 +1112,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,		&rapl_defaults_core),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&rapl_defaults_core),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,        &rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&rapl_defaults_core),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&rapl_defaults_spr_server),
 	X86_MATCH_INTEL_FAM6_MODEL(LAKEFIELD,		&rapl_defaults_core),
 
diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c
index 42f2fc0bc8a9..321af498ee11 100644
--- a/drivers/ras/cec.c
+++ b/drivers/ras/cec.c
@@ -556,6 +556,14 @@ static int __init cec_init(void)
 	if (ce_arr.disabled)
 		return -ENODEV;
 
+	/*
+	 * Intel systems may avoid uncorrectable errors
+	 * if pages with corrected errors are aggressively
+	 * taken offline.
+	 */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		action_threshold = 2;
+
 	ce_arr.array = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!ce_arr.array) {
 		pr_err("Error allocating CE array page!\n");
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 7150b1d0159e..d3e8dc32832d 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -2733,13 +2733,18 @@ static int _regulator_do_enable(struct regulator_dev *rdev)
  */
 static int _regulator_handle_consumer_enable(struct regulator *regulator)
 {
+	int ret;
 	struct regulator_dev *rdev = regulator->rdev;
 
 	lockdep_assert_held_once(&rdev->mutex.base);
 
 	regulator->enable_count++;
-	if (regulator->uA_load && regulator->enable_count == 1)
-		return drms_uA_update(rdev);
+	if (regulator->uA_load && regulator->enable_count == 1) {
+		ret = drms_uA_update(rdev);
+		if (ret)
+			regulator->enable_count--;
+		return ret;
+	}
 
 	return 0;
 }
@@ -4784,10 +4789,10 @@ int regulator_bulk_get(struct device *dev, int num_consumers,
 		consumers[i].consumer = regulator_get(dev,
 						      consumers[i].supply);
 		if (IS_ERR(consumers[i].consumer)) {
-			consumers[i].consumer = NULL;
 			ret = dev_err_probe(dev, PTR_ERR(consumers[i].consumer),
 					    "Failed to get supply '%s'",
 					    consumers[i].supply);
+			consumers[i].consumer = NULL;
 			goto err;
 		}
 
diff --git a/drivers/regulator/max8973-regulator.c b/drivers/regulator/max8973-regulator.c
index fdcb0f508984..596cc36aaff6 100644
--- a/drivers/regulator/max8973-regulator.c
+++ b/drivers/regulator/max8973-regulator.c
@@ -434,9 +434,9 @@ static int max8973_init_dcdc(struct max8973_chip *max,
 	return ret;
 }
 
-static int max8973_thermal_read_temp(void *data, int *temp)
+static int max8973_thermal_read_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct max8973_chip *mchip = data;
+	struct max8973_chip *mchip = tz->devdata;
 	unsigned int val;
 	int ret;
 
@@ -465,7 +465,7 @@ static irqreturn_t max8973_thermal_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static const struct thermal_zone_of_device_ops max77621_tz_ops = {
+static const struct thermal_zone_device_ops max77621_tz_ops = {
 	.get_temp = max8973_thermal_read_temp,
 };
 
@@ -479,8 +479,8 @@ static int max8973_thermal_init(struct max8973_chip *mchip)
 	if (mchip->id != MAX77621)
 		return 0;
 
-	tzd = devm_thermal_zone_of_sensor_register(mchip->dev, 0, mchip,
-						   &max77621_tz_ops);
+	tzd = devm_thermal_of_zone_register(mchip->dev, 0, mchip,
+					    &max77621_tz_ops);
 	if (IS_ERR(tzd)) {
 		ret = PTR_ERR(tzd);
 		dev_err(mchip->dev, "Failed to register thermal sensor: %d\n",
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index 6b617024a67d..d899d6e98fb8 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -766,7 +766,7 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 		((pfuze_chip->chip_id == PFUZE3000) ? "3000" : "3001"))));
 
 	memcpy(pfuze_chip->regulator_descs, pfuze_chip->pfuze_regulators,
-		sizeof(pfuze_chip->regulator_descs));
+		regulator_num * sizeof(struct pfuze_regulator));
 
 	ret = pfuze_parse_regulators_dt(pfuze_chip);
 	if (ret)
diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c
index 81c4f5776109..0f7706e23eb9 100644
--- a/drivers/remoteproc/remoteproc_virtio.c
+++ b/drivers/remoteproc/remoteproc_virtio.c
@@ -158,7 +158,6 @@ static int rproc_virtio_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 				 struct virtqueue *vqs[],
 				 vq_callback_t *callbacks[],
 				 const char * const names[],
-				 u32 sizes[],
 				 const bool * ctx,
 				 struct irq_affinity *desc)
 {
diff --git a/drivers/reset/reset-imx7.c b/drivers/reset/reset-imx7.c
index 185a333df66c..d2408725eb2c 100644
--- a/drivers/reset/reset-imx7.c
+++ b/drivers/reset/reset-imx7.c
@@ -329,6 +329,7 @@ static int imx8mp_reset_set(struct reset_controller_dev *rcdev,
 		break;
 
 	case IMX8MP_RESET_PCIE_CTRL_APPS_EN:
+	case IMX8MP_RESET_PCIEPHY_PERST:
 		value = assert ? 0 : bit;
 		break;
 	}
diff --git a/drivers/reset/reset-microchip-sparx5.c b/drivers/reset/reset-microchip-sparx5.c
index 00b612a0effa..f3528dd1d084 100644
--- a/drivers/reset/reset-microchip-sparx5.c
+++ b/drivers/reset/reset-microchip-sparx5.c
@@ -33,11 +33,8 @@ static struct regmap_config sparx5_reset_regmap_config = {
 	.reg_stride	= 4,
 };
 
-static int sparx5_switch_reset(struct reset_controller_dev *rcdev,
-			       unsigned long id)
+static int sparx5_switch_reset(struct mchp_reset_context *ctx)
 {
-	struct mchp_reset_context *ctx =
-		container_of(rcdev, struct mchp_reset_context, rcdev);
 	u32 val;
 
 	/* Make sure the core is PROTECTED from reset */
@@ -54,8 +51,14 @@ static int sparx5_switch_reset(struct reset_controller_dev *rcdev,
 					1, 100);
 }
 
+static int sparx5_reset_noop(struct reset_controller_dev *rcdev,
+			     unsigned long id)
+{
+	return 0;
+}
+
 static const struct reset_control_ops sparx5_reset_ops = {
-	.reset = sparx5_switch_reset,
+	.reset = sparx5_reset_noop,
 };
 
 static int mchp_sparx5_map_syscon(struct platform_device *pdev, char *name,
@@ -122,6 +125,11 @@ static int mchp_sparx5_reset_probe(struct platform_device *pdev)
 	ctx->rcdev.of_node = dn;
 	ctx->props = device_get_match_data(&pdev->dev);
 
+	/* Issue the reset very early, our actual reset callback is a noop. */
+	err = sparx5_switch_reset(ctx);
+	if (err)
+		return err;
+
 	return devm_reset_controller_register(&pdev->dev, &ctx->rcdev);
 }
 
@@ -163,6 +171,10 @@ static int __init mchp_sparx5_reset_init(void)
 	return platform_driver_register(&mchp_sparx5_reset_driver);
 }
 
+/*
+ * Because this is a global reset, keep this postcore_initcall() to issue the
+ * reset as early as possible during the kernel startup.
+ */
 postcore_initcall(mchp_sparx5_reset_init);
 
 MODULE_DESCRIPTION("Microchip Sparx5 switch reset driver");
diff --git a/drivers/reset/reset-npcm.c b/drivers/reset/reset-npcm.c
index 24c55efa98e5..f2333506b0a6 100644
--- a/drivers/reset/reset-npcm.c
+++ b/drivers/reset/reset-npcm.c
@@ -291,7 +291,7 @@ static void npcm_usb_reset_npcm8xx(struct npcm_rc_data *rc)
 	iprst2 |= ipsrst2_bits;
 	iprst3 |= (ipsrst3_bits | NPCM_IPSRST3_USBPHY1 |
 		   NPCM_IPSRST3_USBPHY2);
-	iprst2 |= ipsrst4_bits;
+	iprst4 |= ipsrst4_bits;
 
 	writel(iprst1, rc->base + NPCM_IPSRST1);
 	writel(iprst2, rc->base + NPCM_IPSRST2);
diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index dc78a523a69f..b6b938aa6615 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -675,12 +675,12 @@ int dasd_alias_remove_device(struct dasd_device *device)
 struct dasd_device *dasd_alias_get_start_dev(struct dasd_device *base_device)
 {
 	struct dasd_eckd_private *alias_priv, *private = base_device->private;
-	struct alias_pav_group *group = private->pavgroup;
 	struct alias_lcu *lcu = private->lcu;
 	struct dasd_device *alias_device;
+	struct alias_pav_group *group;
 	unsigned long flags;
 
-	if (!group || !lcu)
+	if (!lcu)
 		return NULL;
 	if (lcu->pav == NO_PAV ||
 	    lcu->flags & (NEED_UAC_UPDATE | UPDATE_PENDING))
@@ -697,6 +697,11 @@ struct dasd_device *dasd_alias_get_start_dev(struct dasd_device *base_device)
 	}
 
 	spin_lock_irqsave(&lcu->lock, flags);
+	group = private->pavgroup;
+	if (!group) {
+		spin_unlock_irqrestore(&lcu->lock, flags);
+		return NULL;
+	}
 	alias_device = group->next;
 	if (!alias_device) {
 		if (list_empty(&group->aliaslist)) {
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 8f1d1cf23d44..59ac98f2bd27 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -2086,6 +2086,9 @@ static inline void ap_scan_adapter(int ap)
  */
 static bool ap_get_configuration(void)
 {
+	if (!ap_qci_info)	/* QCI not supported */
+		return false;
+
 	memcpy(ap_qci_info_old, ap_qci_info, sizeof(*ap_qci_info));
 	ap_fetch_qci_info(ap_qci_info);
 
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 0c40af157df2..0f17933954fb 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -148,12 +148,16 @@ struct ap_driver {
 	/*
 	 * Called at the start of the ap bus scan function when
 	 * the crypto config information (qci) has changed.
+	 * This callback is not invoked if there is no AP
+	 * QCI support available.
 	 */
 	void (*on_config_changed)(struct ap_config_info *new_config_info,
 				  struct ap_config_info *old_config_info);
 	/*
 	 * Called at the end of the ap bus scan function when
 	 * the crypto config information (qci) has changed.
+	 * This callback is not invoked if there is no AP
+	 * QCI support available.
 	 */
 	void (*on_scan_complete)(struct ap_config_info *new_config_info,
 				 struct ap_config_info *old_config_info);
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 6c8c41fac4e1..ee82207b4e60 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -984,6 +984,11 @@ static ssize_t assign_adapter_store(struct device *dev,
 		goto done;
 	}
 
+	if (test_bit_inv(apid, matrix_mdev->matrix.apm)) {
+		ret = count;
+		goto done;
+	}
+
 	set_bit_inv(apid, matrix_mdev->matrix.apm);
 
 	ret = vfio_ap_mdev_validate_masks(matrix_mdev);
@@ -1109,6 +1114,11 @@ static ssize_t unassign_adapter_store(struct device *dev,
 		goto done;
 	}
 
+	if (!test_bit_inv(apid, matrix_mdev->matrix.apm)) {
+		ret = count;
+		goto done;
+	}
+
 	clear_bit_inv((unsigned long)apid, matrix_mdev->matrix.apm);
 	vfio_ap_mdev_hot_unplug_adapter(matrix_mdev, apid);
 	ret = count;
@@ -1183,6 +1193,11 @@ static ssize_t assign_domain_store(struct device *dev,
 		goto done;
 	}
 
+	if (test_bit_inv(apqi, matrix_mdev->matrix.aqm)) {
+		ret = count;
+		goto done;
+	}
+
 	set_bit_inv(apqi, matrix_mdev->matrix.aqm);
 
 	ret = vfio_ap_mdev_validate_masks(matrix_mdev);
@@ -1286,6 +1301,11 @@ static ssize_t unassign_domain_store(struct device *dev,
 		goto done;
 	}
 
+	if (!test_bit_inv(apqi, matrix_mdev->matrix.aqm)) {
+		ret = count;
+		goto done;
+	}
+
 	clear_bit_inv((unsigned long)apqi, matrix_mdev->matrix.aqm);
 	vfio_ap_mdev_hot_unplug_domain(matrix_mdev, apqi);
 	ret = count;
@@ -1329,6 +1349,11 @@ static ssize_t assign_control_domain_store(struct device *dev,
 		goto done;
 	}
 
+	if (test_bit_inv(id, matrix_mdev->matrix.adm)) {
+		ret = count;
+		goto done;
+	}
+
 	/* Set the bit in the ADM (bitmask) corresponding to the AP control
 	 * domain number (id). The bits in the mask, from most significant to
 	 * least significant, correspond to IDs 0 up to the one less than the
@@ -1378,6 +1403,11 @@ static ssize_t unassign_control_domain_store(struct device *dev,
 		goto done;
 	}
 
+	if (!test_bit_inv(domid, matrix_mdev->matrix.adm)) {
+		ret = count;
+		goto done;
+	}
+
 	clear_bit_inv(domid, matrix_mdev->matrix.adm);
 
 	if (test_bit_inv(domid, matrix_mdev->shadow_apcb.adm)) {
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index 896896e32664..a10dbe632ef9 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -637,7 +637,6 @@ static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 			       struct virtqueue *vqs[],
 			       vq_callback_t *callbacks[],
 			       const char * const names[],
-			       u32 sizes[],
 			       const bool *ctx,
 			       struct irq_affinity *desc)
 {
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 0738238ed6cc..9857dba09c95 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -182,6 +182,15 @@ void scsi_remove_host(struct Scsi_Host *shost)
 	mutex_unlock(&shost->scan_mutex);
 	scsi_proc_host_rm(shost);
 
+	/*
+	 * New SCSI devices cannot be attached anymore because of the SCSI host
+	 * state so drop the tag set refcnt. Wait until the tag set refcnt drops
+	 * to zero because .exit_cmd_priv implementations may need the host
+	 * pointer.
+	 */
+	kref_put(&shost->tagset_refcnt, scsi_mq_free_tags);
+	wait_for_completion(&shost->tagset_freed);
+
 	spin_lock_irqsave(shost->host_lock, flags);
 	if (scsi_host_set_state(shost, SHOST_DEL))
 		BUG_ON(scsi_host_set_state(shost, SHOST_DEL_RECOVERY));
@@ -190,15 +199,6 @@ void scsi_remove_host(struct Scsi_Host *shost)
 	transport_unregister_device(&shost->shost_gendev);
 	device_unregister(&shost->shost_dev);
 	device_del(&shost->shost_gendev);
-
-	/*
-	 * After scsi_remove_host() has returned the scsi LLD module can be
-	 * unloaded and/or the host resources can be released. Hence wait until
-	 * the dependent SCSI targets and devices are gone before returning.
-	 */
-	wait_event(shost->targets_wq, atomic_read(&shost->target_count) == 0);
-
-	scsi_mq_destroy_tags(shost);
 }
 EXPORT_SYMBOL(scsi_remove_host);
 
@@ -254,6 +254,9 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 	if (error)
 		goto fail;
 
+	kref_init(&shost->tagset_refcnt);
+	init_completion(&shost->tagset_freed);
+
 	/*
 	 * Increase usage count temporarily here so that calling
 	 * scsi_autopm_put_host() will trigger runtime idle if there is
@@ -309,8 +312,8 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 	return error;
 
 	/*
-	 * Any resources associated with the SCSI host in this function except
-	 * the tag set will be freed by scsi_host_dev_release().
+	 * Any host allocation in this function will be freed in
+	 * scsi_host_dev_release().
 	 */
  out_del_dev:
 	device_del(&shost->shost_dev);
@@ -326,7 +329,7 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 	pm_runtime_disable(&shost->shost_gendev);
 	pm_runtime_set_suspended(&shost->shost_gendev);
 	pm_runtime_put_noidle(&shost->shost_gendev);
-	scsi_mq_destroy_tags(shost);
+	kref_put(&shost->tagset_refcnt, scsi_mq_free_tags);
  fail:
 	return error;
 }
@@ -406,7 +409,6 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 	INIT_LIST_HEAD(&shost->starved_list);
 	init_waitqueue_head(&shost->host_wait);
 	mutex_init(&shost->scan_mutex);
-	init_waitqueue_head(&shost->targets_wq);
 
 	index = ida_alloc(&host_index_ida, GFP_KERNEL);
 	if (index < 0) {
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index 9c82e5dc4fcc..a36fa1c128a8 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -872,7 +872,8 @@ int sas_change_queue_depth(struct scsi_device *sdev, int depth)
 	struct domain_device *dev = sdev_to_domain_dev(sdev);
 
 	if (dev_is_sata(dev))
-		return __ata_change_queue_depth(dev->sata_dev.ap, sdev, depth);
+		return ata_change_queue_depth(dev->sata_dev.ap,
+					      sas_to_ata_dev(dev), sdev, depth);
 
 	if (!sdev->tagged_supported)
 		depth = 1;
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index c69c5a0979ec..55a1ad6eed03 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -8053,7 +8053,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	/* Allocate device driver memory */
 	rc = lpfc_mem_alloc(phba, SGL_ALIGN_SZ);
 	if (rc)
-		return -ENOMEM;
+		goto out_destroy_workqueue;
 
 	/* IF Type 2 ports get initialized now. */
 	if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) >=
@@ -8481,6 +8481,9 @@ out_free_bsmbx:
 	lpfc_destroy_bootstrap_mbox(phba);
 out_free_mem:
 	lpfc_mem_free(phba);
+out_destroy_workqueue:
+	destroy_workqueue(phba->wq);
+	phba->wq = NULL;
 	return rc;
 }
 
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 084c0f9fdc3a..938a5e435943 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -4272,7 +4272,7 @@ lpfc_fcp_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 		    lpfc_cmd->result == IOERR_ABORT_REQUESTED ||
 		    lpfc_cmd->result == IOERR_RPI_SUSPENDED ||
 		    lpfc_cmd->result == IOERR_SLER_CMD_RCV_FAILURE) {
-			cmd->result = DID_REQUEUE << 16;
+			cmd->result = DID_TRANSPORT_DISRUPTED << 16;
 			break;
 		}
 		if ((lpfc_cmd->result == IOERR_RX_DMA_FAILED ||
@@ -4562,7 +4562,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 			    lpfc_cmd->result == IOERR_NO_RESOURCES ||
 			    lpfc_cmd->result == IOERR_ABORT_REQUESTED ||
 			    lpfc_cmd->result == IOERR_SLER_CMD_RCV_FAILURE) {
-				cmd->result = DID_REQUEUE << 16;
+				cmd->result = DID_TRANSPORT_DISRUPTED << 16;
 				break;
 			}
 			if ((lpfc_cmd->result == IOERR_RX_DMA_FAILED ||
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index a3e117a4b8e7..f6c37a97544e 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -7153,22 +7153,18 @@ static int megasas_alloc_ctrl_mem(struct megasas_instance *instance)
 	switch (instance->adapter_type) {
 	case MFI_SERIES:
 		if (megasas_alloc_mfi_ctrl_mem(instance))
-			goto fail;
+			return -ENOMEM;
 		break;
 	case AERO_SERIES:
 	case VENTURA_SERIES:
 	case THUNDERBOLT_SERIES:
 	case INVADER_SERIES:
 		if (megasas_alloc_fusion_context(instance))
-			goto fail;
+			return -ENOMEM;
 		break;
 	}
 
 	return 0;
- fail:
-	kfree(instance->reply_map);
-	instance->reply_map = NULL;
-	return -ENOMEM;
 }
 
 /*
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index e48d4261d0bc..09c5fe37754c 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -5310,7 +5310,6 @@ megasas_alloc_fusion_context(struct megasas_instance *instance)
 		if (!fusion->log_to_span) {
 			dev_err(&instance->pdev->dev, "Failed from %s %d\n",
 				__func__, __LINE__);
-			kfree(instance->ctrl_context);
 			return -ENOMEM;
 		}
 	}
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 565339a0811d..331e896d8225 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -2993,7 +2993,7 @@ _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev)
 
 	if (ioc->is_mcpu_endpoint ||
 	    sizeof(dma_addr_t) == 4 || ioc->use_32bit_dma ||
-	    dma_get_required_mask(&pdev->dev) <= 32)
+	    dma_get_required_mask(&pdev->dev) <= DMA_BIT_MASK(32))
 		ioc->dma_mask = 32;
 	/* Set 63 bit DMA mask for all SAS3 and SAS35 controllers */
 	else if (ioc->hba_mpi_version_belonged > MPI2_VERSION)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index def37a7e5980..bd6a5f1bd532 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -3670,6 +3670,7 @@ static struct fw_event_work *dequeue_next_fw_event(struct MPT3SAS_ADAPTER *ioc)
 		fw_event = list_first_entry(&ioc->fw_event_list,
 				struct fw_event_work, list);
 		list_del_init(&fw_event->list);
+		fw_event_work_put(fw_event);
 	}
 	spin_unlock_irqrestore(&ioc->fw_event_lock, flags);
 
@@ -3751,7 +3752,6 @@ _scsih_fw_event_cleanup_queue(struct MPT3SAS_ADAPTER *ioc)
 		if (cancel_work_sync(&fw_event->work))
 			fw_event_work_put(fw_event);
 
-		fw_event_work_put(fw_event);
 	}
 	ioc->fw_events_cleanup = 0;
 }
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index 3d6b137314f3..bbc4d5890ae6 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -3686,11 +3686,6 @@ err2:
 err1:
 	scsi_host_put(lport->host);
 err0:
-	if (qedf) {
-		QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_DISC, "Probe done.\n");
-
-		clear_bit(QEDF_PROBING, &qedf->flags);
-	}
 	return rc;
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 2b2f68288375..4acff4e84b90 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -2151,8 +2151,10 @@ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha,
 
 	abort_cmd = ha->tgt.tgt_ops->find_cmd_by_tag(sess,
 				le32_to_cpu(abts->exchange_addr_to_abort));
-	if (!abort_cmd)
+	if (!abort_cmd) {
+		mempool_free(mcmd, qla_tgt_mgmt_cmd_mempool);
 		return -EIO;
+	}
 	mcmd->unpacked_lun = abort_cmd->se_cmd.orig_fe_lun;
 
 	if (abort_cmd->qpair) {
@@ -6935,14 +6937,8 @@ qlt_24xx_config_rings(struct scsi_qla_host *vha)
 
 	if (ha->flags.msix_enabled) {
 		if (IS_QLA83XX(ha) || IS_QLA27XX(ha) || IS_QLA28XX(ha)) {
-			if (IS_QLA2071(ha)) {
-				/* 4 ports Baker: Enable Interrupt Handshake */
-				icb->msix_atio = 0;
-				icb->firmware_options_2 |= cpu_to_le32(BIT_26);
-			} else {
-				icb->msix_atio = cpu_to_le16(msix->entry);
-				icb->firmware_options_2 &= cpu_to_le32(~BIT_26);
-			}
+			icb->msix_atio = cpu_to_le16(msix->entry);
+			icb->firmware_options_2 &= cpu_to_le32(~BIT_26);
 			ql_dbg(ql_dbg_init, vha, 0xf072,
 			    "Registering ICB vector 0x%x for atio que.\n",
 			    msix->entry);
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 086ec5b5862d..c59eac7a32f2 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -586,13 +586,10 @@ EXPORT_SYMBOL(scsi_device_get);
  */
 void scsi_device_put(struct scsi_device *sdev)
 {
-	/*
-	 * Decreasing the module reference count before the device reference
-	 * count is safe since scsi_remove_host() only returns after all
-	 * devices have been removed.
-	 */
-	module_put(sdev->host->hostt->module);
+	struct module *mod = sdev->host->hostt->module;
+
 	put_device(&sdev->sdev_gendev);
+	module_put(mod);
 }
 EXPORT_SYMBOL(scsi_device_put);
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 4dbd29ab1dcc..96e7e3eaca29 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -111,7 +111,7 @@ scsi_set_blocked(struct scsi_cmnd *cmd, int reason)
 	}
 }
 
-static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd)
+static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd, unsigned long msecs)
 {
 	struct request *rq = scsi_cmd_to_rq(cmd);
 
@@ -121,7 +121,12 @@ static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd)
 	} else {
 		WARN_ON_ONCE(true);
 	}
-	blk_mq_requeue_request(rq, true);
+
+	if (msecs) {
+		blk_mq_requeue_request(rq, false);
+		blk_mq_delay_kick_requeue_list(rq->q, msecs);
+	} else
+		blk_mq_requeue_request(rq, true);
 }
 
 /**
@@ -651,14 +656,6 @@ static unsigned int scsi_rq_err_bytes(const struct request *rq)
 	return bytes;
 }
 
-/* Helper for scsi_io_completion() when "reprep" action required. */
-static void scsi_io_completion_reprep(struct scsi_cmnd *cmd,
-				      struct request_queue *q)
-{
-	/* A new command will be prepared and issued. */
-	scsi_mq_requeue_cmd(cmd);
-}
-
 static bool scsi_cmd_runtime_exceeced(struct scsi_cmnd *cmd)
 {
 	struct request *req = scsi_cmd_to_rq(cmd);
@@ -676,14 +673,21 @@ static bool scsi_cmd_runtime_exceeced(struct scsi_cmnd *cmd)
 	return false;
 }
 
+/*
+ * When ALUA transition state is returned, reprep the cmd to
+ * use the ALUA handler's transition timeout. Delay the reprep
+ * 1 sec to avoid aggressive retries of the target in that
+ * state.
+ */
+#define ALUA_TRANSITION_REPREP_DELAY	1000
+
 /* Helper for scsi_io_completion() when special action required. */
 static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
 {
-	struct request_queue *q = cmd->device->request_queue;
 	struct request *req = scsi_cmd_to_rq(cmd);
 	int level = 0;
-	enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY,
-	      ACTION_DELAYED_RETRY} action;
+	enum {ACTION_FAIL, ACTION_REPREP, ACTION_DELAYED_REPREP,
+	      ACTION_RETRY, ACTION_DELAYED_RETRY} action;
 	struct scsi_sense_hdr sshdr;
 	bool sense_valid;
 	bool sense_current = true;      /* false implies "deferred sense" */
@@ -772,8 +776,8 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
 					action = ACTION_DELAYED_RETRY;
 					break;
 				case 0x0a: /* ALUA state transition */
-					blk_stat = BLK_STS_TRANSPORT;
-					fallthrough;
+					action = ACTION_DELAYED_REPREP;
+					break;
 				default:
 					action = ACTION_FAIL;
 					break;
@@ -832,7 +836,10 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
 			return;
 		fallthrough;
 	case ACTION_REPREP:
-		scsi_io_completion_reprep(cmd, q);
+		scsi_mq_requeue_cmd(cmd, 0);
+		break;
+	case ACTION_DELAYED_REPREP:
+		scsi_mq_requeue_cmd(cmd, ALUA_TRANSITION_REPREP_DELAY);
 		break;
 	case ACTION_RETRY:
 		/* Retry the same command immediately */
@@ -926,7 +933,7 @@ static int scsi_io_completion_nz_result(struct scsi_cmnd *cmd, int result,
  * command block will be released and the queue function will be goosed. If we
  * are not done then we have to figure out what to do next:
  *
- *   a) We can call scsi_io_completion_reprep().  The request will be
+ *   a) We can call scsi_mq_requeue_cmd().  The request will be
  *	unprepared and put back on the queue.  Then a new command will
  *	be created for it.  This should be used if we made forward
  *	progress, or if we want to switch from READ(10) to READ(6) for
@@ -942,7 +949,6 @@ static int scsi_io_completion_nz_result(struct scsi_cmnd *cmd, int result,
 void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 {
 	int result = cmd->result;
-	struct request_queue *q = cmd->device->request_queue;
 	struct request *req = scsi_cmd_to_rq(cmd);
 	blk_status_t blk_stat = BLK_STS_OK;
 
@@ -979,7 +985,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	 * request just queue the command up again.
 	 */
 	if (likely(result == 0))
-		scsi_io_completion_reprep(cmd, q);
+		scsi_mq_requeue_cmd(cmd, 0);
 	else
 		scsi_io_completion_action(cmd, result);
 }
@@ -1542,7 +1548,6 @@ static blk_status_t scsi_prepare_cmd(struct request *req)
 	scsi_init_command(sdev, cmd);
 
 	cmd->eh_eflags = 0;
-	cmd->allowed = 0;
 	cmd->prot_type = 0;
 	cmd->prot_flags = 0;
 	cmd->submitter = 0;
@@ -1593,6 +1598,8 @@ static blk_status_t scsi_prepare_cmd(struct request *req)
 			return ret;
 	}
 
+	/* Usually overridden by the ULP */
+	cmd->allowed = 0;
 	memset(cmd->cmnd, 0, sizeof(cmd->cmnd));
 	return scsi_cmd_to_driver(cmd)->init_command(cmd);
 }
@@ -1976,9 +1983,13 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost)
 	return blk_mq_alloc_tag_set(tag_set);
 }
 
-void scsi_mq_destroy_tags(struct Scsi_Host *shost)
+void scsi_mq_free_tags(struct kref *kref)
 {
+	struct Scsi_Host *shost = container_of(kref, typeof(*shost),
+					       tagset_refcnt);
+
 	blk_mq_free_tag_set(&shost->tag_set);
+	complete(&shost->tagset_freed);
 }
 
 /**
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index 429663bd78ec..f385b3f04d6e 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -94,7 +94,7 @@ extern void scsi_run_host_queues(struct Scsi_Host *shost);
 extern void scsi_requeue_run_queue(struct work_struct *work);
 extern void scsi_start_queue(struct scsi_device *sdev);
 extern int scsi_mq_setup_tags(struct Scsi_Host *shost);
-extern void scsi_mq_destroy_tags(struct Scsi_Host *shost);
+extern void scsi_mq_free_tags(struct kref *kref);
 extern void scsi_exit_queue(void);
 extern void scsi_evt_thread(struct work_struct *work);
 
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index ac6059702d13..5d27f5196de6 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -340,6 +340,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 		kfree(sdev);
 		goto out;
 	}
+	kref_get(&sdev->host->tagset_refcnt);
 	sdev->request_queue = q;
 	q->queuedata = sdev;
 	__scsi_init_queue(sdev->host, q);
@@ -406,14 +407,9 @@ static void scsi_target_destroy(struct scsi_target *starget)
 static void scsi_target_dev_release(struct device *dev)
 {
 	struct device *parent = dev->parent;
-	struct Scsi_Host *shost = dev_to_shost(parent);
 	struct scsi_target *starget = to_scsi_target(dev);
 
 	kfree(starget);
-
-	if (atomic_dec_return(&shost->target_count) == 0)
-		wake_up(&shost->targets_wq);
-
 	put_device(parent);
 }
 
@@ -526,10 +522,6 @@ static struct scsi_target *scsi_alloc_target(struct device *parent,
 	starget->state = STARGET_CREATED;
 	starget->scsi_level = SCSI_2;
 	starget->max_target_blocked = SCSI_DEFAULT_TARGET_BLOCKED;
-	init_waitqueue_head(&starget->sdev_wq);
-
-	atomic_inc(&shost->target_count);
-
  retry:
 	spin_lock_irqsave(shost->host_lock, flags);
 
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 9dad2fd5297f..5d61f58399dc 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -443,15 +443,18 @@ static void scsi_device_cls_release(struct device *class_dev)
 
 static void scsi_device_dev_release_usercontext(struct work_struct *work)
 {
-	struct scsi_device *sdev = container_of(work, struct scsi_device,
-						ew.work);
-	struct scsi_target *starget = sdev->sdev_target;
+	struct scsi_device *sdev;
 	struct device *parent;
 	struct list_head *this, *tmp;
 	struct scsi_vpd *vpd_pg80 = NULL, *vpd_pg83 = NULL;
 	struct scsi_vpd *vpd_pg0 = NULL, *vpd_pg89 = NULL;
 	struct scsi_vpd *vpd_pgb0 = NULL, *vpd_pgb1 = NULL, *vpd_pgb2 = NULL;
 	unsigned long flags;
+	struct module *mod;
+
+	sdev = container_of(work, struct scsi_device, ew.work);
+
+	mod = sdev->host->hostt->module;
 
 	scsi_dh_release_device(sdev);
 
@@ -513,16 +516,19 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)
 	kfree(sdev->inquiry);
 	kfree(sdev);
 
-	if (starget && atomic_dec_return(&starget->sdev_count) == 0)
-		wake_up(&starget->sdev_wq);
-
 	if (parent)
 		put_device(parent);
+	module_put(mod);
 }
 
 static void scsi_device_dev_release(struct device *dev)
 {
 	struct scsi_device *sdp = to_scsi_device(dev);
+
+	/* Set module pointer as NULL in case of module unloading */
+	if (!try_module_get(sdp->host->hostt->module))
+		sdp->host->hostt->module = NULL;
+
 	execute_in_process_context(scsi_device_dev_release_usercontext,
 				   &sdp->ew);
 }
@@ -1470,6 +1476,7 @@ void __scsi_remove_device(struct scsi_device *sdev)
 	mutex_unlock(&sdev->state_mutex);
 
 	blk_mq_destroy_queue(sdev->request_queue);
+	kref_put(&sdev->host->tagset_refcnt, scsi_mq_free_tags);
 	cancel_work_sync(&sdev->requeue_work);
 
 	if (sdev->host->hostt->slave_destroy)
@@ -1529,14 +1536,6 @@ static void __scsi_remove_target(struct scsi_target *starget)
 		goto restart;
 	}
 	spin_unlock_irqrestore(shost->host_lock, flags);
-
-	/*
-	 * After scsi_remove_target() returns its caller can remove resources
-	 * associated with @starget, e.g. an rport or session. Wait until all
-	 * devices associated with @starget have been removed to prevent that
-	 * a SCSI error handling callback function triggers a use-after-free.
-	 */
-	wait_event(starget->sdev_wq, atomic_read(&starget->sdev_count) == 0);
 }
 
 /**
@@ -1647,9 +1646,6 @@ void scsi_sysfs_device_initialize(struct scsi_device *sdev)
 	list_add_tail(&sdev->same_target_siblings, &starget->devices);
 	list_add_tail(&sdev->siblings, &shost->__devices);
 	spin_unlock_irqrestore(shost->host_lock, flags);
-
-	atomic_inc(&starget->sdev_count);
-
 	/*
 	 * device can now only be removed via __scsi_remove_device() so hold
 	 * the target.  Target will be held in CREATED state until something
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 8f79fa6318fe..eb76ba055021 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -103,7 +103,6 @@ static void sd_config_discard(struct scsi_disk *, unsigned int);
 static void sd_config_write_same(struct scsi_disk *);
 static int  sd_revalidate_disk(struct gendisk *);
 static void sd_unlock_native_capacity(struct gendisk *disk);
-static void sd_start_done_work(struct work_struct *work);
 static int  sd_probe(struct device *);
 static int  sd_remove(struct device *);
 static void sd_shutdown(struct device *);
@@ -3471,7 +3470,6 @@ static int sd_probe(struct device *dev)
 	sdkp->max_retries = SD_MAX_RETRIES;
 	atomic_set(&sdkp->openers, 0);
 	atomic_set(&sdkp->device->ioerr_cnt, 0);
-	INIT_WORK(&sdkp->start_done_work, sd_start_done_work);
 
 	if (!sdp->request_queue->rq_timeout) {
 		if (sdp->type != TYPE_MOD)
@@ -3594,69 +3592,12 @@ static void scsi_disk_release(struct device *dev)
 	kfree(sdkp);
 }
 
-/* Process sense data after a START command finished. */
-static void sd_start_done_work(struct work_struct *work)
-{
-	struct scsi_disk *sdkp = container_of(work, typeof(*sdkp),
-					      start_done_work);
-	struct scsi_sense_hdr sshdr;
-	int res = sdkp->start_result;
-
-	if (res == 0)
-		return;
-
-	sd_print_result(sdkp, "Start/Stop Unit failed", res);
-
-	if (res < 0)
-		return;
-
-	if (scsi_normalize_sense(sdkp->start_sense_buffer,
-				 sdkp->start_sense_len, &sshdr))
-		sd_print_sense_hdr(sdkp, &sshdr);
-}
-
-/* A START command finished. May be called from interrupt context. */
-static void sd_start_done(struct request *req, blk_status_t status)
-{
-	const struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req);
-	struct scsi_disk *sdkp = scsi_disk(req->q->disk);
-
-	sdkp->start_result = scmd->result;
-	WARN_ON_ONCE(scmd->sense_len > SCSI_SENSE_BUFFERSIZE);
-	sdkp->start_sense_len = scmd->sense_len;
-	memcpy(sdkp->start_sense_buffer, scmd->sense_buffer,
-	       ARRAY_SIZE(sdkp->start_sense_buffer));
-	WARN_ON_ONCE(!schedule_work(&sdkp->start_done_work));
-}
-
-/* Submit a START command asynchronously. */
-static int sd_submit_start(struct scsi_disk *sdkp, u8 cmd[], u8 cmd_len)
-{
-	struct scsi_device *sdev = sdkp->device;
-	struct request_queue *q = sdev->request_queue;
-	struct request *req;
-	struct scsi_cmnd *scmd;
-
-	req = scsi_alloc_request(q, REQ_OP_DRV_IN, BLK_MQ_REQ_PM);
-	if (IS_ERR(req))
-		return PTR_ERR(req);
-
-	scmd = blk_mq_rq_to_pdu(req);
-	scmd->cmd_len = cmd_len;
-	memcpy(scmd->cmnd, cmd, cmd_len);
-	scmd->allowed = sdkp->max_retries;
-	req->timeout = SD_TIMEOUT;
-	req->rq_flags |= RQF_PM | RQF_QUIET;
-	req->end_io = sd_start_done;
-	blk_execute_rq_nowait(req, /*at_head=*/true);
-
-	return 0;
-}
-
 static int sd_start_stop_device(struct scsi_disk *sdkp, int start)
 {
 	unsigned char cmd[6] = { START_STOP };	/* START_VALID */
+	struct scsi_sense_hdr sshdr;
 	struct scsi_device *sdp = sdkp->device;
+	int res;
 
 	if (start)
 		cmd[4] |= 1;	/* START */
@@ -3667,10 +3608,23 @@ static int sd_start_stop_device(struct scsi_disk *sdkp, int start)
 	if (!scsi_device_online(sdp))
 		return -ENODEV;
 
-	/* Wait until processing of sense data has finished. */
-	flush_work(&sdkp->start_done_work);
+	res = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr,
+			SD_TIMEOUT, sdkp->max_retries, 0, RQF_PM, NULL);
+	if (res) {
+		sd_print_result(sdkp, "Start/Stop Unit failed", res);
+		if (res > 0 && scsi_sense_valid(&sshdr)) {
+			sd_print_sense_hdr(sdkp, &sshdr);
+			/* 0x3a is medium not present */
+			if (sshdr.asc == 0x3a)
+				res = 0;
+		}
+	}
 
-	return sd_submit_start(sdkp, cmd, sizeof(cmd));
+	/* SCSI error codes must not go to the generic layer */
+	if (res)
+		return -EIO;
+
+	return 0;
 }
 
 /*
@@ -3697,8 +3651,6 @@ static void sd_shutdown(struct device *dev)
 		sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n");
 		sd_start_stop_device(sdkp, 0);
 	}
-
-	flush_work(&sdkp->start_done_work);
 }
 
 static int sd_suspend_common(struct device *dev, bool ignore_stop_errors)
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index b89187761d61..5eea762f84d1 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -150,11 +150,6 @@ struct scsi_disk {
 	unsigned	urswrz : 1;
 	unsigned	security : 1;
 	unsigned	ignore_medium_access_errors : 1;
-
-	int		start_result;
-	u32		start_sense_len;
-	u8		start_sense_buffer[SCSI_SENSE_BUFFERSIZE];
-	struct work_struct start_done_work;
 };
 #define to_scsi_disk(obj) container_of(obj, struct scsi_disk, disk_dev)
 
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index fe000da11332..8ced292c4b96 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -2012,7 +2012,7 @@ static int storvsc_probe(struct hv_device *device,
 	 */
 	host_dev->handle_error_wq =
 			alloc_ordered_workqueue("storvsc_error_wq_%d",
-						WQ_MEM_RECLAIM,
+						0,
 						host->host_no);
 	if (!host_dev->handle_error_wq) {
 		ret = -ENOMEM;
diff --git a/drivers/soc/bcm/brcmstb/biuctrl.c b/drivers/soc/bcm/brcmstb/biuctrl.c
index 1467bbd59690..e1d7b4543248 100644
--- a/drivers/soc/bcm/brcmstb/biuctrl.c
+++ b/drivers/soc/bcm/brcmstb/biuctrl.c
@@ -288,7 +288,6 @@ static int __init setup_hifcpubiuctrl_regs(struct device_node *np)
 	if (BRCM_ID(family_id) == 0x7260 && BRCM_REV(family_id) == 0)
 		cpubiuctrl_regs = b53_cpubiuctrl_no_wb_regs;
 out:
-	of_node_put(np);
 	return ret;
 }
 
diff --git a/drivers/soc/bcm/brcmstb/pm/pm-arm.c b/drivers/soc/bcm/brcmstb/pm/pm-arm.c
index d6b30d521307..775da69b8efa 100644
--- a/drivers/soc/bcm/brcmstb/pm/pm-arm.c
+++ b/drivers/soc/bcm/brcmstb/pm/pm-arm.c
@@ -684,13 +684,14 @@ static int brcmstb_pm_probe(struct platform_device *pdev)
 	const struct of_device_id *of_id = NULL;
 	struct device_node *dn;
 	void __iomem *base;
-	int ret, i;
+	int ret, i, s;
 
 	/* AON ctrl registers */
 	base = brcmstb_ioremap_match(aon_ctrl_dt_ids, 0, NULL);
 	if (IS_ERR(base)) {
 		pr_err("error mapping AON_CTRL\n");
-		return PTR_ERR(base);
+		ret = PTR_ERR(base);
+		goto aon_err;
 	}
 	ctrl.aon_ctrl_base = base;
 
@@ -700,8 +701,10 @@ static int brcmstb_pm_probe(struct platform_device *pdev)
 		/* Assume standard offset */
 		ctrl.aon_sram = ctrl.aon_ctrl_base +
 				     AON_CTRL_SYSTEM_DATA_RAM_OFS;
+		s = 0;
 	} else {
 		ctrl.aon_sram = base;
+		s = 1;
 	}
 
 	writel_relaxed(0, ctrl.aon_sram + AON_REG_PANIC);
@@ -711,7 +714,8 @@ static int brcmstb_pm_probe(struct platform_device *pdev)
 				     (const void **)&ddr_phy_data);
 	if (IS_ERR(base)) {
 		pr_err("error mapping DDR PHY\n");
-		return PTR_ERR(base);
+		ret = PTR_ERR(base);
+		goto ddr_phy_err;
 	}
 	ctrl.support_warm_boot = ddr_phy_data->supports_warm_boot;
 	ctrl.pll_status_offset = ddr_phy_data->pll_status_offset;
@@ -731,17 +735,20 @@ static int brcmstb_pm_probe(struct platform_device *pdev)
 	for_each_matching_node(dn, ddr_shimphy_dt_ids) {
 		i = ctrl.num_memc;
 		if (i >= MAX_NUM_MEMC) {
+			of_node_put(dn);
 			pr_warn("too many MEMCs (max %d)\n", MAX_NUM_MEMC);
 			break;
 		}
 
 		base = of_io_request_and_map(dn, 0, dn->full_name);
 		if (IS_ERR(base)) {
+			of_node_put(dn);
 			if (!ctrl.support_warm_boot)
 				break;
 
 			pr_err("error mapping DDR SHIMPHY %d\n", i);
-			return PTR_ERR(base);
+			ret = PTR_ERR(base);
+			goto ddr_shimphy_err;
 		}
 		ctrl.memcs[i].ddr_shimphy_base = base;
 		ctrl.num_memc++;
@@ -752,14 +759,18 @@ static int brcmstb_pm_probe(struct platform_device *pdev)
 	for_each_matching_node(dn, brcmstb_memc_of_match) {
 		base = of_iomap(dn, 0);
 		if (!base) {
+			of_node_put(dn);
 			pr_err("error mapping DDR Sequencer %d\n", i);
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto brcmstb_memc_err;
 		}
 
 		of_id = of_match_node(brcmstb_memc_of_match, dn);
 		if (!of_id) {
 			iounmap(base);
-			return -EINVAL;
+			of_node_put(dn);
+			ret = -EINVAL;
+			goto brcmstb_memc_err;
 		}
 
 		ddr_seq_data = of_id->data;
@@ -779,21 +790,24 @@ static int brcmstb_pm_probe(struct platform_device *pdev)
 	dn = of_find_matching_node(NULL, sram_dt_ids);
 	if (!dn) {
 		pr_err("SRAM not found\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto brcmstb_memc_err;
 	}
 
 	ret = brcmstb_init_sram(dn);
 	of_node_put(dn);
 	if (ret) {
 		pr_err("error setting up SRAM for PM\n");
-		return ret;
+		goto brcmstb_memc_err;
 	}
 
 	ctrl.pdev = pdev;
 
 	ctrl.s3_params = kmalloc(sizeof(*ctrl.s3_params), GFP_KERNEL);
-	if (!ctrl.s3_params)
-		return -ENOMEM;
+	if (!ctrl.s3_params) {
+		ret = -ENOMEM;
+		goto s3_params_err;
+	}
 	ctrl.s3_params_pa = dma_map_single(&pdev->dev, ctrl.s3_params,
 					   sizeof(*ctrl.s3_params),
 					   DMA_TO_DEVICE);
@@ -813,7 +827,21 @@ static int brcmstb_pm_probe(struct platform_device *pdev)
 
 out:
 	kfree(ctrl.s3_params);
-
+s3_params_err:
+	iounmap(ctrl.boot_sram);
+brcmstb_memc_err:
+	for (i--; i >= 0; i--)
+		iounmap(ctrl.memcs[i].ddr_ctrl);
+ddr_shimphy_err:
+	for (i = 0; i < ctrl.num_memc; i++)
+		iounmap(ctrl.memcs[i].ddr_shimphy_base);
+
+	iounmap(ctrl.memcs[0].ddr_phy_base);
+ddr_phy_err:
+	iounmap(ctrl.aon_ctrl_base);
+	if (s)
+		iounmap(ctrl.aon_sram);
+aon_err:
 	pr_warn("PM: initialization failed with code %d\n", ret);
 
 	return ret;
diff --git a/drivers/soc/fsl/Kconfig b/drivers/soc/fsl/Kconfig
index 07d52cafbb31..fcec6ed83d5e 100644
--- a/drivers/soc/fsl/Kconfig
+++ b/drivers/soc/fsl/Kconfig
@@ -24,6 +24,7 @@ config FSL_MC_DPIO
         tristate "QorIQ DPAA2 DPIO driver"
         depends on FSL_MC_BUS
         select SOC_BUS
+        select FSL_GUTS
         select DIMLIB
         help
 	  Driver for the DPAA2 DPIO object.  A DPIO provides queue and
diff --git a/drivers/soc/imx/gpcv2.c b/drivers/soc/imx/gpcv2.c
index 6383a4edc360..88aee59730e3 100644
--- a/drivers/soc/imx/gpcv2.c
+++ b/drivers/soc/imx/gpcv2.c
@@ -335,6 +335,8 @@ static int imx_pgc_power_up(struct generic_pm_domain *genpd)
 		}
 	}
 
+	reset_control_assert(domain->reset);
+
 	/* Enable reset clocks for all devices in the domain */
 	ret = clk_bulk_prepare_enable(domain->num_clks, domain->clks);
 	if (ret) {
@@ -342,7 +344,8 @@ static int imx_pgc_power_up(struct generic_pm_domain *genpd)
 		goto out_regulator_disable;
 	}
 
-	reset_control_assert(domain->reset);
+	/* delays for reset to propagate */
+	udelay(5);
 
 	if (domain->bits.pxx) {
 		/* request the domain to power up */
diff --git a/drivers/soc/imx/imx8m-blk-ctrl.c b/drivers/soc/imx/imx8m-blk-ctrl.c
index dff7529268e4..972f289d300a 100644
--- a/drivers/soc/imx/imx8m-blk-ctrl.c
+++ b/drivers/soc/imx/imx8m-blk-ctrl.c
@@ -243,7 +243,6 @@ static int imx8m_blk_ctrl_probe(struct platform_device *pdev)
 			ret = PTR_ERR(domain->power_dev);
 			goto cleanup_pds;
 		}
-		dev_set_name(domain->power_dev, "%s", data->name);
 
 		domain->genpd.name = data->name;
 		domain->genpd.power_on = imx8m_blk_ctrl_power_on;
diff --git a/drivers/soc/sunxi/sunxi_sram.c b/drivers/soc/sunxi/sunxi_sram.c
index a8f3876963a0..09754cd1d57d 100644
--- a/drivers/soc/sunxi/sunxi_sram.c
+++ b/drivers/soc/sunxi/sunxi_sram.c
@@ -78,8 +78,8 @@ static struct sunxi_sram_desc sun4i_a10_sram_d = {
 
 static struct sunxi_sram_desc sun50i_a64_sram_c = {
 	.data	= SUNXI_SRAM_DATA("C", 0x4, 24, 1,
-				  SUNXI_SRAM_MAP(0, 1, "cpu"),
-				  SUNXI_SRAM_MAP(1, 0, "de2")),
+				  SUNXI_SRAM_MAP(1, 0, "cpu"),
+				  SUNXI_SRAM_MAP(0, 1, "de2")),
 };
 
 static const struct of_device_id sunxi_sram_dt_ids[] = {
@@ -254,6 +254,7 @@ int sunxi_sram_claim(struct device *dev)
 	writel(val | ((device << sram_data->offset) & mask),
 	       base + sram_data->reg);
 
+	sram_desc->claimed = true;
 	spin_unlock(&sram_lock);
 
 	return 0;
@@ -329,11 +330,11 @@ static struct regmap_config sunxi_sram_emac_clock_regmap = {
 	.writeable_reg	= sunxi_sram_regmap_accessible_reg,
 };
 
-static int sunxi_sram_probe(struct platform_device *pdev)
+static int __init sunxi_sram_probe(struct platform_device *pdev)
 {
-	struct dentry *d;
 	struct regmap *emac_clock;
 	const struct sunxi_sramc_variant *variant;
+	struct device *dev = &pdev->dev;
 
 	sram_dev = &pdev->dev;
 
@@ -345,13 +346,6 @@ static int sunxi_sram_probe(struct platform_device *pdev)
 	if (IS_ERR(base))
 		return PTR_ERR(base);
 
-	of_platform_populate(pdev->dev.of_node, NULL, NULL, &pdev->dev);
-
-	d = debugfs_create_file("sram", S_IRUGO, NULL, NULL,
-				&sunxi_sram_fops);
-	if (!d)
-		return -ENOMEM;
-
 	if (variant->num_emac_clocks > 0) {
 		emac_clock = devm_regmap_init_mmio(&pdev->dev, base,
 						   &sunxi_sram_emac_clock_regmap);
@@ -360,6 +354,10 @@ static int sunxi_sram_probe(struct platform_device *pdev)
 			return PTR_ERR(emac_clock);
 	}
 
+	of_platform_populate(dev->of_node, NULL, NULL, dev);
+
+	debugfs_create_file("sram", 0444, NULL, NULL, &sunxi_sram_fops);
+
 	return 0;
 }
 
@@ -409,9 +407,8 @@ static struct platform_driver sunxi_sram_driver = {
 		.name		= "sunxi-sram",
 		.of_match_table	= sunxi_sram_dt_match,
 	},
-	.probe	= sunxi_sram_probe,
 };
-module_platform_driver(sunxi_sram_driver);
+builtin_platform_driver_probe(sunxi_sram_driver, sunxi_sram_probe);
 
 MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com>");
 MODULE_DESCRIPTION("Allwinner sunXi SRAM Controller Driver");
diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c
index 9df970eeca45..3a992a6478c3 100644
--- a/drivers/soundwire/qcom.c
+++ b/drivers/soundwire/qcom.c
@@ -169,7 +169,7 @@ struct qcom_swrm_ctrl {
 	u8 wcmd_id;
 	struct qcom_swrm_port_config pconfig[QCOM_SDW_MAX_PORTS];
 	struct sdw_stream_runtime *sruntime[SWRM_MAX_DAIS];
-	enum sdw_slave_status status[SDW_MAX_DEVICES];
+	enum sdw_slave_status status[SDW_MAX_DEVICES + 1];
 	int (*reg_read)(struct qcom_swrm_ctrl *ctrl, int reg, u32 *val);
 	int (*reg_write)(struct qcom_swrm_ctrl *ctrl, int reg, int val);
 	u32 slave_status;
@@ -420,7 +420,7 @@ static int qcom_swrm_get_alert_slave_dev_num(struct qcom_swrm_ctrl *ctrl)
 
 	ctrl->reg_read(ctrl, SWRM_MCP_SLV_STATUS, &val);
 
-	for (dev_num = 0; dev_num < SDW_MAX_DEVICES; dev_num++) {
+	for (dev_num = 0; dev_num <= SDW_MAX_DEVICES; dev_num++) {
 		status = (val >> (dev_num * SWRM_MCP_SLV_STATUS_SZ));
 
 		if ((status & SWRM_MCP_SLV_STATUS_MASK) == SDW_SLAVE_ALERT) {
@@ -440,7 +440,7 @@ static void qcom_swrm_get_device_status(struct qcom_swrm_ctrl *ctrl)
 	ctrl->reg_read(ctrl, SWRM_MCP_SLV_STATUS, &val);
 	ctrl->slave_status = val;
 
-	for (i = 0; i < SDW_MAX_DEVICES; i++) {
+	for (i = 0; i <= SDW_MAX_DEVICES; i++) {
 		u32 s;
 
 		s = (val >> (i * 2));
@@ -1356,10 +1356,6 @@ static int qcom_swrm_probe(struct platform_device *pdev)
 	ctrl->bus.compute_params = &qcom_swrm_compute_params;
 	ctrl->bus.clk_stop_timeout = 300;
 
-	ctrl->audio_cgcr = devm_reset_control_get_exclusive(dev, "swr_audio_cgcr");
-	if (IS_ERR(ctrl->audio_cgcr))
-		dev_err(dev, "Failed to get audio_cgcr reset required for soundwire-v1.6.0\n");
-
 	ret = qcom_swrm_get_port_config(ctrl);
 	if (ret)
 		goto err_clk;
diff --git a/drivers/spi/spi-bitbang-txrx.h b/drivers/spi/spi-bitbang-txrx.h
index 267342dfa738..2dcbe166df63 100644
--- a/drivers/spi/spi-bitbang-txrx.h
+++ b/drivers/spi/spi-bitbang-txrx.h
@@ -116,6 +116,7 @@ bitbang_txrx_le_cpha0(struct spi_device *spi,
 {
 	/* if (cpol == 0) this is SPI_MODE_0; else this is SPI_MODE_2 */
 
+	u8 rxbit = bits - 1;
 	u32 oldbit = !(word & 1);
 	/* clock starts at inactive polarity */
 	for (; likely(bits); bits--) {
@@ -135,7 +136,7 @@ bitbang_txrx_le_cpha0(struct spi_device *spi,
 		/* sample LSB (from slave) on leading edge */
 		word >>= 1;
 		if ((flags & SPI_MASTER_NO_RX) == 0)
-			word |= getmiso(spi) << (bits - 1);
+			word |= getmiso(spi) << rxbit;
 		setsck(spi, cpol);
 	}
 	return word;
@@ -148,6 +149,7 @@ bitbang_txrx_le_cpha1(struct spi_device *spi,
 {
 	/* if (cpol == 0) this is SPI_MODE_1; else this is SPI_MODE_3 */
 
+	u8 rxbit = bits - 1;
 	u32 oldbit = !(word & 1);
 	/* clock starts at inactive polarity */
 	for (; likely(bits); bits--) {
@@ -168,7 +170,7 @@ bitbang_txrx_le_cpha1(struct spi_device *spi,
 		/* sample LSB (from slave) on trailing edge */
 		word >>= 1;
 		if ((flags & SPI_MASTER_NO_RX) == 0)
-			word |= getmiso(spi) << (bits - 1);
+			word |= getmiso(spi) << rxbit;
 	}
 	return word;
 }
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 72b1a5a2298c..e12ab5b43f34 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -39,6 +39,7 @@
 #define CQSPI_DISABLE_DAC_MODE		BIT(1)
 #define CQSPI_SUPPORT_EXTERNAL_DMA	BIT(2)
 #define CQSPI_NO_SUPPORT_WR_COMPLETION	BIT(3)
+#define CQSPI_SLOW_SRAM		BIT(4)
 
 /* Capabilities */
 #define CQSPI_SUPPORTS_OCTAL		BIT(0)
@@ -87,6 +88,7 @@ struct cqspi_st {
 	bool			use_dma_read;
 	u32			pd_dev_id;
 	bool			wr_completion;
+	bool			slow_sram;
 };
 
 struct cqspi_driver_platdata {
@@ -333,7 +335,10 @@ static irqreturn_t cqspi_irq_handler(int this_irq, void *dev)
 		}
 	}
 
-	irq_status &= CQSPI_IRQ_MASK_RD | CQSPI_IRQ_MASK_WR;
+	else if (!cqspi->slow_sram)
+		irq_status &= CQSPI_IRQ_MASK_RD | CQSPI_IRQ_MASK_WR;
+	else
+		irq_status &= CQSPI_REG_IRQ_WATERMARK | CQSPI_IRQ_MASK_WR;
 
 	if (irq_status)
 		complete(&cqspi->transfer_complete);
@@ -673,7 +678,18 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata,
 	/* Clear all interrupts. */
 	writel(CQSPI_IRQ_STATUS_MASK, reg_base + CQSPI_REG_IRQSTATUS);
 
-	writel(CQSPI_IRQ_MASK_RD, reg_base + CQSPI_REG_IRQMASK);
+	/*
+	 * On SoCFPGA platform reading the SRAM is slow due to
+	 * hardware limitation and causing read interrupt storm to CPU,
+	 * so enabling only watermark interrupt to disable all read
+	 * interrupts later as we want to run "bytes to read" loop with
+	 * all the read interrupts disabled for max performance.
+	 */
+
+	if (!cqspi->slow_sram)
+		writel(CQSPI_IRQ_MASK_RD, reg_base + CQSPI_REG_IRQMASK);
+	else
+		writel(CQSPI_REG_IRQ_WATERMARK, reg_base + CQSPI_REG_IRQMASK);
 
 	reinit_completion(&cqspi->transfer_complete);
 	writel(CQSPI_REG_INDIRECTRD_START_MASK,
@@ -684,6 +700,13 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata,
 						 msecs_to_jiffies(CQSPI_READ_TIMEOUT_MS)))
 			ret = -ETIMEDOUT;
 
+		/*
+		 * Disable all read interrupts until
+		 * we are out of "bytes to read"
+		 */
+		if (cqspi->slow_sram)
+			writel(0x0, reg_base + CQSPI_REG_IRQMASK);
+
 		bytes_to_read = cqspi_get_rd_sram_level(cqspi);
 
 		if (ret && bytes_to_read == 0) {
@@ -715,8 +738,11 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata,
 			bytes_to_read = cqspi_get_rd_sram_level(cqspi);
 		}
 
-		if (remaining > 0)
+		if (remaining > 0) {
 			reinit_completion(&cqspi->transfer_complete);
+			if (cqspi->slow_sram)
+				writel(CQSPI_REG_IRQ_WATERMARK, reg_base + CQSPI_REG_IRQMASK);
+		}
 	}
 
 	/* Check indirect done status */
@@ -1667,6 +1693,8 @@ static int cqspi_probe(struct platform_device *pdev)
 			cqspi->use_dma_read = true;
 		if (ddata->quirks & CQSPI_NO_SUPPORT_WR_COMPLETION)
 			cqspi->wr_completion = false;
+		if (ddata->quirks & CQSPI_SLOW_SRAM)
+			cqspi->slow_sram = true;
 
 		if (of_device_is_compatible(pdev->dev.of_node,
 					    "xlnx,versal-ospi-1.0"))
@@ -1779,7 +1807,9 @@ static const struct cqspi_driver_platdata intel_lgm_qspi = {
 };
 
 static const struct cqspi_driver_platdata socfpga_qspi = {
-	.quirks = CQSPI_DISABLE_DAC_MODE | CQSPI_NO_SUPPORT_WR_COMPLETION,
+	.quirks = CQSPI_DISABLE_DAC_MODE
+			| CQSPI_NO_SUPPORT_WR_COMPLETION
+			| CQSPI_SLOW_SRAM,
 };
 
 static const struct cqspi_driver_platdata versal_ospi = {
diff --git a/drivers/spi/spi-meson-spicc.c b/drivers/spi/spi-meson-spicc.c
index 0bc7daa7afc8..e4cb52e1fe26 100644
--- a/drivers/spi/spi-meson-spicc.c
+++ b/drivers/spi/spi-meson-spicc.c
@@ -156,6 +156,7 @@ struct meson_spicc_device {
 	void __iomem			*base;
 	struct clk			*core;
 	struct clk			*pclk;
+	struct clk_divider		pow2_div;
 	struct clk			*clk;
 	struct spi_message		*message;
 	struct spi_transfer		*xfer;
@@ -168,6 +169,8 @@ struct meson_spicc_device {
 	unsigned long			xfer_remain;
 };
 
+#define pow2_clk_to_spicc(_div) container_of(_div, struct meson_spicc_device, pow2_div)
+
 static void meson_spicc_oen_enable(struct meson_spicc_device *spicc)
 {
 	u32 conf;
@@ -421,7 +424,7 @@ static int meson_spicc_prepare_message(struct spi_master *master,
 {
 	struct meson_spicc_device *spicc = spi_master_get_devdata(master);
 	struct spi_device *spi = message->spi;
-	u32 conf = 0;
+	u32 conf = readl_relaxed(spicc->base + SPICC_CONREG) & SPICC_DATARATE_MASK;
 
 	/* Store current message */
 	spicc->message = message;
@@ -458,8 +461,6 @@ static int meson_spicc_prepare_message(struct spi_master *master,
 	/* Select CS */
 	conf |= FIELD_PREP(SPICC_CS_MASK, spi->chip_select);
 
-	/* Default Clock rate core/4 */
-
 	/* Default 8bit word */
 	conf |= FIELD_PREP(SPICC_BITLENGTH_MASK, 8 - 1);
 
@@ -476,12 +477,16 @@ static int meson_spicc_prepare_message(struct spi_master *master,
 static int meson_spicc_unprepare_transfer(struct spi_master *master)
 {
 	struct meson_spicc_device *spicc = spi_master_get_devdata(master);
+	u32 conf = readl_relaxed(spicc->base + SPICC_CONREG) & SPICC_DATARATE_MASK;
 
 	/* Disable all IRQs */
 	writel(0, spicc->base + SPICC_INTREG);
 
 	device_reset_optional(&spicc->pdev->dev);
 
+	/* Set default configuration, keeping datarate field */
+	writel_relaxed(conf, spicc->base + SPICC_CONREG);
+
 	return 0;
 }
 
@@ -518,14 +523,60 @@ static void meson_spicc_cleanup(struct spi_device *spi)
  * Clk path for G12A series:
  *    pclk -> pow2 fixed div -> pow2 div -> mux -> out
  *    pclk -> enh fixed div -> enh div -> mux -> out
+ *
+ * The pow2 divider is tied to the controller HW state, and the
+ * divider is only valid when the controller is initialized.
+ *
+ * A set of clock ops is added to make sure we don't read/set this
+ * clock rate while the controller is in an unknown state.
  */
 
-static int meson_spicc_clk_init(struct meson_spicc_device *spicc)
+static unsigned long meson_spicc_pow2_recalc_rate(struct clk_hw *hw,
+						  unsigned long parent_rate)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	struct meson_spicc_device *spicc = pow2_clk_to_spicc(divider);
+
+	if (!spicc->master->cur_msg || !spicc->master->busy)
+		return 0;
+
+	return clk_divider_ops.recalc_rate(hw, parent_rate);
+}
+
+static int meson_spicc_pow2_determine_rate(struct clk_hw *hw,
+					   struct clk_rate_request *req)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	struct meson_spicc_device *spicc = pow2_clk_to_spicc(divider);
+
+	if (!spicc->master->cur_msg || !spicc->master->busy)
+		return -EINVAL;
+
+	return clk_divider_ops.determine_rate(hw, req);
+}
+
+static int meson_spicc_pow2_set_rate(struct clk_hw *hw, unsigned long rate,
+				     unsigned long parent_rate)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	struct meson_spicc_device *spicc = pow2_clk_to_spicc(divider);
+
+	if (!spicc->master->cur_msg || !spicc->master->busy)
+		return -EINVAL;
+
+	return clk_divider_ops.set_rate(hw, rate, parent_rate);
+}
+
+const struct clk_ops meson_spicc_pow2_clk_ops = {
+	.recalc_rate = meson_spicc_pow2_recalc_rate,
+	.determine_rate = meson_spicc_pow2_determine_rate,
+	.set_rate = meson_spicc_pow2_set_rate,
+};
+
+static int meson_spicc_pow2_clk_init(struct meson_spicc_device *spicc)
 {
 	struct device *dev = &spicc->pdev->dev;
-	struct clk_fixed_factor *pow2_fixed_div, *enh_fixed_div;
-	struct clk_divider *pow2_div, *enh_div;
-	struct clk_mux *mux;
+	struct clk_fixed_factor *pow2_fixed_div;
 	struct clk_init_data init;
 	struct clk *clk;
 	struct clk_parent_data parent_data[2];
@@ -560,31 +611,45 @@ static int meson_spicc_clk_init(struct meson_spicc_device *spicc)
 	if (WARN_ON(IS_ERR(clk)))
 		return PTR_ERR(clk);
 
-	pow2_div = devm_kzalloc(dev, sizeof(*pow2_div), GFP_KERNEL);
-	if (!pow2_div)
-		return -ENOMEM;
-
 	snprintf(name, sizeof(name), "%s#pow2_div", dev_name(dev));
 	init.name = name;
-	init.ops = &clk_divider_ops;
-	init.flags = CLK_SET_RATE_PARENT;
+	init.ops = &meson_spicc_pow2_clk_ops;
+	/*
+	 * Set NOCACHE here to make sure we read the actual HW value
+	 * since we reset the HW after each transfer.
+	 */
+	init.flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE;
 	parent_data[0].hw = &pow2_fixed_div->hw;
 	init.num_parents = 1;
 
-	pow2_div->shift = 16,
-	pow2_div->width = 3,
-	pow2_div->flags = CLK_DIVIDER_POWER_OF_TWO,
-	pow2_div->reg = spicc->base + SPICC_CONREG;
-	pow2_div->hw.init = &init;
+	spicc->pow2_div.shift = 16,
+	spicc->pow2_div.width = 3,
+	spicc->pow2_div.flags = CLK_DIVIDER_POWER_OF_TWO,
+	spicc->pow2_div.reg = spicc->base + SPICC_CONREG;
+	spicc->pow2_div.hw.init = &init;
 
-	clk = devm_clk_register(dev, &pow2_div->hw);
-	if (WARN_ON(IS_ERR(clk)))
-		return PTR_ERR(clk);
+	spicc->clk = devm_clk_register(dev, &spicc->pow2_div.hw);
+	if (WARN_ON(IS_ERR(spicc->clk)))
+		return PTR_ERR(spicc->clk);
 
-	if (!spicc->data->has_enhance_clk_div) {
-		spicc->clk = clk;
-		return 0;
-	}
+	return 0;
+}
+
+static int meson_spicc_enh_clk_init(struct meson_spicc_device *spicc)
+{
+	struct device *dev = &spicc->pdev->dev;
+	struct clk_fixed_factor *enh_fixed_div;
+	struct clk_divider *enh_div;
+	struct clk_mux *mux;
+	struct clk_init_data init;
+	struct clk *clk;
+	struct clk_parent_data parent_data[2];
+	char name[64];
+
+	memset(&init, 0, sizeof(init));
+	memset(&parent_data, 0, sizeof(parent_data));
+
+	init.parent_data = parent_data;
 
 	/* algorithm for enh div: rate = freq / 2 / (N + 1) */
 
@@ -637,7 +702,7 @@ static int meson_spicc_clk_init(struct meson_spicc_device *spicc)
 	snprintf(name, sizeof(name), "%s#sel", dev_name(dev));
 	init.name = name;
 	init.ops = &clk_mux_ops;
-	parent_data[0].hw = &pow2_div->hw;
+	parent_data[0].hw = &spicc->pow2_div.hw;
 	parent_data[1].hw = &enh_div->hw;
 	init.num_parents = 2;
 	init.flags = CLK_SET_RATE_PARENT;
@@ -754,12 +819,20 @@ static int meson_spicc_probe(struct platform_device *pdev)
 
 	meson_spicc_oen_enable(spicc);
 
-	ret = meson_spicc_clk_init(spicc);
+	ret = meson_spicc_pow2_clk_init(spicc);
 	if (ret) {
-		dev_err(&pdev->dev, "clock registration failed\n");
+		dev_err(&pdev->dev, "pow2 clock registration failed\n");
 		goto out_clk;
 	}
 
+	if (spicc->data->has_enhance_clk_div) {
+		ret = meson_spicc_enh_clk_init(spicc);
+		if (ret) {
+			dev_err(&pdev->dev, "clock registration failed\n");
+			goto out_clk;
+		}
+	}
+
 	ret = devm_spi_register_master(&pdev->dev, master);
 	if (ret) {
 		dev_err(&pdev->dev, "spi master registration failed\n");
diff --git a/drivers/spi/spi-mux.c b/drivers/spi/spi-mux.c
index f5d32ec4634e..0709e987bd5a 100644
--- a/drivers/spi/spi-mux.c
+++ b/drivers/spi/spi-mux.c
@@ -161,6 +161,7 @@ static int spi_mux_probe(struct spi_device *spi)
 	ctlr->num_chipselect = mux_control_states(priv->mux);
 	ctlr->bus_num = -1;
 	ctlr->dev.of_node = spi->dev.of_node;
+	ctlr->must_async = true;
 
 	ret = devm_spi_register_controller(&spi->dev, ctlr);
 	if (ret)
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 838d12e65144..c8e079d7e541 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1441,31 +1441,6 @@ static const struct of_device_id pxa2xx_spi_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, pxa2xx_spi_of_match);
 
-#ifdef CONFIG_ACPI
-
-static int pxa2xx_spi_get_port_id(struct device *dev)
-{
-	struct acpi_device *adev;
-	unsigned int devid;
-	int port_id = -1;
-
-	adev = ACPI_COMPANION(dev);
-	if (adev && adev->pnp.unique_id &&
-	    !kstrtouint(adev->pnp.unique_id, 0, &devid))
-		port_id = devid;
-	return port_id;
-}
-
-#else /* !CONFIG_ACPI */
-
-static int pxa2xx_spi_get_port_id(struct device *dev)
-{
-	return -1;
-}
-
-#endif /* CONFIG_ACPI */
-
-
 #ifdef CONFIG_PCI
 
 static bool pxa2xx_spi_idma_filter(struct dma_chan *chan, void *param)
@@ -1479,13 +1454,16 @@ static struct pxa2xx_spi_controller *
 pxa2xx_spi_init_pdata(struct platform_device *pdev)
 {
 	struct pxa2xx_spi_controller *pdata;
+	struct device *dev = &pdev->dev;
+	struct device *parent = dev->parent;
 	struct ssp_device *ssp;
 	struct resource *res;
-	struct device *parent = pdev->dev.parent;
 	struct pci_dev *pcidev = dev_is_pci(parent) ? to_pci_dev(parent) : NULL;
 	const struct pci_device_id *pcidev_id = NULL;
 	enum pxa_ssp_type type;
 	const void *match;
+	int status;
+	u64 uid;
 
 	if (pcidev)
 		pcidev_id = pci_match_id(pxa2xx_spi_pci_compound_match, pcidev);
@@ -1529,7 +1507,12 @@ pxa2xx_spi_init_pdata(struct platform_device *pdev)
 
 	ssp->type = type;
 	ssp->dev = &pdev->dev;
-	ssp->port_id = pxa2xx_spi_get_port_id(&pdev->dev);
+
+	status = acpi_dev_uid_to_integer(ACPI_COMPANION(dev), &uid);
+	if (status)
+		ssp->port_id = -1;
+	else
+		ssp->port_id = uid;
 
 	pdata->is_slave = device_property_read_bool(&pdev->dev, "spi-slave");
 	pdata->num_chipselect = 1;
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 8f97a3eacdea..30e82f968639 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -95,7 +95,7 @@ static ssize_t driver_override_show(struct device *dev,
 }
 static DEVICE_ATTR_RW(driver_override);
 
-static struct spi_statistics *spi_alloc_pcpu_stats(struct device *dev)
+static struct spi_statistics __percpu *spi_alloc_pcpu_stats(struct device *dev)
 {
 	struct spi_statistics __percpu *pcpu_stats;
 
@@ -162,7 +162,7 @@ static struct device_attribute dev_attr_spi_device_##field = {		\
 }
 
 #define SPI_STATISTICS_SHOW_NAME(name, file, field)			\
-static ssize_t spi_statistics_##name##_show(struct spi_statistics *stat, \
+static ssize_t spi_statistics_##name##_show(struct spi_statistics __percpu *stat, \
 					    char *buf)			\
 {									\
 	ssize_t len;							\
@@ -309,7 +309,7 @@ static const struct attribute_group *spi_master_groups[] = {
 	NULL,
 };
 
-static void spi_statistics_add_transfer_stats(struct spi_statistics *pcpu_stats,
+static void spi_statistics_add_transfer_stats(struct spi_statistics __percpu *pcpu_stats,
 					      struct spi_transfer *xfer,
 					      struct spi_controller *ctlr)
 {
@@ -1275,8 +1275,8 @@ static int spi_transfer_wait(struct spi_controller *ctlr,
 			     struct spi_message *msg,
 			     struct spi_transfer *xfer)
 {
-	struct spi_statistics *statm = ctlr->pcpu_statistics;
-	struct spi_statistics *stats = msg->spi->pcpu_statistics;
+	struct spi_statistics __percpu *statm = ctlr->pcpu_statistics;
+	struct spi_statistics __percpu *stats = msg->spi->pcpu_statistics;
 	u32 speed_hz = xfer->speed_hz;
 	unsigned long long ms;
 
@@ -1432,8 +1432,8 @@ static int spi_transfer_one_message(struct spi_controller *ctlr,
 	struct spi_transfer *xfer;
 	bool keep_cs = false;
 	int ret = 0;
-	struct spi_statistics *statm = ctlr->pcpu_statistics;
-	struct spi_statistics *stats = msg->spi->pcpu_statistics;
+	struct spi_statistics __percpu *statm = ctlr->pcpu_statistics;
+	struct spi_statistics __percpu *stats = msg->spi->pcpu_statistics;
 
 	spi_set_cs(msg->spi, true, false);
 
@@ -1727,8 +1727,7 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread)
 	spin_unlock_irqrestore(&ctlr->queue_lock, flags);
 
 	ret = __spi_pump_transfer_message(ctlr, msg, was_busy);
-	if (!ret)
-		kthread_queue_work(ctlr->kworker, &ctlr->pump_messages);
+	kthread_queue_work(ctlr->kworker, &ctlr->pump_messages);
 
 	ctlr->cur_msg = NULL;
 	ctlr->fallback = false;
@@ -4033,7 +4032,7 @@ static int __spi_sync(struct spi_device *spi, struct spi_message *message)
 	 * guard against reentrancy from a different context. The io_mutex
 	 * will catch those cases.
 	 */
-	if (READ_ONCE(ctlr->queue_empty)) {
+	if (READ_ONCE(ctlr->queue_empty) && !ctlr->must_async) {
 		message->actual_length = 0;
 		message->status = -EINPROGRESS;
 
@@ -4375,7 +4374,7 @@ static int acpi_spi_notify(struct notifier_block *nb, unsigned long value,
 
 	switch (value) {
 	case ACPI_RECONFIG_DEVICE_ADD:
-		ctlr = acpi_spi_find_controller_by_adev(adev->parent);
+		ctlr = acpi_spi_find_controller_by_adev(acpi_dev_parent(adev));
 		if (!ctlr)
 			break;
 
diff --git a/drivers/staging/media/rkvdec/rkvdec-h264.c b/drivers/staging/media/rkvdec/rkvdec-h264.c
index 4af5a831bde0..4fc167b42cf0 100644
--- a/drivers/staging/media/rkvdec/rkvdec-h264.c
+++ b/drivers/staging/media/rkvdec/rkvdec-h264.c
@@ -1162,8 +1162,8 @@ static int rkvdec_h264_run(struct rkvdec_ctx *ctx)
 
 	schedule_delayed_work(&rkvdec->watchdog_work, msecs_to_jiffies(2000));
 
-	writel(0xffffffff, rkvdec->regs + RKVDEC_REG_STRMD_ERR_EN);
-	writel(0xffffffff, rkvdec->regs + RKVDEC_REG_H264_ERR_E);
+	writel(0, rkvdec->regs + RKVDEC_REG_STRMD_ERR_EN);
+	writel(0, rkvdec->regs + RKVDEC_REG_H264_ERR_E);
 	writel(1, rkvdec->regs + RKVDEC_REG_PREF_LUMA_CACHE_COMMAND);
 	writel(1, rkvdec->regs + RKVDEC_REG_PREF_CHR_CACHE_COMMAND);
 
diff --git a/drivers/staging/r8188eu/os_dep/os_intfs.c b/drivers/staging/r8188eu/os_dep/os_intfs.c
index cac9553666e6..aa100b5141e1 100644
--- a/drivers/staging/r8188eu/os_dep/os_intfs.c
+++ b/drivers/staging/r8188eu/os_dep/os_intfs.c
@@ -18,6 +18,7 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Realtek Wireless Lan Driver");
 MODULE_AUTHOR("Realtek Semiconductor Corp.");
 MODULE_VERSION(DRIVERVERSION);
+MODULE_FIRMWARE("rtlwifi/rtl8188eufw.bin");
 
 #define CONFIG_BR_EXT_BRNAME "br0"
 #define RTW_NOTCH_FILTER 0 /* 0:Disable, 1:Enable, */
diff --git a/drivers/staging/r8188eu/os_dep/usb_intf.c b/drivers/staging/r8188eu/os_dep/usb_intf.c
index cc2b44f60c46..9147d176da4f 100644
--- a/drivers/staging/r8188eu/os_dep/usb_intf.c
+++ b/drivers/staging/r8188eu/os_dep/usb_intf.c
@@ -28,6 +28,7 @@ static struct usb_device_id rtw_usb_id_tbl[] = {
 	/*=== Realtek demoboard ===*/
 	{USB_DEVICE(USB_VENDER_ID_REALTEK, 0x8179)}, /* 8188EUS */
 	{USB_DEVICE(USB_VENDER_ID_REALTEK, 0x0179)}, /* 8188ETV */
+	{USB_DEVICE(USB_VENDER_ID_REALTEK, 0xffef)}, /* Rosewill USB-N150 Nano */
 	/*=== Customer ID ===*/
 	/****** 8188EUS ********/
 	{USB_DEVICE(0x07B8, 0x8179)}, /* Abocom - Abocom */
diff --git a/drivers/staging/rtl8712/rtl8712_cmd.c b/drivers/staging/rtl8712/rtl8712_cmd.c
index 2326aae6709e..bb7db96ed821 100644
--- a/drivers/staging/rtl8712/rtl8712_cmd.c
+++ b/drivers/staging/rtl8712/rtl8712_cmd.c
@@ -117,34 +117,6 @@ static void r871x_internal_cmd_hdl(struct _adapter *padapter, u8 *pbuf)
 	kfree(pdrvcmd->pbuf);
 }
 
-static u8 read_macreg_hdl(struct _adapter *padapter, u8 *pbuf)
-{
-	void (*pcmd_callback)(struct _adapter *dev, struct cmd_obj	*pcmd);
-	struct cmd_obj *pcmd  = (struct cmd_obj *)pbuf;
-
-	/*  invoke cmd->callback function */
-	pcmd_callback = cmd_callback[pcmd->cmdcode].callback;
-	if (!pcmd_callback)
-		r8712_free_cmd_obj(pcmd);
-	else
-		pcmd_callback(padapter, pcmd);
-	return H2C_SUCCESS;
-}
-
-static u8 write_macreg_hdl(struct _adapter *padapter, u8 *pbuf)
-{
-	void (*pcmd_callback)(struct _adapter *dev, struct cmd_obj	*pcmd);
-	struct cmd_obj *pcmd  = (struct cmd_obj *)pbuf;
-
-	/*  invoke cmd->callback function */
-	pcmd_callback = cmd_callback[pcmd->cmdcode].callback;
-	if (!pcmd_callback)
-		r8712_free_cmd_obj(pcmd);
-	else
-		pcmd_callback(padapter, pcmd);
-	return H2C_SUCCESS;
-}
-
 static u8 read_bbreg_hdl(struct _adapter *padapter, u8 *pbuf)
 {
 	struct cmd_obj *pcmd  = (struct cmd_obj *)pbuf;
@@ -213,14 +185,6 @@ static struct cmd_obj *cmd_hdl_filter(struct _adapter *padapter,
 	pcmd_r = NULL;
 
 	switch (pcmd->cmdcode) {
-	case GEN_CMD_CODE(_Read_MACREG):
-		read_macreg_hdl(padapter, (u8 *)pcmd);
-		pcmd_r = pcmd;
-		break;
-	case GEN_CMD_CODE(_Write_MACREG):
-		write_macreg_hdl(padapter, (u8 *)pcmd);
-		pcmd_r = pcmd;
-		break;
 	case GEN_CMD_CODE(_Read_BBREG):
 		read_bbreg_hdl(padapter, (u8 *)pcmd);
 		break;
diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
index f2b1bcefcadd..27295bda3e0b 100644
--- a/drivers/tee/tee_shm.c
+++ b/drivers/tee/tee_shm.c
@@ -9,6 +9,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/tee_drv.h>
+#include <linux/uaccess.h>
 #include <linux/uio.h>
 #include "tee_private.h"
 
@@ -326,6 +327,9 @@ struct tee_shm *tee_shm_register_user_buf(struct tee_context *ctx,
 	void *ret;
 	int id;
 
+	if (!access_ok((void __user *)addr, length))
+		return ERR_PTR(-EFAULT);
+
 	mutex_lock(&teedev->mutex);
 	id = idr_alloc(&teedev->idr, NULL, 1, 0, GFP_KERNEL);
 	mutex_unlock(&teedev->mutex);
diff --git a/drivers/thermal/amlogic_thermal.c b/drivers/thermal/amlogic_thermal.c
index e61b91d14ad1..d30cb791e63c 100644
--- a/drivers/thermal/amlogic_thermal.c
+++ b/drivers/thermal/amlogic_thermal.c
@@ -179,12 +179,12 @@ static int amlogic_thermal_disable(struct amlogic_thermal *data)
 	return 0;
 }
 
-static int amlogic_thermal_get_temp(void *data, int *temp)
+static int amlogic_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
 	unsigned int tval;
-	struct amlogic_thermal *pdata = data;
+	struct amlogic_thermal *pdata = tz->devdata;
 
-	if (!data)
+	if (!pdata)
 		return -EINVAL;
 
 	regmap_read(pdata->regmap, TSENSOR_STAT0, &tval);
@@ -195,7 +195,7 @@ static int amlogic_thermal_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops amlogic_thermal_ops = {
+static const struct thermal_zone_device_ops amlogic_thermal_ops = {
 	.get_temp	= amlogic_thermal_get_temp,
 };
 
@@ -276,10 +276,10 @@ static int amlogic_thermal_probe(struct platform_device *pdev)
 		return PTR_ERR(pdata->sec_ao_map);
 	}
 
-	pdata->tzd = devm_thermal_zone_of_sensor_register(&pdev->dev,
-							  0,
-							  pdata,
-							  &amlogic_thermal_ops);
+	pdata->tzd = devm_thermal_of_zone_register(&pdev->dev,
+						   0,
+						   pdata,
+						   &amlogic_thermal_ops);
 	if (IS_ERR(pdata->tzd)) {
 		ret = PTR_ERR(pdata->tzd);
 		dev_err(dev, "Failed to register tsensor: %d\n", ret);
diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index c2ebfb5be4b3..52d63b3997fe 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -420,9 +420,9 @@ static struct thermal_zone_device_ops legacy_ops = {
 	.get_temp = armada_get_temp_legacy,
 };
 
-static int armada_get_temp(void *_sensor, int *temp)
+static int armada_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct armada_thermal_sensor *sensor = _sensor;
+	struct armada_thermal_sensor *sensor = tz->devdata;
 	struct armada_thermal_priv *priv = sensor->priv;
 	int ret;
 
@@ -450,7 +450,7 @@ unlock_mutex:
 	return ret;
 }
 
-static const struct thermal_zone_of_device_ops of_ops = {
+static const struct thermal_zone_device_ops of_ops = {
 	.get_temp = armada_get_temp,
 };
 
@@ -928,9 +928,9 @@ static int armada_thermal_probe(struct platform_device *pdev)
 		/* Register the sensor */
 		sensor->priv = priv;
 		sensor->id = sensor_id;
-		tz = devm_thermal_zone_of_sensor_register(&pdev->dev,
-							  sensor->id, sensor,
-							  &of_ops);
+		tz = devm_thermal_of_zone_register(&pdev->dev,
+						   sensor->id, sensor,
+						   &of_ops);
 		if (IS_ERR(tz)) {
 			dev_info(&pdev->dev, "Thermal sensor %d unavailable\n",
 				 sensor_id);
diff --git a/drivers/thermal/broadcom/bcm2711_thermal.c b/drivers/thermal/broadcom/bcm2711_thermal.c
index e9bef5c3414b..1f8651d15160 100644
--- a/drivers/thermal/broadcom/bcm2711_thermal.c
+++ b/drivers/thermal/broadcom/bcm2711_thermal.c
@@ -31,11 +31,11 @@ struct bcm2711_thermal_priv {
 	struct thermal_zone_device *thermal;
 };
 
-static int bcm2711_get_temp(void *data, int *temp)
+static int bcm2711_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct bcm2711_thermal_priv *priv = data;
-	int slope = thermal_zone_get_slope(priv->thermal);
-	int offset = thermal_zone_get_offset(priv->thermal);
+	struct bcm2711_thermal_priv *priv = tz->devdata;
+	int slope = thermal_zone_get_slope(tz);
+	int offset = thermal_zone_get_offset(tz);
 	u32 val;
 	int ret;
 
@@ -54,7 +54,7 @@ static int bcm2711_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops bcm2711_thermal_of_ops = {
+static const struct thermal_zone_device_ops bcm2711_thermal_of_ops = {
 	.get_temp	= bcm2711_get_temp,
 };
 
@@ -88,8 +88,8 @@ static int bcm2711_thermal_probe(struct platform_device *pdev)
 	}
 	priv->regmap = regmap;
 
-	thermal = devm_thermal_zone_of_sensor_register(dev, 0, priv,
-						       &bcm2711_thermal_of_ops);
+	thermal = devm_thermal_of_zone_register(dev, 0, priv,
+						&bcm2711_thermal_of_ops);
 	if (IS_ERR(thermal)) {
 		ret = PTR_ERR(thermal);
 		dev_err(dev, "could not register sensor: %d\n", ret);
diff --git a/drivers/thermal/broadcom/bcm2835_thermal.c b/drivers/thermal/broadcom/bcm2835_thermal.c
index c8e4344d5a3d..2c67841a1115 100644
--- a/drivers/thermal/broadcom/bcm2835_thermal.c
+++ b/drivers/thermal/broadcom/bcm2835_thermal.c
@@ -88,9 +88,9 @@ static int bcm2835_thermal_temp2adc(int temp, int offset, int slope)
 	return temp;
 }
 
-static int bcm2835_thermal_get_temp(void *d, int *temp)
+static int bcm2835_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct bcm2835_thermal_data *data = d;
+	struct bcm2835_thermal_data *data = tz->devdata;
 	u32 val = readl(data->regs + BCM2835_TS_TSENSSTAT);
 
 	if (!(val & BCM2835_TS_TSENSSTAT_VALID))
@@ -135,7 +135,7 @@ static void bcm2835_thermal_debugfs(struct platform_device *pdev)
 	debugfs_create_regset32("regset", 0444, data->debugfsdir, regset);
 }
 
-static const struct thermal_zone_of_device_ops bcm2835_thermal_ops = {
+static const struct thermal_zone_device_ops bcm2835_thermal_ops = {
 	.get_temp = bcm2835_thermal_get_temp,
 };
 
@@ -206,8 +206,8 @@ static int bcm2835_thermal_probe(struct platform_device *pdev)
 			 data->clk, rate);
 
 	/* register of thermal sensor and get info from DT */
-	tz = thermal_zone_of_sensor_register(&pdev->dev, 0, data,
-					     &bcm2835_thermal_ops);
+	tz = devm_thermal_of_zone_register(&pdev->dev, 0, data,
+					   &bcm2835_thermal_ops);
 	if (IS_ERR(tz)) {
 		err = PTR_ERR(tz);
 		dev_err(&pdev->dev,
@@ -277,7 +277,7 @@ static int bcm2835_thermal_probe(struct platform_device *pdev)
 
 	return 0;
 err_tz:
-	thermal_zone_of_sensor_unregister(&pdev->dev, tz);
+	thermal_of_zone_unregister(tz);
 err_clk:
 	clk_disable_unprepare(data->clk);
 
@@ -290,7 +290,7 @@ static int bcm2835_thermal_remove(struct platform_device *pdev)
 	struct thermal_zone_device *tz = data->tz;
 
 	debugfs_remove_recursive(data->debugfsdir);
-	thermal_zone_of_sensor_unregister(&pdev->dev, tz);
+	thermal_of_zone_unregister(tz);
 	clk_disable_unprepare(data->clk);
 
 	return 0;
diff --git a/drivers/thermal/broadcom/brcmstb_thermal.c b/drivers/thermal/broadcom/brcmstb_thermal.c
index 0cedb8b4f00a..c79c6cfdd74d 100644
--- a/drivers/thermal/broadcom/brcmstb_thermal.c
+++ b/drivers/thermal/broadcom/brcmstb_thermal.c
@@ -105,7 +105,7 @@ static struct avs_tmon_trip avs_tmon_trips[] = {
 struct brcmstb_thermal_params {
 	unsigned int offset;
 	unsigned int mult;
-	const struct thermal_zone_of_device_ops *of_ops;
+	const struct thermal_zone_device_ops *of_ops;
 };
 
 struct brcmstb_thermal_priv {
@@ -150,9 +150,9 @@ static inline u32 avs_tmon_temp_to_code(struct brcmstb_thermal_priv *priv,
 		return (u32)((offset - temp) / mult);
 }
 
-static int brcmstb_get_temp(void *data, int *temp)
+static int brcmstb_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct brcmstb_thermal_priv *priv = data;
+	struct brcmstb_thermal_priv *priv = tz->devdata;
 	u32 val;
 	long t;
 
@@ -260,9 +260,9 @@ static irqreturn_t brcmstb_tmon_irq_thread(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int brcmstb_set_trips(void *data, int low, int high)
+static int brcmstb_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	struct brcmstb_thermal_priv *priv = data;
+	struct brcmstb_thermal_priv *priv = tz->devdata;
 
 	dev_dbg(priv->dev, "set trips %d <--> %d\n", low, high);
 
@@ -288,7 +288,7 @@ static int brcmstb_set_trips(void *data, int low, int high)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops brcmstb_16nm_of_ops = {
+static const struct thermal_zone_device_ops brcmstb_16nm_of_ops = {
 	.get_temp	= brcmstb_get_temp,
 };
 
@@ -298,7 +298,7 @@ static const struct brcmstb_thermal_params brcmstb_16nm_params = {
 	.of_ops	= &brcmstb_16nm_of_ops,
 };
 
-static const struct thermal_zone_of_device_ops brcmstb_28nm_of_ops = {
+static const struct thermal_zone_device_ops brcmstb_28nm_of_ops = {
 	.get_temp	= brcmstb_get_temp,
 	.set_trips	= brcmstb_set_trips,
 };
@@ -318,7 +318,7 @@ MODULE_DEVICE_TABLE(of, brcmstb_thermal_id_table);
 
 static int brcmstb_thermal_probe(struct platform_device *pdev)
 {
-	const struct thermal_zone_of_device_ops *of_ops;
+	const struct thermal_zone_device_ops *of_ops;
 	struct thermal_zone_device *thermal;
 	struct brcmstb_thermal_priv *priv;
 	struct resource *res;
@@ -341,8 +341,8 @@ static int brcmstb_thermal_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, priv);
 	of_ops = priv->temp_params->of_ops;
 
-	thermal = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, priv,
-						       of_ops);
+	thermal = devm_thermal_of_zone_register(&pdev->dev, 0, priv,
+						of_ops);
 	if (IS_ERR(thermal)) {
 		ret = PTR_ERR(thermal);
 		dev_err(&pdev->dev, "could not register sensor: %d\n", ret);
diff --git a/drivers/thermal/broadcom/ns-thermal.c b/drivers/thermal/broadcom/ns-thermal.c
index c9468ba9d449..07a8a3f49bd0 100644
--- a/drivers/thermal/broadcom/ns-thermal.c
+++ b/drivers/thermal/broadcom/ns-thermal.c
@@ -14,19 +14,14 @@
 #define PVTMON_CONTROL0_SEL_TEST_MODE			0x0000000e
 #define PVTMON_STATUS					0x08
 
-struct ns_thermal {
-	struct thermal_zone_device *tz;
-	void __iomem *pvtmon;
-};
-
-static int ns_thermal_get_temp(void *data, int *temp)
+static int ns_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct ns_thermal *ns_thermal = data;
-	int offset = thermal_zone_get_offset(ns_thermal->tz);
-	int slope = thermal_zone_get_slope(ns_thermal->tz);
+	void __iomem *pvtmon = tz->devdata;
+	int offset = thermal_zone_get_offset(tz);
+	int slope = thermal_zone_get_slope(tz);
 	u32 val;
 
-	val = readl(ns_thermal->pvtmon + PVTMON_CONTROL0);
+	val = readl(pvtmon + PVTMON_CONTROL0);
 	if ((val & PVTMON_CONTROL0_SEL_MASK) != PVTMON_CONTROL0_SEL_TEMP_MONITOR) {
 		/* Clear current mode selection */
 		val &= ~PVTMON_CONTROL0_SEL_MASK;
@@ -34,50 +29,47 @@ static int ns_thermal_get_temp(void *data, int *temp)
 		/* Set temp monitor mode (it's the default actually) */
 		val |= PVTMON_CONTROL0_SEL_TEMP_MONITOR;
 
-		writel(val, ns_thermal->pvtmon + PVTMON_CONTROL0);
+		writel(val, pvtmon + PVTMON_CONTROL0);
 	}
 
-	val = readl(ns_thermal->pvtmon + PVTMON_STATUS);
+	val = readl(pvtmon + PVTMON_STATUS);
 	*temp = slope * val + offset;
 
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops ns_thermal_ops = {
+static const struct thermal_zone_device_ops ns_thermal_ops = {
 	.get_temp = ns_thermal_get_temp,
 };
 
 static int ns_thermal_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct ns_thermal *ns_thermal;
-
-	ns_thermal = devm_kzalloc(dev, sizeof(*ns_thermal), GFP_KERNEL);
-	if (!ns_thermal)
-		return -ENOMEM;
+	struct thermal_zone_device *tz;
+	void __iomem *pvtmon;
 
-	ns_thermal->pvtmon = of_iomap(dev_of_node(dev), 0);
-	if (WARN_ON(!ns_thermal->pvtmon))
+	pvtmon = of_iomap(dev_of_node(dev), 0);
+	if (WARN_ON(!pvtmon))
 		return -ENOENT;
 
-	ns_thermal->tz = devm_thermal_zone_of_sensor_register(dev, 0,
-							      ns_thermal,
-							      &ns_thermal_ops);
-	if (IS_ERR(ns_thermal->tz)) {
-		iounmap(ns_thermal->pvtmon);
-		return PTR_ERR(ns_thermal->tz);
+	tz = devm_thermal_of_zone_register(dev, 0,
+					   pvtmon,
+					   &ns_thermal_ops);
+	if (IS_ERR(tz)) {
+		iounmap(pvtmon);
+		return PTR_ERR(tz);
 	}
 
-	platform_set_drvdata(pdev, ns_thermal);
+	platform_set_drvdata(pdev, pvtmon);
 
 	return 0;
 }
 
 static int ns_thermal_remove(struct platform_device *pdev)
 {
-	struct ns_thermal *ns_thermal = platform_get_drvdata(pdev);
+	void __iomem *pvtmon = platform_get_drvdata(pdev);
 
-	iounmap(ns_thermal->pvtmon);
+	iounmap(pvtmon);
 
 	return 0;
 }
diff --git a/drivers/thermal/broadcom/sr-thermal.c b/drivers/thermal/broadcom/sr-thermal.c
index 85ab9edd580c..2b93502543ff 100644
--- a/drivers/thermal/broadcom/sr-thermal.c
+++ b/drivers/thermal/broadcom/sr-thermal.c
@@ -19,7 +19,6 @@
 #define SR_TMON_MAX_LIST        6
 
 struct sr_tmon {
-	struct thermal_zone_device *tz;
 	unsigned int crit_temp;
 	unsigned int tmon_id;
 	struct sr_thermal *priv;
@@ -31,9 +30,9 @@ struct sr_thermal {
 	struct sr_tmon tmon[SR_TMON_MAX_LIST];
 };
 
-static int sr_get_temp(void *data, int *temp)
+static int sr_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct sr_tmon *tmon = data;
+	struct sr_tmon *tmon = tz->devdata;
 	struct sr_thermal *sr_thermal = tmon->priv;
 
 	*temp = readl(sr_thermal->regs + SR_TMON_TEMP_BASE(tmon->tmon_id));
@@ -41,13 +40,14 @@ static int sr_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops sr_tz_ops = {
+static const struct thermal_zone_device_ops sr_tz_ops = {
 	.get_temp = sr_get_temp,
 };
 
 static int sr_thermal_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	struct thermal_zone_device *tz;
 	struct sr_thermal *sr_thermal;
 	struct sr_tmon *tmon;
 	struct resource *res;
@@ -84,10 +84,10 @@ static int sr_thermal_probe(struct platform_device *pdev)
 		writel(0, sr_thermal->regs + SR_TMON_TEMP_BASE(i));
 		tmon->tmon_id = i;
 		tmon->priv = sr_thermal;
-		tmon->tz = devm_thermal_zone_of_sensor_register(dev, i, tmon,
-								&sr_tz_ops);
-		if (IS_ERR(tmon->tz))
-			return PTR_ERR(tmon->tz);
+		tz = devm_thermal_of_zone_register(dev, i, tmon,
+						   &sr_tz_ops);
+		if (IS_ERR(tz))
+			return PTR_ERR(tz);
 
 		dev_dbg(dev, "thermal sensor %d registered\n", i);
 	}
diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c
index b76293cc989c..9f8b438fcf8f 100644
--- a/drivers/thermal/cpufreq_cooling.c
+++ b/drivers/thermal/cpufreq_cooling.c
@@ -475,7 +475,7 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
 
 /**
  * __cpufreq_cooling_register - helper function to create cpufreq cooling device
- * @np: a valid struct device_node to the cooling device device tree node
+ * @np: a valid struct device_node to the cooling device tree node
  * @policy: cpufreq policy
  * Normally this should be same as cpufreq policy->related_cpus.
  * @em: Energy Model of the cpufreq policy
@@ -501,17 +501,17 @@ __cpufreq_cooling_register(struct device_node *np,
 	struct thermal_cooling_device_ops *cooling_ops;
 	char *name;
 
+	if (IS_ERR_OR_NULL(policy)) {
+		pr_err("%s: cpufreq policy isn't valid: %p\n", __func__, policy);
+		return ERR_PTR(-EINVAL);
+	}
+
 	dev = get_cpu_device(policy->cpu);
 	if (unlikely(!dev)) {
 		pr_warn("No cpu device for cpu %d\n", policy->cpu);
 		return ERR_PTR(-ENODEV);
 	}
 
-	if (IS_ERR_OR_NULL(policy)) {
-		pr_err("%s: cpufreq policy isn't valid: %p\n", __func__, policy);
-		return ERR_PTR(-EINVAL);
-	}
-
 	i = cpufreq_table_count_valid_entries(policy);
 	if (!i) {
 		pr_debug("%s: CPUFreq table not found or has no valid entries\n",
diff --git a/drivers/thermal/da9062-thermal.c b/drivers/thermal/da9062-thermal.c
index 180edec34e07..7dcfde7a9f2c 100644
--- a/drivers/thermal/da9062-thermal.c
+++ b/drivers/thermal/da9062-thermal.c
@@ -248,10 +248,9 @@ static int da9062_thermal_probe(struct platform_device *pdev)
 		jiffies_to_msecs(thermal->zone->passive_delay_jiffies));
 
 	ret = platform_get_irq_byname(pdev, "THERMAL");
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to get platform IRQ.\n");
+	if (ret < 0)
 		goto err_zone;
-	}
+
 	thermal->irq = ret;
 
 	ret = request_threaded_irq(thermal->irq, NULL,
diff --git a/drivers/thermal/db8500_thermal.c b/drivers/thermal/db8500_thermal.c
index 121cf853e545..cb10e280681f 100644
--- a/drivers/thermal/db8500_thermal.c
+++ b/drivers/thermal/db8500_thermal.c
@@ -58,9 +58,9 @@ struct db8500_thermal_zone {
 };
 
 /* Callback to get current temperature */
-static int db8500_thermal_get_temp(void *data, int *temp)
+static int db8500_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct db8500_thermal_zone *th = data;
+	struct db8500_thermal_zone *th = tz->devdata;
 
 	/*
 	 * TODO: There is no PRCMU interface to get temperature data currently,
@@ -72,7 +72,7 @@ static int db8500_thermal_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static struct thermal_zone_of_device_ops thdev_ops = {
+static const struct thermal_zone_device_ops thdev_ops = {
 	.get_temp = db8500_thermal_get_temp,
 };
 
@@ -182,7 +182,7 @@ static int db8500_thermal_probe(struct platform_device *pdev)
 	}
 
 	/* register of thermal sensor and get info from DT */
-	th->tz = devm_thermal_zone_of_sensor_register(dev, 0, th, &thdev_ops);
+	th->tz = devm_thermal_of_zone_register(dev, 0, th, &thdev_ops);
 	if (IS_ERR(th->tz)) {
 		dev_err(dev, "register thermal zone sensor failed\n");
 		return PTR_ERR(th->tz);
diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c
index 991a1c54296d..a08bbe33be96 100644
--- a/drivers/thermal/gov_bang_bang.c
+++ b/drivers/thermal/gov_bang_bang.c
@@ -31,8 +31,6 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip)
 				trip, trip_temp, tz->temperature,
 				trip_hyst);
 
-	mutex_lock(&tz->lock);
-
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
 		if (instance->trip != trip)
 			continue;
@@ -65,8 +63,6 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip)
 		instance->cdev->updated = false; /* cdev needs update */
 		mutex_unlock(&instance->cdev->lock);
 	}
-
-	mutex_unlock(&tz->lock);
 }
 
 /**
@@ -100,15 +96,13 @@ static int bang_bang_control(struct thermal_zone_device *tz, int trip)
 {
 	struct thermal_instance *instance;
 
-	thermal_zone_trip_update(tz, trip);
+	lockdep_assert_held(&tz->lock);
 
-	mutex_lock(&tz->lock);
+	thermal_zone_trip_update(tz, trip);
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node)
 		thermal_cdev_update(instance->cdev);
 
-	mutex_unlock(&tz->lock);
-
 	return 0;
 }
 
diff --git a/drivers/thermal/gov_fair_share.c b/drivers/thermal/gov_fair_share.c
index 6a2abcfc648f..a4ee4661e9cc 100644
--- a/drivers/thermal/gov_fair_share.c
+++ b/drivers/thermal/gov_fair_share.c
@@ -82,7 +82,7 @@ static int fair_share_throttle(struct thermal_zone_device *tz, int trip)
 	int total_instance = 0;
 	int cur_trip_level = get_trip_level(tz);
 
-	mutex_lock(&tz->lock);
+	lockdep_assert_held(&tz->lock);
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
 		if (instance->trip != trip)
@@ -112,7 +112,6 @@ static int fair_share_throttle(struct thermal_zone_device *tz, int trip)
 		mutex_unlock(&cdev->lock);
 	}
 
-	mutex_unlock(&tz->lock);
 	return 0;
 }
 
diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index 1d5052470967..2d1aeaba38a8 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -392,8 +392,6 @@ static int allocate_power(struct thermal_zone_device *tz,
 	int i, num_actors, total_weight, ret = 0;
 	int trip_max_desired_temperature = params->trip_max_desired_temperature;
 
-	mutex_lock(&tz->lock);
-
 	num_actors = 0;
 	total_weight = 0;
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
@@ -404,10 +402,8 @@ static int allocate_power(struct thermal_zone_device *tz,
 		}
 	}
 
-	if (!num_actors) {
-		ret = -ENODEV;
-		goto unlock;
-	}
+	if (!num_actors)
+		return -ENODEV;
 
 	/*
 	 * We need to allocate five arrays of the same size:
@@ -421,10 +417,8 @@ static int allocate_power(struct thermal_zone_device *tz,
 	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*extra_actor_power));
 	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*weighted_req_power));
 	req_power = kcalloc(num_actors * 5, sizeof(*req_power), GFP_KERNEL);
-	if (!req_power) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	if (!req_power)
+		return -ENOMEM;
 
 	max_power = &req_power[num_actors];
 	granted_power = &req_power[2 * num_actors];
@@ -496,8 +490,6 @@ static int allocate_power(struct thermal_zone_device *tz,
 				      control_temp - tz->temperature);
 
 	kfree(req_power);
-unlock:
-	mutex_unlock(&tz->lock);
 
 	return ret;
 }
@@ -576,7 +568,6 @@ static void allow_maximum_power(struct thermal_zone_device *tz, bool update)
 	struct power_allocator_params *params = tz->governor_data;
 	u32 req_power;
 
-	mutex_lock(&tz->lock);
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
 		struct thermal_cooling_device *cdev = instance->cdev;
 
@@ -598,7 +589,6 @@ static void allow_maximum_power(struct thermal_zone_device *tz, bool update)
 
 		mutex_unlock(&instance->cdev->lock);
 	}
-	mutex_unlock(&tz->lock);
 }
 
 /**
@@ -712,6 +702,8 @@ static int power_allocator_throttle(struct thermal_zone_device *tz, int trip)
 	struct power_allocator_params *params = tz->governor_data;
 	bool update;
 
+	lockdep_assert_held(&tz->lock);
+
 	/*
 	 * We get called for every trip point but we only need to do
 	 * our calculations once
diff --git a/drivers/thermal/gov_step_wise.c b/drivers/thermal/gov_step_wise.c
index 9729b46d0258..cdd3354bc27f 100644
--- a/drivers/thermal/gov_step_wise.c
+++ b/drivers/thermal/gov_step_wise.c
@@ -117,8 +117,6 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip)
 	dev_dbg(&tz->device, "Trip%d[type=%d,temp=%d]:trend=%d,throttle=%d\n",
 				trip, trip_type, trip_temp, trend, throttle);
 
-	mutex_lock(&tz->lock);
-
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
 		if (instance->trip != trip)
 			continue;
@@ -145,8 +143,6 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip)
 		instance->cdev->updated = false; /* cdev needs update */
 		mutex_unlock(&instance->cdev->lock);
 	}
-
-	mutex_unlock(&tz->lock);
 }
 
 /**
@@ -164,15 +160,13 @@ static int step_wise_throttle(struct thermal_zone_device *tz, int trip)
 {
 	struct thermal_instance *instance;
 
-	thermal_zone_trip_update(tz, trip);
+	lockdep_assert_held(&tz->lock);
 
-	mutex_lock(&tz->lock);
+	thermal_zone_trip_update(tz, trip);
 
 	list_for_each_entry(instance, &tz->thermal_instances, tz_node)
 		thermal_cdev_update(instance->cdev);
 
-	mutex_unlock(&tz->lock);
-
 	return 0;
 }
 
diff --git a/drivers/thermal/gov_user_space.c b/drivers/thermal/gov_user_space.c
index a62a4e90bd3f..8bc1c22aaf03 100644
--- a/drivers/thermal/gov_user_space.c
+++ b/drivers/thermal/gov_user_space.c
@@ -34,7 +34,8 @@ static int notify_user_space(struct thermal_zone_device *tz, int trip)
 	char *thermal_prop[5];
 	int i;
 
-	mutex_lock(&tz->lock);
+	lockdep_assert_held(&tz->lock);
+
 	thermal_prop[0] = kasprintf(GFP_KERNEL, "NAME=%s", tz->type);
 	thermal_prop[1] = kasprintf(GFP_KERNEL, "TEMP=%d", tz->temperature);
 	thermal_prop[2] = kasprintf(GFP_KERNEL, "TRIP=%d", trip);
@@ -43,7 +44,7 @@ static int notify_user_space(struct thermal_zone_device *tz, int trip)
 	kobject_uevent_env(&tz->device.kobj, KOBJ_CHANGE, thermal_prop);
 	for (i = 0; i < 4; ++i)
 		kfree(thermal_prop[i]);
-	mutex_unlock(&tz->lock);
+
 	return 0;
 }
 
diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c
index 19a242c69ce6..d6974db7aaf7 100644
--- a/drivers/thermal/hisi_thermal.c
+++ b/drivers/thermal/hisi_thermal.c
@@ -434,9 +434,9 @@ static int hi3660_thermal_probe(struct hisi_thermal_data *data)
 	return 0;
 }
 
-static int hisi_thermal_get_temp(void *__data, int *temp)
+static int hisi_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct hisi_thermal_sensor *sensor = __data;
+	struct hisi_thermal_sensor *sensor = tz->devdata;
 	struct hisi_thermal_data *data = sensor->data;
 
 	*temp = data->ops->get_temp(sensor);
@@ -447,7 +447,7 @@ static int hisi_thermal_get_temp(void *__data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops hisi_of_thermal_ops = {
+static const struct thermal_zone_device_ops hisi_of_thermal_ops = {
 	.get_temp = hisi_thermal_get_temp,
 };
 
@@ -459,7 +459,7 @@ static irqreturn_t hisi_thermal_alarm_irq_thread(int irq, void *dev)
 
 	data->ops->irq_handler(sensor);
 
-	hisi_thermal_get_temp(sensor, &temp);
+	temp = data->ops->get_temp(sensor);
 
 	if (temp >= sensor->thres_temp) {
 		dev_crit(&data->pdev->dev,
@@ -484,9 +484,9 @@ static int hisi_thermal_register_sensor(struct platform_device *pdev,
 	int ret, i;
 	const struct thermal_trip *trip;
 
-	sensor->tzd = devm_thermal_zone_of_sensor_register(&pdev->dev,
-							   sensor->id, sensor,
-							   &hisi_of_thermal_ops);
+	sensor->tzd = devm_thermal_of_zone_register(&pdev->dev,
+						    sensor->id, sensor,
+						    &hisi_of_thermal_ops);
 	if (IS_ERR(sensor->tzd)) {
 		ret = PTR_ERR(sensor->tzd);
 		sensor->tzd = NULL;
diff --git a/drivers/thermal/imx8mm_thermal.c b/drivers/thermal/imx8mm_thermal.c
index af666bd9e8d4..e2c2673025a7 100644
--- a/drivers/thermal/imx8mm_thermal.c
+++ b/drivers/thermal/imx8mm_thermal.c
@@ -96,15 +96,15 @@ static int imx8mp_tmu_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static int tmu_get_temp(void *data, int *temp)
+static int tmu_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct tmu_sensor *sensor = data;
+	struct tmu_sensor *sensor = tz->devdata;
 	struct imx8mm_tmu *tmu = sensor->priv;
 
-	return tmu->socdata->get_temp(data, temp);
+	return tmu->socdata->get_temp(sensor, temp);
 }
 
-static struct thermal_zone_of_device_ops tmu_tz_ops = {
+static const struct thermal_zone_device_ops tmu_tz_ops = {
 	.get_temp = tmu_get_temp,
 };
 
@@ -165,9 +165,9 @@ static int imx8mm_tmu_probe(struct platform_device *pdev)
 	for (i = 0; i < data->num_sensors; i++) {
 		tmu->sensors[i].priv = tmu;
 		tmu->sensors[i].tzd =
-			devm_thermal_zone_of_sensor_register(&pdev->dev, i,
-							     &tmu->sensors[i],
-							     &tmu_tz_ops);
+			devm_thermal_of_zone_register(&pdev->dev, i,
+						      &tmu->sensors[i],
+						      &tmu_tz_ops);
 		if (IS_ERR(tmu->sensors[i].tzd)) {
 			ret = PTR_ERR(tmu->sensors[i].tzd);
 			dev_err(&pdev->dev,
diff --git a/drivers/thermal/imx_sc_thermal.c b/drivers/thermal/imx_sc_thermal.c
index 331a241eb0ef..10bfa6507eb4 100644
--- a/drivers/thermal/imx_sc_thermal.c
+++ b/drivers/thermal/imx_sc_thermal.c
@@ -43,11 +43,11 @@ struct imx_sc_msg_misc_get_temp {
 	} data;
 } __packed __aligned(4);
 
-static int imx_sc_thermal_get_temp(void *data, int *temp)
+static int imx_sc_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
 	struct imx_sc_msg_misc_get_temp msg;
 	struct imx_sc_rpc_msg *hdr = &msg.hdr;
-	struct imx_sc_sensor *sensor = data;
+	struct imx_sc_sensor *sensor = tz->devdata;
 	int ret;
 
 	msg.data.req.resource_id = sensor->resource_id;
@@ -70,7 +70,7 @@ static int imx_sc_thermal_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops imx_sc_thermal_ops = {
+static const struct thermal_zone_device_ops imx_sc_thermal_ops = {
 	.get_temp = imx_sc_thermal_get_temp,
 };
 
@@ -109,10 +109,10 @@ static int imx_sc_thermal_probe(struct platform_device *pdev)
 			break;
 		}
 
-		sensor->tzd = devm_thermal_zone_of_sensor_register(&pdev->dev,
-								   sensor->resource_id,
-								   sensor,
-								   &imx_sc_thermal_ops);
+		sensor->tzd = devm_thermal_of_zone_register(&pdev->dev,
+							    sensor->resource_id,
+							    sensor,
+							    &imx_sc_thermal_ops);
 		if (IS_ERR(sensor->tzd)) {
 			dev_err(&pdev->dev, "failed to register thermal zone\n");
 			ret = PTR_ERR(sensor->tzd);
diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
index 80d4e0676083..db8a6f63657d 100644
--- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
+++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
@@ -527,7 +527,7 @@ static void int3400_setup_gddv(struct int3400_thermal_priv *priv)
 	priv->data_vault = kmemdup(obj->package.elements[0].buffer.pointer,
 				   obj->package.elements[0].buffer.length,
 				   GFP_KERNEL);
-	if (!priv->data_vault)
+	if (ZERO_OR_NULL_PTR(priv->data_vault))
 		goto out_free;
 
 	bin_attr_data_vault.private = priv->data_vault;
@@ -597,7 +597,7 @@ static int int3400_thermal_probe(struct platform_device *pdev)
 			goto free_imok;
 	}
 
-	if (priv->data_vault) {
+	if (!ZERO_OR_NULL_PTR(priv->data_vault)) {
 		result = sysfs_create_group(&pdev->dev.kobj,
 					    &data_attribute_group);
 		if (result)
@@ -614,7 +614,7 @@ static int int3400_thermal_probe(struct platform_device *pdev)
 
 free_sysfs:
 	cleanup_odvp(priv);
-	if (priv->data_vault) {
+	if (!ZERO_OR_NULL_PTR(priv->data_vault)) {
 		sysfs_remove_group(&pdev->dev.kobj, &data_attribute_group);
 		kfree(priv->data_vault);
 	}
@@ -647,7 +647,7 @@ static int int3400_thermal_remove(struct platform_device *pdev)
 	if (!priv->rel_misc_dev_res)
 		acpi_thermal_rel_misc_device_remove(priv->adev->handle);
 
-	if (priv->data_vault)
+	if (!ZERO_OR_NULL_PTR(priv->data_vault))
 		sysfs_remove_group(&pdev->dev.kobj, &data_attribute_group);
 	sysfs_remove_group(&pdev->dev.kobj, &uuid_attribute_group);
 	sysfs_remove_group(&pdev->dev.kobj, &imok_attribute_group);
diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c
index c2dc4c158b9d..bf1b1cdfade4 100644
--- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c
+++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c
@@ -373,18 +373,7 @@ static struct pci_driver proc_thermal_pci_driver = {
 	.driver.pm	= &proc_thermal_pci_pm,
 };
 
-static int __init proc_thermal_init(void)
-{
-	return pci_register_driver(&proc_thermal_pci_driver);
-}
-
-static void __exit proc_thermal_exit(void)
-{
-	pci_unregister_driver(&proc_thermal_pci_driver);
-}
-
-module_init(proc_thermal_init);
-module_exit(proc_thermal_exit);
+module_pci_driver(proc_thermal_pci_driver);
 
 MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
 MODULE_DESCRIPTION("Processor Thermal Reporting Device Driver");
diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci_legacy.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci_legacy.c
index 4571a1a53b84..09e032f822f3 100644
--- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci_legacy.c
+++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci_legacy.c
@@ -151,18 +151,7 @@ static struct pci_driver proc_thermal_pci_driver = {
 	.driver.pm	= &proc_thermal_pci_pm,
 };
 
-static int __init proc_thermal_init(void)
-{
-	return pci_register_driver(&proc_thermal_pci_driver);
-}
-
-static void __exit proc_thermal_exit(void)
-{
-	pci_unregister_driver(&proc_thermal_pci_driver);
-}
-
-module_init(proc_thermal_init);
-module_exit(proc_thermal_exit);
+module_pci_driver(proc_thermal_pci_driver);
 
 MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
 MODULE_DESCRIPTION("Processor Thermal Reporting Device Driver");
diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c
index c841ab37e7c6..2a5570b9799a 100644
--- a/drivers/thermal/intel/intel_powerclamp.c
+++ b/drivers/thermal/intel/intel_powerclamp.c
@@ -62,8 +62,7 @@ static struct dentry *debug_dir;
 static unsigned int set_target_ratio;
 static unsigned int current_ratio;
 static bool should_skip;
-static bool reduce_irq;
-static atomic_t idle_wakeup_counter;
+
 static unsigned int control_cpu; /* The cpu assigned to collect stat and update
 				  * control parameters. default to BSP but BSP
 				  * can be offlined.
@@ -285,9 +284,6 @@ static unsigned int get_compensation(int ratio)
 			cal_data[ratio + 1].steady_comp) / 3;
 	}
 
-	/* REVISIT: simple penalty of double idle injection */
-	if (reduce_irq)
-		comp = ratio;
 	/* do not exceed limit */
 	if (comp + ratio >= MAX_TARGET_RATIO)
 		comp = MAX_TARGET_RATIO - ratio - 1;
@@ -301,13 +297,9 @@ static void adjust_compensation(int target_ratio, unsigned int win)
 	struct powerclamp_calibration_data *d = &cal_data[target_ratio];
 
 	/*
-	 * adjust compensations if confidence level has not been reached or
-	 * there are too many wakeups during the last idle injection period, we
-	 * cannot trust the data for compensation.
+	 * adjust compensations if confidence level has not been reached.
 	 */
-	if (d->confidence >= CONFIDENCE_OK ||
-		atomic_read(&idle_wakeup_counter) >
-		win * num_online_cpus())
+	if (d->confidence >= CONFIDENCE_OK)
 		return;
 
 	delta = set_target_ratio - current_ratio;
@@ -347,14 +339,7 @@ static bool powerclamp_adjust_controls(unsigned int target_ratio,
 	tsc_last = tsc_now;
 
 	adjust_compensation(target_ratio, win);
-	/*
-	 * too many external interrupts, set flag such
-	 * that we can take measure later.
-	 */
-	reduce_irq = atomic_read(&idle_wakeup_counter) >=
-		2 * win * num_online_cpus();
 
-	atomic_set(&idle_wakeup_counter, 0);
 	/* if we are above target+guard, skip */
 	return set_target_ratio + guard <= current_ratio;
 }
@@ -532,8 +517,10 @@ static int start_power_clamp(void)
 
 	/* prefer BSP */
 	control_cpu = 0;
-	if (!cpu_online(control_cpu))
-		control_cpu = smp_processor_id();
+	if (!cpu_online(control_cpu)) {
+		control_cpu = get_cpu();
+		put_cpu();
+	}
 
 	clamping = true;
 	schedule_delayed_work(&poll_pkg_cstate_work, 0);
diff --git a/drivers/thermal/k3_bandgap.c b/drivers/thermal/k3_bandgap.c
index 5d0b3ffc6f46..22c9bcb899c3 100644
--- a/drivers/thermal/k3_bandgap.c
+++ b/drivers/thermal/k3_bandgap.c
@@ -139,9 +139,9 @@ static int k3_bgp_read_temp(struct k3_thermal_data *devdata,
 	return 0;
 }
 
-static int k3_thermal_get_temp(void *devdata, int *temp)
+static int k3_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct k3_thermal_data *data = devdata;
+	struct k3_thermal_data *data = tz->devdata;
 	int ret = 0;
 
 	ret = k3_bgp_read_temp(data, temp);
@@ -151,7 +151,7 @@ static int k3_thermal_get_temp(void *devdata, int *temp)
 	return ret;
 }
 
-static const struct thermal_zone_of_device_ops k3_of_thermal_ops = {
+static const struct thermal_zone_device_ops k3_of_thermal_ops = {
 	.get_temp = k3_thermal_get_temp,
 };
 
@@ -213,9 +213,9 @@ static int k3_bandgap_probe(struct platform_device *pdev)
 		writel(val, data[id].bgp->base + data[id].ctrl_offset);
 
 		data[id].tzd =
-		devm_thermal_zone_of_sensor_register(dev, id,
-						     &data[id],
-						     &k3_of_thermal_ops);
+		devm_thermal_of_zone_register(dev, id,
+					      &data[id],
+					      &k3_of_thermal_ops);
 		if (IS_ERR(data[id].tzd)) {
 			dev_err(dev, "thermal zone device is NULL\n");
 			ret = PTR_ERR(data[id].tzd);
diff --git a/drivers/thermal/k3_j72xx_bandgap.c b/drivers/thermal/k3_j72xx_bandgap.c
index 115a44eb4fbf..16b6bcf1bf4f 100644
--- a/drivers/thermal/k3_j72xx_bandgap.c
+++ b/drivers/thermal/k3_j72xx_bandgap.c
@@ -247,9 +247,9 @@ static inline int k3_bgp_read_temp(struct k3_thermal_data *devdata,
 }
 
 /* Get temperature callback function for thermal zone */
-static int k3_thermal_get_temp(void *devdata, int *temp)
+static int k3_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct k3_thermal_data *data = devdata;
+	struct k3_thermal_data *data = tz->devdata;
 	int ret = 0;
 
 	ret = k3_bgp_read_temp(data, temp);
@@ -259,7 +259,7 @@ static int k3_thermal_get_temp(void *devdata, int *temp)
 	return ret;
 }
 
-static const struct thermal_zone_of_device_ops k3_of_thermal_ops = {
+static const struct thermal_zone_device_ops k3_of_thermal_ops = {
 	.get_temp = k3_thermal_get_temp,
 };
 
@@ -474,10 +474,8 @@ static int k3_j72xx_bandgap_probe(struct platform_device *pdev)
 		writel(val, data[id].bgp->cfg2_base + data[id].ctrl_offset);
 
 		bgp->ts_data[id] = &data[id];
-		ti_thermal =
-		devm_thermal_zone_of_sensor_register(bgp->dev, id,
-						     &data[id],
-						     &k3_of_thermal_ops);
+		ti_thermal = devm_thermal_of_zone_register(bgp->dev, id, &data[id],
+							   &k3_of_thermal_ops);
 		if (IS_ERR(ti_thermal)) {
 			dev_err(bgp->dev, "thermal zone device is NULL\n");
 			ret = PTR_ERR(ti_thermal);
diff --git a/drivers/thermal/max77620_thermal.c b/drivers/thermal/max77620_thermal.c
index 82d06c7411eb..6451a55eb582 100644
--- a/drivers/thermal/max77620_thermal.c
+++ b/drivers/thermal/max77620_thermal.c
@@ -44,9 +44,9 @@ struct max77620_therm_info {
  * Return 0 on success otherwise error number to show reason of failure.
  */
 
-static int max77620_thermal_read_temp(void *data, int *temp)
+static int max77620_thermal_read_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct max77620_therm_info *mtherm = data;
+	struct max77620_therm_info *mtherm = tz->devdata;
 	unsigned int val;
 	int ret;
 
@@ -66,7 +66,7 @@ static int max77620_thermal_read_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops max77620_thermal_ops = {
+static const struct thermal_zone_device_ops max77620_thermal_ops = {
 	.get_temp = max77620_thermal_read_temp,
 };
 
@@ -114,7 +114,7 @@ static int max77620_thermal_probe(struct platform_device *pdev)
 	 */
 	device_set_of_node_from_dev(&pdev->dev, pdev->dev.parent);
 
-	mtherm->tz_device = devm_thermal_zone_of_sensor_register(&pdev->dev, 0,
+	mtherm->tz_device = devm_thermal_of_zone_register(&pdev->dev, 0,
 				mtherm, &max77620_thermal_ops);
 	if (IS_ERR(mtherm->tz_device)) {
 		ret = PTR_ERR(mtherm->tz_device);
diff --git a/drivers/thermal/mtk_thermal.c b/drivers/thermal/mtk_thermal.c
index ede94eadddda..8440692e3890 100644
--- a/drivers/thermal/mtk_thermal.c
+++ b/drivers/thermal/mtk_thermal.c
@@ -679,9 +679,9 @@ static int mtk_thermal_bank_temperature(struct mtk_thermal_bank *bank)
 	return max;
 }
 
-static int mtk_read_temp(void *data, int *temperature)
+static int mtk_read_temp(struct thermal_zone_device *tz, int *temperature)
 {
-	struct mtk_thermal *mt = data;
+	struct mtk_thermal *mt = tz->devdata;
 	int i;
 	int tempmax = INT_MIN;
 
@@ -700,7 +700,7 @@ static int mtk_read_temp(void *data, int *temperature)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops mtk_thermal_ops = {
+static const struct thermal_zone_device_ops mtk_thermal_ops = {
 	.get_temp = mtk_read_temp,
 };
 
@@ -1082,8 +1082,8 @@ static int mtk_thermal_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, mt);
 
-	tzdev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, mt,
-						     &mtk_thermal_ops);
+	tzdev = devm_thermal_of_zone_register(&pdev->dev, 0, mt,
+					      &mtk_thermal_ops);
 	if (IS_ERR(tzdev)) {
 		ret = PTR_ERR(tzdev);
 		goto err_disable_clk_peri_therm;
diff --git a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c
index 073943cbcc2b..af68adf720cc 100644
--- a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c
+++ b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c
@@ -357,9 +357,9 @@ static irqreturn_t adc_tm5_gen2_isr(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int adc_tm5_get_temp(void *data, int *temp)
+static int adc_tm5_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct adc_tm5_channel *channel = data;
+	struct adc_tm5_channel *channel = tz->devdata;
 	int ret;
 
 	if (!channel || !channel->iio)
@@ -639,9 +639,9 @@ config_fail:
 	return ret;
 }
 
-static int adc_tm5_set_trips(void *data, int low, int high)
+static int adc_tm5_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	struct adc_tm5_channel *channel = data;
+	struct adc_tm5_channel *channel = tz->devdata;
 	struct adc_tm5_chip *chip;
 	int ret;
 
@@ -660,7 +660,7 @@ static int adc_tm5_set_trips(void *data, int low, int high)
 	return ret;
 }
 
-static struct thermal_zone_of_device_ops adc_tm5_thermal_ops = {
+static const struct thermal_zone_device_ops adc_tm5_thermal_ops = {
 	.get_temp = adc_tm5_get_temp,
 	.set_trips = adc_tm5_set_trips,
 };
@@ -672,11 +672,10 @@ static int adc_tm5_register_tzd(struct adc_tm5_chip *adc_tm)
 
 	for (i = 0; i < adc_tm->nchannels; i++) {
 		adc_tm->channels[i].chip = adc_tm;
-
-		tzd = devm_thermal_zone_of_sensor_register(adc_tm->dev,
-							   adc_tm->channels[i].channel,
-							   &adc_tm->channels[i],
-							   &adc_tm5_thermal_ops);
+		tzd = devm_thermal_of_zone_register(adc_tm->dev,
+						    adc_tm->channels[i].channel,
+						    &adc_tm->channels[i],
+						    &adc_tm5_thermal_ops);
 		if (IS_ERR(tzd)) {
 			if (PTR_ERR(tzd) == -ENODEV) {
 				dev_warn(adc_tm->dev, "thermal sensor on channel %d is not used\n",
@@ -1026,10 +1025,8 @@ static int adc_tm5_probe(struct platform_device *pdev)
 	adc_tm->base = reg;
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "get_irq failed: %d\n", irq);
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = adc_tm5_get_dt_data(adc_tm, node);
 	if (ret) {
diff --git a/drivers/thermal/qcom/qcom-spmi-temp-alarm.c b/drivers/thermal/qcom/qcom-spmi-temp-alarm.c
index 770f82cc9bca..be785ab37e53 100644
--- a/drivers/thermal/qcom/qcom-spmi-temp-alarm.c
+++ b/drivers/thermal/qcom/qcom-spmi-temp-alarm.c
@@ -186,9 +186,9 @@ static int qpnp_tm_update_temp_no_adc(struct qpnp_tm_chip *chip)
 	return 0;
 }
 
-static int qpnp_tm_get_temp(void *data, int *temp)
+static int qpnp_tm_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct qpnp_tm_chip *chip = data;
+	struct qpnp_tm_chip *chip = tz->devdata;
 	int ret, mili_celsius;
 
 	if (!temp)
@@ -263,9 +263,9 @@ skip:
 	return qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
 }
 
-static int qpnp_tm_set_trip_temp(void *data, int trip, int temp)
+static int qpnp_tm_set_trip_temp(struct thermal_zone_device *tz, int trip, int temp)
 {
-	struct qpnp_tm_chip *chip = data;
+	struct qpnp_tm_chip *chip = tz->devdata;
 	const struct thermal_trip *trip_points;
 	int ret;
 
@@ -283,7 +283,7 @@ static int qpnp_tm_set_trip_temp(void *data, int trip, int temp)
 	return ret;
 }
 
-static const struct thermal_zone_of_device_ops qpnp_tm_sensor_ops = {
+static const struct thermal_zone_device_ops qpnp_tm_sensor_ops = {
 	.get_temp = qpnp_tm_get_temp,
 	.set_trip_temp = qpnp_tm_set_trip_temp,
 };
@@ -446,7 +446,7 @@ static int qpnp_tm_probe(struct platform_device *pdev)
 	 * read the trip points. get_temp() returns the default temperature
 	 * before the hardware initialization is completed.
 	 */
-	chip->tz_dev = devm_thermal_zone_of_sensor_register(
+	chip->tz_dev = devm_thermal_of_zone_register(
 		&pdev->dev, 0, chip, &qpnp_tm_sensor_ops);
 	if (IS_ERR(chip->tz_dev)) {
 		dev_err(&pdev->dev, "failed to register sensor\n");
diff --git a/drivers/thermal/qcom/tsens.c b/drivers/thermal/qcom/tsens.c
index e49f58e83513..b1b10005fb28 100644
--- a/drivers/thermal/qcom/tsens.c
+++ b/drivers/thermal/qcom/tsens.c
@@ -532,9 +532,9 @@ static irqreturn_t tsens_irq_thread(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int tsens_set_trips(void *_sensor, int low, int high)
+static int tsens_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	struct tsens_sensor *s = _sensor;
+	struct tsens_sensor *s = tz->devdata;
 	struct tsens_priv *priv = s->priv;
 	struct device *dev = priv->dev;
 	struct tsens_irq_data d;
@@ -925,9 +925,9 @@ err_put_device:
 	return ret;
 }
 
-static int tsens_get_temp(void *data, int *temp)
+static int tsens_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct tsens_sensor *s = data;
+	struct tsens_sensor *s = tz->devdata;
 	struct tsens_priv *priv = s->priv;
 
 	return priv->ops->get_temp(s, temp);
@@ -991,7 +991,7 @@ static const struct of_device_id tsens_table[] = {
 };
 MODULE_DEVICE_TABLE(of, tsens_table);
 
-static const struct thermal_zone_of_device_ops tsens_of_ops = {
+static const struct thermal_zone_device_ops tsens_of_ops = {
 	.get_temp = tsens_get_temp,
 	.set_trips = tsens_set_trips,
 };
@@ -1044,9 +1044,9 @@ static int tsens_register(struct tsens_priv *priv)
 
 	for (i = 0;  i < priv->num_sensors; i++) {
 		priv->sensor[i].priv = priv;
-		tzd = devm_thermal_zone_of_sensor_register(priv->dev, priv->sensor[i].hw_id,
-							   &priv->sensor[i],
-							   &tsens_of_ops);
+		tzd = devm_thermal_of_zone_register(priv->dev, priv->sensor[i].hw_id,
+						    &priv->sensor[i],
+						    &tsens_of_ops);
 		if (IS_ERR(tzd))
 			continue;
 		priv->sensor[i].tzd = tzd;
diff --git a/drivers/thermal/qoriq_thermal.c b/drivers/thermal/qoriq_thermal.c
index 73049f9bea25..d111e218f362 100644
--- a/drivers/thermal/qoriq_thermal.c
+++ b/drivers/thermal/qoriq_thermal.c
@@ -82,9 +82,9 @@ static struct qoriq_tmu_data *qoriq_sensor_to_data(struct qoriq_sensor *s)
 	return container_of(s, struct qoriq_tmu_data, sensor[s->id]);
 }
 
-static int tmu_get_temp(void *p, int *temp)
+static int tmu_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct qoriq_sensor *qsensor = p;
+	struct qoriq_sensor *qsensor = tz->devdata;
 	struct qoriq_tmu_data *qdata = qoriq_sensor_to_data(qsensor);
 	u32 val;
 	/*
@@ -122,7 +122,7 @@ static int tmu_get_temp(void *p, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops tmu_tz_ops = {
+static const struct thermal_zone_device_ops tmu_tz_ops = {
 	.get_temp = tmu_get_temp,
 };
 
@@ -146,9 +146,9 @@ static int qoriq_tmu_register_tmu_zone(struct device *dev,
 
 		sensor->id = id;
 
-		tzd = devm_thermal_zone_of_sensor_register(dev, id,
-							   sensor,
-							   &tmu_tz_ops);
+		tzd = devm_thermal_of_zone_register(dev, id,
+						    sensor,
+						    &tmu_tz_ops);
 		ret = PTR_ERR_OR_ZERO(tzd);
 		if (ret) {
 			if (ret == -ENODEV)
diff --git a/drivers/thermal/rcar_gen3_thermal.c b/drivers/thermal/rcar_gen3_thermal.c
index cda7c52f2319..4c1c6f89aa2f 100644
--- a/drivers/thermal/rcar_gen3_thermal.c
+++ b/drivers/thermal/rcar_gen3_thermal.c
@@ -164,9 +164,9 @@ static int rcar_gen3_thermal_round(int temp)
 	return result * RCAR3_THERMAL_GRAN;
 }
 
-static int rcar_gen3_thermal_get_temp(void *devdata, int *temp)
+static int rcar_gen3_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct rcar_gen3_thermal_tsc *tsc = devdata;
+	struct rcar_gen3_thermal_tsc *tsc = tz->devdata;
 	int mcelsius, val;
 	int reg;
 
@@ -203,9 +203,9 @@ static int rcar_gen3_thermal_mcelsius_to_temp(struct rcar_gen3_thermal_tsc *tsc,
 	return INT_FIXPT(val);
 }
 
-static int rcar_gen3_thermal_set_trips(void *devdata, int low, int high)
+static int rcar_gen3_thermal_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	struct rcar_gen3_thermal_tsc *tsc = devdata;
+	struct rcar_gen3_thermal_tsc *tsc = tz->devdata;
 	u32 irqmsk = 0;
 
 	if (low != -INT_MAX) {
@@ -225,7 +225,7 @@ static int rcar_gen3_thermal_set_trips(void *devdata, int low, int high)
 	return 0;
 }
 
-static struct thermal_zone_of_device_ops rcar_gen3_tz_of_ops = {
+static struct thermal_zone_device_ops rcar_gen3_tz_of_ops = {
 	.get_temp	= rcar_gen3_thermal_get_temp,
 	.set_trips	= rcar_gen3_thermal_set_trips,
 };
@@ -508,8 +508,8 @@ static int rcar_gen3_thermal_probe(struct platform_device *pdev)
 	for (i = 0; i < priv->num_tscs; i++) {
 		struct rcar_gen3_thermal_tsc *tsc = priv->tscs[i];
 
-		zone = devm_thermal_zone_of_sensor_register(dev, i, tsc,
-							    &rcar_gen3_tz_of_ops);
+		zone = devm_thermal_of_zone_register(dev, i, tsc,
+						     &rcar_gen3_tz_of_ops);
 		if (IS_ERR(zone)) {
 			dev_err(dev, "Sensor %u: Can't register thermal zone\n", i);
 			ret = PTR_ERR(zone);
@@ -560,7 +560,7 @@ static int __maybe_unused rcar_gen3_thermal_resume(struct device *dev)
 
 		priv->thermal_init(tsc);
 		if (zone->ops->set_trips)
-			rcar_gen3_thermal_set_trips(tsc, zone->prev_low_trip,
+			rcar_gen3_thermal_set_trips(zone, zone->prev_low_trip,
 						    zone->prev_high_trip);
 	}
 
diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c
index 1d729ed4d685..4df42d70d867 100644
--- a/drivers/thermal/rcar_thermal.c
+++ b/drivers/thermal/rcar_thermal.c
@@ -271,13 +271,6 @@ static int rcar_thermal_get_current_temp(struct rcar_thermal_priv *priv,
 	return 0;
 }
 
-static int rcar_thermal_of_get_temp(void *data, int *temp)
-{
-	struct rcar_thermal_priv *priv = data;
-
-	return rcar_thermal_get_current_temp(priv, temp);
-}
-
 static int rcar_thermal_get_temp(struct thermal_zone_device *zone, int *temp)
 {
 	struct rcar_thermal_priv *priv = rcar_zone_to_priv(zone);
@@ -323,8 +316,8 @@ static int rcar_thermal_get_trip_temp(struct thermal_zone_device *zone,
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops rcar_thermal_zone_of_ops = {
-	.get_temp	= rcar_thermal_of_get_temp,
+static struct thermal_zone_device_ops rcar_thermal_zone_of_ops = {
+	.get_temp	= rcar_thermal_get_temp,
 };
 
 static struct thermal_zone_device_ops rcar_thermal_zone_ops = {
@@ -534,7 +527,7 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 			goto error_unregister;
 
 		if (chip->use_of_thermal) {
-			priv->zone = devm_thermal_zone_of_sensor_register(
+			priv->zone = devm_thermal_of_zone_register(
 						dev, i, priv,
 						&rcar_thermal_zone_of_ops);
 		} else {
diff --git a/drivers/thermal/rockchip_thermal.c b/drivers/thermal/rockchip_thermal.c
index dc3a9c276a09..819e059cde71 100644
--- a/drivers/thermal/rockchip_thermal.c
+++ b/drivers/thermal/rockchip_thermal.c
@@ -1211,9 +1211,9 @@ static irqreturn_t rockchip_thermal_alarm_irq_thread(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
-static int rockchip_thermal_set_trips(void *_sensor, int low, int high)
+static int rockchip_thermal_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	struct rockchip_thermal_sensor *sensor = _sensor;
+	struct rockchip_thermal_sensor *sensor = tz->devdata;
 	struct rockchip_thermal_data *thermal = sensor->thermal;
 	const struct rockchip_tsadc_chip *tsadc = thermal->chip;
 
@@ -1224,9 +1224,9 @@ static int rockchip_thermal_set_trips(void *_sensor, int low, int high)
 				     sensor->id, thermal->regs, high);
 }
 
-static int rockchip_thermal_get_temp(void *_sensor, int *out_temp)
+static int rockchip_thermal_get_temp(struct thermal_zone_device *tz, int *out_temp)
 {
-	struct rockchip_thermal_sensor *sensor = _sensor;
+	struct rockchip_thermal_sensor *sensor = tz->devdata;
 	struct rockchip_thermal_data *thermal = sensor->thermal;
 	const struct rockchip_tsadc_chip *tsadc = sensor->thermal->chip;
 	int retval;
@@ -1239,7 +1239,7 @@ static int rockchip_thermal_get_temp(void *_sensor, int *out_temp)
 	return retval;
 }
 
-static const struct thermal_zone_of_device_ops rockchip_of_thermal_ops = {
+static const struct thermal_zone_device_ops rockchip_of_thermal_ops = {
 	.get_temp = rockchip_thermal_get_temp,
 	.set_trips = rockchip_thermal_set_trips,
 };
@@ -1326,8 +1326,8 @@ rockchip_thermal_register_sensor(struct platform_device *pdev,
 
 	sensor->thermal = thermal;
 	sensor->id = id;
-	sensor->tzd = devm_thermal_zone_of_sensor_register(&pdev->dev, id,
-					sensor, &rockchip_of_thermal_ops);
+	sensor->tzd = devm_thermal_of_zone_register(&pdev->dev, id, sensor,
+						    &rockchip_of_thermal_ops);
 	if (IS_ERR(sensor->tzd)) {
 		error = PTR_ERR(sensor->tzd);
 		dev_err(&pdev->dev, "failed to register sensor %d: %d\n",
diff --git a/drivers/thermal/rzg2l_thermal.c b/drivers/thermal/rzg2l_thermal.c
index 51ae80eda6af..2e0649f38506 100644
--- a/drivers/thermal/rzg2l_thermal.c
+++ b/drivers/thermal/rzg2l_thermal.c
@@ -73,9 +73,9 @@ static inline void rzg2l_thermal_write(struct rzg2l_thermal_priv *priv, u32 reg,
 	iowrite32(data, priv->base + reg);
 }
 
-static int rzg2l_thermal_get_temp(void *devdata, int *temp)
+static int rzg2l_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct rzg2l_thermal_priv *priv = devdata;
+	struct rzg2l_thermal_priv *priv = tz->devdata;
 	u32 result = 0, dsensor, ts_code_ave;
 	int val, i;
 
@@ -114,7 +114,7 @@ static int rzg2l_thermal_get_temp(void *devdata, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops rzg2l_tz_of_ops = {
+static const struct thermal_zone_device_ops rzg2l_tz_of_ops = {
 	.get_temp = rzg2l_thermal_get_temp,
 };
 
@@ -207,8 +207,8 @@ static int rzg2l_thermal_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	zone = devm_thermal_zone_of_sensor_register(dev, 0, priv,
-						    &rzg2l_tz_of_ops);
+	zone = devm_thermal_of_zone_register(dev, 0, priv,
+					     &rzg2l_tz_of_ops);
 	if (IS_ERR(zone)) {
 		dev_err(dev, "Can't register thermal zone");
 		ret = PTR_ERR(zone);
diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c
index f4ab4c5b4b62..51874d0a284c 100644
--- a/drivers/thermal/samsung/exynos_tmu.c
+++ b/drivers/thermal/samsung/exynos_tmu.c
@@ -650,9 +650,9 @@ static void exynos7_tmu_control(struct platform_device *pdev, bool on)
 	writel(con, data->base + EXYNOS_TMU_REG_CONTROL);
 }
 
-static int exynos_get_temp(void *p, int *temp)
+static int exynos_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct exynos_tmu_data *data = p;
+	struct exynos_tmu_data *data = tz->devdata;
 	int value, ret = 0;
 
 	if (!data || !data->tmu_read)
@@ -728,9 +728,9 @@ static void exynos4412_tmu_set_emulation(struct exynos_tmu_data *data,
 	writel(val, data->base + emul_con);
 }
 
-static int exynos_tmu_set_emulation(void *drv_data, int temp)
+static int exynos_tmu_set_emulation(struct thermal_zone_device *tz, int temp)
 {
-	struct exynos_tmu_data *data = drv_data;
+	struct exynos_tmu_data *data = tz->devdata;
 	int ret = -EINVAL;
 
 	if (data->soc == SOC_ARCH_EXYNOS4210)
@@ -750,7 +750,7 @@ out:
 }
 #else
 #define exynos4412_tmu_set_emulation NULL
-static int exynos_tmu_set_emulation(void *drv_data, int temp)
+static int exynos_tmu_set_emulation(struct thermal_zone_device *tz, int temp)
 	{ return -EINVAL; }
 #endif /* CONFIG_THERMAL_EMULATION */
 
@@ -997,7 +997,7 @@ static int exynos_map_dt_data(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops exynos_sensor_ops = {
+static const struct thermal_zone_device_ops exynos_sensor_ops = {
 	.get_temp = exynos_get_temp,
 	.set_emul_temp = exynos_tmu_set_emulation,
 };
@@ -1091,8 +1091,8 @@ static int exynos_tmu_probe(struct platform_device *pdev)
 	 * data->tzd must be registered before calling exynos_tmu_initialize(),
 	 * requesting irq and calling exynos_tmu_control().
 	 */
-	data->tzd = thermal_zone_of_sensor_register(&pdev->dev, 0, data,
-						    &exynos_sensor_ops);
+	data->tzd = devm_thermal_of_zone_register(&pdev->dev, 0, data,
+						  &exynos_sensor_ops);
 	if (IS_ERR(data->tzd)) {
 		ret = PTR_ERR(data->tzd);
 		if (ret != -EPROBE_DEFER)
@@ -1104,21 +1104,19 @@ static int exynos_tmu_probe(struct platform_device *pdev)
 	ret = exynos_tmu_initialize(pdev);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to initialize TMU\n");
-		goto err_thermal;
+		goto err_sclk;
 	}
 
 	ret = devm_request_irq(&pdev->dev, data->irq, exynos_tmu_irq,
 		IRQF_TRIGGER_RISING | IRQF_SHARED, dev_name(&pdev->dev), data);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to request irq: %d\n", data->irq);
-		goto err_thermal;
+		goto err_sclk;
 	}
 
 	exynos_tmu_control(pdev, true);
 	return 0;
 
-err_thermal:
-	thermal_zone_of_sensor_unregister(&pdev->dev, data->tzd);
 err_sclk:
 	clk_disable_unprepare(data->sclk);
 err_clk:
@@ -1136,9 +1134,7 @@ err_sensor:
 static int exynos_tmu_remove(struct platform_device *pdev)
 {
 	struct exynos_tmu_data *data = platform_get_drvdata(pdev);
-	struct thermal_zone_device *tzd = data->tzd;
 
-	thermal_zone_of_sensor_unregister(&pdev->dev, tzd);
 	exynos_tmu_control(pdev, false);
 
 	clk_disable_unprepare(data->sclk);
diff --git a/drivers/thermal/sprd_thermal.c b/drivers/thermal/sprd_thermal.c
index fff80fc18002..ac884514f116 100644
--- a/drivers/thermal/sprd_thermal.c
+++ b/drivers/thermal/sprd_thermal.c
@@ -204,9 +204,9 @@ static int sprd_thm_temp_to_rawdata(int temp, struct sprd_thermal_sensor *sen)
 	return clamp(val, val, (u32)(SPRD_THM_RAW_DATA_HIGH - 1));
 }
 
-static int sprd_thm_read_temp(void *devdata, int *temp)
+static int sprd_thm_read_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct sprd_thermal_sensor *sen = devdata;
+	struct sprd_thermal_sensor *sen = tz->devdata;
 	u32 data;
 
 	data = readl(sen->data->base + SPRD_THM_TEMP(sen->id)) &
@@ -217,7 +217,7 @@ static int sprd_thm_read_temp(void *devdata, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops sprd_thm_ops = {
+static const struct thermal_zone_device_ops sprd_thm_ops = {
 	.get_temp = sprd_thm_read_temp,
 };
 
@@ -408,10 +408,10 @@ static int sprd_thm_probe(struct platform_device *pdev)
 
 		sprd_thm_sensor_init(thm, sen);
 
-		sen->tzd = devm_thermal_zone_of_sensor_register(sen->dev,
-								sen->id,
-								sen,
-								&sprd_thm_ops);
+		sen->tzd = devm_thermal_of_zone_register(sen->dev,
+							 sen->id,
+							 sen,
+							 &sprd_thm_ops);
 		if (IS_ERR(sen->tzd)) {
 			dev_err(&pdev->dev, "register thermal zone failed %d\n",
 				sen->id);
@@ -523,8 +523,8 @@ static int sprd_thm_remove(struct platform_device *pdev)
 
 	for (i = 0; i < thm->nr_sensors; i++) {
 		sprd_thm_toggle_sensor(thm->sensor[i], false);
-		devm_thermal_zone_of_sensor_unregister(&pdev->dev,
-						       thm->sensor[i]->tzd);
+		devm_thermal_of_zone_unregister(&pdev->dev,
+						thm->sensor[i]->tzd);
 	}
 
 	clk_disable_unprepare(thm->clk);
diff --git a/drivers/thermal/st/stm_thermal.c b/drivers/thermal/st/stm_thermal.c
index 5fd3fb8912a6..78feb802a87d 100644
--- a/drivers/thermal/st/stm_thermal.c
+++ b/drivers/thermal/st/stm_thermal.c
@@ -302,9 +302,9 @@ static int stm_disable_irq(struct stm_thermal_sensor *sensor)
 	return 0;
 }
 
-static int stm_thermal_set_trips(void *data, int low, int high)
+static int stm_thermal_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	struct stm_thermal_sensor *sensor = data;
+	struct stm_thermal_sensor *sensor = tz->devdata;
 	u32 itr1, th;
 	int ret;
 
@@ -350,9 +350,9 @@ static int stm_thermal_set_trips(void *data, int low, int high)
 }
 
 /* Callback to get temperature from HW */
-static int stm_thermal_get_temp(void *data, int *temp)
+static int stm_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct stm_thermal_sensor *sensor = data;
+	struct stm_thermal_sensor *sensor = tz->devdata;
 	u32 periods;
 	int freqM, ret;
 
@@ -474,7 +474,7 @@ static int stm_thermal_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(stm_thermal_pm_ops,
 			 stm_thermal_suspend, stm_thermal_resume);
 
-static const struct thermal_zone_of_device_ops stm_tz_ops = {
+static const struct thermal_zone_device_ops stm_tz_ops = {
 	.get_temp	= stm_thermal_get_temp,
 	.set_trips	= stm_thermal_set_trips,
 };
@@ -539,9 +539,9 @@ static int stm_thermal_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	sensor->th_dev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0,
-							      sensor,
-							      &stm_tz_ops);
+	sensor->th_dev = devm_thermal_of_zone_register(&pdev->dev, 0,
+						       sensor,
+						       &stm_tz_ops);
 
 	if (IS_ERR(sensor->th_dev)) {
 		dev_err(&pdev->dev, "%s: thermal zone sensor registering KO\n",
@@ -572,7 +572,6 @@ static int stm_thermal_probe(struct platform_device *pdev)
 	return 0;
 
 err_tz:
-	thermal_zone_of_sensor_unregister(&pdev->dev, sensor->th_dev);
 	return ret;
 }
 
@@ -582,7 +581,6 @@ static int stm_thermal_remove(struct platform_device *pdev)
 
 	stm_thermal_sensor_off(sensor);
 	thermal_remove_hwmon_sysfs(sensor->th_dev);
-	thermal_zone_of_sensor_unregister(&pdev->dev, sensor->th_dev);
 
 	return 0;
 }
diff --git a/drivers/thermal/sun8i_thermal.c b/drivers/thermal/sun8i_thermal.c
index 212c87e63a66..e64d06d1328c 100644
--- a/drivers/thermal/sun8i_thermal.c
+++ b/drivers/thermal/sun8i_thermal.c
@@ -108,9 +108,9 @@ static int sun50i_h5_calc_temp(struct ths_device *tmdev,
 		return -1590 * reg / 10 + 276000;
 }
 
-static int sun8i_ths_get_temp(void *data, int *temp)
+static int sun8i_ths_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct tsensor *s = data;
+	struct tsensor *s = tz->devdata;
 	struct ths_device *tmdev = s->tmdev;
 	int val = 0;
 
@@ -135,7 +135,7 @@ static int sun8i_ths_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops ths_ops = {
+static const struct thermal_zone_device_ops ths_ops = {
 	.get_temp = sun8i_ths_get_temp,
 };
 
@@ -468,10 +468,10 @@ static int sun8i_ths_register(struct ths_device *tmdev)
 		tmdev->sensor[i].tmdev = tmdev;
 		tmdev->sensor[i].id = i;
 		tmdev->sensor[i].tzd =
-			devm_thermal_zone_of_sensor_register(tmdev->dev,
-							     i,
-							     &tmdev->sensor[i],
-							     &ths_ops);
+			devm_thermal_of_zone_register(tmdev->dev,
+						      i,
+						      &tmdev->sensor[i],
+						      &ths_ops);
 		if (IS_ERR(tmdev->sensor[i].tzd))
 			return PTR_ERR(tmdev->sensor[i].tzd);
 
diff --git a/drivers/thermal/tegra/soctherm.c b/drivers/thermal/tegra/soctherm.c
index 825eab526619..1efe470f31e9 100644
--- a/drivers/thermal/tegra/soctherm.c
+++ b/drivers/thermal/tegra/soctherm.c
@@ -421,9 +421,9 @@ static int translate_temp(u16 val)
 	return t;
 }
 
-static int tegra_thermctl_get_temp(void *data, int *out_temp)
+static int tegra_thermctl_get_temp(struct thermal_zone_device *tz, int *out_temp)
 {
-	struct tegra_thermctl_zone *zone = data;
+	struct tegra_thermctl_zone *zone = tz->devdata;
 	u32 val;
 
 	val = readl(zone->reg);
@@ -582,10 +582,9 @@ static int tsensor_group_thermtrip_get(struct tegra_soctherm *ts, int id)
 	return temp;
 }
 
-static int tegra_thermctl_set_trip_temp(void *data, int trip, int temp)
+static int tegra_thermctl_set_trip_temp(struct thermal_zone_device *tz, int trip, int temp)
 {
-	struct tegra_thermctl_zone *zone = data;
-	struct thermal_zone_device *tz = zone->tz;
+	struct tegra_thermctl_zone *zone = tz->devdata;
 	struct tegra_soctherm *ts = zone->ts;
 	const struct tegra_tsensor_group *sg = zone->sg;
 	struct device *dev = zone->dev;
@@ -657,9 +656,9 @@ static void thermal_irq_disable(struct tegra_thermctl_zone *zn)
 	mutex_unlock(&zn->ts->thermctl_lock);
 }
 
-static int tegra_thermctl_set_trips(void *data, int lo, int hi)
+static int tegra_thermctl_set_trips(struct thermal_zone_device *tz, int lo, int hi)
 {
-	struct tegra_thermctl_zone *zone = data;
+	struct tegra_thermctl_zone *zone = tz->devdata;
 	u32 r;
 
 	thermal_irq_disable(zone);
@@ -682,7 +681,7 @@ static int tegra_thermctl_set_trips(void *data, int lo, int hi)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops tegra_of_thermal_ops = {
+static const struct thermal_zone_device_ops tegra_of_thermal_ops = {
 	.get_temp = tegra_thermctl_get_temp,
 	.set_trip_temp = tegra_thermctl_set_trip_temp,
 	.set_trips = tegra_thermctl_set_trips,
@@ -2194,9 +2193,9 @@ static int tegra_soctherm_probe(struct platform_device *pdev)
 		zone->sg = soc->ttgs[i];
 		zone->ts = tegra;
 
-		z = devm_thermal_zone_of_sensor_register(&pdev->dev,
-							 soc->ttgs[i]->id, zone,
-							 &tegra_of_thermal_ops);
+		z = devm_thermal_of_zone_register(&pdev->dev,
+						  soc->ttgs[i]->id, zone,
+						  &tegra_of_thermal_ops);
 		if (IS_ERR(z)) {
 			err = PTR_ERR(z);
 			dev_err(&pdev->dev, "failed to register sensor: %d\n",
diff --git a/drivers/thermal/tegra/tegra-bpmp-thermal.c b/drivers/thermal/tegra/tegra-bpmp-thermal.c
index 5affc3d196be..eb84f0b9dc7c 100644
--- a/drivers/thermal/tegra/tegra-bpmp-thermal.c
+++ b/drivers/thermal/tegra/tegra-bpmp-thermal.c
@@ -30,9 +30,9 @@ struct tegra_bpmp_thermal {
 	struct tegra_bpmp_thermal_zone **zones;
 };
 
-static int tegra_bpmp_thermal_get_temp(void *data, int *out_temp)
+static int __tegra_bpmp_thermal_get_temp(struct tegra_bpmp_thermal_zone *zone,
+					 int *out_temp)
 {
-	struct tegra_bpmp_thermal_zone *zone = data;
 	struct mrq_thermal_host_to_bpmp_request req;
 	union mrq_thermal_bpmp_to_host_response reply;
 	struct tegra_bpmp_message msg;
@@ -60,9 +60,14 @@ static int tegra_bpmp_thermal_get_temp(void *data, int *out_temp)
 	return 0;
 }
 
-static int tegra_bpmp_thermal_set_trips(void *data, int low, int high)
+static int tegra_bpmp_thermal_get_temp(struct thermal_zone_device *tz, int *out_temp)
 {
-	struct tegra_bpmp_thermal_zone *zone = data;
+	return __tegra_bpmp_thermal_get_temp(tz->devdata, out_temp);
+}
+
+static int tegra_bpmp_thermal_set_trips(struct thermal_zone_device *tz, int low, int high)
+{
+	struct tegra_bpmp_thermal_zone *zone = tz->devdata;
 	struct mrq_thermal_host_to_bpmp_request req;
 	struct tegra_bpmp_message msg;
 	int err;
@@ -157,7 +162,7 @@ static int tegra_bpmp_thermal_get_num_zones(struct tegra_bpmp *bpmp,
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops tegra_bpmp_of_thermal_ops = {
+static const struct thermal_zone_device_ops tegra_bpmp_of_thermal_ops = {
 	.get_temp = tegra_bpmp_thermal_get_temp,
 	.set_trips = tegra_bpmp_thermal_set_trips,
 };
@@ -200,13 +205,13 @@ static int tegra_bpmp_thermal_probe(struct platform_device *pdev)
 		zone->idx = i;
 		zone->tegra = tegra;
 
-		err = tegra_bpmp_thermal_get_temp(zone, &temp);
+		err = __tegra_bpmp_thermal_get_temp(zone, &temp);
 		if (err < 0) {
 			devm_kfree(&pdev->dev, zone);
 			continue;
 		}
 
-		tzd = devm_thermal_zone_of_sensor_register(
+		tzd = devm_thermal_of_zone_register(
 			&pdev->dev, i, zone, &tegra_bpmp_of_thermal_ops);
 		if (IS_ERR(tzd)) {
 			if (PTR_ERR(tzd) == -EPROBE_DEFER)
diff --git a/drivers/thermal/tegra/tegra30-tsensor.c b/drivers/thermal/tegra/tegra30-tsensor.c
index 05886684f429..c34501287e96 100644
--- a/drivers/thermal/tegra/tegra30-tsensor.c
+++ b/drivers/thermal/tegra/tegra30-tsensor.c
@@ -159,9 +159,9 @@ static void devm_tegra_tsensor_hw_disable(void *data)
 	tegra_tsensor_hw_disable(ts);
 }
 
-static int tegra_tsensor_get_temp(void *data, int *temp)
+static int tegra_tsensor_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	const struct tegra_tsensor_channel *tsc = data;
+	const struct tegra_tsensor_channel *tsc = tz->devdata;
 	const struct tegra_tsensor *ts = tsc->ts;
 	int err, c1, c2, c3, c4, counter;
 	u32 val;
@@ -217,9 +217,9 @@ static int tegra_tsensor_temp_to_counter(const struct tegra_tsensor *ts, int tem
 	return DIV_ROUND_CLOSEST(c2 * 1000000 - ts->calib.b, ts->calib.a);
 }
 
-static int tegra_tsensor_set_trips(void *data, int low, int high)
+static int tegra_tsensor_set_trips(struct thermal_zone_device *tz, int low, int high)
 {
-	const struct tegra_tsensor_channel *tsc = data;
+	const struct tegra_tsensor_channel *tsc = tz->devdata;
 	const struct tegra_tsensor *ts = tsc->ts;
 	u32 val;
 
@@ -240,7 +240,7 @@ static int tegra_tsensor_set_trips(void *data, int low, int high)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops ops = {
+static const struct thermal_zone_device_ops ops = {
 	.get_temp = tegra_tsensor_get_temp,
 	.set_trips = tegra_tsensor_set_trips,
 };
@@ -516,7 +516,7 @@ static int tegra_tsensor_register_channel(struct tegra_tsensor *ts,
 	tsc->id = id;
 	tsc->regs = ts->regs + 0x40 * (hw_id + 1);
 
-	tsc->tzd = devm_thermal_zone_of_sensor_register(ts->dev, id, tsc, &ops);
+	tsc->tzd = devm_thermal_of_zone_register(ts->dev, id, tsc, &ops);
 	if (IS_ERR(tsc->tzd)) {
 		if (PTR_ERR(tsc->tzd) != -ENODEV)
 			return dev_err_probe(ts->dev, PTR_ERR(tsc->tzd),
diff --git a/drivers/thermal/thermal-generic-adc.c b/drivers/thermal/thermal-generic-adc.c
index 73665c3ccfe0..323e273e3298 100644
--- a/drivers/thermal/thermal-generic-adc.c
+++ b/drivers/thermal/thermal-generic-adc.c
@@ -52,9 +52,9 @@ static int gadc_thermal_adc_to_temp(struct gadc_thermal_info *gti, int val)
 	return temp;
 }
 
-static int gadc_thermal_get_temp(void *data, int *temp)
+static int gadc_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
-	struct gadc_thermal_info *gti = data;
+	struct gadc_thermal_info *gti = tz->devdata;
 	int val;
 	int ret;
 
@@ -68,7 +68,7 @@ static int gadc_thermal_get_temp(void *data, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops gadc_thermal_ops = {
+static const struct thermal_zone_device_ops gadc_thermal_ops = {
 	.get_temp = gadc_thermal_get_temp,
 };
 
@@ -143,8 +143,8 @@ static int gadc_thermal_probe(struct platform_device *pdev)
 	gti->dev = &pdev->dev;
 	platform_set_drvdata(pdev, gti);
 
-	gti->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, gti,
-							   &gadc_thermal_ops);
+	gti->tz_dev = devm_thermal_of_zone_register(&pdev->dev, 0, gti,
+						    &gadc_thermal_ops);
 	if (IS_ERR(gti->tz_dev)) {
 		ret = PTR_ERR(gti->tz_dev);
 		if (ret != -EPROBE_DEFER)
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 6a5d0ae5d7a4..7e669b60a065 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -295,27 +295,14 @@ static void thermal_zone_device_set_polling(struct thermal_zone_device *tz,
 		cancel_delayed_work(&tz->poll_queue);
 }
 
-static inline bool should_stop_polling(struct thermal_zone_device *tz)
-{
-	return !thermal_zone_device_is_enabled(tz);
-}
-
 static void monitor_thermal_zone(struct thermal_zone_device *tz)
 {
-	bool stop;
-
-	stop = should_stop_polling(tz);
-
-	mutex_lock(&tz->lock);
-
-	if (!stop && tz->passive)
+	if (tz->mode != THERMAL_DEVICE_ENABLED)
+		thermal_zone_device_set_polling(tz, 0);
+	else if (tz->passive)
 		thermal_zone_device_set_polling(tz, tz->passive_delay_jiffies);
-	else if (!stop && tz->polling_delay_jiffies)
+	else if (tz->polling_delay_jiffies)
 		thermal_zone_device_set_polling(tz, tz->polling_delay_jiffies);
-	else
-		thermal_zone_device_set_polling(tz, 0);
-
-	mutex_unlock(&tz->lock);
 }
 
 static void handle_non_critical_trips(struct thermal_zone_device *tz, int trip)
@@ -383,18 +370,13 @@ static void handle_thermal_trip(struct thermal_zone_device *tz, int trip)
 		handle_critical_trips(tz, trip, trip_temp, type);
 	else
 		handle_non_critical_trips(tz, trip);
-	/*
-	 * Alright, we handled this trip successfully.
-	 * So, start monitoring again.
-	 */
-	monitor_thermal_zone(tz);
 }
 
 static void update_temperature(struct thermal_zone_device *tz)
 {
 	int temp, ret;
 
-	ret = thermal_zone_get_temp(tz, &temp);
+	ret = __thermal_zone_get_temp(tz, &temp);
 	if (ret) {
 		if (ret != -EAGAIN)
 			dev_warn(&tz->device,
@@ -403,10 +385,8 @@ static void update_temperature(struct thermal_zone_device *tz)
 		return;
 	}
 
-	mutex_lock(&tz->lock);
 	tz->last_temperature = tz->temperature;
 	tz->temperature = temp;
-	mutex_unlock(&tz->lock);
 
 	trace_thermal_temperature(tz);
 
@@ -469,15 +449,9 @@ EXPORT_SYMBOL_GPL(thermal_zone_device_disable);
 
 int thermal_zone_device_is_enabled(struct thermal_zone_device *tz)
 {
-	enum thermal_device_mode mode;
-
-	mutex_lock(&tz->lock);
-
-	mode = tz->mode;
+	lockdep_assert_held(&tz->lock);
 
-	mutex_unlock(&tz->lock);
-
-	return mode == THERMAL_DEVICE_ENABLED;
+	return tz->mode == THERMAL_DEVICE_ENABLED;
 }
 
 void thermal_zone_device_update(struct thermal_zone_device *tz,
@@ -485,9 +459,6 @@ void thermal_zone_device_update(struct thermal_zone_device *tz,
 {
 	int count;
 
-	if (should_stop_polling(tz))
-		return;
-
 	if (atomic_read(&in_suspend))
 		return;
 
@@ -495,14 +466,23 @@ void thermal_zone_device_update(struct thermal_zone_device *tz,
 		      "'get_temp' ops set\n", __func__))
 		return;
 
+	mutex_lock(&tz->lock);
+
+	if (!thermal_zone_device_is_enabled(tz))
+		goto out;
+
 	update_temperature(tz);
 
-	thermal_zone_set_trips(tz);
+	__thermal_zone_set_trips(tz);
 
 	tz->notify_event = event;
 
 	for (count = 0; count < tz->num_trips; count++)
 		handle_thermal_trip(tz, count);
+
+	monitor_thermal_zone(tz);
+out:
+	mutex_unlock(&tz->lock);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_device_update);
 
@@ -1212,7 +1192,20 @@ thermal_zone_device_register_with_trips(const char *type, struct thermal_trip *t
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (num_trips > THERMAL_MAX_TRIPS || num_trips < 0 || mask >> num_trips) {
+	/*
+	 * Max trip count can't exceed 31 as the "mask >> num_trips" condition.
+	 * For example, shifting by 32 will result in compiler warning:
+	 * warning: right shift count >= width of type [-Wshift-count- overflow]
+	 *
+	 * Also "mask >> num_trips" will always be true with 32 bit shift.
+	 * E.g. mask = 0x80000000 for trip id 31 to be RW. Then
+	 * mask >> 32 = 0x80000000
+	 * This will result in failure for the below condition.
+	 *
+	 * Check will be true when the bit 31 of the mask is set.
+	 * 32 bit shift will cause overflow of 4 byte integer.
+	 */
+	if (num_trips > (BITS_PER_TYPE(int) - 1) || num_trips < 0 || mask >> num_trips) {
 		pr_err("Incorrect number of thermal trips\n");
 		return ERR_PTR(-EINVAL);
 	}
@@ -1239,7 +1232,7 @@ thermal_zone_device_register_with_trips(const char *type, struct thermal_trip *t
 	}
 
 	tz->id = id;
-	strlcpy(tz->type, type, sizeof(tz->type));
+	strscpy(tz->type, type, sizeof(tz->type));
 
 	result = dev_set_name(&tz->device, "thermal_zone%d", tz->id);
 	if (result)
@@ -1329,6 +1322,7 @@ free_tz:
 	kfree(tz);
 	return ERR_PTR(result);
 }
+EXPORT_SYMBOL_GPL(thermal_zone_device_register_with_trips);
 
 struct thermal_zone_device *thermal_zone_device_register(const char *type, int ntrips, int mask,
 							 void *devdata, struct thermal_zone_device_ops *ops,
@@ -1457,9 +1451,6 @@ static int thermal_pm_notify(struct notifier_block *nb,
 	case PM_POST_SUSPEND:
 		atomic_set(&in_suspend, 0);
 		list_for_each_entry(tz, &thermal_tz_list, node) {
-			if (!thermal_zone_device_is_enabled(tz))
-				continue;
-
 			thermal_zone_device_init(tz);
 			thermal_zone_device_update(tz,
 						   THERMAL_EVENT_UNSPECIFIED);
@@ -1491,10 +1482,6 @@ static int __init thermal_init(void)
 	if (result)
 		goto unregister_governors;
 
-	result = of_parse_thermal_zones();
-	if (result)
-		goto unregister_class;
-
 	result = register_pm_notifier(&thermal_pm_nb);
 	if (result)
 		pr_warn("Thermal: Can not register suspend notifier, return %d\n",
@@ -1502,8 +1489,6 @@ static int __init thermal_init(void)
 
 	return 0;
 
-unregister_class:
-	class_unregister(&thermal_class);
 unregister_governors:
 	thermal_unregister_governors();
 error:
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index c991bb290512..1571917bd3c8 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -112,6 +112,8 @@ int thermal_build_list_of_policies(char *buf);
 
 /* Helpers */
 void thermal_zone_set_trips(struct thermal_zone_device *tz);
+void __thermal_zone_set_trips(struct thermal_zone_device *tz);
+int __thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp);
 
 /* sysfs I/F */
 int thermal_zone_create_device_groups(struct thermal_zone_device *, int);
@@ -135,13 +137,11 @@ thermal_cooling_device_stats_update(struct thermal_cooling_device *cdev,
 
 /* device tree support */
 #ifdef CONFIG_THERMAL_OF
-int of_parse_thermal_zones(void);
 int of_thermal_get_ntrips(struct thermal_zone_device *);
 bool of_thermal_is_trip_valid(struct thermal_zone_device *, int);
 const struct thermal_trip *
 of_thermal_get_trip_points(struct thermal_zone_device *);
 #else
-static inline int of_parse_thermal_zones(void) { return 0; }
 static inline int of_thermal_get_ntrips(struct thermal_zone_device *tz)
 {
 	return 0;
diff --git a/drivers/thermal/thermal_helpers.c b/drivers/thermal/thermal_helpers.c
index 690890f054a3..c65cdce8f856 100644
--- a/drivers/thermal/thermal_helpers.c
+++ b/drivers/thermal/thermal_helpers.c
@@ -64,27 +64,17 @@ get_thermal_instance(struct thermal_zone_device *tz,
 }
 EXPORT_SYMBOL(get_thermal_instance);
 
-/**
- * thermal_zone_get_temp() - returns the temperature of a thermal zone
- * @tz: a valid pointer to a struct thermal_zone_device
- * @temp: a valid pointer to where to store the resulting temperature.
- *
- * When a valid thermal zone reference is passed, it will fetch its
- * temperature and fill @temp.
- *
- * Return: On success returns 0, an error code otherwise
- */
-int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp)
+int __thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp)
 {
 	int ret = -EINVAL;
 	int count;
 	int crit_temp = INT_MAX;
 	enum thermal_trip_type type;
 
-	if (!tz || IS_ERR(tz) || !tz->ops->get_temp)
-		goto exit;
+	lockdep_assert_held(&tz->lock);
 
-	mutex_lock(&tz->lock);
+	if (!tz || IS_ERR(tz) || !tz->ops->get_temp)
+		return -EINVAL;
 
 	ret = tz->ops->get_temp(tz, temp);
 
@@ -107,35 +97,42 @@ int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp)
 			*temp = tz->emul_temperature;
 	}
 
-	mutex_unlock(&tz->lock);
-exit:
 	return ret;
 }
-EXPORT_SYMBOL_GPL(thermal_zone_get_temp);
 
 /**
- * thermal_zone_set_trips - Computes the next trip points for the driver
- * @tz: a pointer to a thermal zone device structure
+ * thermal_zone_get_temp() - returns the temperature of a thermal zone
+ * @tz: a valid pointer to a struct thermal_zone_device
+ * @temp: a valid pointer to where to store the resulting temperature.
  *
- * The function computes the next temperature boundaries by browsing
- * the trip points. The result is the closer low and high trip points
- * to the current temperature. These values are passed to the backend
- * driver to let it set its own notification mechanism (usually an
- * interrupt).
+ * When a valid thermal zone reference is passed, it will fetch its
+ * temperature and fill @temp.
  *
- * It does not return a value
+ * Return: On success returns 0, an error code otherwise
  */
-void thermal_zone_set_trips(struct thermal_zone_device *tz)
+int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp)
+{
+	int ret;
+
+	mutex_lock(&tz->lock);
+	ret = __thermal_zone_get_temp(tz, temp);
+	mutex_unlock(&tz->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(thermal_zone_get_temp);
+
+void __thermal_zone_set_trips(struct thermal_zone_device *tz)
 {
 	int low = -INT_MAX;
 	int high = INT_MAX;
 	int trip_temp, hysteresis;
 	int i, ret;
 
-	mutex_lock(&tz->lock);
+	lockdep_assert_held(&tz->lock);
 
 	if (!tz->ops->set_trips || !tz->ops->get_trip_hyst)
-		goto exit;
+		return;
 
 	for (i = 0; i < tz->num_trips; i++) {
 		int trip_low;
@@ -154,7 +151,7 @@ void thermal_zone_set_trips(struct thermal_zone_device *tz)
 
 	/* No need to change trip points */
 	if (tz->prev_low_trip == low && tz->prev_high_trip == high)
-		goto exit;
+		return;
 
 	tz->prev_low_trip = low;
 	tz->prev_high_trip = high;
@@ -169,8 +166,24 @@ void thermal_zone_set_trips(struct thermal_zone_device *tz)
 	ret = tz->ops->set_trips(tz, low, high);
 	if (ret)
 		dev_err(&tz->device, "Failed to set trips: %d\n", ret);
+}
 
-exit:
+/**
+ * thermal_zone_set_trips - Computes the next trip points for the driver
+ * @tz: a pointer to a thermal zone device structure
+ *
+ * The function computes the next temperature boundaries by browsing
+ * the trip points. The result is the closer low and high trip points
+ * to the current temperature. These values are passed to the backend
+ * driver to let it set its own notification mechanism (usually an
+ * interrupt).
+ *
+ * It does not return a value
+ */
+void thermal_zone_set_trips(struct thermal_zone_device *tz)
+{
+	mutex_lock(&tz->lock);
+	__thermal_zone_set_trips(tz);
 	mutex_unlock(&tz->lock);
 }
 
diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c
index 09e49ec8b6f4..f53f4ceb6a5d 100644
--- a/drivers/thermal/thermal_hwmon.c
+++ b/drivers/thermal/thermal_hwmon.c
@@ -147,7 +147,7 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&hwmon->tz_list);
-	strlcpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH);
+	strscpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH);
 	strreplace(hwmon->type, '-', '_');
 	hwmon->device = hwmon_device_register_for_thermal(&tz->device,
 							  hwmon->type, hwmon);
diff --git a/drivers/thermal/thermal_mmio.c b/drivers/thermal/thermal_mmio.c
index 360b0dfdc3b0..39c921415989 100644
--- a/drivers/thermal/thermal_mmio.c
+++ b/drivers/thermal/thermal_mmio.c
@@ -20,11 +20,10 @@ static u32 thermal_mmio_readb(void __iomem *mmio_base)
 	return readb(mmio_base);
 }
 
-static int thermal_mmio_get_temperature(void *private, int *temp)
+static int thermal_mmio_get_temperature(struct thermal_zone_device *tz, int *temp)
 {
 	int t;
-	struct thermal_mmio *sensor =
-		(struct thermal_mmio *)private;
+	struct thermal_mmio *sensor = tz->devdata;
 
 	t = sensor->read_mmio(sensor->mmio_base) & sensor->mask;
 	t *= sensor->factor;
@@ -34,7 +33,7 @@ static int thermal_mmio_get_temperature(void *private, int *temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops thermal_mmio_ops = {
+static const struct thermal_zone_device_ops thermal_mmio_ops = {
 	.get_temp = thermal_mmio_get_temperature,
 };
 
@@ -68,10 +67,10 @@ static int thermal_mmio_probe(struct platform_device *pdev)
 		}
 	}
 
-	thermal_zone = devm_thermal_zone_of_sensor_register(&pdev->dev,
-							    0,
-							    sensor,
-							    &thermal_mmio_ops);
+	thermal_zone = devm_thermal_of_zone_register(&pdev->dev,
+						     0,
+						     sensor,
+						     &thermal_mmio_ops);
 	if (IS_ERR(thermal_zone)) {
 		dev_err(&pdev->dev,
 			"failed to register sensor (%ld)\n",
@@ -79,7 +78,7 @@ static int thermal_mmio_probe(struct platform_device *pdev)
 		return PTR_ERR(thermal_zone);
 	}
 
-	thermal_mmio_get_temperature(sensor, &temperature);
+	thermal_mmio_get_temperature(thermal_zone, &temperature);
 	dev_info(&pdev->dev,
 		 "thermal mmio sensor %s registered, current temperature: %d\n",
 		 pdev->name, temperature);
@@ -107,7 +106,7 @@ static struct platform_driver thermal_mmio_driver = {
 	.probe = thermal_mmio_probe,
 	.driver = {
 		.name = "thermal-mmio",
-		.of_match_table = of_match_ptr(thermal_mmio_id_table),
+		.of_match_table = thermal_mmio_id_table,
 	},
 };
 
diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c
index 802c30b72a92..fd2fb84bf246 100644
--- a/drivers/thermal/thermal_of.c
+++ b/drivers/thermal/thermal_of.c
@@ -19,93 +19,6 @@
 
 #include "thermal_core.h"
 
-/***   Private data structures to represent thermal device tree data ***/
-
-/**
- * struct __thermal_cooling_bind_param - a cooling device for a trip point
- * @cooling_device: a pointer to identify the referred cooling device
- * @min: minimum cooling state used at this trip point
- * @max: maximum cooling state used at this trip point
- */
-
-struct __thermal_cooling_bind_param {
-	struct device_node *cooling_device;
-	unsigned long min;
-	unsigned long max;
-};
-
-/**
- * struct __thermal_bind_params - a match between trip and cooling device
- * @tcbp: a pointer to an array of cooling devices
- * @count: number of elements in array
- * @trip_id: the trip point index
- * @usage: the percentage (from 0 to 100) of cooling contribution
- */
-
-struct __thermal_bind_params {
-	struct __thermal_cooling_bind_param *tcbp;
-	unsigned int count;
-	unsigned int trip_id;
-	unsigned int usage;
-};
-
-/**
- * struct __thermal_zone - internal representation of a thermal zone
- * @passive_delay: polling interval while passive cooling is activated
- * @polling_delay: zone polling interval
- * @slope: slope of the temperature adjustment curve
- * @offset: offset of the temperature adjustment curve
- * @ntrips: number of trip points
- * @trips: an array of trip points (0..ntrips - 1)
- * @num_tbps: number of thermal bind params
- * @tbps: an array of thermal bind params (0..num_tbps - 1)
- * @sensor_data: sensor private data used while reading temperature and trend
- * @ops: set of callbacks to handle the thermal zone based on DT
- */
-
-struct __thermal_zone {
-	int passive_delay;
-	int polling_delay;
-	int slope;
-	int offset;
-
-	/* trip data */
-	int ntrips;
-	struct thermal_trip *trips;
-
-	/* cooling binding data */
-	int num_tbps;
-	struct __thermal_bind_params *tbps;
-
-	/* sensor interface */
-	void *sensor_data;
-	const struct thermal_zone_of_device_ops *ops;
-};
-
-/***   DT thermal zone device callbacks   ***/
-
-static int of_thermal_get_temp(struct thermal_zone_device *tz,
-			       int *temp)
-{
-	struct __thermal_zone *data = tz->devdata;
-
-	if (!data->ops || !data->ops->get_temp)
-		return -EINVAL;
-
-	return data->ops->get_temp(data->sensor_data, temp);
-}
-
-static int of_thermal_set_trips(struct thermal_zone_device *tz,
-				int low, int high)
-{
-	struct __thermal_zone *data = tz->devdata;
-
-	if (!data->ops || !data->ops->set_trips)
-		return -EINVAL;
-
-	return data->ops->set_trips(data->sensor_data, low, high);
-}
-
 /**
  * of_thermal_get_ntrips - function to export number of available trip
  *			   points.
@@ -158,114 +71,6 @@ of_thermal_get_trip_points(struct thermal_zone_device *tz)
 }
 EXPORT_SYMBOL_GPL(of_thermal_get_trip_points);
 
-/**
- * of_thermal_set_emul_temp - function to set emulated temperature
- *
- * @tz:	pointer to a thermal zone
- * @temp:	temperature to set
- *
- * This function gives the ability to set emulated value of temperature,
- * which is handy for debugging
- *
- * Return: zero on success, error code otherwise
- */
-static int of_thermal_set_emul_temp(struct thermal_zone_device *tz,
-				    int temp)
-{
-	struct __thermal_zone *data = tz->devdata;
-
-	if (!data->ops || !data->ops->set_emul_temp)
-		return -EINVAL;
-
-	return data->ops->set_emul_temp(data->sensor_data, temp);
-}
-
-static int of_thermal_get_trend(struct thermal_zone_device *tz, int trip,
-				enum thermal_trend *trend)
-{
-	struct __thermal_zone *data = tz->devdata;
-
-	if (!data->ops || !data->ops->get_trend)
-		return -EINVAL;
-
-	return data->ops->get_trend(data->sensor_data, trip, trend);
-}
-
-static int of_thermal_change_mode(struct thermal_zone_device *tz,
-				enum thermal_device_mode mode)
-{
-	struct __thermal_zone *data = tz->devdata;
-
-	return data->ops->change_mode(data->sensor_data, mode);
-}
-
-static int of_thermal_bind(struct thermal_zone_device *thermal,
-			   struct thermal_cooling_device *cdev)
-{
-	struct __thermal_zone *data = thermal->devdata;
-	struct __thermal_bind_params *tbp;
-	struct __thermal_cooling_bind_param *tcbp;
-	int i, j;
-
-	if (!data || IS_ERR(data))
-		return -ENODEV;
-
-	/* find where to bind */
-	for (i = 0; i < data->num_tbps; i++) {
-		tbp = data->tbps + i;
-
-		for (j = 0; j < tbp->count; j++) {
-			tcbp = tbp->tcbp + j;
-
-			if (tcbp->cooling_device == cdev->np) {
-				int ret;
-
-				ret = thermal_zone_bind_cooling_device(thermal,
-						tbp->trip_id, cdev,
-						tcbp->max,
-						tcbp->min,
-						tbp->usage);
-				if (ret)
-					return ret;
-			}
-		}
-	}
-
-	return 0;
-}
-
-static int of_thermal_unbind(struct thermal_zone_device *thermal,
-			     struct thermal_cooling_device *cdev)
-{
-	struct __thermal_zone *data = thermal->devdata;
-	struct __thermal_bind_params *tbp;
-	struct __thermal_cooling_bind_param *tcbp;
-	int i, j;
-
-	if (!data || IS_ERR(data))
-		return -ENODEV;
-
-	/* find where to unbind */
-	for (i = 0; i < data->num_tbps; i++) {
-		tbp = data->tbps + i;
-
-		for (j = 0; j < tbp->count; j++) {
-			tcbp = tbp->tcbp + j;
-
-			if (tcbp->cooling_device == cdev->np) {
-				int ret;
-
-				ret = thermal_zone_unbind_cooling_device(thermal,
-							tbp->trip_id, cdev);
-				if (ret)
-					return ret;
-			}
-		}
-	}
-
-	return 0;
-}
-
 static int of_thermal_get_trip_type(struct thermal_zone_device *tz, int trip,
 				    enum thermal_trip_type *type)
 {
@@ -288,28 +93,6 @@ static int of_thermal_get_trip_temp(struct thermal_zone_device *tz, int trip,
 	return 0;
 }
 
-static int of_thermal_set_trip_temp(struct thermal_zone_device *tz, int trip,
-				    int temp)
-{
-	struct __thermal_zone *data = tz->devdata;
-
-	if (trip >= tz->num_trips || trip < 0)
-		return -EDOM;
-
-	if (data->ops && data->ops->set_trip_temp) {
-		int ret;
-
-		ret = data->ops->set_trip_temp(data->sensor_data, trip, temp);
-		if (ret)
-			return ret;
-	}
-
-	/* thermal framework should take care of data->mask & (1 << trip) */
-	tz->trips[trip].temperature = temp;
-
-	return 0;
-}
-
 static int of_thermal_get_trip_hyst(struct thermal_zone_device *tz, int trip,
 				    int *hyst)
 {
@@ -347,62 +130,6 @@ static int of_thermal_get_crit_temp(struct thermal_zone_device *tz,
 	return -EINVAL;
 }
 
-static struct thermal_zone_device_ops of_thermal_ops = {
-	.get_trip_type = of_thermal_get_trip_type,
-	.get_trip_temp = of_thermal_get_trip_temp,
-	.set_trip_temp = of_thermal_set_trip_temp,
-	.get_trip_hyst = of_thermal_get_trip_hyst,
-	.set_trip_hyst = of_thermal_set_trip_hyst,
-	.get_crit_temp = of_thermal_get_crit_temp,
-
-	.bind = of_thermal_bind,
-	.unbind = of_thermal_unbind,
-};
-
-/***   sensor API   ***/
-
-static struct thermal_zone_device *
-thermal_zone_of_add_sensor(struct device_node *zone,
-			   struct device_node *sensor, void *data,
-			   const struct thermal_zone_of_device_ops *ops)
-{
-	struct thermal_zone_device *tzd;
-	struct __thermal_zone *tz;
-
-	tzd = thermal_zone_get_zone_by_name(zone->name);
-	if (IS_ERR(tzd))
-		return ERR_PTR(-EPROBE_DEFER);
-
-	tz = tzd->devdata;
-
-	if (!ops)
-		return ERR_PTR(-EINVAL);
-
-	mutex_lock(&tzd->lock);
-	tz->ops = ops;
-	tz->sensor_data = data;
-
-	tzd->ops->get_temp = of_thermal_get_temp;
-	tzd->ops->get_trend = of_thermal_get_trend;
-
-	/*
-	 * The thermal zone core will calculate the window if they have set the
-	 * optional set_trips pointer.
-	 */
-	if (ops->set_trips)
-		tzd->ops->set_trips = of_thermal_set_trips;
-
-	if (ops->set_emul_temp)
-		tzd->ops->set_emul_temp = of_thermal_set_emul_temp;
-
-	if (ops->change_mode)
-		tzd->ops->change_mode = of_thermal_change_mode;
-
-	mutex_unlock(&tzd->lock);
-
-	return tzd;
-}
-
 /**
  * thermal_zone_of_get_sensor_id - get sensor ID from a DT thermal zone
  * @tz_np: a valid thermal zone device node.
@@ -447,207 +174,6 @@ int thermal_zone_of_get_sensor_id(struct device_node *tz_np,
 }
 EXPORT_SYMBOL_GPL(thermal_zone_of_get_sensor_id);
 
-/**
- * thermal_zone_of_sensor_register - registers a sensor to a DT thermal zone
- * @dev: a valid struct device pointer of a sensor device. Must contain
- *       a valid .of_node, for the sensor node.
- * @sensor_id: a sensor identifier, in case the sensor IP has more
- *             than one sensors
- * @data: a private pointer (owned by the caller) that will be passed
- *        back, when a temperature reading is needed.
- * @ops: struct thermal_zone_of_device_ops *. Must contain at least .get_temp.
- *
- * This function will search the list of thermal zones described in device
- * tree and look for the zone that refer to the sensor device pointed by
- * @dev->of_node as temperature providers. For the zone pointing to the
- * sensor node, the sensor will be added to the DT thermal zone device.
- *
- * The thermal zone temperature is provided by the @get_temp function
- * pointer. When called, it will have the private pointer @data back.
- *
- * The thermal zone temperature trend is provided by the @get_trend function
- * pointer. When called, it will have the private pointer @data back.
- *
- * TODO:
- * 01 - This function must enqueue the new sensor instead of using
- * it as the only source of temperature values.
- *
- * 02 - There must be a way to match the sensor with all thermal zones
- * that refer to it.
- *
- * Return: On success returns a valid struct thermal_zone_device,
- * otherwise, it returns a corresponding ERR_PTR(). Caller must
- * check the return value with help of IS_ERR() helper.
- */
-struct thermal_zone_device *
-thermal_zone_of_sensor_register(struct device *dev, int sensor_id, void *data,
-				const struct thermal_zone_of_device_ops *ops)
-{
-	struct device_node *np, *child, *sensor_np;
-	struct thermal_zone_device *tzd = ERR_PTR(-ENODEV);
-
-	np = of_find_node_by_name(NULL, "thermal-zones");
-	if (!np)
-		return ERR_PTR(-ENODEV);
-
-	if (!dev || !dev->of_node) {
-		of_node_put(np);
-		return ERR_PTR(-ENODEV);
-	}
-
-	sensor_np = of_node_get(dev->of_node);
-
-	for_each_available_child_of_node(np, child) {
-		int ret, id;
-
-		/* For now, thermal framework supports only 1 sensor per zone */
-		ret = thermal_zone_of_get_sensor_id(child, sensor_np, &id);
-		if (ret)
-			continue;
-
-		if (id == sensor_id) {
-			tzd = thermal_zone_of_add_sensor(child, sensor_np,
-							 data, ops);
-			if (!IS_ERR(tzd))
-				thermal_zone_device_enable(tzd);
-
-			of_node_put(child);
-			goto exit;
-		}
-	}
-exit:
-	of_node_put(sensor_np);
-	of_node_put(np);
-
-	return tzd;
-}
-EXPORT_SYMBOL_GPL(thermal_zone_of_sensor_register);
-
-/**
- * thermal_zone_of_sensor_unregister - unregisters a sensor from a DT thermal zone
- * @dev: a valid struct device pointer of a sensor device. Must contain
- *       a valid .of_node, for the sensor node.
- * @tzd: a pointer to struct thermal_zone_device where the sensor is registered.
- *
- * This function removes the sensor callbacks and private data from the
- * thermal zone device registered with thermal_zone_of_sensor_register()
- * API. It will also silent the zone by remove the .get_temp() and .get_trend()
- * thermal zone device callbacks.
- *
- * TODO: When the support to several sensors per zone is added, this
- * function must search the sensor list based on @dev parameter.
- *
- */
-void thermal_zone_of_sensor_unregister(struct device *dev,
-				       struct thermal_zone_device *tzd)
-{
-	struct __thermal_zone *tz;
-
-	if (!dev || !tzd || !tzd->devdata)
-		return;
-
-	tz = tzd->devdata;
-
-	/* no __thermal_zone, nothing to be done */
-	if (!tz)
-		return;
-
-	/* stop temperature polling */
-	thermal_zone_device_disable(tzd);
-
-	mutex_lock(&tzd->lock);
-	tzd->ops->get_temp = NULL;
-	tzd->ops->get_trend = NULL;
-	tzd->ops->set_emul_temp = NULL;
-	tzd->ops->change_mode = NULL;
-
-	tz->ops = NULL;
-	tz->sensor_data = NULL;
-	mutex_unlock(&tzd->lock);
-}
-EXPORT_SYMBOL_GPL(thermal_zone_of_sensor_unregister);
-
-static void devm_thermal_zone_of_sensor_release(struct device *dev, void *res)
-{
-	thermal_zone_of_sensor_unregister(dev,
-					  *(struct thermal_zone_device **)res);
-}
-
-static int devm_thermal_zone_of_sensor_match(struct device *dev, void *res,
-					     void *data)
-{
-	struct thermal_zone_device **r = res;
-
-	if (WARN_ON(!r || !*r))
-		return 0;
-
-	return *r == data;
-}
-
-/**
- * devm_thermal_zone_of_sensor_register - Resource managed version of
- *				thermal_zone_of_sensor_register()
- * @dev: a valid struct device pointer of a sensor device. Must contain
- *       a valid .of_node, for the sensor node.
- * @sensor_id: a sensor identifier, in case the sensor IP has more
- *	       than one sensors
- * @data: a private pointer (owned by the caller) that will be passed
- *	  back, when a temperature reading is needed.
- * @ops: struct thermal_zone_of_device_ops *. Must contain at least .get_temp.
- *
- * Refer thermal_zone_of_sensor_register() for more details.
- *
- * Return: On success returns a valid struct thermal_zone_device,
- * otherwise, it returns a corresponding ERR_PTR(). Caller must
- * check the return value with help of IS_ERR() helper.
- * Registered thermal_zone_device device will automatically be
- * released when device is unbounded.
- */
-struct thermal_zone_device *devm_thermal_zone_of_sensor_register(
-	struct device *dev, int sensor_id,
-	void *data, const struct thermal_zone_of_device_ops *ops)
-{
-	struct thermal_zone_device **ptr, *tzd;
-
-	ptr = devres_alloc(devm_thermal_zone_of_sensor_release, sizeof(*ptr),
-			   GFP_KERNEL);
-	if (!ptr)
-		return ERR_PTR(-ENOMEM);
-
-	tzd = thermal_zone_of_sensor_register(dev, sensor_id, data, ops);
-	if (IS_ERR(tzd)) {
-		devres_free(ptr);
-		return tzd;
-	}
-
-	*ptr = tzd;
-	devres_add(dev, ptr);
-
-	return tzd;
-}
-EXPORT_SYMBOL_GPL(devm_thermal_zone_of_sensor_register);
-
-/**
- * devm_thermal_zone_of_sensor_unregister - Resource managed version of
- *				thermal_zone_of_sensor_unregister().
- * @dev: Device for which which resource was allocated.
- * @tzd: a pointer to struct thermal_zone_device where the sensor is registered.
- *
- * This function removes the sensor callbacks and private data from the
- * thermal zone device registered with devm_thermal_zone_of_sensor_register()
- * API. It will also silent the zone by remove the .get_temp() and .get_trend()
- * thermal zone device callbacks.
- * Normally this function will not need to be called and the resource
- * management code will ensure that the resource is freed.
- */
-void devm_thermal_zone_of_sensor_unregister(struct device *dev,
-					    struct thermal_zone_device *tzd)
-{
-	WARN_ON(devres_release(dev, devm_thermal_zone_of_sensor_release,
-			       devm_thermal_zone_of_sensor_match, tzd));
-}
-EXPORT_SYMBOL_GPL(devm_thermal_zone_of_sensor_unregister);
-
 /***   functions parsing device tree nodes   ***/
 
 static int of_find_trip_id(struct device_node *np, struct device_node *trip)
@@ -679,98 +205,6 @@ out:
 	return i;
 }
 
-/**
- * thermal_of_populate_bind_params - parse and fill cooling map data
- * @np: DT node containing a cooling-map node
- * @__tbp: data structure to be filled with cooling map info
- * @trips: array of thermal zone trip points
- * @ntrips: number of trip points inside trips.
- *
- * This function parses a cooling-map type of node represented by
- * @np parameter and fills the read data into @__tbp data structure.
- * It needs the already parsed array of trip points of the thermal zone
- * in consideration.
- *
- * Return: 0 on success, proper error code otherwise
- */
-static int thermal_of_populate_bind_params(struct device_node *tz_np,
-					   struct device_node *np,
-					   struct __thermal_bind_params *__tbp)
-{
-	struct of_phandle_args cooling_spec;
-	struct __thermal_cooling_bind_param *__tcbp;
-	struct device_node *trip;
-	int ret, i, count;
-	int trip_id;
-	u32 prop;
-
-	/* Default weight. Usage is optional */
-	__tbp->usage = THERMAL_WEIGHT_DEFAULT;
-	ret = of_property_read_u32(np, "contribution", &prop);
-	if (ret == 0)
-		__tbp->usage = prop;
-
-	trip = of_parse_phandle(np, "trip", 0);
-	if (!trip) {
-		pr_err("missing trip property\n");
-		return -ENODEV;
-	}
-
-	trip_id = of_find_trip_id(tz_np, trip);
-	if (trip_id < 0) {
-		ret = trip_id;
-		goto end;
-	}
-
-	__tbp->trip_id = trip_id;
-
-	count = of_count_phandle_with_args(np, "cooling-device",
-					   "#cooling-cells");
-	if (count <= 0) {
-		pr_err("Add a cooling_device property with at least one device\n");
-		ret = -ENOENT;
-		goto end;
-	}
-
-	__tcbp = kcalloc(count, sizeof(*__tcbp), GFP_KERNEL);
-	if (!__tcbp) {
-		ret = -ENOMEM;
-		goto end;
-	}
-
-	for (i = 0; i < count; i++) {
-		ret = of_parse_phandle_with_args(np, "cooling-device",
-				"#cooling-cells", i, &cooling_spec);
-		if (ret < 0) {
-			pr_err("Invalid cooling-device entry\n");
-			goto free_tcbp;
-		}
-
-		__tcbp[i].cooling_device = cooling_spec.np;
-
-		if (cooling_spec.args_count >= 2) { /* at least min and max */
-			__tcbp[i].min = cooling_spec.args[0];
-			__tcbp[i].max = cooling_spec.args[1];
-		} else {
-			pr_err("wrong reference to cooling device, missing limits\n");
-		}
-	}
-
-	__tbp->tcbp = __tcbp;
-	__tbp->count = count;
-
-	goto end;
-
-free_tcbp:
-	for (i = i - 1; i >= 0; i--)
-		of_node_put(__tcbp[i].cooling_device);
-	kfree(__tcbp);
-end:
-	of_node_put(trip);
-
-	return ret;
-}
-
 /*
  * It maps 'enum thermal_trip_type' found in include/linux/thermal.h
  * into the device tree binding of 'trip', property type.
@@ -811,16 +245,6 @@ static int thermal_of_get_trip_type(struct device_node *np,
 	return -ENODEV;
 }
 
-/**
- * thermal_of_populate_trip - parse and fill one trip point data
- * @np: DT node containing a trip point node
- * @trip: trip point data structure to be filled up
- *
- * This function parses a trip point type of node represented by
- * @np parameter and fills the read data into @trip data structure.
- *
- * Return: 0 on success, proper error code otherwise
- */
 static int thermal_of_populate_trip(struct device_node *np,
 				    struct thermal_trip *trip)
 {
@@ -897,258 +321,458 @@ out_of_node_put:
 	return ERR_PTR(ret);
 }
 
-/**
- * thermal_of_build_thermal_zone - parse and fill one thermal zone data
- * @np: DT node containing a thermal zone node
- *
- * This function parses a thermal zone type of node represented by
- * @np parameter and fills the read data into a __thermal_zone data structure
- * and return this pointer.
- *
- * TODO: Missing properties to parse: thermal-sensor-names
- *
- * Return: On success returns a valid struct __thermal_zone,
- * otherwise, it returns a corresponding ERR_PTR(). Caller must
- * check the return value with help of IS_ERR() helper.
- */
-static struct __thermal_zone
-__init *thermal_of_build_thermal_zone(struct device_node *np)
+static struct device_node *of_thermal_zone_find(struct device_node *sensor, int id)
 {
-	struct device_node *child = NULL, *gchild;
-	struct __thermal_zone *tz;
-	int ret, i;
-	u32 prop, coef[2];
+	struct device_node *np, *tz;
+	struct of_phandle_args sensor_specs;
 
+	np = of_find_node_by_name(NULL, "thermal-zones");
 	if (!np) {
-		pr_err("no thermal zone np\n");
-		return ERR_PTR(-EINVAL);
+		pr_debug("No thermal zones description\n");
+		return ERR_PTR(-ENODEV);
 	}
 
-	tz = kzalloc(sizeof(*tz), GFP_KERNEL);
-	if (!tz)
-		return ERR_PTR(-ENOMEM);
+	/*
+	 * Search for each thermal zone, a defined sensor
+	 * corresponding to the one passed as parameter
+	 */
+	for_each_available_child_of_node(np, tz) {
+
+		int count, i;
+
+		count = of_count_phandle_with_args(tz, "thermal-sensors",
+						   "#thermal-sensor-cells");
+		if (count <= 0) {
+			pr_err("%pOFn: missing thermal sensor\n", tz);
+			tz = ERR_PTR(-EINVAL);
+			goto out;
+		}
+
+		for (i = 0; i < count; i++) {
+
+			int ret;
 
-	ret = of_property_read_u32(np, "polling-delay-passive", &prop);
+			ret = of_parse_phandle_with_args(tz, "thermal-sensors",
+							 "#thermal-sensor-cells",
+							 i, &sensor_specs);
+			if (ret < 0) {
+				pr_err("%pOFn: Failed to read thermal-sensors cells: %d\n", tz, ret);
+				tz = ERR_PTR(ret);
+				goto out;
+			}
+
+			if ((sensor == sensor_specs.np) && id == (sensor_specs.args_count ?
+								  sensor_specs.args[0] : 0)) {
+				pr_debug("sensor %pOFn id=%d belongs to %pOFn\n", sensor, id, tz);
+				goto out;
+			}
+		}
+	}
+	tz = ERR_PTR(-ENODEV);
+out:
+	of_node_put(np);
+	return tz;
+}
+
+static int thermal_of_monitor_init(struct device_node *np, int *delay, int *pdelay)
+{
+	int ret;
+
+	ret = of_property_read_u32(np, "polling-delay-passive", pdelay);
 	if (ret < 0) {
 		pr_err("%pOFn: missing polling-delay-passive property\n", np);
-		goto free_tz;
+		return ret;
 	}
-	tz->passive_delay = prop;
 
-	ret = of_property_read_u32(np, "polling-delay", &prop);
+	ret = of_property_read_u32(np, "polling-delay", delay);
 	if (ret < 0) {
 		pr_err("%pOFn: missing polling-delay property\n", np);
-		goto free_tz;
+		return ret;
 	}
-	tz->polling_delay = prop;
+
+	return 0;
+}
+
+static struct thermal_zone_params *thermal_of_parameters_init(struct device_node *np)
+{
+	struct thermal_zone_params *tzp;
+	int coef[2];
+	int ncoef = ARRAY_SIZE(coef);
+	int prop, ret;
+
+	tzp = kzalloc(sizeof(*tzp), GFP_KERNEL);
+	if (!tzp)
+		return ERR_PTR(-ENOMEM);
+
+	tzp->no_hwmon = true;
+
+	if (!of_property_read_u32(np, "sustainable-power", &prop))
+		tzp->sustainable_power = prop;
 
 	/*
-	 * REVIST: for now, the thermal framework supports only
-	 * one sensor per thermal zone. Thus, we are considering
-	 * only the first two values as slope and offset.
+	 * For now, the thermal framework supports only one sensor per
+	 * thermal zone. Thus, we are considering only the first two
+	 * values as slope and offset.
 	 */
-	ret = of_property_read_u32_array(np, "coefficients", coef, 2);
-	if (ret == 0) {
-		tz->slope = coef[0];
-		tz->offset = coef[1];
-	} else {
-		tz->slope = 1;
-		tz->offset = 0;
+	ret = of_property_read_u32_array(np, "coefficients", coef, ncoef);
+	if (ret) {
+		coef[0] = 1;
+		coef[1] = 0;
+	}
+
+	tzp->slope = coef[0];
+	tzp->offset = coef[1];
+
+	return tzp;
+}
+
+static struct device_node *thermal_of_zone_get_by_name(struct thermal_zone_device *tz)
+{
+	struct device_node *np, *tz_np;
+
+	np = of_find_node_by_name(NULL, "thermal-zones");
+	if (!np)
+		return ERR_PTR(-ENODEV);
+
+	tz_np = of_get_child_by_name(np, tz->type);
+
+	of_node_put(np);
+
+	if (!tz_np)
+		return ERR_PTR(-ENODEV);
+
+	return tz_np;
+}
+
+static int __thermal_of_unbind(struct device_node *map_np, int index, int trip_id,
+			       struct thermal_zone_device *tz, struct thermal_cooling_device *cdev)
+{
+	struct of_phandle_args cooling_spec;
+	int ret;
+
+	ret = of_parse_phandle_with_args(map_np, "cooling-device", "#cooling-cells",
+					 index, &cooling_spec);
+
+	of_node_put(cooling_spec.np);
+
+	if (ret < 0) {
+		pr_err("Invalid cooling-device entry\n");
+		return ret;
 	}
 
-	tz->trips = thermal_of_trips_init(np, &tz->ntrips);
-	if (IS_ERR(tz->trips)) {
-		ret = PTR_ERR(tz->trips);
-		goto finish;
+	if (cooling_spec.args_count < 2) {
+		pr_err("wrong reference to cooling device, missing limits\n");
+		return -EINVAL;
 	}
 
-	/* cooling-maps */
-	child = of_get_child_by_name(np, "cooling-maps");
+	if (cooling_spec.np != cdev->np)
+		return 0;
 
-	/* cooling-maps not provided */
-	if (!child)
-		goto finish;
+	ret = thermal_zone_unbind_cooling_device(tz, trip_id, cdev);
+	if (ret)
+		pr_err("Failed to unbind '%s' with '%s': %d\n", tz->type, cdev->type, ret);
 
-	tz->num_tbps = of_get_child_count(child);
-	if (tz->num_tbps == 0)
-		goto finish;
+	return ret;
+}
 
-	tz->tbps = kcalloc(tz->num_tbps, sizeof(*tz->tbps), GFP_KERNEL);
-	if (!tz->tbps) {
-		ret = -ENOMEM;
-		goto free_trips;
+static int __thermal_of_bind(struct device_node *map_np, int index, int trip_id,
+			     struct thermal_zone_device *tz, struct thermal_cooling_device *cdev)
+{
+	struct of_phandle_args cooling_spec;
+	int ret, weight = THERMAL_WEIGHT_DEFAULT;
+
+	of_property_read_u32(map_np, "contribution", &weight);
+
+	ret = of_parse_phandle_with_args(map_np, "cooling-device", "#cooling-cells",
+					 index, &cooling_spec);
+
+	of_node_put(cooling_spec.np);
+
+	if (ret < 0) {
+		pr_err("Invalid cooling-device entry\n");
+		return ret;
 	}
 
-	i = 0;
-	for_each_child_of_node(child, gchild) {
-		ret = thermal_of_populate_bind_params(np, gchild, &tz->tbps[i++]);
-		if (ret) {
-			of_node_put(gchild);
-			goto free_tbps;
-		}
+	if (cooling_spec.args_count < 2) {
+		pr_err("wrong reference to cooling device, missing limits\n");
+		return -EINVAL;
 	}
 
-finish:
-	of_node_put(child);
+	if (cooling_spec.np != cdev->np)
+		return 0;
+
+	ret = thermal_zone_bind_cooling_device(tz, trip_id, cdev, cooling_spec.args[1],
+					       cooling_spec.args[0],
+					       weight);
+	if (ret)
+		pr_err("Failed to bind '%s' with '%s': %d\n", tz->type, cdev->type, ret);
 
-	return tz;
+	return ret;
+}
 
-free_tbps:
-	for (i = i - 1; i >= 0; i--) {
-		struct __thermal_bind_params *tbp = tz->tbps + i;
-		int j;
+static int thermal_of_for_each_cooling_device(struct device_node *tz_np, struct device_node *map_np,
+					      struct thermal_zone_device *tz, struct thermal_cooling_device *cdev,
+					      int (*action)(struct device_node *, int, int,
+							    struct thermal_zone_device *, struct thermal_cooling_device *))
+{
+	struct device_node *tr_np;
+	int count, i, trip_id;
 
-		for (j = 0; j < tbp->count; j++)
-			of_node_put(tbp->tcbp[j].cooling_device);
+	tr_np = of_parse_phandle(map_np, "trip", 0);
+	if (!tr_np)
+		return -ENODEV;
 
-		kfree(tbp->tcbp);
+	trip_id = of_find_trip_id(tz_np, tr_np);
+	if (trip_id < 0)
+		return trip_id;
+
+	count = of_count_phandle_with_args(map_np, "cooling-device", "#cooling-cells");
+	if (count <= 0) {
+		pr_err("Add a cooling_device property with at least one device\n");
+		return -ENOENT;
 	}
 
-	kfree(tz->tbps);
-free_trips:
-	kfree(tz->trips);
-free_tz:
-	kfree(tz);
-	of_node_put(child);
+	/*
+	 * At this point, we don't want to bail out when there is an
+	 * error, we will try to bind/unbind as many as possible
+	 * cooling devices
+	 */
+	for (i = 0; i < count; i++)
+		action(map_np, i, trip_id, tz, cdev);
 
-	return ERR_PTR(ret);
+	return 0;
 }
 
-static __init void of_thermal_free_zone(struct __thermal_zone *tz)
+static int thermal_of_for_each_cooling_maps(struct thermal_zone_device *tz,
+					    struct thermal_cooling_device *cdev,
+					    int (*action)(struct device_node *, int, int,
+							  struct thermal_zone_device *, struct thermal_cooling_device *))
 {
-	struct __thermal_bind_params *tbp;
-	int i, j;
+	struct device_node *tz_np, *cm_np, *child;
+	int ret = 0;
 
-	for (i = 0; i < tz->num_tbps; i++) {
-		tbp = tz->tbps + i;
+	tz_np = thermal_of_zone_get_by_name(tz);
+	if (IS_ERR(tz_np)) {
+		pr_err("Failed to get node tz by name\n");
+		return PTR_ERR(tz_np);
+	}
 
-		for (j = 0; j < tbp->count; j++)
-			of_node_put(tbp->tcbp[j].cooling_device);
+	cm_np = of_get_child_by_name(tz_np, "cooling-maps");
+	if (!cm_np)
+		goto out;
 
-		kfree(tbp->tcbp);
+	for_each_child_of_node(cm_np, child) {
+		ret = thermal_of_for_each_cooling_device(tz_np, child, tz, cdev, action);
+		if (ret)
+			break;
 	}
 
-	kfree(tz->tbps);
-	kfree(tz->trips);
-	kfree(tz);
+	of_node_put(cm_np);
+out:
+	of_node_put(tz_np);
+
+	return ret;
+}
+
+static int thermal_of_bind(struct thermal_zone_device *tz,
+			   struct thermal_cooling_device *cdev)
+{
+	return thermal_of_for_each_cooling_maps(tz, cdev, __thermal_of_bind);
+}
+
+static int thermal_of_unbind(struct thermal_zone_device *tz,
+			     struct thermal_cooling_device *cdev)
+{
+	return thermal_of_for_each_cooling_maps(tz, cdev, __thermal_of_unbind);
 }
 
 /**
- * of_thermal_destroy_zones - remove all zones parsed and allocated resources
+ * thermal_of_zone_unregister - Cleanup the specific allocated ressources
  *
- * Finds all zones parsed and added to the thermal framework and remove them
- * from the system, together with their resources.
+ * This function disables the thermal zone and frees the different
+ * ressources allocated specific to the thermal OF.
  *
+ * @tz: a pointer to the thermal zone structure
  */
-static __init void of_thermal_destroy_zones(void)
+void thermal_of_zone_unregister(struct thermal_zone_device *tz)
 {
-	struct device_node *np, *child;
+	struct thermal_trip *trips = tz->trips;
+	struct thermal_zone_params *tzp = tz->tzp;
+	struct thermal_zone_device_ops *ops = tz->ops;
 
-	np = of_find_node_by_name(NULL, "thermal-zones");
-	if (!np) {
-		pr_debug("unable to find thermal zones\n");
-		return;
+	thermal_zone_device_disable(tz);
+	thermal_zone_device_unregister(tz);
+	kfree(trips);
+	kfree(tzp);
+	kfree(ops);
+}
+EXPORT_SYMBOL_GPL(thermal_of_zone_unregister);
+
+/**
+ * thermal_of_zone_register - Register a thermal zone with device node
+ * sensor
+ *
+ * The thermal_of_zone_register() parses a device tree given a device
+ * node sensor and identifier. It searches for the thermal zone
+ * associated to the couple sensor/id and retrieves all the thermal
+ * zone properties and registers new thermal zone with those
+ * properties.
+ *
+ * @sensor: A device node pointer corresponding to the sensor in the device tree
+ * @id: An integer as sensor identifier
+ * @data: A private data to be stored in the thermal zone dedicated private area
+ * @ops: A set of thermal sensor ops
+ *
+ * Return: a valid thermal zone structure pointer on success.
+ * 	- EINVAL: if the device tree thermal description is malformed
+ *	- ENOMEM: if one structure can not be allocated
+ *	- Other negative errors are returned by the underlying called functions
+ */
+struct thermal_zone_device *thermal_of_zone_register(struct device_node *sensor, int id, void *data,
+						     const struct thermal_zone_device_ops *ops)
+{
+	struct thermal_zone_device *tz;
+	struct thermal_trip *trips;
+	struct thermal_zone_params *tzp;
+	struct thermal_zone_device_ops *of_ops;
+	struct device_node *np;
+	int delay, pdelay;
+	int ntrips, mask;
+	int ret;
+
+	of_ops = kmemdup(ops, sizeof(*ops), GFP_KERNEL);
+	if (!of_ops)
+		return ERR_PTR(-ENOMEM);
+
+	np = of_thermal_zone_find(sensor, id);
+	if (IS_ERR(np)) {
+		if (PTR_ERR(np) != -ENODEV)
+			pr_err("Failed to find thermal zone for %pOFn id=%d\n", sensor, id);
+		return ERR_CAST(np);
 	}
 
-	for_each_available_child_of_node(np, child) {
-		struct thermal_zone_device *zone;
+	trips = thermal_of_trips_init(np, &ntrips);
+	if (IS_ERR(trips)) {
+		pr_err("Failed to find trip points for %pOFn id=%d\n", sensor, id);
+		return ERR_CAST(trips);
+	}
 
-		zone = thermal_zone_get_zone_by_name(child->name);
-		if (IS_ERR(zone))
-			continue;
+	ret = thermal_of_monitor_init(np, &delay, &pdelay);
+	if (ret) {
+		pr_err("Failed to initialize monitoring delays from %pOFn\n", np);
+		goto out_kfree_trips;
+	}
 
-		thermal_zone_device_unregister(zone);
-		kfree(zone->tzp);
-		kfree(zone->ops);
-		of_thermal_free_zone(zone->devdata);
+	tzp = thermal_of_parameters_init(np);
+	if (IS_ERR(tzp)) {
+		ret = PTR_ERR(tzp);
+		pr_err("Failed to initialize parameter from %pOFn: %d\n", np, ret);
+		goto out_kfree_trips;
 	}
-	of_node_put(np);
+
+	of_ops->get_trip_type = of_ops->get_trip_type ? : of_thermal_get_trip_type;
+	of_ops->get_trip_temp = of_ops->get_trip_temp ? : of_thermal_get_trip_temp;
+	of_ops->get_trip_hyst = of_ops->get_trip_hyst ? : of_thermal_get_trip_hyst;
+	of_ops->set_trip_hyst = of_ops->set_trip_hyst ? : of_thermal_set_trip_hyst;
+	of_ops->get_crit_temp = of_ops->get_crit_temp ? : of_thermal_get_crit_temp;
+	of_ops->bind = thermal_of_bind;
+	of_ops->unbind = thermal_of_unbind;
+
+	mask = GENMASK_ULL((ntrips) - 1, 0);
+
+	tz = thermal_zone_device_register_with_trips(np->name, trips, ntrips,
+						     mask, data, of_ops, tzp,
+						     pdelay, delay);
+	if (IS_ERR(tz)) {
+		ret = PTR_ERR(tz);
+		pr_err("Failed to register thermal zone %pOFn: %d\n", np, ret);
+		goto out_kfree_tzp;
+	}
+
+	ret = thermal_zone_device_enable(tz);
+	if (ret) {
+		pr_err("Failed to enabled thermal zone '%s', id=%d: %d\n",
+		       tz->type, tz->id, ret);
+		thermal_of_zone_unregister(tz);
+		return ERR_PTR(ret);
+	}
+
+	return tz;
+
+out_kfree_tzp:
+	kfree(tzp);
+out_kfree_trips:
+	kfree(trips);
+
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(thermal_of_zone_register);
+
+static void devm_thermal_of_zone_release(struct device *dev, void *res)
+{
+	thermal_of_zone_unregister(*(struct thermal_zone_device **)res);
+}
+
+static int devm_thermal_of_zone_match(struct device *dev, void *res,
+				      void *data)
+{
+	struct thermal_zone_device **r = res;
+
+	if (WARN_ON(!r || !*r))
+		return 0;
+
+	return *r == data;
 }
 
 /**
- * of_parse_thermal_zones - parse device tree thermal data
+ * devm_thermal_of_zone_register - register a thermal tied with the sensor life cycle
  *
- * Initialization function that can be called by machine initialization
- * code to parse thermal data and populate the thermal framework
- * with hardware thermal zones info. This function only parses thermal zones.
- * Cooling devices and sensor devices nodes are supposed to be parsed
- * by their respective drivers.
- *
- * Return: 0 on success, proper error code otherwise
+ * This function is the device version of the thermal_of_zone_register() function.
  *
+ * @dev: a device structure pointer to sensor to be tied with the thermal zone OF life cycle
+ * @sensor_id: the sensor identifier
+ * @data: a pointer to a private data to be stored in the thermal zone 'devdata' field
+ * @ops: a pointer to the ops structure associated with the sensor
  */
-int __init of_parse_thermal_zones(void)
+struct thermal_zone_device *devm_thermal_of_zone_register(struct device *dev, int sensor_id, void *data,
+							  const struct thermal_zone_device_ops *ops)
 {
-	struct device_node *np, *child;
-	struct __thermal_zone *tz;
-	struct thermal_zone_device_ops *ops;
-
-	np = of_find_node_by_name(NULL, "thermal-zones");
-	if (!np) {
-		pr_debug("unable to find thermal zones\n");
-		return 0; /* Run successfully on systems without thermal DT */
-	}
-
-	for_each_available_child_of_node(np, child) {
-		struct thermal_zone_device *zone;
-		struct thermal_zone_params *tzp;
-		int i, mask = 0;
-		u32 prop;
-
-		tz = thermal_of_build_thermal_zone(child);
-		if (IS_ERR(tz)) {
-			pr_err("failed to build thermal zone %pOFn: %ld\n",
-			       child,
-			       PTR_ERR(tz));
-			continue;
-		}
-
-		ops = kmemdup(&of_thermal_ops, sizeof(*ops), GFP_KERNEL);
-		if (!ops)
-			goto exit_free;
+	struct thermal_zone_device **ptr, *tzd;
 
-		tzp = kzalloc(sizeof(*tzp), GFP_KERNEL);
-		if (!tzp) {
-			kfree(ops);
-			goto exit_free;
-		}
+	ptr = devres_alloc(devm_thermal_of_zone_release, sizeof(*ptr),
+			   GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
 
-		/* No hwmon because there might be hwmon drivers registering */
-		tzp->no_hwmon = true;
-
-		if (!of_property_read_u32(child, "sustainable-power", &prop))
-			tzp->sustainable_power = prop;
-
-		for (i = 0; i < tz->ntrips; i++)
-			mask |= 1 << i;
-
-		/* these two are left for temperature drivers to use */
-		tzp->slope = tz->slope;
-		tzp->offset = tz->offset;
-
-		zone = thermal_zone_device_register_with_trips(child->name, tz->trips, tz->ntrips,
-							       mask, tz, ops, tzp, tz->passive_delay,
-							       tz->polling_delay);
-		if (IS_ERR(zone)) {
-			pr_err("Failed to build %pOFn zone %ld\n", child,
-			       PTR_ERR(zone));
-			kfree(tzp);
-			kfree(ops);
-			of_thermal_free_zone(tz);
-			/* attempting to build remaining zones still */
-		}
+	tzd = thermal_of_zone_register(dev->of_node, sensor_id, data, ops);
+	if (IS_ERR(tzd)) {
+		devres_free(ptr);
+		return tzd;
 	}
-	of_node_put(np);
-
-	return 0;
 
-exit_free:
-	of_node_put(child);
-	of_node_put(np);
-	of_thermal_free_zone(tz);
+	*ptr = tzd;
+	devres_add(dev, ptr);
 
-	/* no memory available, so free what we have built */
-	of_thermal_destroy_zones();
+	return tzd;
+}
+EXPORT_SYMBOL_GPL(devm_thermal_of_zone_register);
 
-	return -ENOMEM;
+/**
+ * devm_thermal_of_zone_unregister - Resource managed version of
+ *				thermal_of_zone_unregister().
+ * @dev: Device for which which resource was allocated.
+ * @tz: a pointer to struct thermal_zone where the sensor is registered.
+ *
+ * This function removes the sensor callbacks and private data from the
+ * thermal zone device registered with devm_thermal_zone_of_sensor_register()
+ * API. It will also silent the zone by remove the .get_temp() and .get_trend()
+ * thermal zone device callbacks.
+ * Normally this function will not need to be called and the resource
+ * management code will ensure that the resource is freed.
+ */
+void devm_thermal_of_zone_unregister(struct device *dev, struct thermal_zone_device *tz)
+{
+	WARN_ON(devres_release(dev, devm_thermal_of_zone_release,
+			       devm_thermal_of_zone_match, tz));
 }
+EXPORT_SYMBOL_GPL(devm_thermal_of_zone_unregister);
diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c
index 3a8d6e747c25..78c5841bdfae 100644
--- a/drivers/thermal/thermal_sysfs.c
+++ b/drivers/thermal/thermal_sysfs.c
@@ -49,7 +49,11 @@ static ssize_t
 mode_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct thermal_zone_device *tz = to_thermal_zone(dev);
-	int enabled = thermal_zone_device_is_enabled(tz);
+	int enabled;
+
+	mutex_lock(&tz->lock);
+	enabled = thermal_zone_device_is_enabled(tz);
+	mutex_unlock(&tz->lock);
 
 	return sprintf(buf, "%s\n", enabled ? "enabled" : "disabled");
 }
@@ -115,7 +119,7 @@ trip_point_temp_store(struct device *dev, struct device_attribute *attr,
 	int temperature, hyst = 0;
 	enum thermal_trip_type type;
 
-	if (!tz->ops->set_trip_temp)
+	if (!tz->ops->set_trip_temp && !tz->trips)
 		return -EPERM;
 
 	if (sscanf(attr->attr.name, "trip_point_%d_temp", &trip) != 1)
@@ -128,6 +132,9 @@ trip_point_temp_store(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
+	if (tz->trips)
+		tz->trips[trip].temperature = temperature;
+
 	if (tz->ops->get_trip_hyst) {
 		ret = tz->ops->get_trip_hyst(tz, trip, &hyst);
 		if (ret)
diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
index 703039d8b937..8a9055bd376e 100644
--- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
+++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c
@@ -65,10 +65,10 @@ static inline int ti_thermal_hotspot_temperature(int t, int s, int c)
 
 /* thermal zone ops */
 /* Get temperature callback function for thermal zone */
-static inline int __ti_thermal_get_temp(void *devdata, int *temp)
+static inline int __ti_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
 {
 	struct thermal_zone_device *pcb_tz = NULL;
-	struct ti_thermal_data *data = devdata;
+	struct ti_thermal_data *data = tz->devdata;
 	struct ti_bandgap *bgp;
 	const struct ti_temp_sensor *s;
 	int ret, tmp, slope, constant;
@@ -85,8 +85,8 @@ static inline int __ti_thermal_get_temp(void *devdata, int *temp)
 		return ret;
 
 	/* Default constants */
-	slope = thermal_zone_get_slope(data->ti_thermal);
-	constant = thermal_zone_get_offset(data->ti_thermal);
+	slope = thermal_zone_get_slope(tz);
+	constant = thermal_zone_get_offset(tz);
 
 	pcb_tz = data->pcb_tz;
 	/* In case pcb zone is available, use the extrapolation rule with it */
@@ -107,9 +107,9 @@ static inline int __ti_thermal_get_temp(void *devdata, int *temp)
 	return ret;
 }
 
-static int __ti_thermal_get_trend(void *p, int trip, enum thermal_trend *trend)
+static int __ti_thermal_get_trend(struct thermal_zone_device *tz, int trip, enum thermal_trend *trend)
 {
-	struct ti_thermal_data *data = p;
+	struct ti_thermal_data *data = tz->devdata;
 	struct ti_bandgap *bgp;
 	int id, tr, ret = 0;
 
@@ -130,7 +130,7 @@ static int __ti_thermal_get_trend(void *p, int trip, enum thermal_trend *trend)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops ti_of_thermal_ops = {
+static const struct thermal_zone_device_ops ti_of_thermal_ops = {
 	.get_temp = __ti_thermal_get_temp,
 	.get_trend = __ti_thermal_get_trend,
 };
@@ -170,7 +170,7 @@ int ti_thermal_expose_sensor(struct ti_bandgap *bgp, int id,
 		return -EINVAL;
 
 	/* in case this is specified by DT */
-	data->ti_thermal = devm_thermal_zone_of_sensor_register(bgp->dev, id,
+	data->ti_thermal = devm_thermal_of_zone_register(bgp->dev, id,
 					data, &ti_of_thermal_ops);
 	if (IS_ERR(data->ti_thermal)) {
 		dev_err(bgp->dev, "thermal zone device is NULL\n");
diff --git a/drivers/thermal/uniphier_thermal.c b/drivers/thermal/uniphier_thermal.c
index 4cae5561a2a3..4111d99ef50e 100644
--- a/drivers/thermal/uniphier_thermal.c
+++ b/drivers/thermal/uniphier_thermal.c
@@ -187,9 +187,9 @@ static void uniphier_tm_disable_sensor(struct uniphier_tm_dev *tdev)
 	usleep_range(1000, 2000);	/* The spec note says at least 1ms */
 }
 
-static int uniphier_tm_get_temp(void *data, int *out_temp)
+static int uniphier_tm_get_temp(struct thermal_zone_device *tz, int *out_temp)
 {
-	struct uniphier_tm_dev *tdev = data;
+	struct uniphier_tm_dev *tdev = tz->devdata;
 	struct regmap *map = tdev->regmap;
 	int ret;
 	u32 temp;
@@ -204,7 +204,7 @@ static int uniphier_tm_get_temp(void *data, int *out_temp)
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops uniphier_of_thermal_ops = {
+static const struct thermal_zone_device_ops uniphier_of_thermal_ops = {
 	.get_temp = uniphier_tm_get_temp,
 };
 
@@ -289,8 +289,8 @@ static int uniphier_tm_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, tdev);
 
-	tdev->tz_dev = devm_thermal_zone_of_sensor_register(dev, 0, tdev,
-						&uniphier_of_thermal_ops);
+	tdev->tz_dev = devm_thermal_of_zone_register(dev, 0, tdev,
+						     &uniphier_of_thermal_ops);
 	if (IS_ERR(tdev->tz_dev)) {
 		dev_err(dev, "failed to register sensor device\n");
 		return PTR_ERR(tdev->tz_dev);
diff --git a/drivers/thunderbolt/Kconfig b/drivers/thunderbolt/Kconfig
index e76a6c173637..f12d0a3ee3e2 100644
--- a/drivers/thunderbolt/Kconfig
+++ b/drivers/thunderbolt/Kconfig
@@ -29,8 +29,7 @@ config USB4_DEBUGFS_WRITE
 
 config USB4_KUNIT_TEST
 	bool "KUnit tests" if !KUNIT_ALL_TESTS
-	depends on (USB4=m || KUNIT=y)
-	depends on KUNIT
+	depends on USB4 && KUNIT=y
 	default KUNIT_ALL_TESTS
 
 config USB4_DMA_TEST
diff --git a/drivers/thunderbolt/acpi.c b/drivers/thunderbolt/acpi.c
index b1f0dc8df47c..7a8adf5ad5a0 100644
--- a/drivers/thunderbolt/acpi.c
+++ b/drivers/thunderbolt/acpi.c
@@ -42,7 +42,7 @@ static acpi_status tb_acpi_add_link(acpi_handle handle, u32 level, void *data,
 	 */
 	dev = acpi_get_first_physical_node(adev);
 	while (!dev) {
-		adev = adev->parent;
+		adev = acpi_dev_parent(adev);
 		if (!adev)
 			break;
 		dev = acpi_get_first_physical_node(adev);
diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c
index e5ede5debfb0..0c661a706160 100644
--- a/drivers/thunderbolt/ctl.c
+++ b/drivers/thunderbolt/ctl.c
@@ -407,7 +407,7 @@ static void tb_ctl_rx_submit(struct ctl_pkg *pkg)
 
 static int tb_async_error(const struct ctl_pkg *pkg)
 {
-	const struct cfg_error_pkg *error = (const struct cfg_error_pkg *)pkg;
+	const struct cfg_error_pkg *error = pkg->buffer;
 
 	if (pkg->frame.eof != TB_CFG_PKG_ERROR)
 		return false;
diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c
index ae38f0d25a8d..572b5896caa3 100644
--- a/drivers/thunderbolt/icm.c
+++ b/drivers/thunderbolt/icm.c
@@ -2529,6 +2529,7 @@ struct tb *icm_probe(struct tb_nhi *nhi)
 		tb->cm_ops = &icm_icl_ops;
 		break;
 
+	case PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_2C_NHI:
 	case PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_4C_NHI:
 		icm->is_supported = icm_tgl_is_supported;
 		icm->get_mode = icm_ar_get_mode;
diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h
index f09da5b62233..01190d9ced16 100644
--- a/drivers/thunderbolt/nhi.h
+++ b/drivers/thunderbolt/nhi.h
@@ -55,6 +55,7 @@ extern const struct tb_nhi_ops icl_nhi_ops;
  * need for the PCI quirk anymore as we will use ICM also on Apple
  * hardware.
  */
+#define PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_2C_NHI		0x1134
 #define PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_4C_NHI		0x1137
 #define PCI_DEVICE_ID_INTEL_WIN_RIDGE_2C_NHI            0x157d
 #define PCI_DEVICE_ID_INTEL_WIN_RIDGE_2C_BRIDGE         0x157e
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 244f8cd38b25..77d7f07ca075 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -2413,6 +2413,7 @@ int tb_switch_configure(struct tb_switch *sw)
 		 * additional capabilities.
 		 */
 		sw->config.cmuv = USB4_VERSION_1_0;
+		sw->config.plug_events_delay = 0xa;
 
 		/* Enumerate the switch */
 		ret = tb_sw_write(sw, (u32 *)&sw->config + 1, TB_CFG_SWITCH,
@@ -3786,14 +3787,18 @@ int tb_switch_pcie_l1_enable(struct tb_switch *sw)
  */
 int tb_switch_xhci_connect(struct tb_switch *sw)
 {
-	bool usb_port1, usb_port3, xhci_port1, xhci_port3;
 	struct tb_port *port1, *port3;
 	int ret;
 
+	if (sw->generation != 3)
+		return 0;
+
 	port1 = &sw->ports[1];
 	port3 = &sw->ports[3];
 
 	if (tb_switch_is_alpine_ridge(sw)) {
+		bool usb_port1, usb_port3, xhci_port1, xhci_port3;
+
 		usb_port1 = tb_lc_is_usb_plugged(port1);
 		usb_port3 = tb_lc_is_usb_plugged(port3);
 		xhci_port1 = tb_lc_is_xhci_connected(port1);
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index caa5c14ed57f..01c112e2e214 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -248,7 +248,7 @@ struct gsm_mux {
 	bool constipated;		/* Asked by remote to shut up */
 	bool has_devices;		/* Devices were registered */
 
-	spinlock_t tx_lock;
+	struct mutex tx_mutex;
 	unsigned int tx_bytes;		/* TX data outstanding */
 #define TX_THRESH_HI		8192
 #define TX_THRESH_LO		2048
@@ -256,7 +256,7 @@ struct gsm_mux {
 	struct list_head tx_data_list;	/* Pending data packets */
 
 	/* Control messages */
-	struct timer_list kick_timer;	/* Kick TX queuing on timeout */
+	struct delayed_work kick_timeout;	/* Kick TX queuing on timeout */
 	struct timer_list t2_timer;	/* Retransmit timer for commands */
 	int cretries;			/* Command retry counter */
 	struct gsm_control *pending_cmd;/* Our current pending command */
@@ -680,7 +680,6 @@ static int gsm_send(struct gsm_mux *gsm, int addr, int cr, int control)
 	struct gsm_msg *msg;
 	u8 *dp;
 	int ocr;
-	unsigned long flags;
 
 	msg = gsm_data_alloc(gsm, addr, 0, control);
 	if (!msg)
@@ -702,10 +701,10 @@ static int gsm_send(struct gsm_mux *gsm, int addr, int cr, int control)
 
 	gsm_print_packet("Q->", addr, cr, control, NULL, 0);
 
-	spin_lock_irqsave(&gsm->tx_lock, flags);
+	mutex_lock(&gsm->tx_mutex);
 	list_add_tail(&msg->list, &gsm->tx_ctrl_list);
 	gsm->tx_bytes += msg->len;
-	spin_unlock_irqrestore(&gsm->tx_lock, flags);
+	mutex_unlock(&gsm->tx_mutex);
 	gsmld_write_trigger(gsm);
 
 	return 0;
@@ -730,7 +729,7 @@ static void gsm_dlci_clear_queues(struct gsm_mux *gsm, struct gsm_dlci *dlci)
 	spin_unlock_irqrestore(&dlci->lock, flags);
 
 	/* Clear data packets in MUX write queue */
-	spin_lock_irqsave(&gsm->tx_lock, flags);
+	mutex_lock(&gsm->tx_mutex);
 	list_for_each_entry_safe(msg, nmsg, &gsm->tx_data_list, list) {
 		if (msg->addr != addr)
 			continue;
@@ -738,7 +737,7 @@ static void gsm_dlci_clear_queues(struct gsm_mux *gsm, struct gsm_dlci *dlci)
 		list_del(&msg->list);
 		kfree(msg);
 	}
-	spin_unlock_irqrestore(&gsm->tx_lock, flags);
+	mutex_unlock(&gsm->tx_mutex);
 }
 
 /**
@@ -1009,7 +1008,7 @@ static void __gsm_data_queue(struct gsm_dlci *dlci, struct gsm_msg *msg)
 	gsm->tx_bytes += msg->len;
 
 	gsmld_write_trigger(gsm);
-	mod_timer(&gsm->kick_timer, jiffies + 10 * gsm->t1 * HZ / 100);
+	schedule_delayed_work(&gsm->kick_timeout, 10 * gsm->t1 * HZ / 100);
 }
 
 /**
@@ -1024,10 +1023,9 @@ static void __gsm_data_queue(struct gsm_dlci *dlci, struct gsm_msg *msg)
 
 static void gsm_data_queue(struct gsm_dlci *dlci, struct gsm_msg *msg)
 {
-	unsigned long flags;
-	spin_lock_irqsave(&dlci->gsm->tx_lock, flags);
+	mutex_lock(&dlci->gsm->tx_mutex);
 	__gsm_data_queue(dlci, msg);
-	spin_unlock_irqrestore(&dlci->gsm->tx_lock, flags);
+	mutex_unlock(&dlci->gsm->tx_mutex);
 }
 
 /**
@@ -1039,7 +1037,7 @@ static void gsm_data_queue(struct gsm_dlci *dlci, struct gsm_msg *msg)
  *	is data. Keep to the MRU of the mux. This path handles the usual tty
  *	interface which is a byte stream with optional modem data.
  *
- *	Caller must hold the tx_lock of the mux.
+ *	Caller must hold the tx_mutex of the mux.
  */
 
 static int gsm_dlci_data_output(struct gsm_mux *gsm, struct gsm_dlci *dlci)
@@ -1099,7 +1097,7 @@ static int gsm_dlci_data_output(struct gsm_mux *gsm, struct gsm_dlci *dlci)
  *	is data. Keep to the MRU of the mux. This path handles framed data
  *	queued as skbuffs to the DLCI.
  *
- *	Caller must hold the tx_lock of the mux.
+ *	Caller must hold the tx_mutex of the mux.
  */
 
 static int gsm_dlci_data_output_framed(struct gsm_mux *gsm,
@@ -1115,7 +1113,7 @@ static int gsm_dlci_data_output_framed(struct gsm_mux *gsm,
 	if (dlci->adaption == 4)
 		overhead = 1;
 
-	/* dlci->skb is locked by tx_lock */
+	/* dlci->skb is locked by tx_mutex */
 	if (dlci->skb == NULL) {
 		dlci->skb = skb_dequeue_tail(&dlci->skb_list);
 		if (dlci->skb == NULL)
@@ -1169,7 +1167,7 @@ static int gsm_dlci_data_output_framed(struct gsm_mux *gsm,
  *	Push an empty frame in to the transmit queue to update the modem status
  *	bits and to transmit an optional break.
  *
- *	Caller must hold the tx_lock of the mux.
+ *	Caller must hold the tx_mutex of the mux.
  */
 
 static int gsm_dlci_modem_output(struct gsm_mux *gsm, struct gsm_dlci *dlci,
@@ -1283,13 +1281,12 @@ static int gsm_dlci_data_sweep(struct gsm_mux *gsm)
 
 static void gsm_dlci_data_kick(struct gsm_dlci *dlci)
 {
-	unsigned long flags;
 	int sweep;
 
 	if (dlci->constipated)
 		return;
 
-	spin_lock_irqsave(&dlci->gsm->tx_lock, flags);
+	mutex_lock(&dlci->gsm->tx_mutex);
 	/* If we have nothing running then we need to fire up */
 	sweep = (dlci->gsm->tx_bytes < TX_THRESH_LO);
 	if (dlci->gsm->tx_bytes == 0) {
@@ -1300,7 +1297,7 @@ static void gsm_dlci_data_kick(struct gsm_dlci *dlci)
 	}
 	if (sweep)
 		gsm_dlci_data_sweep(dlci->gsm);
-	spin_unlock_irqrestore(&dlci->gsm->tx_lock, flags);
+	mutex_unlock(&dlci->gsm->tx_mutex);
 }
 
 /*
@@ -1984,24 +1981,23 @@ static void gsm_dlci_command(struct gsm_dlci *dlci, const u8 *data, int len)
 }
 
 /**
- *	gsm_kick_timer	-	transmit if possible
- *	@t: timer contained in our gsm object
+ *	gsm_kick_timeout	-	transmit if possible
+ *	@work: work contained in our gsm object
  *
  *	Transmit data from DLCIs if the queue is empty. We can't rely on
  *	a tty wakeup except when we filled the pipe so we need to fire off
  *	new data ourselves in other cases.
  */
-static void gsm_kick_timer(struct timer_list *t)
+static void gsm_kick_timeout(struct work_struct *work)
 {
-	struct gsm_mux *gsm = from_timer(gsm, t, kick_timer);
-	unsigned long flags;
+	struct gsm_mux *gsm = container_of(work, struct gsm_mux, kick_timeout.work);
 	int sent = 0;
 
-	spin_lock_irqsave(&gsm->tx_lock, flags);
+	mutex_lock(&gsm->tx_mutex);
 	/* If we have nothing running then we need to fire up */
 	if (gsm->tx_bytes < TX_THRESH_LO)
 		sent = gsm_dlci_data_sweep(gsm);
-	spin_unlock_irqrestore(&gsm->tx_lock, flags);
+	mutex_unlock(&gsm->tx_mutex);
 
 	if (sent && debug & 4)
 		pr_info("%s TX queue stalled\n", __func__);
@@ -2458,7 +2454,7 @@ static void gsm_cleanup_mux(struct gsm_mux *gsm, bool disc)
 	}
 
 	/* Finish outstanding timers, making sure they are done */
-	del_timer_sync(&gsm->kick_timer);
+	cancel_delayed_work_sync(&gsm->kick_timeout);
 	del_timer_sync(&gsm->t2_timer);
 
 	/* Finish writing to ldisc */
@@ -2501,13 +2497,6 @@ static int gsm_activate_mux(struct gsm_mux *gsm)
 	if (dlci == NULL)
 		return -ENOMEM;
 
-	timer_setup(&gsm->kick_timer, gsm_kick_timer, 0);
-	timer_setup(&gsm->t2_timer, gsm_control_retransmit, 0);
-	INIT_WORK(&gsm->tx_work, gsmld_write_task);
-	init_waitqueue_head(&gsm->event);
-	spin_lock_init(&gsm->control_lock);
-	spin_lock_init(&gsm->tx_lock);
-
 	if (gsm->encoding == 0)
 		gsm->receive = gsm0_receive;
 	else
@@ -2538,6 +2527,7 @@ static void gsm_free_mux(struct gsm_mux *gsm)
 			break;
 		}
 	}
+	mutex_destroy(&gsm->tx_mutex);
 	mutex_destroy(&gsm->mutex);
 	kfree(gsm->txframe);
 	kfree(gsm->buf);
@@ -2609,9 +2599,15 @@ static struct gsm_mux *gsm_alloc_mux(void)
 	}
 	spin_lock_init(&gsm->lock);
 	mutex_init(&gsm->mutex);
+	mutex_init(&gsm->tx_mutex);
 	kref_init(&gsm->ref);
 	INIT_LIST_HEAD(&gsm->tx_ctrl_list);
 	INIT_LIST_HEAD(&gsm->tx_data_list);
+	INIT_DELAYED_WORK(&gsm->kick_timeout, gsm_kick_timeout);
+	timer_setup(&gsm->t2_timer, gsm_control_retransmit, 0);
+	INIT_WORK(&gsm->tx_work, gsmld_write_task);
+	init_waitqueue_head(&gsm->event);
+	spin_lock_init(&gsm->control_lock);
 
 	gsm->t1 = T1;
 	gsm->t2 = T2;
@@ -2636,6 +2632,7 @@ static struct gsm_mux *gsm_alloc_mux(void)
 	}
 	spin_unlock(&gsm_mux_lock);
 	if (i == MAX_MUX) {
+		mutex_destroy(&gsm->tx_mutex);
 		mutex_destroy(&gsm->mutex);
 		kfree(gsm->txframe);
 		kfree(gsm->buf);
@@ -2791,17 +2788,16 @@ static void gsmld_write_trigger(struct gsm_mux *gsm)
 static void gsmld_write_task(struct work_struct *work)
 {
 	struct gsm_mux *gsm = container_of(work, struct gsm_mux, tx_work);
-	unsigned long flags;
 	int i, ret;
 
 	/* All outstanding control channel and control messages and one data
 	 * frame is sent.
 	 */
 	ret = -ENODEV;
-	spin_lock_irqsave(&gsm->tx_lock, flags);
+	mutex_lock(&gsm->tx_mutex);
 	if (gsm->tty)
 		ret = gsm_data_kick(gsm);
-	spin_unlock_irqrestore(&gsm->tx_lock, flags);
+	mutex_unlock(&gsm->tx_mutex);
 
 	if (ret >= 0)
 		for (i = 0; i < NUM_DLCI; i++)
@@ -2858,7 +2854,8 @@ static void gsmld_receive_buf(struct tty_struct *tty, const unsigned char *cp,
 			flags = *fp++;
 		switch (flags) {
 		case TTY_NORMAL:
-			gsm->receive(gsm, *cp);
+			if (gsm->receive)
+				gsm->receive(gsm, *cp);
 			break;
 		case TTY_OVERRUN:
 		case TTY_BREAK:
@@ -2946,10 +2943,6 @@ static int gsmld_open(struct tty_struct *tty)
 
 	gsmld_attach_gsm(tty, gsm);
 
-	timer_setup(&gsm->kick_timer, gsm_kick_timer, 0);
-	timer_setup(&gsm->t2_timer, gsm_control_retransmit, 0);
-	INIT_WORK(&gsm->tx_work, gsmld_write_task);
-
 	return 0;
 }
 
@@ -3012,7 +3005,6 @@ static ssize_t gsmld_write(struct tty_struct *tty, struct file *file,
 			   const unsigned char *buf, size_t nr)
 {
 	struct gsm_mux *gsm = tty->disc_data;
-	unsigned long flags;
 	int space;
 	int ret;
 
@@ -3020,13 +3012,13 @@ static ssize_t gsmld_write(struct tty_struct *tty, struct file *file,
 		return -ENODEV;
 
 	ret = -ENOBUFS;
-	spin_lock_irqsave(&gsm->tx_lock, flags);
+	mutex_lock(&gsm->tx_mutex);
 	space = tty_write_room(tty);
 	if (space >= nr)
 		ret = tty->ops->write(tty, buf, nr);
 	else
 		set_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
-	spin_unlock_irqrestore(&gsm->tx_lock, flags);
+	mutex_unlock(&gsm->tx_mutex);
 
 	return ret;
 }
@@ -3323,14 +3315,13 @@ static struct tty_ldisc_ops tty_ldisc_packet = {
 static void gsm_modem_upd_via_data(struct gsm_dlci *dlci, u8 brk)
 {
 	struct gsm_mux *gsm = dlci->gsm;
-	unsigned long flags;
 
 	if (dlci->state != DLCI_OPEN || dlci->adaption != 2)
 		return;
 
-	spin_lock_irqsave(&gsm->tx_lock, flags);
+	mutex_lock(&gsm->tx_mutex);
 	gsm_dlci_modem_output(gsm, dlci, brk);
-	spin_unlock_irqrestore(&gsm->tx_lock, flags);
+	mutex_unlock(&gsm->tx_mutex);
 }
 
 /**
diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
index 0dcecbbc3967..f7fbef83583c 100644
--- a/drivers/tty/serial/8250/8250_omap.c
+++ b/drivers/tty/serial/8250/8250_omap.c
@@ -1334,6 +1334,7 @@ static int omap8250_probe(struct platform_device *pdev)
 	up.port.throttle = omap_8250_throttle;
 	up.port.unthrottle = omap_8250_unthrottle;
 	up.port.rs485_config = serial8250_em485_config;
+	up.port.rs485_supported = serial8250_em485_supported;
 	up.rs485_start_tx = serial8250_em485_start_tx;
 	up.rs485_stop_tx = serial8250_em485_stop_tx;
 	up.port.has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE);
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 30ba9eef7b39..7450d3853031 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -294,9 +294,6 @@ static int atmel_config_rs485(struct uart_port *port, struct ktermios *termios,
 
 	mode = atmel_uart_readl(port, ATMEL_US_MR);
 
-	/* Resetting serial mode to RS232 (0x0) */
-	mode &= ~ATMEL_US_USMODE;
-
 	if (rs485conf->flags & SER_RS485_ENABLED) {
 		dev_dbg(port->dev, "Setting UART to RS485\n");
 		if (rs485conf->flags & SER_RS485_RX_DURING_TX)
@@ -306,6 +303,7 @@ static int atmel_config_rs485(struct uart_port *port, struct ktermios *termios,
 
 		atmel_uart_writel(port, ATMEL_US_TTGR,
 				  rs485conf->delay_rts_after_send);
+		mode &= ~ATMEL_US_USMODE;
 		mode |= ATMEL_US_USMODE_RS485;
 	} else {
 		dev_dbg(port->dev, "Setting UART to RS232\n");
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index f6c33cd228c8..fbc4b071b330 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -1394,9 +1394,9 @@ static int lpuart_config_rs485(struct uart_port *port, struct ktermios *termios,
 		 * Note: UART is assumed to be active high.
 		 */
 		if (rs485->flags & SER_RS485_RTS_ON_SEND)
-			modem &= ~UARTMODEM_TXRTSPOL;
-		else if (rs485->flags & SER_RS485_RTS_AFTER_SEND)
 			modem |= UARTMODEM_TXRTSPOL;
+		else if (rs485->flags & SER_RS485_RTS_AFTER_SEND)
+			modem &= ~UARTMODEM_TXRTSPOL;
 	}
 
 	writeb(modem, sport->port.membase + UARTMODEM);
@@ -2191,6 +2191,7 @@ lpuart32_set_termios(struct uart_port *port, struct ktermios *termios,
 	uart_update_timeout(port, termios->c_cflag, baud);
 
 	/* wait transmit engin complete */
+	lpuart32_write(&sport->port, 0, UARTMODIR);
 	lpuart32_wait_bit_set(&sport->port, UARTSTAT, UARTSTAT_TC);
 
 	/* disable transmit and receive */
@@ -2723,14 +2724,15 @@ static int lpuart_probe(struct platform_device *pdev)
 		lpuart_reg.cons = LPUART_CONSOLE;
 		handler = lpuart_int;
 	}
-	ret = uart_add_one_port(&lpuart_reg, &sport->port);
-	if (ret)
-		goto failed_attach_port;
 
 	ret = lpuart_global_reset(sport);
 	if (ret)
 		goto failed_reset;
 
+	ret = uart_add_one_port(&lpuart_reg, &sport->port);
+	if (ret)
+		goto failed_attach_port;
+
 	ret = uart_get_rs485_mode(&sport->port);
 	if (ret)
 		goto failed_get_rs485;
@@ -2746,9 +2748,9 @@ static int lpuart_probe(struct platform_device *pdev)
 
 failed_irq_request:
 failed_get_rs485:
-failed_reset:
 	uart_remove_one_port(&lpuart_reg, &sport->port);
 failed_attach_port:
+failed_reset:
 	lpuart_disable_clks(sport);
 	return ret;
 }
diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c
index ad4f3567ff90..a5748e41483b 100644
--- a/drivers/tty/serial/serial-tegra.c
+++ b/drivers/tty/serial/serial-tegra.c
@@ -525,7 +525,7 @@ static void tegra_uart_tx_dma_complete(void *args)
 	count = tup->tx_bytes_requested - state.residue;
 	async_tx_ack(tup->tx_dma_desc);
 	spin_lock_irqsave(&tup->uport.lock, flags);
-	xmit->tail = (xmit->tail + count) & (UART_XMIT_SIZE - 1);
+	uart_xmit_advance(&tup->uport, count);
 	tup->tx_in_progress = 0;
 	if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
 		uart_write_wakeup(&tup->uport);
@@ -613,7 +613,6 @@ static unsigned int tegra_uart_tx_empty(struct uart_port *u)
 static void tegra_uart_stop_tx(struct uart_port *u)
 {
 	struct tegra_uart_port *tup = to_tegra_uport(u);
-	struct circ_buf *xmit = &tup->uport.state->xmit;
 	struct dma_tx_state state;
 	unsigned int count;
 
@@ -624,7 +623,7 @@ static void tegra_uart_stop_tx(struct uart_port *u)
 	dmaengine_tx_status(tup->tx_dma_chan, tup->tx_cookie, &state);
 	count = tup->tx_bytes_requested - state.residue;
 	async_tx_ack(tup->tx_dma_desc);
-	xmit->tail = (xmit->tail + count) & (UART_XMIT_SIZE - 1);
+	uart_xmit_advance(&tup->uport, count);
 	tup->tx_in_progress = 0;
 }
 
diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c
index 5c3a07546a58..4b1d4fe8458e 100644
--- a/drivers/tty/serial/sifive.c
+++ b/drivers/tty/serial/sifive.c
@@ -945,7 +945,7 @@ static int sifive_serial_probe(struct platform_device *pdev)
 		return PTR_ERR(base);
 	}
 
-	clk = devm_clk_get(&pdev->dev, NULL);
+	clk = devm_clk_get_enabled(&pdev->dev, NULL);
 	if (IS_ERR(clk)) {
 		dev_err(&pdev->dev, "unable to find controller clock\n");
 		return PTR_ERR(clk);
diff --git a/drivers/tty/serial/tegra-tcu.c b/drivers/tty/serial/tegra-tcu.c
index 4877c54c613d..889b701ba7c6 100644
--- a/drivers/tty/serial/tegra-tcu.c
+++ b/drivers/tty/serial/tegra-tcu.c
@@ -101,7 +101,7 @@ static void tegra_tcu_uart_start_tx(struct uart_port *port)
 			break;
 
 		tegra_tcu_write(tcu, &xmit->buf[xmit->tail], count);
-		xmit->tail = (xmit->tail + count) & (UART_XMIT_SIZE - 1);
+		uart_xmit_advance(port, count);
 	}
 
 	uart_write_wakeup(port);
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index 9fdecc795b6b..5e287dedce01 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -470,7 +470,6 @@ static void lookahead_bufs(struct tty_port *port, struct tty_buffer *head)
 
 	while (head) {
 		struct tty_buffer *next;
-		unsigned char *p, *f = NULL;
 		unsigned int count;
 
 		/*
@@ -489,11 +488,16 @@ static void lookahead_bufs(struct tty_port *port, struct tty_buffer *head)
 			continue;
 		}
 
-		p = char_buf_ptr(head, head->lookahead);
-		if (~head->flags & TTYB_NORMAL)
-			f = flag_buf_ptr(head, head->lookahead);
+		if (port->client_ops->lookahead_buf) {
+			unsigned char *p, *f = NULL;
+
+			p = char_buf_ptr(head, head->lookahead);
+			if (~head->flags & TTYB_NORMAL)
+				f = flag_buf_ptr(head, head->lookahead);
+
+			port->client_ops->lookahead_buf(port, p, f, count);
+		}
 
-		port->client_ops->lookahead_buf(port, p, f, count);
 		head->lookahead += count;
 	}
 }
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index ae9c926acd6f..0b669c82ddc9 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -4662,9 +4662,11 @@ static int con_font_set(struct vc_data *vc, struct console_font_op *op)
 	console_lock();
 	if (vc->vc_mode != KD_TEXT)
 		rc = -EINVAL;
-	else if (vc->vc_sw->con_font_set)
+	else if (vc->vc_sw->con_font_set) {
+		if (vc_is_sel(vc))
+			clear_selection();
 		rc = vc->vc_sw->con_font_set(vc, &font, op->flags);
-	else
+	} else
 		rc = -ENOSYS;
 	console_unlock();
 	kfree(font.data);
@@ -4691,9 +4693,11 @@ static int con_font_default(struct vc_data *vc, struct console_font_op *op)
 		console_unlock();
 		return -EINVAL;
 	}
-	if (vc->vc_sw->con_font_default)
+	if (vc->vc_sw->con_font_default) {
+		if (vc_is_sel(vc))
+			clear_selection();
 		rc = vc->vc_sw->con_font_default(vc, &font, s);
-	else
+	} else
 		rc = -ENOSYS;
 	console_unlock();
 	if (!rc) {
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 6bc679d22927..a202d7d5240d 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -8741,6 +8741,8 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 	struct scsi_device *sdp;
 	unsigned long flags;
 	int ret, retries;
+	unsigned long deadline;
+	int32_t remaining;
 
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	sdp = hba->ufs_device_wlun;
@@ -8773,9 +8775,14 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 	 * callbacks hence set the RQF_PM flag so that it doesn't resume the
 	 * already suspended childs.
 	 */
+	deadline = jiffies + 10 * HZ;
 	for (retries = 3; retries > 0; --retries) {
+		ret = -ETIMEDOUT;
+		remaining = deadline - jiffies;
+		if (remaining <= 0)
+			break;
 		ret = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr,
-				START_STOP_TIMEOUT, 0, 0, RQF_PM, NULL);
+				   remaining / HZ, 0, 0, RQF_PM, NULL);
 		if (!scsi_status_is_check_condition(ret) ||
 				!scsi_sense_valid(&sshdr) ||
 				sshdr.sense_key != UNIT_ATTENTION)
diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c
index eced97538082..c3628a8645a5 100644
--- a/drivers/ufs/host/ufs-exynos.c
+++ b/drivers/ufs/host/ufs-exynos.c
@@ -1711,7 +1711,7 @@ static struct exynos_ufs_uic_attr fsd_uic_attr = {
 	.pa_dbg_option_suite		= 0x2E820183,
 };
 
-struct exynos_ufs_drv_data fsd_ufs_drvs = {
+static const struct exynos_ufs_drv_data fsd_ufs_drvs = {
 	.uic_attr               = &fsd_uic_attr,
 	.quirks                 = UFSHCD_QUIRK_PRDT_BYTE_GRAN |
 				  UFSHCI_QUIRK_BROKEN_REQ_LIST_CLR |
diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index d21b69997e75..5adcb349718c 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -1530,7 +1530,8 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev,
 						TRB_LEN(le32_to_cpu(trb->length));
 
 				if (priv_req->num_of_trb > 1 &&
-					le32_to_cpu(trb->control) & TRB_SMM)
+					le32_to_cpu(trb->control) & TRB_SMM &&
+					le32_to_cpu(trb->control) & TRB_CHAIN)
 					transfer_end = true;
 
 				cdns3_ep_inc_deq(priv_ep);
@@ -1690,6 +1691,7 @@ static int cdns3_check_ep_interrupt_proceed(struct cdns3_endpoint *priv_ep)
 				ep_cfg &= ~EP_CFG_ENABLE;
 				writel(ep_cfg, &priv_dev->regs->ep_cfg);
 				priv_ep->flags &= ~EP_QUIRK_ISO_OUT_EN;
+				priv_ep->flags |= EP_UPDATE_EP_TRBADDR;
 			}
 			cdns3_transfer_completed(priv_dev, priv_ep);
 		} else if (!(priv_ep->flags & EP_STALLED) &&
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 483bcb1213f7..cc637c4599e1 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1810,6 +1810,9 @@ static const struct usb_device_id acm_ids[] = {
 	{ USB_DEVICE(0x09d8, 0x0320), /* Elatec GmbH TWN3 */
 	.driver_info = NO_UNION_NORMAL, /* has misplaced union descriptor */
 	},
+	{ USB_DEVICE(0x0c26, 0x0020), /* Icom ICF3400 Serie */
+	.driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */
+	},
 	{ USB_DEVICE(0x0ca6, 0xa050), /* Castles VEGA3000 */
 	.driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */
 	},
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 2633acde7ac1..bbab424b0d55 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -6038,6 +6038,11 @@ re_enumerate:
  * the reset is over (using their post_reset method).
  *
  * Return: The same as for usb_reset_and_verify_device().
+ * However, if a reset is already in progress (for instance, if a
+ * driver doesn't have pre_reset() or post_reset() callbacks, and while
+ * being unbound or re-bound during the ongoing reset its disconnect()
+ * or probe() routine tries to perform a second, nested reset), the
+ * routine returns -EINPROGRESS.
  *
  * Note:
  * The caller must own the device lock.  For example, it's safe to use
@@ -6071,6 +6076,10 @@ int usb_reset_device(struct usb_device *udev)
 		return -EISDIR;
 	}
 
+	if (udev->reset_in_progress)
+		return -EINPROGRESS;
+	udev->reset_in_progress = 1;
+
 	port_dev = hub->ports[udev->portnum - 1];
 
 	/*
@@ -6135,6 +6144,7 @@ int usb_reset_device(struct usb_device *udev)
 
 	usb_autosuspend_device(udev);
 	memalloc_noio_restore(noio_flag);
+	udev->reset_in_progress = 0;
 	return ret;
 }
 EXPORT_SYMBOL_GPL(usb_reset_device);
diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c
index c8ba87df7abe..fd0ccf6f3ec5 100644
--- a/drivers/usb/dwc2/platform.c
+++ b/drivers/usb/dwc2/platform.c
@@ -154,9 +154,9 @@ static int __dwc2_lowlevel_hw_enable(struct dwc2_hsotg *hsotg)
 	} else if (hsotg->plat && hsotg->plat->phy_init) {
 		ret = hsotg->plat->phy_init(pdev, hsotg->plat->phy_type);
 	} else {
-		ret = phy_power_on(hsotg->phy);
+		ret = phy_init(hsotg->phy);
 		if (ret == 0)
-			ret = phy_init(hsotg->phy);
+			ret = phy_power_on(hsotg->phy);
 	}
 
 	return ret;
@@ -188,9 +188,9 @@ static int __dwc2_lowlevel_hw_disable(struct dwc2_hsotg *hsotg)
 	} else if (hsotg->plat && hsotg->plat->phy_exit) {
 		ret = hsotg->plat->phy_exit(pdev, hsotg->plat->phy_type);
 	} else {
-		ret = phy_exit(hsotg->phy);
+		ret = phy_power_off(hsotg->phy);
 		if (ret == 0)
-			ret = phy_power_off(hsotg->phy);
+			ret = phy_exit(hsotg->phy);
 	}
 	if (ret)
 		return ret;
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index c5c238ab3083..d0237b30c9be 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -833,15 +833,16 @@ static void dwc3_core_exit(struct dwc3 *dwc)
 {
 	dwc3_event_buffers_cleanup(dwc);
 
+	usb_phy_set_suspend(dwc->usb2_phy, 1);
+	usb_phy_set_suspend(dwc->usb3_phy, 1);
+	phy_power_off(dwc->usb2_generic_phy);
+	phy_power_off(dwc->usb3_generic_phy);
+
 	usb_phy_shutdown(dwc->usb2_phy);
 	usb_phy_shutdown(dwc->usb3_phy);
 	phy_exit(dwc->usb2_generic_phy);
 	phy_exit(dwc->usb3_generic_phy);
 
-	usb_phy_set_suspend(dwc->usb2_phy, 1);
-	usb_phy_set_suspend(dwc->usb3_phy, 1);
-	phy_power_off(dwc->usb2_generic_phy);
-	phy_power_off(dwc->usb3_generic_phy);
 	dwc3_clk_disable(dwc);
 	reset_control_assert(dwc->reset);
 }
@@ -1751,12 +1752,6 @@ static int dwc3_probe(struct platform_device *pdev)
 
 	dwc3_get_properties(dwc);
 
-	if (!dwc->sysdev_is_parent) {
-		ret = dma_set_mask_and_coherent(dwc->sysdev, DMA_BIT_MASK(64));
-		if (ret)
-			return ret;
-	}
-
 	dwc->reset = devm_reset_control_array_get_optional_shared(dev);
 	if (IS_ERR(dwc->reset))
 		return PTR_ERR(dwc->reset);
@@ -1821,7 +1816,13 @@ static int dwc3_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, dwc);
 	dwc3_cache_hwparams(dwc);
-	device_init_wakeup(&pdev->dev, of_property_read_bool(dev->of_node, "wakeup-source"));
+
+	if (!dwc->sysdev_is_parent &&
+	    DWC3_GHWPARAMS0_AWIDTH(dwc->hwparams.hwparams0) == 64) {
+		ret = dma_set_mask_and_coherent(dwc->sysdev, DMA_BIT_MASK(64));
+		if (ret)
+			goto disable_clks;
+	}
 
 	spin_lock_init(&dwc->lock);
 	mutex_init(&dwc->mutex);
@@ -1879,16 +1880,16 @@ err5:
 	dwc3_debugfs_exit(dwc);
 	dwc3_event_buffers_cleanup(dwc);
 
-	usb_phy_shutdown(dwc->usb2_phy);
-	usb_phy_shutdown(dwc->usb3_phy);
-	phy_exit(dwc->usb2_generic_phy);
-	phy_exit(dwc->usb3_generic_phy);
-
 	usb_phy_set_suspend(dwc->usb2_phy, 1);
 	usb_phy_set_suspend(dwc->usb3_phy, 1);
 	phy_power_off(dwc->usb2_generic_phy);
 	phy_power_off(dwc->usb3_generic_phy);
 
+	usb_phy_shutdown(dwc->usb2_phy);
+	usb_phy_shutdown(dwc->usb3_phy);
+	phy_exit(dwc->usb2_generic_phy);
+	phy_exit(dwc->usb3_generic_phy);
+
 	dwc3_ulpi_exit(dwc);
 
 err4:
@@ -1983,7 +1984,7 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg)
 		dwc3_core_exit(dwc);
 		break;
 	case DWC3_GCTL_PRTCAP_HOST:
-		if (!PMSG_IS_AUTO(msg) && !device_can_wakeup(dwc->dev)) {
+		if (!PMSG_IS_AUTO(msg) && !device_may_wakeup(dwc->dev)) {
 			dwc3_core_exit(dwc);
 			break;
 		}
@@ -2044,7 +2045,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg)
 		spin_unlock_irqrestore(&dwc->lock, flags);
 		break;
 	case DWC3_GCTL_PRTCAP_HOST:
-		if (!PMSG_IS_AUTO(msg) && !device_can_wakeup(dwc->dev)) {
+		if (!PMSG_IS_AUTO(msg) && !device_may_wakeup(dwc->dev)) {
 			ret = dwc3_core_init_for_resume(dwc);
 			if (ret)
 				return ret;
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 6b018048fe2e..4ee4ca09873a 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -44,6 +44,7 @@
 #define PCI_DEVICE_ID_INTEL_ADLP		0x51ee
 #define PCI_DEVICE_ID_INTEL_ADLM		0x54ee
 #define PCI_DEVICE_ID_INTEL_ADLS		0x7ae1
+#define PCI_DEVICE_ID_INTEL_RPL			0x460e
 #define PCI_DEVICE_ID_INTEL_RPLS		0x7a61
 #define PCI_DEVICE_ID_INTEL_MTLP		0x7ec1
 #define PCI_DEVICE_ID_INTEL_MTL			0x7e7e
@@ -456,6 +457,9 @@ static const struct pci_device_id dwc3_pci_id_table[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ADLS),
 	  (kernel_ulong_t) &dwc3_pci_intel_swnode, },
 
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_RPL),
+	  (kernel_ulong_t) &dwc3_pci_intel_swnode, },
+
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_RPLS),
 	  (kernel_ulong_t) &dwc3_pci_intel_swnode, },
 
diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c
index c5e482f53e9d..d3f3937d7005 100644
--- a/drivers/usb/dwc3/dwc3-qcom.c
+++ b/drivers/usb/dwc3/dwc3-qcom.c
@@ -17,7 +17,6 @@
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/phy/phy.h>
-#include <linux/pm_domain.h>
 #include <linux/usb/of.h>
 #include <linux/reset.h>
 #include <linux/iopoll.h>
@@ -299,11 +298,24 @@ static void dwc3_qcom_interconnect_exit(struct dwc3_qcom *qcom)
 	icc_put(qcom->icc_path_apps);
 }
 
+/* Only usable in contexts where the role can not change. */
+static bool dwc3_qcom_is_host(struct dwc3_qcom *qcom)
+{
+	struct dwc3 *dwc = platform_get_drvdata(qcom->dwc3);
+
+	return dwc->xhci;
+}
+
 static enum usb_device_speed dwc3_qcom_read_usb2_speed(struct dwc3_qcom *qcom)
 {
 	struct dwc3 *dwc = platform_get_drvdata(qcom->dwc3);
-	struct usb_hcd *hcd = platform_get_drvdata(dwc->xhci);
 	struct usb_device *udev;
+	struct usb_hcd __maybe_unused *hcd;
+
+	/*
+	 * FIXME: Fix this layering violation.
+	 */
+	hcd = platform_get_drvdata(dwc->xhci);
 
 	/*
 	 * It is possible to query the speed of all children of
@@ -311,8 +323,11 @@ static enum usb_device_speed dwc3_qcom_read_usb2_speed(struct dwc3_qcom *qcom)
 	 * currently supports only 1 port per controller. So
 	 * this is sufficient.
 	 */
+#ifdef CONFIG_USB
 	udev = usb_hub_find_child(hcd->self.root_hub, 1);
-
+#else
+	udev = NULL;
+#endif
 	if (!udev)
 		return USB_SPEED_UNKNOWN;
 
@@ -387,7 +402,7 @@ static void dwc3_qcom_enable_interrupts(struct dwc3_qcom *qcom)
 	dwc3_qcom_enable_wakeup_irq(qcom->ss_phy_irq, 0);
 }
 
-static int dwc3_qcom_suspend(struct dwc3_qcom *qcom)
+static int dwc3_qcom_suspend(struct dwc3_qcom *qcom, bool wakeup)
 {
 	u32 val;
 	int i, ret;
@@ -406,7 +421,11 @@ static int dwc3_qcom_suspend(struct dwc3_qcom *qcom)
 	if (ret)
 		dev_warn(qcom->dev, "failed to disable interconnect: %d\n", ret);
 
-	if (device_may_wakeup(qcom->dev)) {
+	/*
+	 * The role is stable during suspend as role switching is done from a
+	 * freezable workqueue.
+	 */
+	if (dwc3_qcom_is_host(qcom) && wakeup) {
 		qcom->usb2_speed = dwc3_qcom_read_usb2_speed(qcom);
 		dwc3_qcom_enable_interrupts(qcom);
 	}
@@ -416,7 +435,7 @@ static int dwc3_qcom_suspend(struct dwc3_qcom *qcom)
 	return 0;
 }
 
-static int dwc3_qcom_resume(struct dwc3_qcom *qcom)
+static int dwc3_qcom_resume(struct dwc3_qcom *qcom, bool wakeup)
 {
 	int ret;
 	int i;
@@ -424,7 +443,7 @@ static int dwc3_qcom_resume(struct dwc3_qcom *qcom)
 	if (!qcom->is_suspended)
 		return 0;
 
-	if (device_may_wakeup(qcom->dev))
+	if (dwc3_qcom_is_host(qcom) && wakeup)
 		dwc3_qcom_disable_interrupts(qcom);
 
 	for (i = 0; i < qcom->num_clocks; i++) {
@@ -458,7 +477,11 @@ static irqreturn_t qcom_dwc3_resume_irq(int irq, void *data)
 	if (qcom->pm_suspended)
 		return IRQ_HANDLED;
 
-	if (dwc->xhci)
+	/*
+	 * This is safe as role switching is done from a freezable workqueue
+	 * and the wakeup interrupts are disabled as part of resume.
+	 */
+	if (dwc3_qcom_is_host(qcom))
 		pm_runtime_resume(&dwc->xhci->dev);
 
 	return IRQ_HANDLED;
@@ -757,13 +780,13 @@ dwc3_qcom_create_urs_usb_platdev(struct device *dev)
 
 static int dwc3_qcom_probe(struct platform_device *pdev)
 {
-	struct device_node *np = pdev->dev.of_node;
-	struct device *dev = &pdev->dev;
-	struct dwc3_qcom *qcom;
-	struct resource	*res, *parent_res = NULL;
-	int ret, i;
-	bool ignore_pipe_clk;
-	struct generic_pm_domain *genpd;
+	struct device_node	*np = pdev->dev.of_node;
+	struct device		*dev = &pdev->dev;
+	struct dwc3_qcom	*qcom;
+	struct resource		*res, *parent_res = NULL;
+	int			ret, i;
+	bool			ignore_pipe_clk;
+	bool			wakeup_source;
 
 	qcom = devm_kzalloc(&pdev->dev, sizeof(*qcom), GFP_KERNEL);
 	if (!qcom)
@@ -772,8 +795,6 @@ static int dwc3_qcom_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, qcom);
 	qcom->dev = &pdev->dev;
 
-	genpd = pd_to_genpd(qcom->dev->pm_domain);
-
 	if (has_acpi_companion(dev)) {
 		qcom->acpi_pdata = acpi_device_get_match_data(dev);
 		if (!qcom->acpi_pdata) {
@@ -881,16 +902,9 @@ static int dwc3_qcom_probe(struct platform_device *pdev)
 	if (ret)
 		goto interconnect_exit;
 
-	if (device_can_wakeup(&qcom->dwc3->dev)) {
-		/*
-		 * Setting GENPD_FLAG_ALWAYS_ON flag takes care of keeping
-		 * genpd on in both runtime suspend and system suspend cases.
-		 */
-		genpd->flags |= GENPD_FLAG_ALWAYS_ON;
-		device_init_wakeup(&pdev->dev, true);
-	} else {
-		genpd->flags |= GENPD_FLAG_RPM_ALWAYS_ON;
-	}
+	wakeup_source = of_property_read_bool(dev->of_node, "wakeup-source");
+	device_init_wakeup(&pdev->dev, wakeup_source);
+	device_init_wakeup(&qcom->dwc3->dev, wakeup_source);
 
 	qcom->is_suspended = false;
 	pm_runtime_set_active(dev);
@@ -944,39 +958,45 @@ static int dwc3_qcom_remove(struct platform_device *pdev)
 static int __maybe_unused dwc3_qcom_pm_suspend(struct device *dev)
 {
 	struct dwc3_qcom *qcom = dev_get_drvdata(dev);
-	int ret = 0;
+	bool wakeup = device_may_wakeup(dev);
+	int ret;
 
-	ret = dwc3_qcom_suspend(qcom);
-	if (!ret)
-		qcom->pm_suspended = true;
+	ret = dwc3_qcom_suspend(qcom, wakeup);
+	if (ret)
+		return ret;
 
-	return ret;
+	qcom->pm_suspended = true;
+
+	return 0;
 }
 
 static int __maybe_unused dwc3_qcom_pm_resume(struct device *dev)
 {
 	struct dwc3_qcom *qcom = dev_get_drvdata(dev);
+	bool wakeup = device_may_wakeup(dev);
 	int ret;
 
-	ret = dwc3_qcom_resume(qcom);
-	if (!ret)
-		qcom->pm_suspended = false;
+	ret = dwc3_qcom_resume(qcom, wakeup);
+	if (ret)
+		return ret;
 
-	return ret;
+	qcom->pm_suspended = false;
+
+	return 0;
 }
 
 static int __maybe_unused dwc3_qcom_runtime_suspend(struct device *dev)
 {
 	struct dwc3_qcom *qcom = dev_get_drvdata(dev);
 
-	return dwc3_qcom_suspend(qcom);
+	return dwc3_qcom_suspend(qcom, true);
 }
 
 static int __maybe_unused dwc3_qcom_runtime_resume(struct device *dev)
 {
 	struct dwc3_qcom *qcom = dev_get_drvdata(dev);
 
-	return dwc3_qcom_resume(qcom);
+	return dwc3_qcom_resume(qcom, true);
 }
 
 static const struct dev_pm_ops dwc3_qcom_dev_pm_ops = {
diff --git a/drivers/usb/dwc3/dwc3-st.c b/drivers/usb/dwc3/dwc3-st.c
index 166b5bde45cb..6c14a79279f9 100644
--- a/drivers/usb/dwc3/dwc3-st.c
+++ b/drivers/usb/dwc3/dwc3-st.c
@@ -251,7 +251,7 @@ static int st_dwc3_probe(struct platform_device *pdev)
 	/* Manage SoftReset */
 	reset_control_deassert(dwc3_data->rstc_rst);
 
-	child = of_get_child_by_name(node, "dwc3");
+	child = of_get_child_by_name(node, "usb");
 	if (!child) {
 		dev_err(&pdev->dev, "failed to find dwc3 core node\n");
 		ret = -ENODEV;
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index aeeec751c53c..eca945feeec3 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2539,9 +2539,6 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on)
 
 	is_on = !!is_on;
 
-	if (dwc->pullups_connected == is_on)
-		return 0;
-
 	dwc->softconnect = is_on;
 
 	/*
@@ -2566,6 +2563,11 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on)
 		return 0;
 	}
 
+	if (dwc->pullups_connected == is_on) {
+		pm_runtime_put(dwc->dev);
+		return 0;
+	}
+
 	if (!is_on) {
 		ret = dwc3_gadget_soft_disconnect(dwc);
 	} else {
diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c
index f56c30cf151e..a7154fe8206d 100644
--- a/drivers/usb/dwc3/host.c
+++ b/drivers/usb/dwc3/host.c
@@ -11,8 +11,13 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 
+#include "../host/xhci-plat.h"
 #include "core.h"
 
+static const struct xhci_plat_priv dwc3_xhci_plat_priv = {
+	.quirks = XHCI_SKIP_PHY_INIT,
+};
+
 static void dwc3_host_fill_xhci_irq_res(struct dwc3 *dwc,
 					int irq, char *name)
 {
@@ -92,6 +97,11 @@ int dwc3_host_init(struct dwc3 *dwc)
 		goto err;
 	}
 
+	ret = platform_device_add_data(xhci, &dwc3_xhci_plat_priv,
+					sizeof(dwc3_xhci_plat_priv));
+	if (ret)
+		goto err;
+
 	memset(props, 0, sizeof(struct property_entry) * ARRAY_SIZE(props));
 
 	if (dwc->usb3_lpm_capable)
@@ -135,4 +145,5 @@ err:
 void dwc3_host_exit(struct dwc3 *dwc)
 {
 	platform_device_unregister(dwc->xhci);
+	dwc->xhci = NULL;
 }
diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c
index 1905a8d8e0c9..08726e4c68a5 100644
--- a/drivers/usb/gadget/function/f_uac2.c
+++ b/drivers/usb/gadget/function/f_uac2.c
@@ -291,6 +291,12 @@ static struct usb_endpoint_descriptor ss_ep_int_desc = {
 	.bInterval = 4,
 };
 
+static struct usb_ss_ep_comp_descriptor ss_ep_int_desc_comp = {
+	.bLength = sizeof(ss_ep_int_desc_comp),
+	.bDescriptorType = USB_DT_SS_ENDPOINT_COMP,
+	.wBytesPerInterval = cpu_to_le16(6),
+};
+
 /* Audio Streaming OUT Interface - Alt0 */
 static struct usb_interface_descriptor std_as_out_if0_desc = {
 	.bLength = sizeof std_as_out_if0_desc,
@@ -604,7 +610,8 @@ static struct usb_descriptor_header *ss_audio_desc[] = {
 	(struct usb_descriptor_header *)&in_feature_unit_desc,
 	(struct usb_descriptor_header *)&io_out_ot_desc,
 
-  (struct usb_descriptor_header *)&ss_ep_int_desc,
+	(struct usb_descriptor_header *)&ss_ep_int_desc,
+	(struct usb_descriptor_header *)&ss_ep_int_desc_comp,
 
 	(struct usb_descriptor_header *)&std_as_out_if0_desc,
 	(struct usb_descriptor_header *)&std_as_out_if1_desc,
@@ -800,6 +807,7 @@ static void setup_headers(struct f_uac2_opts *opts,
 	struct usb_ss_ep_comp_descriptor *epout_desc_comp = NULL;
 	struct usb_ss_ep_comp_descriptor *epin_desc_comp = NULL;
 	struct usb_ss_ep_comp_descriptor *epin_fback_desc_comp = NULL;
+	struct usb_ss_ep_comp_descriptor *ep_int_desc_comp = NULL;
 	struct usb_endpoint_descriptor *epout_desc;
 	struct usb_endpoint_descriptor *epin_desc;
 	struct usb_endpoint_descriptor *epin_fback_desc;
@@ -827,6 +835,7 @@ static void setup_headers(struct f_uac2_opts *opts,
 		epin_fback_desc = &ss_epin_fback_desc;
 		epin_fback_desc_comp = &ss_epin_fback_desc_comp;
 		ep_int_desc = &ss_ep_int_desc;
+		ep_int_desc_comp = &ss_ep_int_desc_comp;
 	}
 
 	i = 0;
@@ -855,8 +864,11 @@ static void setup_headers(struct f_uac2_opts *opts,
 	if (EPOUT_EN(opts))
 		headers[i++] = USBDHDR(&io_out_ot_desc);
 
-	if (FUOUT_EN(opts) || FUIN_EN(opts))
+	if (FUOUT_EN(opts) || FUIN_EN(opts)) {
 		headers[i++] = USBDHDR(ep_int_desc);
+		if (ep_int_desc_comp)
+			headers[i++] = USBDHDR(ep_int_desc_comp);
+	}
 
 	if (EPOUT_EN(opts)) {
 		headers[i++] = USBDHDR(&std_as_out_if0_desc);
diff --git a/drivers/usb/gadget/function/storage_common.c b/drivers/usb/gadget/function/storage_common.c
index 03035dbbe97b..208c6a92780a 100644
--- a/drivers/usb/gadget/function/storage_common.c
+++ b/drivers/usb/gadget/function/storage_common.c
@@ -294,8 +294,10 @@ EXPORT_SYMBOL_GPL(fsg_lun_fsync_sub);
 void store_cdrom_address(u8 *dest, int msf, u32 addr)
 {
 	if (msf) {
-		/* Convert to Minutes-Seconds-Frames */
-		addr >>= 2;		/* Convert to 2048-byte frames */
+		/*
+		 * Convert to Minutes-Seconds-Frames.
+		 * Sector size is already set to 2048 bytes.
+		 */
 		addr += 2*75;		/* Lead-in occupies 2 seconds */
 		dest[3] = addr % 75;	/* Frames */
 		addr /= 75;
diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index cafcf260394c..c63c0c2cf649 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -736,7 +736,10 @@ int usb_gadget_disconnect(struct usb_gadget *gadget)
 	ret = gadget->ops->pullup(gadget, 0);
 	if (!ret) {
 		gadget->connected = 0;
-		gadget->udc->driver->disconnect(gadget);
+		mutex_lock(&udc_lock);
+		if (gadget->udc->driver)
+			gadget->udc->driver->disconnect(gadget);
+		mutex_unlock(&udc_lock);
 	}
 
 out:
@@ -1489,7 +1492,6 @@ static int gadget_bind_driver(struct device *dev)
 
 	usb_gadget_udc_set_speed(udc, driver->max_speed);
 
-	mutex_lock(&udc_lock);
 	ret = driver->bind(udc->gadget, driver);
 	if (ret)
 		goto err_bind;
@@ -1499,7 +1501,6 @@ static int gadget_bind_driver(struct device *dev)
 		goto err_start;
 	usb_gadget_enable_async_callbacks(udc);
 	usb_udc_connect_control(udc);
-	mutex_unlock(&udc_lock);
 
 	kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
 	return 0;
@@ -1512,6 +1513,7 @@ static int gadget_bind_driver(struct device *dev)
 		dev_err(&udc->dev, "failed to start %s: %d\n",
 			driver->function, ret);
 
+	mutex_lock(&udc_lock);
 	udc->driver = NULL;
 	driver->is_bound = false;
 	mutex_unlock(&udc_lock);
@@ -1529,7 +1531,6 @@ static void gadget_unbind_driver(struct device *dev)
 
 	kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
 
-	mutex_lock(&udc_lock);
 	usb_gadget_disconnect(gadget);
 	usb_gadget_disable_async_callbacks(udc);
 	if (gadget->irq)
@@ -1537,6 +1538,7 @@ static void gadget_unbind_driver(struct device *dev)
 	udc->driver->unbind(gadget);
 	usb_gadget_udc_stop(udc);
 
+	mutex_lock(&udc_lock);
 	driver->is_bound = false;
 	udc->driver = NULL;
 	mutex_unlock(&udc_lock);
@@ -1612,7 +1614,7 @@ static ssize_t soft_connect_store(struct device *dev,
 	struct usb_udc		*udc = container_of(dev, struct usb_udc, dev);
 	ssize_t			ret;
 
-	mutex_lock(&udc_lock);
+	device_lock(&udc->gadget->dev);
 	if (!udc->driver) {
 		dev_err(dev, "soft-connect without a gadget driver\n");
 		ret = -EOPNOTSUPP;
@@ -1633,7 +1635,7 @@ static ssize_t soft_connect_store(struct device *dev,
 
 	ret = n;
 out:
-	mutex_unlock(&udc_lock);
+	device_unlock(&udc->gadget->dev);
 	return ret;
 }
 static DEVICE_ATTR_WO(soft_connect);
@@ -1652,11 +1654,15 @@ static ssize_t function_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
 	struct usb_udc		*udc = container_of(dev, struct usb_udc, dev);
-	struct usb_gadget_driver *drv = udc->driver;
+	struct usb_gadget_driver *drv;
+	int			rc = 0;
 
-	if (!drv || !drv->function)
-		return 0;
-	return scnprintf(buf, PAGE_SIZE, "%s\n", drv->function);
+	mutex_lock(&udc_lock);
+	drv = udc->driver;
+	if (drv && drv->function)
+		rc = scnprintf(buf, PAGE_SIZE, "%s\n", drv->function);
+	mutex_unlock(&udc_lock);
+	return rc;
 }
 static DEVICE_ATTR_RO(function);
 
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 0fdc014c9401..4619d5e89d5b 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -652,7 +652,7 @@ struct xhci_hub *xhci_get_rhub(struct usb_hcd *hcd)
  * It will release and re-aquire the lock while calling ACPI
  * method.
  */
-void xhci_set_port_power(struct xhci_hcd *xhci, struct usb_hcd *hcd,
+static void xhci_set_port_power(struct xhci_hcd *xhci, struct usb_hcd *hcd,
 				u16 index, bool on, unsigned long *flags)
 	__must_hold(&xhci->lock)
 {
@@ -1648,6 +1648,17 @@ int xhci_hub_status_data(struct usb_hcd *hcd, char *buf)
 
 	status = bus_state->resuming_ports;
 
+	/*
+	 * SS devices are only visible to roothub after link training completes.
+	 * Keep polling roothubs for a grace period after xHC start
+	 */
+	if (xhci->run_graceperiod) {
+		if (time_before(jiffies, xhci->run_graceperiod))
+			status = 1;
+		else
+			xhci->run_graceperiod = 0;
+	}
+
 	mask = PORT_CSC | PORT_PEC | PORT_OCC | PORT_PLC | PORT_WRC | PORT_CEC;
 
 	/* For each port, did anything change?  If so, set that bit in buf. */
diff --git a/drivers/usb/host/xhci-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c
index 06a6b19acaae..579899eb24c1 100644
--- a/drivers/usb/host/xhci-mtk-sch.c
+++ b/drivers/usb/host/xhci-mtk-sch.c
@@ -425,7 +425,6 @@ static int check_fs_bus_bw(struct mu3h_sch_ep_info *sch_ep, int offset)
 
 static int check_sch_tt(struct mu3h_sch_ep_info *sch_ep, u32 offset)
 {
-	u32 extra_cs_count;
 	u32 start_ss, last_ss;
 	u32 start_cs, last_cs;
 
@@ -461,18 +460,12 @@ static int check_sch_tt(struct mu3h_sch_ep_info *sch_ep, u32 offset)
 		if (last_cs > 7)
 			return -ESCH_CS_OVERFLOW;
 
-		if (sch_ep->ep_type == ISOC_IN_EP)
-			extra_cs_count = (last_cs == 7) ? 1 : 2;
-		else /*  ep_type : INTR IN / INTR OUT */
-			extra_cs_count = 1;
-
-		cs_count += extra_cs_count;
 		if (cs_count > 7)
 			cs_count = 7; /* HW limit */
 
 		sch_ep->cs_count = cs_count;
-		/* one for ss, the other for idle */
-		sch_ep->num_budget_microframes = cs_count + 2;
+		/* ss, idle are ignored */
+		sch_ep->num_budget_microframes = cs_count;
 
 		/*
 		 * if interval=1, maxp >752, num_budge_micoframe is larger
@@ -771,8 +764,8 @@ int xhci_mtk_drop_ep(struct usb_hcd *hcd, struct usb_device *udev,
 	if (ret)
 		return ret;
 
-	if (ep->hcpriv)
-		drop_ep_quirk(hcd, udev, ep);
+	/* needn't check @ep->hcpriv, xhci_endpoint_disable set it NULL */
+	drop_ep_quirk(hcd, udev, ep);
 
 	return 0;
 }
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 044855818cb1..a8641b6536ee 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -398,12 +398,17 @@ static int xhci_plat_remove(struct platform_device *dev)
 	pm_runtime_get_sync(&dev->dev);
 	xhci->xhc_state |= XHCI_STATE_REMOVING;
 
-	usb_remove_hcd(shared_hcd);
-	xhci->shared_hcd = NULL;
+	if (shared_hcd) {
+		usb_remove_hcd(shared_hcd);
+		xhci->shared_hcd = NULL;
+	}
+
 	usb_phy_shutdown(hcd->usb_phy);
 
 	usb_remove_hcd(hcd);
-	usb_put_hcd(shared_hcd);
+
+	if (shared_hcd)
+		usb_put_hcd(shared_hcd);
 
 	clk_disable_unprepare(clk);
 	clk_disable_unprepare(reg_clk);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 65858f607437..38649284ff88 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -151,9 +151,11 @@ int xhci_start(struct xhci_hcd *xhci)
 		xhci_err(xhci, "Host took too long to start, "
 				"waited %u microseconds.\n",
 				XHCI_MAX_HALT_USEC);
-	if (!ret)
+	if (!ret) {
 		/* clear state flags. Including dying, halted or removing */
 		xhci->xhc_state = 0;
+		xhci->run_graceperiod = jiffies + msecs_to_jiffies(500);
+	}
 
 	return ret;
 }
@@ -791,8 +793,6 @@ static void xhci_stop(struct usb_hcd *hcd)
 void xhci_shutdown(struct usb_hcd *hcd)
 {
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
-	unsigned long flags;
-	int i;
 
 	if (xhci->quirks & XHCI_SPURIOUS_REBOOT)
 		usb_disable_xhci_ports(to_pci_dev(hcd->self.sysdev));
@@ -808,21 +808,12 @@ void xhci_shutdown(struct usb_hcd *hcd)
 		del_timer_sync(&xhci->shared_hcd->rh_timer);
 	}
 
-	spin_lock_irqsave(&xhci->lock, flags);
+	spin_lock_irq(&xhci->lock);
 	xhci_halt(xhci);
-
-	/* Power off USB2 ports*/
-	for (i = 0; i < xhci->usb2_rhub.num_ports; i++)
-		xhci_set_port_power(xhci, xhci->main_hcd, i, false, &flags);
-
-	/* Power off USB3 ports*/
-	for (i = 0; i < xhci->usb3_rhub.num_ports; i++)
-		xhci_set_port_power(xhci, xhci->shared_hcd, i, false, &flags);
-
 	/* Workaround for spurious wakeups at shutdown with HSW */
 	if (xhci->quirks & XHCI_SPURIOUS_WAKEUP)
 		xhci_reset(xhci, XHCI_RESET_SHORT_USEC);
-	spin_unlock_irqrestore(&xhci->lock, flags);
+	spin_unlock_irq(&xhci->lock);
 
 	xhci_cleanup_msix(xhci);
 
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 1960b47acfb2..7caa0db5e826 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1826,7 +1826,7 @@ struct xhci_hcd {
 
 	/* Host controller watchdog timer structures */
 	unsigned int		xhc_state;
-
+	unsigned long		run_graceperiod;
 	u32			command;
 	struct s3_save		s3;
 /* Host controller is dying - not responding to commands. "I'm not dead yet!"
@@ -2196,8 +2196,6 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, u16 wIndex,
 int xhci_hub_status_data(struct usb_hcd *hcd, char *buf);
 int xhci_find_raw_port_number(struct usb_hcd *hcd, int port1);
 struct xhci_hub *xhci_get_rhub(struct usb_hcd *hcd);
-void xhci_set_port_power(struct xhci_hcd *xhci, struct usb_hcd *hcd, u16 index,
-			 bool on, unsigned long *flags);
 
 void xhci_hc_died(struct xhci_hcd *xhci);
 
diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c
index d1df153e7f5a..d63c63942af1 100644
--- a/drivers/usb/misc/onboard_usb_hub.c
+++ b/drivers/usb/misc/onboard_usb_hub.c
@@ -71,10 +71,7 @@ static int onboard_hub_power_off(struct onboard_hub *hub)
 {
 	int err;
 
-	if (hub->reset_gpio) {
-		gpiod_set_value_cansleep(hub->reset_gpio, 1);
-		fsleep(hub->pdata->reset_us);
-	}
+	gpiod_set_value_cansleep(hub->reset_gpio, 1);
 
 	err = regulator_disable(hub->vdd);
 	if (err) {
diff --git a/drivers/usb/musb/Kconfig b/drivers/usb/musb/Kconfig
index f906dfd360d3..6c8f7763e75e 100644
--- a/drivers/usb/musb/Kconfig
+++ b/drivers/usb/musb/Kconfig
@@ -86,7 +86,7 @@ config USB_MUSB_TUSB6010
 	tristate "TUSB6010"
 	depends on HAS_IOMEM
 	depends on ARCH_OMAP2PLUS || COMPILE_TEST
-	depends on NOP_USB_XCEIV = USB_MUSB_HDRC # both built-in or both modules
+	depends on NOP_USB_XCEIV!=m || USB_MUSB_HDRC=m
 
 config USB_MUSB_OMAP2PLUS
 	tristate "OMAP2430 and onwards"
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index 2798fca71261..af01a462cc43 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -97,7 +97,10 @@ struct ch341_private {
 	u8 mcr;
 	u8 msr;
 	u8 lcr;
+
 	unsigned long quirks;
+	u8 version;
+
 	unsigned long break_end;
 };
 
@@ -250,8 +253,12 @@ static int ch341_set_baudrate_lcr(struct usb_device *dev,
 	/*
 	 * CH341A buffers data until a full endpoint-size packet (32 bytes)
 	 * has been received unless bit 7 is set.
+	 *
+	 * At least one device with version 0x27 appears to have this bit
+	 * inverted.
 	 */
-	val |= BIT(7);
+	if (priv->version > 0x27)
+		val |= BIT(7);
 
 	r = ch341_control_out(dev, CH341_REQ_WRITE_REG,
 			      CH341_REG_DIVISOR << 8 | CH341_REG_PRESCALER,
@@ -265,6 +272,9 @@ static int ch341_set_baudrate_lcr(struct usb_device *dev,
 	 * (stop bits, parity and word length). Version 0x30 and above use
 	 * CH341_REG_LCR only and CH341_REG_LCR2 is always set to zero.
 	 */
+	if (priv->version < 0x30)
+		return 0;
+
 	r = ch341_control_out(dev, CH341_REQ_WRITE_REG,
 			      CH341_REG_LCR2 << 8 | CH341_REG_LCR, lcr);
 	if (r)
@@ -308,7 +318,9 @@ static int ch341_configure(struct usb_device *dev, struct ch341_private *priv)
 	r = ch341_control_in(dev, CH341_REQ_READ_VERSION, 0, 0, buffer, size);
 	if (r)
 		return r;
-	dev_dbg(&dev->dev, "Chip version: 0x%02x\n", buffer[0]);
+
+	priv->version = buffer[0];
+	dev_dbg(&dev->dev, "Chip version: 0x%02x\n", priv->version);
 
 	r = ch341_control_out(dev, CH341_REQ_SERIAL_INIT, 0, 0);
 	if (r < 0)
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index c374620a486f..a34957c4b64c 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -130,6 +130,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x83AA) }, /* Mark-10 Digital Force Gauge */
 	{ USB_DEVICE(0x10C4, 0x83D8) }, /* DekTec DTA Plus VHF/UHF Booster/Attenuator */
 	{ USB_DEVICE(0x10C4, 0x8411) }, /* Kyocera GPS Module */
+	{ USB_DEVICE(0x10C4, 0x8414) }, /* Decagon USB Cable Adapter */
 	{ USB_DEVICE(0x10C4, 0x8418) }, /* IRZ Automation Teleport SG-10 GSM/GPRS Modem */
 	{ USB_DEVICE(0x10C4, 0x846E) }, /* BEI USB Sensor Interface (VCP) */
 	{ USB_DEVICE(0x10C4, 0x8470) }, /* Juniper Networks BX Series System Console */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index d5a3986dfee7..52d59be92034 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1045,6 +1045,8 @@ static const struct usb_device_id id_table_combined[] = {
 	/* IDS GmbH devices */
 	{ USB_DEVICE(IDS_VID, IDS_SI31A_PID) },
 	{ USB_DEVICE(IDS_VID, IDS_CM31A_PID) },
+	/* Omron devices */
+	{ USB_DEVICE(OMRON_VID, OMRON_CS1W_CIF31_PID) },
 	/* U-Blox devices */
 	{ USB_DEVICE(UBLOX_VID, UBLOX_C099F9P_ZED_PID) },
 	{ USB_DEVICE(UBLOX_VID, UBLOX_C099F9P_ODIN_PID) },
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 4e92c165c86b..31c8ccabbbb7 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -662,6 +662,12 @@
 #define INFINEON_TRIBOARD_TC2X7_PID	0x0043 /* DAS JTAG TriBoard TC2X7 V1.0 */
 
 /*
+ * Omron corporation (https://www.omron.com)
+ */
+ #define OMRON_VID			0x0590
+ #define OMRON_CS1W_CIF31_PID		0x00b2
+
+/*
  * Acton Research Corp.
  */
 #define ACTON_VID		0x0647	/* Vendor ID */
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index de59fa919540..697683e3fbff 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -253,8 +253,10 @@ static void option_instat_callback(struct urb *urb);
 #define QUECTEL_PRODUCT_BG96			0x0296
 #define QUECTEL_PRODUCT_EP06			0x0306
 #define QUECTEL_PRODUCT_EM05G			0x030a
+#define QUECTEL_PRODUCT_EM060K			0x030b
 #define QUECTEL_PRODUCT_EM12			0x0512
 #define QUECTEL_PRODUCT_RM500Q			0x0800
+#define QUECTEL_PRODUCT_RM520N			0x0801
 #define QUECTEL_PRODUCT_EC200S_CN		0x6002
 #define QUECTEL_PRODUCT_EC200T			0x6026
 #define QUECTEL_PRODUCT_RM500K			0x7001
@@ -438,6 +440,8 @@ static void option_instat_callback(struct urb *urb);
 #define CINTERION_PRODUCT_MV31_2_RMNET		0x00b9
 #define CINTERION_PRODUCT_MV32_WA		0x00f1
 #define CINTERION_PRODUCT_MV32_WB		0x00f2
+#define CINTERION_PRODUCT_MV32_WA_RMNET		0x00f3
+#define CINTERION_PRODUCT_MV32_WB_RMNET		0x00f4
 
 /* Olivetti products */
 #define OLIVETTI_VENDOR_ID			0x0b3c
@@ -573,6 +577,10 @@ static void option_instat_callback(struct urb *urb);
 #define WETELECOM_PRODUCT_6802			0x6802
 #define WETELECOM_PRODUCT_WMD300		0x6803
 
+/* OPPO products */
+#define OPPO_VENDOR_ID				0x22d9
+#define OPPO_PRODUCT_R11			0x276c
+
 
 /* Device flags */
 
@@ -1131,6 +1139,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0xff, 0xff),
 	  .driver_info = NUMEP2 },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0, 0) },
+	{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, 0x0203, 0xff), /* BG95-M3 */
+	  .driver_info = ZLP },
 	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96),
 	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff),
@@ -1138,6 +1148,9 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) },
 	{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G, 0xff),
 	  .driver_info = RSVD(6) | ZLP },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0x00, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0xff, 0x30) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0xff, 0x40) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0xff, 0xff),
 	  .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0, 0) },
@@ -1149,6 +1162,9 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x10),
 	  .driver_info = ZLP },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0xff, 0x30) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200S_CN, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500K, 0xff, 0x00, 0x00) },
@@ -1993,8 +2009,12 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(0)},
 	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV32_WA, 0xff),
 	  .driver_info = RSVD(3)},
+	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV32_WA_RMNET, 0xff),
+	  .driver_info = RSVD(0) },
 	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV32_WB, 0xff),
 	  .driver_info = RSVD(3)},
+	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV32_WB_RMNET, 0xff),
+	  .driver_info = RSVD(0) },
 	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100),
 	  .driver_info = RSVD(4) },
 	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD120),
@@ -2155,6 +2175,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) },			/* GosunCn GM500 RNDIS */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) },			/* GosunCn GM500 MBIM */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1406, 0xff) },			/* GosunCn GM500 ECM/NCM */
+	{ USB_DEVICE_AND_INTERFACE_INFO(OPPO_VENDOR_ID, OPPO_PRODUCT_R11, 0xff, 0xff, 0x30) },
 	{ } /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, option_ids);
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 1a05e3dcfec8..4993227ab293 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -2294,6 +2294,13 @@ UNUSUAL_DEV( 0x1e74, 0x4621, 0x0000, 0x0000,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_BULK_IGNORE_TAG | US_FL_MAX_SECTORS_64 ),
 
+/* Reported by Witold Lipieta <witold.lipieta@thaumatec.com> */
+UNUSUAL_DEV( 0x1fc9, 0x0117, 0x0100, 0x0100,
+		"NXP Semiconductors",
+		"PN7462AU",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_IGNORE_RESIDUE ),
+
 /* Supplied with some Castlewood ORB removable drives */
 UNUSUAL_DEV(  0x2027, 0xa001, 0x0000, 0x9999,
 		"Double-H Technology",
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 4051c8cd0cd8..251778d14e2d 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -52,6 +52,13 @@ UNUSUAL_DEV(0x059f, 0x1061, 0x0000, 0x9999,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_REPORT_OPCODES | US_FL_NO_SAME),
 
+/* Reported-by: Hongling Zeng <zenghongling@kylinos.cn> */
+UNUSUAL_DEV(0x090c, 0x2000, 0x0000, 0x9999,
+		"Hiksemi",
+		"External HDD",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_IGNORE_UAS),
+
 /*
  * Apricorn USB3 dongle sometimes returns "USBSUSBSUSBS" in response to SCSI
  * commands in UAS mode.  Observed with the 1.28 firmware; are there others?
@@ -62,6 +69,13 @@ UNUSUAL_DEV(0x0984, 0x0301, 0x0128, 0x0128,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_IGNORE_UAS),
 
+/* Reported-by: Tom Hu <huxiaoying@kylinos.cn> */
+UNUSUAL_DEV(0x0b05, 0x1932, 0x0000, 0x9999,
+		"ASUS",
+		"External HDD",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_IGNORE_UAS),
+
 /* Reported-by: David Webb <djw@noc.ac.uk> */
 UNUSUAL_DEV(0x0bc2, 0x331a, 0x0000, 0x9999,
 		"Seagate",
@@ -69,6 +83,13 @@ UNUSUAL_DEV(0x0bc2, 0x331a, 0x0000, 0x9999,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_REPORT_LUNS),
 
+/* Reported-by: Hongling Zeng <zenghongling@kylinos.cn> */
+UNUSUAL_DEV(0x0bda, 0x9210, 0x0000, 0x9999,
+		"Hiksemi",
+		"External HDD",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_IGNORE_UAS),
+
 /* Reported-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> */
 UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999,
 		"Initio Corporation",
@@ -111,6 +132,13 @@ UNUSUAL_DEV(0x154b, 0xf00d, 0x0000, 0x9999,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_ATA_1X),
 
+/* Reported-by: Hongling Zeng <zenghongling@kylinos.cn> */
+UNUSUAL_DEV(0x17ef, 0x3899, 0x0000, 0x9999,
+		"Thinkplus",
+		"External HDD",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_IGNORE_UAS),
+
 /* Reported-by: Hans de Goede <hdegoede@redhat.com> */
 UNUSUAL_DEV(0x2109, 0x0711, 0x0000, 0x9999,
 		"VIA",
diff --git a/drivers/usb/typec/Kconfig b/drivers/usb/typec/Kconfig
index 5defdfead653..831e7049977d 100644
--- a/drivers/usb/typec/Kconfig
+++ b/drivers/usb/typec/Kconfig
@@ -56,6 +56,7 @@ config TYPEC_ANX7411
 	tristate "Analogix ANX7411 Type-C DRP Port controller driver"
 	depends on I2C
 	depends on USB_ROLE_SWITCH
+	depends on POWER_SUPPLY
 	help
 	  Say Y or M here if your system has Analogix ANX7411 Type-C DRP Port
 	  controller driver.
diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c
index c1d8c23baa39..de66a2949e33 100644
--- a/drivers/usb/typec/altmodes/displayport.c
+++ b/drivers/usb/typec/altmodes/displayport.c
@@ -99,8 +99,8 @@ static int dp_altmode_configure(struct dp_altmode *dp, u8 con)
 	case DP_STATUS_CON_UFP_D:
 	case DP_STATUS_CON_BOTH: /* NOTE: First acting as DP source */
 		conf |= DP_CONF_UFP_U_AS_UFP_D;
-		pin_assign = DP_CAP_DFP_D_PIN_ASSIGN(dp->alt->vdo) &
-			     DP_CAP_UFP_D_PIN_ASSIGN(dp->port->vdo);
+		pin_assign = DP_CAP_PIN_ASSIGN_UFP_D(dp->alt->vdo) &
+				 DP_CAP_PIN_ASSIGN_DFP_D(dp->port->vdo);
 		break;
 	default:
 		break;
diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index ebc29ec20e3f..bd5e5dd70431 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -2346,6 +2346,7 @@ static void __exit typec_exit(void)
 	ida_destroy(&typec_index_ida);
 	bus_unregister(&typec_bus);
 	class_unregister(&typec_mux_class);
+	class_unregister(&retimer_class);
 }
 module_exit(typec_exit);
 
diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c
index 47b733f78fb0..e1f4df7238bf 100644
--- a/drivers/usb/typec/mux/intel_pmc_mux.c
+++ b/drivers/usb/typec/mux/intel_pmc_mux.c
@@ -569,13 +569,6 @@ err_unregister_switch:
 	return ret;
 }
 
-static int is_memory(struct acpi_resource *res, void *data)
-{
-	struct resource r;
-
-	return !acpi_dev_resource_memory(res, &r);
-}
-
 /* IOM ACPI IDs and IOM_PORT_STATUS_OFFSET */
 static const struct acpi_device_id iom_acpi_ids[] = {
 	/* TigerLake */
@@ -583,6 +576,9 @@ static const struct acpi_device_id iom_acpi_ids[] = {
 
 	/* AlderLake */
 	{ "INTC1079", 0x160, },
+
+	/* Meteor Lake */
+	{ "INTC107A", 0x160, },
 	{}
 };
 
@@ -606,7 +602,7 @@ static int pmc_usb_probe_iom(struct pmc_usb *pmc)
 		return -ENODEV;
 
 	INIT_LIST_HEAD(&resource_list);
-	ret = acpi_dev_get_resources(adev, &resource_list, is_memory, NULL);
+	ret = acpi_dev_get_memory_resources(adev, &resource_list);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index ea5a917c51b1..904c7b4ce2f0 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -6320,6 +6320,13 @@ static int tcpm_psy_set_prop(struct power_supply *psy,
 	struct tcpm_port *port = power_supply_get_drvdata(psy);
 	int ret;
 
+	/*
+	 * All the properties below are related to USB PD. The check needs to be
+	 * property specific when a non-pd related property is added.
+	 */
+	if (!port->pd_supported)
+		return -EOPNOTSUPP;
+
 	switch (psp) {
 	case POWER_SUPPLY_PROP_ONLINE:
 		ret = tcpm_psy_set_online(port, val);
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 1aea46493b85..6364f0d467ea 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -588,8 +588,6 @@ static int ucsi_get_pdos(struct ucsi_connector *con, int is_partner,
 				num_pdos * sizeof(u32));
 	if (ret < 0 && ret != -ETIMEDOUT)
 		dev_err(ucsi->dev, "UCSI_GET_PDOS failed (%d)\n", ret);
-	if (ret == 0 && offset == 0)
-		dev_warn(ucsi->dev, "UCSI_GET_PDOS returned 0 bytes\n");
 
 	return ret;
 }
@@ -1200,32 +1198,6 @@ out_unlock:
 	return ret;
 }
 
-static void ucsi_unregister_connectors(struct ucsi *ucsi)
-{
-	struct ucsi_connector *con;
-	int i;
-
-	if (!ucsi->connector)
-		return;
-
-	for (i = 0; i < ucsi->cap.num_connectors; i++) {
-		con = &ucsi->connector[i];
-
-		if (!con->wq)
-			break;
-
-		cancel_work_sync(&con->work);
-		ucsi_unregister_partner(con);
-		ucsi_unregister_altmodes(con, UCSI_RECIPIENT_CON);
-		ucsi_unregister_port_psy(con);
-		destroy_workqueue(con->wq);
-		typec_unregister_port(con->port);
-	}
-
-	kfree(ucsi->connector);
-	ucsi->connector = NULL;
-}
-
 /**
  * ucsi_init - Initialize UCSI interface
  * @ucsi: UCSI to be initialized
@@ -1234,6 +1206,7 @@ static void ucsi_unregister_connectors(struct ucsi *ucsi)
  */
 static int ucsi_init(struct ucsi *ucsi)
 {
+	struct ucsi_connector *con;
 	u64 command;
 	int ret;
 	int i;
@@ -1264,7 +1237,7 @@ static int ucsi_init(struct ucsi *ucsi)
 	}
 
 	/* Allocate the connectors. Released in ucsi_unregister() */
-	ucsi->connector = kcalloc(ucsi->cap.num_connectors,
+	ucsi->connector = kcalloc(ucsi->cap.num_connectors + 1,
 				  sizeof(*ucsi->connector), GFP_KERNEL);
 	if (!ucsi->connector) {
 		ret = -ENOMEM;
@@ -1288,7 +1261,15 @@ static int ucsi_init(struct ucsi *ucsi)
 	return 0;
 
 err_unregister:
-	ucsi_unregister_connectors(ucsi);
+	for (con = ucsi->connector; con->port; con++) {
+		ucsi_unregister_partner(con);
+		ucsi_unregister_altmodes(con, UCSI_RECIPIENT_CON);
+		ucsi_unregister_port_psy(con);
+		if (con->wq)
+			destroy_workqueue(con->wq);
+		typec_unregister_port(con->port);
+		con->port = NULL;
+	}
 
 err_reset:
 	memset(&ucsi->cap, 0, sizeof(ucsi->cap));
@@ -1402,6 +1383,7 @@ EXPORT_SYMBOL_GPL(ucsi_register);
 void ucsi_unregister(struct ucsi *ucsi)
 {
 	u64 cmd = UCSI_SET_NOTIFICATION_ENABLE;
+	int i;
 
 	/* Make sure that we are not in the middle of driver initialization */
 	cancel_delayed_work_sync(&ucsi->work);
@@ -1409,7 +1391,18 @@ void ucsi_unregister(struct ucsi *ucsi)
 	/* Disable notifications */
 	ucsi->ops->async_write(ucsi, UCSI_CONTROL, &cmd, sizeof(cmd));
 
-	ucsi_unregister_connectors(ucsi);
+	for (i = 0; i < ucsi->cap.num_connectors; i++) {
+		cancel_work_sync(&ucsi->connector[i].work);
+		ucsi_unregister_partner(&ucsi->connector[i]);
+		ucsi_unregister_altmodes(&ucsi->connector[i],
+					 UCSI_RECIPIENT_CON);
+		ucsi_unregister_port_psy(&ucsi->connector[i]);
+		if (ucsi->connector[i].wq)
+			destroy_workqueue(ucsi->connector[i].wq);
+		typec_unregister_port(ucsi->connector[i].port);
+	}
+
+	kfree(ucsi->connector);
 }
 EXPORT_SYMBOL_GPL(ucsi_unregister);
 
diff --git a/drivers/vdpa/ifcvf/ifcvf_base.c b/drivers/vdpa/ifcvf/ifcvf_base.c
index 75a703b803a2..3e4486bfa0b7 100644
--- a/drivers/vdpa/ifcvf/ifcvf_base.c
+++ b/drivers/vdpa/ifcvf/ifcvf_base.c
@@ -323,7 +323,7 @@ u16 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid)
 	u32 q_pair_id;
 
 	ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg;
-	q_pair_id = qid / hw->nr_vring;
+	q_pair_id = qid / 2;
 	avail_idx_addr = &ifcvf_lm->vring_lm_cfg[q_pair_id].idx_addr[qid % 2];
 	last_avail_idx = vp_ioread16(avail_idx_addr);
 
@@ -337,7 +337,7 @@ int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u16 num)
 	u32 q_pair_id;
 
 	ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg;
-	q_pair_id = qid / hw->nr_vring;
+	q_pair_id = qid / 2;
 	avail_idx_addr = &ifcvf_lm->vring_lm_cfg[q_pair_id].idx_addr[qid % 2];
 	hw->vring[qid].last_avail_idx = num;
 	vp_iowrite16(num, avail_idx_addr);
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index ed100a35e596..90913365def4 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1320,6 +1320,8 @@ static void teardown_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *
 
 static int create_rqt(struct mlx5_vdpa_net *ndev)
 {
+	int rqt_table_size = roundup_pow_of_two(ndev->rqt_size);
+	int act_sz = roundup_pow_of_two(ndev->cur_num_vqs / 2);
 	__be32 *list;
 	void *rqtc;
 	int inlen;
@@ -1327,7 +1329,7 @@ static int create_rqt(struct mlx5_vdpa_net *ndev)
 	int i, j;
 	int err;
 
-	inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + ndev->rqt_size * MLX5_ST_SZ_BYTES(rq_num);
+	inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + rqt_table_size * MLX5_ST_SZ_BYTES(rq_num);
 	in = kzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -1336,12 +1338,12 @@ static int create_rqt(struct mlx5_vdpa_net *ndev)
 	rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context);
 
 	MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q);
-	MLX5_SET(rqtc, rqtc, rqt_max_size, ndev->rqt_size);
+	MLX5_SET(rqtc, rqtc, rqt_max_size, rqt_table_size);
 	list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]);
-	for (i = 0, j = 0; i < ndev->rqt_size; i++, j += 2)
+	for (i = 0, j = 0; i < act_sz; i++, j += 2)
 		list[i] = cpu_to_be32(ndev->vqs[j % ndev->cur_num_vqs].virtq_id);
 
-	MLX5_SET(rqtc, rqtc, rqt_actual_size, ndev->rqt_size);
+	MLX5_SET(rqtc, rqtc, rqt_actual_size, act_sz);
 	err = mlx5_vdpa_create_rqt(&ndev->mvdev, in, inlen, &ndev->res.rqtn);
 	kfree(in);
 	if (err)
@@ -1354,6 +1356,7 @@ static int create_rqt(struct mlx5_vdpa_net *ndev)
 
 static int modify_rqt(struct mlx5_vdpa_net *ndev, int num)
 {
+	int act_sz = roundup_pow_of_two(num / 2);
 	__be32 *list;
 	void *rqtc;
 	int inlen;
@@ -1361,7 +1364,7 @@ static int modify_rqt(struct mlx5_vdpa_net *ndev, int num)
 	int i, j;
 	int err;
 
-	inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + ndev->rqt_size * MLX5_ST_SZ_BYTES(rq_num);
+	inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + act_sz * MLX5_ST_SZ_BYTES(rq_num);
 	in = kzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -1372,10 +1375,10 @@ static int modify_rqt(struct mlx5_vdpa_net *ndev, int num)
 	MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q);
 
 	list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]);
-	for (i = 0, j = 0; i < ndev->rqt_size; i++, j += 2)
+	for (i = 0, j = 0; i < act_sz; i++, j = j + 2)
 		list[i] = cpu_to_be32(ndev->vqs[j % num].virtq_id);
 
-	MLX5_SET(rqtc, rqtc, rqt_actual_size, ndev->rqt_size);
+	MLX5_SET(rqtc, rqtc, rqt_actual_size, act_sz);
 	err = mlx5_vdpa_modify_rqt(&ndev->mvdev, in, inlen, ndev->res.rqtn);
 	kfree(in);
 	if (err)
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index 41c0b29739f1..35dceee3ed56 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -673,10 +673,15 @@ static void vduse_vdpa_get_config(struct vdpa_device *vdpa, unsigned int offset,
 {
 	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
 
-	if (offset > dev->config_size ||
-	    len > dev->config_size - offset)
+	/* Initialize the buffer in case of partial copy. */
+	memset(buf, 0, len);
+
+	if (offset > dev->config_size)
 		return;
 
+	if (len > dev->config_size - offset)
+		len = dev->config_size - offset;
+
 	memcpy(buf, dev->config + offset, len);
 }
 
diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c
index e163aa9f6144..0cbdcd14f1c8 100644
--- a/drivers/vfio/pci/vfio_pci_zdev.c
+++ b/drivers/vfio/pci/vfio_pci_zdev.c
@@ -151,7 +151,10 @@ int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev)
 	if (!vdev->vdev.kvm)
 		return 0;
 
-	return kvm_s390_pci_register_kvm(zdev, vdev->vdev.kvm);
+	if (zpci_kvm_hook.kvm_register)
+		return zpci_kvm_hook.kvm_register(zdev, vdev->vdev.kvm);
+
+	return -ENOENT;
 }
 
 void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev)
@@ -161,5 +164,6 @@ void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev)
 	if (!zdev || !vdev->vdev.kvm)
 		return;
 
-	kvm_s390_pci_unregister_kvm(zdev);
+	if (zpci_kvm_hook.kvm_unregister)
+		zpci_kvm_hook.kvm_unregister(zdev);
 }
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index db516c90a977..8706482665d1 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -558,6 +558,18 @@ static int vaddr_get_pfns(struct mm_struct *mm, unsigned long vaddr,
 	ret = pin_user_pages_remote(mm, vaddr, npages, flags | FOLL_LONGTERM,
 				    pages, NULL, NULL);
 	if (ret > 0) {
+		int i;
+
+		/*
+		 * The zero page is always resident, we don't need to pin it
+		 * and it falls into our invalid/reserved test so we don't
+		 * unpin in put_pfn().  Unpin all zero pages in the batch here.
+		 */
+		for (i = 0 ; i < ret; i++) {
+			if (unlikely(is_zero_pfn(page_to_pfn(pages[i]))))
+				unpin_user_page(pages[i]);
+		}
+
 		*pfn = page_to_pfn(pages[0]);
 		goto done;
 	}
diff --git a/drivers/video/console/sticore.c b/drivers/video/console/sticore.c
index bd4dc97d4d34..db568f67e4dc 100644
--- a/drivers/video/console/sticore.c
+++ b/drivers/video/console/sticore.c
@@ -290,7 +290,7 @@ static char default_sti_path[21] __read_mostly;
 static int __init sti_setup(char *str)
 {
 	if (str)
-		strlcpy (default_sti_path, str, sizeof (default_sti_path));
+		strscpy(default_sti_path, str, sizeof(default_sti_path));
 	
 	return 1;
 }
diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c
index a3e6faed7745..14eb718bd67c 100644
--- a/drivers/video/fbdev/aty/atyfb_base.c
+++ b/drivers/video/fbdev/aty/atyfb_base.c
@@ -3891,7 +3891,7 @@ static int __init atyfb_setup(char *options)
 			 && (!strncmp(this_opt, "Mach64:", 7))) {
 			static unsigned char m64_num;
 			static char mach64_str[80];
-			strlcpy(mach64_str, this_opt + 7, sizeof(mach64_str));
+			strscpy(mach64_str, this_opt + 7, sizeof(mach64_str));
 			if (!store_video_par(mach64_str, m64_num)) {
 				m64_num++;
 				mach64_count = m64_num;
diff --git a/drivers/video/fbdev/aty/radeon_base.c b/drivers/video/fbdev/aty/radeon_base.c
index 6851f47613e1..a14a8d73035c 100644
--- a/drivers/video/fbdev/aty/radeon_base.c
+++ b/drivers/video/fbdev/aty/radeon_base.c
@@ -1980,7 +1980,7 @@ static int radeon_set_fbinfo(struct radeonfb_info *rinfo)
 	info->screen_base = rinfo->fb_base;
 	info->screen_size = rinfo->mapped_vram;
 	/* Fill fix common fields */
-	strlcpy(info->fix.id, rinfo->name, sizeof(info->fix.id));
+	strscpy(info->fix.id, rinfo->name, sizeof(info->fix.id));
         info->fix.smem_start = rinfo->fb_base_phys;
         info->fix.smem_len = rinfo->video_ram;
         info->fix.type = FB_TYPE_PACKED_PIXELS;
@@ -2094,34 +2094,34 @@ static void radeon_identify_vram(struct radeonfb_info *rinfo)
 	u32 tmp;
 
 	/* framebuffer size */
-        if ((rinfo->family == CHIP_FAMILY_RS100) ||
+	if ((rinfo->family == CHIP_FAMILY_RS100) ||
             (rinfo->family == CHIP_FAMILY_RS200) ||
             (rinfo->family == CHIP_FAMILY_RS300) ||
             (rinfo->family == CHIP_FAMILY_RC410) ||
             (rinfo->family == CHIP_FAMILY_RS400) ||
 	    (rinfo->family == CHIP_FAMILY_RS480) ) {
-          u32 tom = INREG(NB_TOM);
-          tmp = ((((tom >> 16) - (tom & 0xffff) + 1) << 6) * 1024);
-
- 		radeon_fifo_wait(6);
-          OUTREG(MC_FB_LOCATION, tom);
-          OUTREG(DISPLAY_BASE_ADDR, (tom & 0xffff) << 16);
-          OUTREG(CRTC2_DISPLAY_BASE_ADDR, (tom & 0xffff) << 16);
-          OUTREG(OV0_BASE_ADDR, (tom & 0xffff) << 16);
-
-          /* This is supposed to fix the crtc2 noise problem. */
-          OUTREG(GRPH2_BUFFER_CNTL, INREG(GRPH2_BUFFER_CNTL) & ~0x7f0000);
-
-          if ((rinfo->family == CHIP_FAMILY_RS100) ||
-              (rinfo->family == CHIP_FAMILY_RS200)) {
-             /* This is to workaround the asic bug for RMX, some versions
-                of BIOS doesn't have this register initialized correctly.
-             */
-             OUTREGP(CRTC_MORE_CNTL, CRTC_H_CUTOFF_ACTIVE_EN,
-                     ~CRTC_H_CUTOFF_ACTIVE_EN);
-          }
-        } else {
-          tmp = INREG(CNFG_MEMSIZE);
+		u32 tom = INREG(NB_TOM);
+
+		tmp = ((((tom >> 16) - (tom & 0xffff) + 1) << 6) * 1024);
+		radeon_fifo_wait(6);
+		OUTREG(MC_FB_LOCATION, tom);
+		OUTREG(DISPLAY_BASE_ADDR, (tom & 0xffff) << 16);
+		OUTREG(CRTC2_DISPLAY_BASE_ADDR, (tom & 0xffff) << 16);
+		OUTREG(OV0_BASE_ADDR, (tom & 0xffff) << 16);
+
+		/* This is supposed to fix the crtc2 noise problem. */
+		OUTREG(GRPH2_BUFFER_CNTL, INREG(GRPH2_BUFFER_CNTL) & ~0x7f0000);
+
+		if ((rinfo->family == CHIP_FAMILY_RS100) ||
+		    (rinfo->family == CHIP_FAMILY_RS200)) {
+			/* This is to workaround the asic bug for RMX, some versions
+			 * of BIOS doesn't have this register initialized correctly.
+			 */
+			OUTREGP(CRTC_MORE_CNTL, CRTC_H_CUTOFF_ACTIVE_EN,
+				~CRTC_H_CUTOFF_ACTIVE_EN);
+		}
+	} else {
+		tmp = INREG(CNFG_MEMSIZE);
         }
 
 	/* mem size is bits [28:0], mask off the rest */
diff --git a/drivers/video/fbdev/bw2.c b/drivers/video/fbdev/bw2.c
index e7702fe1fe7d..6403ae07970d 100644
--- a/drivers/video/fbdev/bw2.c
+++ b/drivers/video/fbdev/bw2.c
@@ -182,7 +182,7 @@ static int bw2_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg)
 
 static void bw2_init_fix(struct fb_info *info, int linebytes)
 {
-	strlcpy(info->fix.id, "bwtwo", sizeof(info->fix.id));
+	strscpy(info->fix.id, "bwtwo", sizeof(info->fix.id));
 
 	info->fix.type = FB_TYPE_PACKED_PIXELS;
 	info->fix.visual = FB_VISUAL_MONO01;
diff --git a/drivers/video/fbdev/chipsfb.c b/drivers/video/fbdev/chipsfb.c
index 393894af26f8..2b00a9d554fc 100644
--- a/drivers/video/fbdev/chipsfb.c
+++ b/drivers/video/fbdev/chipsfb.c
@@ -430,6 +430,7 @@ static int chipsfb_pci_init(struct pci_dev *dp, const struct pci_device_id *ent)
  err_release_fb:
 	framebuffer_release(p);
  err_disable:
+	pci_disable_device(dp);
  err_out:
 	return rc;
 }
diff --git a/drivers/video/fbdev/cirrusfb.c b/drivers/video/fbdev/cirrusfb.c
index a41a75841e10..2a9fa06881b5 100644
--- a/drivers/video/fbdev/cirrusfb.c
+++ b/drivers/video/fbdev/cirrusfb.c
@@ -1999,7 +1999,7 @@ static int cirrusfb_set_fbinfo(struct fb_info *info)
 	}
 
 	/* Fill fix common fields */
-	strlcpy(info->fix.id, cirrusfb_board_info[cinfo->btype].name,
+	strscpy(info->fix.id, cirrusfb_board_info[cinfo->btype].name,
 		sizeof(info->fix.id));
 
 	/* monochrome: only 1 memory plane */
diff --git a/drivers/video/fbdev/clps711x-fb.c b/drivers/video/fbdev/clps711x-fb.c
index 771ce1f76951..a1061c2f1640 100644
--- a/drivers/video/fbdev/clps711x-fb.c
+++ b/drivers/video/fbdev/clps711x-fb.c
@@ -326,7 +326,7 @@ static int clps711x_fb_probe(struct platform_device *pdev)
 	info->var.vmode = FB_VMODE_NONINTERLACED;
 	info->fix.type = FB_TYPE_PACKED_PIXELS;
 	info->fix.accel = FB_ACCEL_NONE;
-	strlcpy(info->fix.id, CLPS711X_FB_NAME, sizeof(info->fix.id));
+	strscpy(info->fix.id, CLPS711X_FB_NAME, sizeof(info->fix.id));
 	fb_videomode_to_var(&info->var, &cfb->mode);
 
 	ret = fb_alloc_cmap(&info->cmap, BIT(CLPS711X_FB_BPP_MAX), 0);
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index cf9ac4da0a82..098b62f7b701 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -412,7 +412,7 @@ static int __init fb_console_setup(char *this_opt)
 
 	while ((options = strsep(&this_opt, ",")) != NULL) {
 		if (!strncmp(options, "font:", 5)) {
-			strlcpy(fontname, options + 5, sizeof(fontname));
+			strscpy(fontname, options + 5, sizeof(fontname));
 			continue;
 		}
 		
@@ -2401,15 +2401,21 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount,
 	struct fb_info *info = fbcon_info_from_console(vc->vc_num);
 	struct fbcon_ops *ops = info->fbcon_par;
 	struct fbcon_display *p = &fb_display[vc->vc_num];
-	int resize;
+	int resize, ret, old_userfont, old_width, old_height, old_charcount;
 	char *old_data = NULL;
 
 	resize = (w != vc->vc_font.width) || (h != vc->vc_font.height);
 	if (p->userfont)
 		old_data = vc->vc_font.data;
 	vc->vc_font.data = (void *)(p->fontdata = data);
+	old_userfont = p->userfont;
 	if ((p->userfont = userfont))
 		REFCOUNT(data)++;
+
+	old_width = vc->vc_font.width;
+	old_height = vc->vc_font.height;
+	old_charcount = vc->vc_font.charcount;
+
 	vc->vc_font.width = w;
 	vc->vc_font.height = h;
 	vc->vc_font.charcount = charcount;
@@ -2425,7 +2431,9 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount,
 		rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres);
 		cols /= w;
 		rows /= h;
-		vc_resize(vc, cols, rows);
+		ret = vc_resize(vc, cols, rows);
+		if (ret)
+			goto err_out;
 	} else if (con_is_visible(vc)
 		   && vc->vc_mode == KD_TEXT) {
 		fbcon_clear_margins(vc, 0);
@@ -2435,6 +2443,21 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount,
 	if (old_data && (--REFCOUNT(old_data) == 0))
 		kfree(old_data - FONT_EXTRA_WORDS * sizeof(int));
 	return 0;
+
+err_out:
+	p->fontdata = old_data;
+	vc->vc_font.data = (void *)old_data;
+
+	if (userfont) {
+		p->userfont = old_userfont;
+		REFCOUNT(data)--;
+	}
+
+	vc->vc_font.width = old_width;
+	vc->vc_font.height = old_height;
+	vc->vc_font.charcount = old_charcount;
+
+	return ret;
 }
 
 /*
diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c
index c2a60b187467..4d7f63892dcc 100644
--- a/drivers/video/fbdev/core/fbsysfs.c
+++ b/drivers/video/fbdev/core/fbsysfs.c
@@ -84,6 +84,10 @@ void framebuffer_release(struct fb_info *info)
 	if (WARN_ON(refcount_read(&info->count)))
 		return;
 
+#if IS_ENABLED(CONFIG_FB_BACKLIGHT)
+	mutex_destroy(&info->bl_curve_mutex);
+#endif
+
 	kfree(info->apertures);
 	kfree(info);
 }
diff --git a/drivers/video/fbdev/cyber2000fb.c b/drivers/video/fbdev/cyber2000fb.c
index d45355b9a58c..8f041f9b14c7 100644
--- a/drivers/video/fbdev/cyber2000fb.c
+++ b/drivers/video/fbdev/cyber2000fb.c
@@ -1134,7 +1134,7 @@ int cyber2000fb_attach(struct cyberpro_info *info, int idx)
 		info->fb_size	      = int_cfb_info->fb.fix.smem_len;
 		info->info	      = int_cfb_info;
 
-		strlcpy(info->dev_name, int_cfb_info->fb.fix.id,
+		strscpy(info->dev_name, int_cfb_info->fb.fix.id,
 			sizeof(info->dev_name));
 	}
 
@@ -1229,7 +1229,7 @@ static int cyber2000fb_ddc_getsda(void *data)
 
 static int cyber2000fb_setup_ddc_bus(struct cfb_info *cfb)
 {
-	strlcpy(cfb->ddc_adapter.name, cfb->fb.fix.id,
+	strscpy(cfb->ddc_adapter.name, cfb->fb.fix.id,
 		sizeof(cfb->ddc_adapter.name));
 	cfb->ddc_adapter.owner		= THIS_MODULE;
 	cfb->ddc_adapter.class		= I2C_CLASS_DDC;
@@ -1304,7 +1304,7 @@ static int cyber2000fb_i2c_getscl(void *data)
 
 static int cyber2000fb_i2c_register(struct cfb_info *cfb)
 {
-	strlcpy(cfb->i2c_adapter.name, cfb->fb.fix.id,
+	strscpy(cfb->i2c_adapter.name, cfb->fb.fix.id,
 		sizeof(cfb->i2c_adapter.name));
 	cfb->i2c_adapter.owner = THIS_MODULE;
 	cfb->i2c_adapter.algo_data = &cfb->i2c_algo;
@@ -1500,7 +1500,7 @@ static int cyber2000fb_setup(char *options)
 		if (strncmp(opt, "font:", 5) == 0) {
 			static char default_font_storage[40];
 
-			strlcpy(default_font_storage, opt + 5,
+			strscpy(default_font_storage, opt + 5,
 				sizeof(default_font_storage));
 			default_font = default_font_storage;
 			continue;
diff --git a/drivers/video/fbdev/ffb.c b/drivers/video/fbdev/ffb.c
index b3d580e57221..7cba3969a970 100644
--- a/drivers/video/fbdev/ffb.c
+++ b/drivers/video/fbdev/ffb.c
@@ -883,7 +883,7 @@ static void ffb_init_fix(struct fb_info *info)
 	} else
 		ffb_type_name = "Elite 3D";
 
-	strlcpy(info->fix.id, ffb_type_name, sizeof(info->fix.id));
+	strscpy(info->fix.id, ffb_type_name, sizeof(info->fix.id));
 
 	info->fix.type = FB_TYPE_PACKED_PIXELS;
 	info->fix.visual = FB_VISUAL_TRUECOLOR;
diff --git a/drivers/video/fbdev/geode/gx1fb_core.c b/drivers/video/fbdev/geode/gx1fb_core.c
index 5d34d89fb665..e41204ecb0e3 100644
--- a/drivers/video/fbdev/geode/gx1fb_core.c
+++ b/drivers/video/fbdev/geode/gx1fb_core.c
@@ -410,13 +410,13 @@ static void __init gx1fb_setup(char *options)
 			continue;
 
 		if (!strncmp(this_opt, "mode:", 5))
-			strlcpy(mode_option, this_opt + 5, sizeof(mode_option));
+			strscpy(mode_option, this_opt + 5, sizeof(mode_option));
 		else if (!strncmp(this_opt, "crt:", 4))
 			crt_option = !!simple_strtoul(this_opt + 4, NULL, 0);
 		else if (!strncmp(this_opt, "panel:", 6))
-			strlcpy(panel_option, this_opt + 6, sizeof(panel_option));
+			strscpy(panel_option, this_opt + 6, sizeof(panel_option));
 		else
-			strlcpy(mode_option, this_opt, sizeof(mode_option));
+			strscpy(mode_option, this_opt, sizeof(mode_option));
 	}
 }
 #endif
diff --git a/drivers/video/fbdev/gxt4500.c b/drivers/video/fbdev/gxt4500.c
index e5475ae1e158..94588b809ebf 100644
--- a/drivers/video/fbdev/gxt4500.c
+++ b/drivers/video/fbdev/gxt4500.c
@@ -650,7 +650,7 @@ static int gxt4500_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	cardtype = ent->driver_data;
 	par->refclk_ps = cardinfo[cardtype].refclk_ps;
 	info->fix = gxt4500_fix;
-	strlcpy(info->fix.id, cardinfo[cardtype].cardname,
+	strscpy(info->fix.id, cardinfo[cardtype].cardname,
 		sizeof(info->fix.id));
 	info->pseudo_palette = par->pseudo_palette;
 
diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index 886c564787f1..b58b445bb529 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -74,10 +74,6 @@
 #define SYNTHVID_DEPTH_WIN8 32
 #define SYNTHVID_FB_SIZE_WIN8 (8 * 1024 * 1024)
 
-#define PCI_VENDOR_ID_MICROSOFT 0x1414
-#define PCI_DEVICE_ID_HYPERV_VIDEO 0x5353
-
-
 enum pipe_msg_type {
 	PIPE_MSG_INVALID,
 	PIPE_MSG_DATA,
diff --git a/drivers/video/fbdev/i740fb.c b/drivers/video/fbdev/i740fb.c
index 7f09a0daaaa2..bd30d8314b68 100644
--- a/drivers/video/fbdev/i740fb.c
+++ b/drivers/video/fbdev/i740fb.c
@@ -159,7 +159,7 @@ static int i740fb_setup_ddc_bus(struct fb_info *info)
 {
 	struct i740fb_par *par = info->par;
 
-	strlcpy(par->ddc_adapter.name, info->fix.id,
+	strscpy(par->ddc_adapter.name, info->fix.id,
 		sizeof(par->ddc_adapter.name));
 	par->ddc_adapter.owner		= THIS_MODULE;
 	par->ddc_adapter.class		= I2C_CLASS_DDC;
diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c
index d97d7456d15a..94f3bc637fc8 100644
--- a/drivers/video/fbdev/imxfb.c
+++ b/drivers/video/fbdev/imxfb.c
@@ -681,7 +681,7 @@ static int imxfb_init_fbinfo(struct platform_device *pdev)
 
 	fbi->devtype = pdev->id_entry->driver_data;
 
-	strlcpy(info->fix.id, IMX_NAME, sizeof(info->fix.id));
+	strscpy(info->fix.id, IMX_NAME, sizeof(info->fix.id));
 
 	info->fix.type			= FB_TYPE_PACKED_PIXELS;
 	info->fix.type_aux		= 0;
diff --git a/drivers/video/fbdev/matrox/matroxfb_base.c b/drivers/video/fbdev/matrox/matroxfb_base.c
index 236521b19daf..68bba2688f4c 100644
--- a/drivers/video/fbdev/matrox/matroxfb_base.c
+++ b/drivers/video/fbdev/matrox/matroxfb_base.c
@@ -2383,9 +2383,9 @@ static int __init matroxfb_setup(char *options) {
 		else if (!strncmp(this_opt, "mem:", 4))
 			mem = simple_strtoul(this_opt+4, NULL, 0);
 		else if (!strncmp(this_opt, "mode:", 5))
-			strlcpy(videomode, this_opt+5, sizeof(videomode));
+			strscpy(videomode, this_opt + 5, sizeof(videomode));
 		else if (!strncmp(this_opt, "outputs:", 8))
-			strlcpy(outputs, this_opt+8, sizeof(outputs));
+			strscpy(outputs, this_opt + 8, sizeof(outputs));
 		else if (!strncmp(this_opt, "dfp:", 4)) {
 			dfp_type = simple_strtoul(this_opt+4, NULL, 0);
 			dfp = 1;
@@ -2455,7 +2455,7 @@ static int __init matroxfb_setup(char *options) {
 			else if (!strcmp(this_opt, "dfp"))
 				dfp = value;
 			else {
-				strlcpy(videomode, this_opt, sizeof(videomode));
+				strscpy(videomode, this_opt, sizeof(videomode));
 			}
 		}
 	}
diff --git a/drivers/video/fbdev/omap/omapfb_main.c b/drivers/video/fbdev/omap/omapfb_main.c
index dfb4ddc45701..17cda5765683 100644
--- a/drivers/video/fbdev/omap/omapfb_main.c
+++ b/drivers/video/fbdev/omap/omapfb_main.c
@@ -1642,15 +1642,13 @@ static int omapfb_do_probe(struct platform_device *pdev,
 		goto cleanup;
 	}
 	fbdev->int_irq = platform_get_irq(pdev, 0);
-	if (!fbdev->int_irq) {
-		dev_err(&pdev->dev, "unable to get irq\n");
+	if (fbdev->int_irq < 0) {
 		r = ENXIO;
 		goto cleanup;
 	}
 
 	fbdev->ext_irq = platform_get_irq(pdev, 1);
-	if (!fbdev->ext_irq) {
-		dev_err(&pdev->dev, "unable to get irq\n");
+	if (fbdev->ext_irq < 0) {
 		r = ENXIO;
 		goto cleanup;
 	}
diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
index afa688e754b9..5ccddcfce722 100644
--- a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
+++ b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
@@ -1331,7 +1331,7 @@ static void clear_fb_info(struct fb_info *fbi)
 {
 	memset(&fbi->var, 0, sizeof(fbi->var));
 	memset(&fbi->fix, 0, sizeof(fbi->fix));
-	strlcpy(fbi->fix.id, MODULE_NAME, sizeof(fbi->fix.id));
+	strscpy(fbi->fix.id, MODULE_NAME, sizeof(fbi->fix.id));
 }
 
 static int omapfb_free_all_fbmem(struct omapfb2_device *fbdev)
diff --git a/drivers/video/fbdev/pm2fb.c b/drivers/video/fbdev/pm2fb.c
index d3be2c64f1c0..8fd79deb1e2a 100644
--- a/drivers/video/fbdev/pm2fb.c
+++ b/drivers/video/fbdev/pm2fb.c
@@ -617,6 +617,11 @@ static int pm2fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 		return -EINVAL;
 	}
 
+	if (!var->pixclock) {
+		DPRINTK("pixclock is zero\n");
+		return -EINVAL;
+	}
+
 	if (PICOS2KHZ(var->pixclock) > PM2_MAX_PIXCLOCK) {
 		DPRINTK("pixclock too high (%ldKHz)\n",
 			PICOS2KHZ(var->pixclock));
diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c
index e943300d23e8..d5d0bbd39213 100644
--- a/drivers/video/fbdev/pxa168fb.c
+++ b/drivers/video/fbdev/pxa168fb.c
@@ -640,7 +640,7 @@ static int pxa168fb_probe(struct platform_device *pdev)
 	info->flags = FBINFO_DEFAULT | FBINFO_PARTIAL_PAN_OK |
 		      FBINFO_HWACCEL_XPAN | FBINFO_HWACCEL_YPAN;
 	info->node = -1;
-	strlcpy(info->fix.id, mi->id, 16);
+	strscpy(info->fix.id, mi->id, 16);
 	info->fix.type = FB_TYPE_PACKED_PIXELS;
 	info->fix.type_aux = 0;
 	info->fix.xpanstep = 0;
diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c
index 66cfc3e9d3cf..696ac5431180 100644
--- a/drivers/video/fbdev/pxafb.c
+++ b/drivers/video/fbdev/pxafb.c
@@ -2042,7 +2042,7 @@ static int __init pxafb_setup_options(void)
 		return -ENODEV;
 
 	if (options)
-		strlcpy(g_options, options, sizeof(g_options));
+		strscpy(g_options, options, sizeof(g_options));
 
 	return 0;
 }
diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c
index 5069f6f67923..67b63a753cb2 100644
--- a/drivers/video/fbdev/s3fb.c
+++ b/drivers/video/fbdev/s3fb.c
@@ -248,7 +248,7 @@ static int s3fb_setup_ddc_bus(struct fb_info *info)
 {
 	struct s3fb_info *par = info->par;
 
-	strlcpy(par->ddc_adapter.name, info->fix.id,
+	strscpy(par->ddc_adapter.name, info->fix.id,
 		sizeof(par->ddc_adapter.name));
 	par->ddc_adapter.owner		= THIS_MODULE;
 	par->ddc_adapter.class		= I2C_CLASS_DDC;
diff --git a/drivers/video/fbdev/simplefb.c b/drivers/video/fbdev/simplefb.c
index cf2a90ecd64e..e770b4a356b5 100644
--- a/drivers/video/fbdev/simplefb.c
+++ b/drivers/video/fbdev/simplefb.c
@@ -355,7 +355,7 @@ static int simplefb_regulators_get(struct simplefb_par *par,
 		if (!p || p == prop->name)
 			continue;
 
-		strlcpy(name, prop->name,
+		strscpy(name, prop->name,
 			strlen(prop->name) - strlen(SUPPLY_SUFFIX) + 1);
 		regulator = devm_regulator_get_optional(&pdev->dev, name);
 		if (IS_ERR(regulator)) {
diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c
index f28fd69d5eb7..c9e77429dfa3 100644
--- a/drivers/video/fbdev/sis/sis_main.c
+++ b/drivers/video/fbdev/sis/sis_main.c
@@ -649,37 +649,37 @@ sisfb_validate_mode(struct sis_video_info *ivideo, int myindex, u32 vbflags)
 	u16 xres=0, yres, myres;
 
 #ifdef CONFIG_FB_SIS_300
-	if(ivideo->sisvga_engine == SIS_300_VGA) {
-		if(!(sisbios_mode[myindex].chipset & MD_SIS300))
+	if (ivideo->sisvga_engine == SIS_300_VGA) {
+		if (!(sisbios_mode[myindex].chipset & MD_SIS300))
 			return -1 ;
 	}
 #endif
 #ifdef CONFIG_FB_SIS_315
-	if(ivideo->sisvga_engine == SIS_315_VGA) {
-		if(!(sisbios_mode[myindex].chipset & MD_SIS315))
+	if (ivideo->sisvga_engine == SIS_315_VGA) {
+		if (!(sisbios_mode[myindex].chipset & MD_SIS315))
 			return -1;
 	}
 #endif
 
 	myres = sisbios_mode[myindex].yres;
 
-	switch(vbflags & VB_DISPTYPE_DISP2) {
+	switch (vbflags & VB_DISPTYPE_DISP2) {
 
 	case CRT2_LCD:
 		xres = ivideo->lcdxres; yres = ivideo->lcdyres;
 
-		if((ivideo->SiS_Pr.SiS_CustomT != CUT_PANEL848) &&
-		   (ivideo->SiS_Pr.SiS_CustomT != CUT_PANEL856)) {
-			if(sisbios_mode[myindex].xres > xres)
+		if ((ivideo->SiS_Pr.SiS_CustomT != CUT_PANEL848) &&
+		    (ivideo->SiS_Pr.SiS_CustomT != CUT_PANEL856)) {
+			if (sisbios_mode[myindex].xres > xres)
 				return -1;
-			if(myres > yres)
+			if (myres > yres)
 				return -1;
 		}
 
-		if(ivideo->sisfb_fstn) {
-			if(sisbios_mode[myindex].xres == 320) {
-				if(myres == 240) {
-					switch(sisbios_mode[myindex].mode_no[1]) {
+		if (ivideo->sisfb_fstn) {
+			if (sisbios_mode[myindex].xres == 320) {
+				if (myres == 240) {
+					switch (sisbios_mode[myindex].mode_no[1]) {
 						case 0x50: myindex = MODE_FSTN_8;  break;
 						case 0x56: myindex = MODE_FSTN_16; break;
 						case 0x53: return -1;
@@ -688,7 +688,7 @@ sisfb_validate_mode(struct sis_video_info *ivideo, int myindex, u32 vbflags)
 			}
 		}
 
-		if(SiS_GetModeID_LCD(ivideo->sisvga_engine, vbflags, sisbios_mode[myindex].xres,
+		if (SiS_GetModeID_LCD(ivideo->sisvga_engine, vbflags, sisbios_mode[myindex].xres,
 			 	sisbios_mode[myindex].yres, 0, ivideo->sisfb_fstn,
 			 	ivideo->SiS_Pr.SiS_CustomT, xres, yres, ivideo->vbflags2) < 0x14) {
 			return -1;
@@ -696,14 +696,14 @@ sisfb_validate_mode(struct sis_video_info *ivideo, int myindex, u32 vbflags)
 		break;
 
 	case CRT2_TV:
-		if(SiS_GetModeID_TV(ivideo->sisvga_engine, vbflags, sisbios_mode[myindex].xres,
+		if (SiS_GetModeID_TV(ivideo->sisvga_engine, vbflags, sisbios_mode[myindex].xres,
 				sisbios_mode[myindex].yres, 0, ivideo->vbflags2) < 0x14) {
 			return -1;
 		}
 		break;
 
 	case CRT2_VGA:
-		if(SiS_GetModeID_VGA2(ivideo->sisvga_engine, vbflags, sisbios_mode[myindex].xres,
+		if (SiS_GetModeID_VGA2(ivideo->sisvga_engine, vbflags, sisbios_mode[myindex].xres,
 				sisbios_mode[myindex].yres, 0, ivideo->vbflags2) < 0x14) {
 			return -1;
 		}
@@ -1872,7 +1872,7 @@ sisfb_get_fix(struct fb_fix_screeninfo *fix, int con, struct fb_info *info)
 
 	memset(fix, 0, sizeof(struct fb_fix_screeninfo));
 
-	strlcpy(fix->id, ivideo->myid, sizeof(fix->id));
+	strscpy(fix->id, ivideo->myid, sizeof(fix->id));
 
 	mutex_lock(&info->mm_lock);
 	fix->smem_start  = ivideo->video_base + ivideo->video_offset;
@@ -2204,82 +2204,88 @@ static bool sisfb_test_DDC1(struct sis_video_info *ivideo)
 
 static void sisfb_sense_crt1(struct sis_video_info *ivideo)
 {
-    bool mustwait = false;
-    u8  sr1F, cr17;
+	bool mustwait = false;
+	u8  sr1F, cr17;
 #ifdef CONFIG_FB_SIS_315
-    u8  cr63=0;
+	u8  cr63 = 0;
 #endif
-    u16 temp = 0xffff;
-    int i;
+	u16 temp = 0xffff;
+	int i;
+
+	sr1F = SiS_GetReg(SISSR, 0x1F);
+	SiS_SetRegOR(SISSR, 0x1F, 0x04);
+	SiS_SetRegAND(SISSR, 0x1F, 0x3F);
 
-    sr1F = SiS_GetReg(SISSR, 0x1F);
-    SiS_SetRegOR(SISSR, 0x1F, 0x04);
-    SiS_SetRegAND(SISSR, 0x1F, 0x3F);
-    if(sr1F & 0xc0) mustwait = true;
+	if (sr1F & 0xc0)
+		mustwait = true;
 
 #ifdef CONFIG_FB_SIS_315
-    if(ivideo->sisvga_engine == SIS_315_VGA) {
-       cr63 = SiS_GetReg(SISCR, ivideo->SiS_Pr.SiS_MyCR63);
-       cr63 &= 0x40;
-       SiS_SetRegAND(SISCR, ivideo->SiS_Pr.SiS_MyCR63, 0xBF);
-    }
+	if (ivideo->sisvga_engine == SIS_315_VGA) {
+		cr63 = SiS_GetReg(SISCR, ivideo->SiS_Pr.SiS_MyCR63);
+		cr63 &= 0x40;
+		SiS_SetRegAND(SISCR, ivideo->SiS_Pr.SiS_MyCR63, 0xBF);
+	}
 #endif
 
-    cr17 = SiS_GetReg(SISCR, 0x17);
-    cr17 &= 0x80;
-    if(!cr17) {
-       SiS_SetRegOR(SISCR, 0x17, 0x80);
-       mustwait = true;
-       SiS_SetReg(SISSR, 0x00, 0x01);
-       SiS_SetReg(SISSR, 0x00, 0x03);
-    }
+	cr17 = SiS_GetReg(SISCR, 0x17);
+	cr17 &= 0x80;
 
-    if(mustwait) {
-       for(i=0; i < 10; i++) sisfbwaitretracecrt1(ivideo);
-    }
+	if (!cr17) {
+		SiS_SetRegOR(SISCR, 0x17, 0x80);
+		mustwait = true;
+		SiS_SetReg(SISSR, 0x00, 0x01);
+		SiS_SetReg(SISSR, 0x00, 0x03);
+	}
 
+	if (mustwait) {
+		for (i = 0; i < 10; i++)
+			sisfbwaitretracecrt1(ivideo);
+	}
 #ifdef CONFIG_FB_SIS_315
-    if(ivideo->chip >= SIS_330) {
-       SiS_SetRegAND(SISCR, 0x32, ~0x20);
-       if(ivideo->chip >= SIS_340) {
-	   SiS_SetReg(SISCR, 0x57, 0x4a);
-       } else {
-	   SiS_SetReg(SISCR, 0x57, 0x5f);
-       }
-	SiS_SetRegOR(SISCR, 0x53, 0x02);
-	while ((SiS_GetRegByte(SISINPSTAT)) & 0x01)    break;
-	while (!((SiS_GetRegByte(SISINPSTAT)) & 0x01)) break;
-	if ((SiS_GetRegByte(SISMISCW)) & 0x10) temp = 1;
-	SiS_SetRegAND(SISCR, 0x53, 0xfd);
-	SiS_SetRegAND(SISCR, 0x57, 0x00);
-    }
+	if (ivideo->chip >= SIS_330) {
+		SiS_SetRegAND(SISCR, 0x32, ~0x20);
+		if (ivideo->chip >= SIS_340)
+			SiS_SetReg(SISCR, 0x57, 0x4a);
+		else
+			SiS_SetReg(SISCR, 0x57, 0x5f);
+
+		SiS_SetRegOR(SISCR, 0x53, 0x02);
+		while ((SiS_GetRegByte(SISINPSTAT)) & 0x01)
+			break;
+		while (!((SiS_GetRegByte(SISINPSTAT)) & 0x01))
+			break;
+		if ((SiS_GetRegByte(SISMISCW)) & 0x10)
+			temp = 1;
+
+		SiS_SetRegAND(SISCR, 0x53, 0xfd);
+		SiS_SetRegAND(SISCR, 0x57, 0x00);
+	}
 #endif
 
-    if(temp == 0xffff) {
-       i = 3;
-       do {
-	  temp = SiS_HandleDDC(&ivideo->SiS_Pr, ivideo->vbflags,
-		ivideo->sisvga_engine, 0, 0, NULL, ivideo->vbflags2);
-       } while(((temp == 0) || (temp == 0xffff)) && i--);
+	if (temp == 0xffff) {
+		i = 3;
 
-       if((temp == 0) || (temp == 0xffff)) {
-          if(sisfb_test_DDC1(ivideo)) temp = 1;
-       }
-    }
+		do {
+			temp = SiS_HandleDDC(&ivideo->SiS_Pr, ivideo->vbflags,
+			ivideo->sisvga_engine, 0, 0, NULL, ivideo->vbflags2);
+		} while (((temp == 0) || (temp == 0xffff)) && i--);
 
-    if((temp) && (temp != 0xffff)) {
-       SiS_SetRegOR(SISCR, 0x32, 0x20);
-    }
+		if ((temp == 0) || (temp == 0xffff)) {
+			if (sisfb_test_DDC1(ivideo))
+				temp = 1;
+		}
+	}
+
+	if ((temp) && (temp != 0xffff))
+		SiS_SetRegOR(SISCR, 0x32, 0x20);
 
 #ifdef CONFIG_FB_SIS_315
-    if(ivideo->sisvga_engine == SIS_315_VGA) {
-	SiS_SetRegANDOR(SISCR, ivideo->SiS_Pr.SiS_MyCR63, 0xBF, cr63);
-    }
+	if (ivideo->sisvga_engine == SIS_315_VGA)
+		SiS_SetRegANDOR(SISCR, ivideo->SiS_Pr.SiS_MyCR63, 0xBF, cr63);
 #endif
 
-    SiS_SetRegANDOR(SISCR, 0x17, 0x7F, cr17);
-
-    SiS_SetReg(SISSR, 0x1F, sr1F);
+	SiS_SetRegANDOR(SISCR, 0x17, 0x7F, cr17);
+	SiS_SetReg(SISSR, 0x1F, sr1F);
 }
 
 /* Determine and detect attached devices on SiS30x */
@@ -2293,25 +2299,25 @@ static void SiS_SenseLCD(struct sis_video_info *ivideo)
 	ivideo->SiS_Pr.PanelSelfDetected = false;
 
 	/* LCD detection only for TMDS bridges */
-	if(!(ivideo->vbflags2 & VB2_SISTMDSBRIDGE))
+	if (!(ivideo->vbflags2 & VB2_SISTMDSBRIDGE))
 		return;
-	if(ivideo->vbflags2 & VB2_30xBDH)
+	if (ivideo->vbflags2 & VB2_30xBDH)
 		return;
 
 	/* If LCD already set up by BIOS, skip it */
 	reg = SiS_GetReg(SISCR, 0x32);
-	if(reg & 0x08)
+	if (reg & 0x08)
 		return;
 
 	realcrtno = 1;
-	if(ivideo->SiS_Pr.DDCPortMixup)
+	if (ivideo->SiS_Pr.DDCPortMixup)
 		realcrtno = 0;
 
 	/* Check DDC capabilities */
 	temp = SiS_HandleDDC(&ivideo->SiS_Pr, ivideo->vbflags, ivideo->sisvga_engine,
 				realcrtno, 0, &buffer[0], ivideo->vbflags2);
 
-	if((!temp) || (temp == 0xffff) || (!(temp & 0x02)))
+	if ((!temp) || (temp == 0xffff) || (!(temp & 0x02)))
 		return;
 
 	/* Read DDC data */
@@ -2320,17 +2326,17 @@ static void SiS_SenseLCD(struct sis_video_info *ivideo)
 		temp = SiS_HandleDDC(&ivideo->SiS_Pr, ivideo->vbflags,
 				ivideo->sisvga_engine, realcrtno, 1,
 				&buffer[0], ivideo->vbflags2);
-	} while((temp) && i--);
+	} while ((temp) && i--);
 
-	if(temp)
+	if (temp)
 		return;
 
 	/* No digital device */
-	if(!(buffer[0x14] & 0x80))
+	if (!(buffer[0x14] & 0x80))
 		return;
 
 	/* First detailed timing preferred timing? */
-	if(!(buffer[0x18] & 0x02))
+	if (!(buffer[0x18] & 0x02))
 		return;
 
 	xres = buffer[0x38] | ((buffer[0x3a] & 0xf0) << 4);
@@ -2338,26 +2344,26 @@ static void SiS_SenseLCD(struct sis_video_info *ivideo)
 
 	switch(xres) {
 		case 1024:
-			if(yres == 768)
+			if (yres == 768)
 				paneltype = 0x02;
 			break;
 		case 1280:
-			if(yres == 1024)
+			if (yres == 1024)
 				paneltype = 0x03;
 			break;
 		case 1600:
-			if((yres == 1200) && (ivideo->vbflags2 & VB2_30xC))
+			if ((yres == 1200) && (ivideo->vbflags2 & VB2_30xC))
 				paneltype = 0x0b;
 			break;
 	}
 
-	if(!paneltype)
+	if (!paneltype)
 		return;
 
-	if(buffer[0x23])
+	if (buffer[0x23])
 		cr37 |= 0x10;
 
-	if((buffer[0x47] & 0x18) == 0x18)
+	if ((buffer[0x47] & 0x18) == 0x18)
 		cr37 |= ((((buffer[0x47] & 0x06) ^ 0x06) << 5) | 0x20);
 	else
 		cr37 |= 0xc0;
@@ -2372,31 +2378,34 @@ static void SiS_SenseLCD(struct sis_video_info *ivideo)
 
 static int SISDoSense(struct sis_video_info *ivideo, u16 type, u16 test)
 {
-    int temp, mytest, result, i, j;
-
-    for(j = 0; j < 10; j++) {
-       result = 0;
-       for(i = 0; i < 3; i++) {
-          mytest = test;
-	   SiS_SetReg(SISPART4, 0x11, (type & 0x00ff));
-          temp = (type >> 8) | (mytest & 0x00ff);
-	  SiS_SetRegANDOR(SISPART4, 0x10, 0xe0, temp);
-          SiS_DDC2Delay(&ivideo->SiS_Pr, 0x1500);
-          mytest >>= 8;
-          mytest &= 0x7f;
-	   temp = SiS_GetReg(SISPART4, 0x03);
-          temp ^= 0x0e;
-          temp &= mytest;
-          if(temp == mytest) result++;
+	int temp, mytest, result, i, j;
+
+	for (j = 0; j < 10; j++) {
+		result = 0;
+		for (i = 0; i < 3; i++) {
+			mytest = test;
+			SiS_SetReg(SISPART4, 0x11, (type & 0x00ff));
+			temp = (type >> 8) | (mytest & 0x00ff);
+			SiS_SetRegANDOR(SISPART4, 0x10, 0xe0, temp);
+			SiS_DDC2Delay(&ivideo->SiS_Pr, 0x1500);
+			mytest >>= 8;
+			mytest &= 0x7f;
+			temp = SiS_GetReg(SISPART4, 0x03);
+			temp ^= 0x0e;
+			temp &= mytest;
+			if (temp == mytest)
+				result++;
 #if 1
-	  SiS_SetReg(SISPART4, 0x11, 0x00);
-	  SiS_SetRegAND(SISPART4, 0x10, 0xe0);
-	  SiS_DDC2Delay(&ivideo->SiS_Pr, 0x1000);
+			SiS_SetReg(SISPART4, 0x11, 0x00);
+			SiS_SetRegAND(SISPART4, 0x10, 0xe0);
+			SiS_DDC2Delay(&ivideo->SiS_Pr, 0x1000);
 #endif
-       }
-       if((result == 0) || (result >= 2)) break;
-    }
-    return result;
+		}
+
+		if ((result == 0) || (result >= 2))
+			break;
+	}
+	return result;
 }
 
 static void SiS_Sense30x(struct sis_video_info *ivideo)
@@ -4262,18 +4271,17 @@ static int sisfb_post_300_rwtest(struct sis_video_info *ivideo, int iteration,
 	unsigned int k, RankCapacity, PageCapacity, BankNumHigh, BankNumMid;
 	unsigned int PhysicalAdrOtherPage, PhysicalAdrHigh, PhysicalAdrHalfPage;
 
-	 for(k = 0; k < ARRAY_SIZE(SiS_DRAMType); k++) {
-
+	for (k = 0; k < ARRAY_SIZE(SiS_DRAMType); k++) {
 		RankCapacity = buswidth * SiS_DRAMType[k][3];
 
-		if(RankCapacity != PseudoRankCapacity)
+		if (RankCapacity != PseudoRankCapacity)
 			continue;
 
-		if((SiS_DRAMType[k][2] + SiS_DRAMType[k][0]) > PseudoAdrPinCount)
+		if ((SiS_DRAMType[k][2] + SiS_DRAMType[k][0]) > PseudoAdrPinCount)
 			continue;
 
 		BankNumHigh = RankCapacity * 16 * iteration - 1;
-		if(iteration == 3) {             /* Rank No */
+		if (iteration == 3) {             /* Rank No */
 			BankNumMid  = RankCapacity * 16 - 1;
 		} else {
 			BankNumMid  = RankCapacity * 16 * iteration / 2 - 1;
@@ -4287,18 +4295,22 @@ static int sisfb_post_300_rwtest(struct sis_video_info *ivideo, int iteration,
 		SiS_SetRegAND(SISSR, 0x15, 0xFB); /* Test */
 		SiS_SetRegOR(SISSR, 0x15, 0x04);  /* Test */
 		sr14 = (SiS_DRAMType[k][3] * buswidth) - 1;
-		if(buswidth == 4)      sr14 |= 0x80;
-		else if(buswidth == 2) sr14 |= 0x40;
+
+		if (buswidth == 4)
+			sr14 |= 0x80;
+		else if (buswidth == 2)
+			sr14 |= 0x40;
+
 		SiS_SetReg(SISSR, 0x13, SiS_DRAMType[k][4]);
 		SiS_SetReg(SISSR, 0x14, sr14);
 
 		BankNumHigh <<= 16;
 		BankNumMid <<= 16;
 
-		if((BankNumHigh + PhysicalAdrHigh      >= mapsize) ||
-		   (BankNumMid  + PhysicalAdrHigh      >= mapsize) ||
-		   (BankNumHigh + PhysicalAdrHalfPage  >= mapsize) ||
-		   (BankNumHigh + PhysicalAdrOtherPage >= mapsize))
+		if ((BankNumHigh + PhysicalAdrHigh >= mapsize) ||
+		    (BankNumMid  + PhysicalAdrHigh >= mapsize) ||
+		    (BankNumHigh + PhysicalAdrHalfPage  >= mapsize) ||
+		    (BankNumHigh + PhysicalAdrOtherPage >= mapsize))
 			continue;
 
 		/* Write data */
@@ -4312,7 +4324,7 @@ static int sisfb_post_300_rwtest(struct sis_video_info *ivideo, int iteration,
 				(FBAddr + BankNumHigh + PhysicalAdrOtherPage));
 
 		/* Read data */
-		if(readw(FBAddr + BankNumHigh + PhysicalAdrHigh) == PhysicalAdrHigh)
+		if (readw(FBAddr + BankNumHigh + PhysicalAdrHigh) == PhysicalAdrHigh)
 			return 1;
 	}
 
@@ -5867,7 +5879,7 @@ static int sisfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			ivideo->cardnumber++;
 	}
 
-	strlcpy(ivideo->myid, chipinfo->chip_name, sizeof(ivideo->myid));
+	strscpy(ivideo->myid, chipinfo->chip_name, sizeof(ivideo->myid));
 
 	ivideo->warncount = 0;
 	ivideo->chip_id = pdev->device;
@@ -6150,24 +6162,20 @@ static int sisfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 #endif
 
 #ifdef CONFIG_FB_SIS_315
-		if(ivideo->sisvga_engine == SIS_315_VGA) {
+		if (ivideo->sisvga_engine == SIS_315_VGA) {
 			int result = 1;
-		/*	if((ivideo->chip == SIS_315H)   ||
-			   (ivideo->chip == SIS_315)    ||
-			   (ivideo->chip == SIS_315PRO) ||
-			   (ivideo->chip == SIS_330)) {
-				sisfb_post_sis315330(pdev);
-			} else */ if(ivideo->chip == XGI_20) {
+
+			if (ivideo->chip == XGI_20) {
 				result = sisfb_post_xgi(pdev);
 				ivideo->sisfb_can_post = 1;
-			} else if((ivideo->chip == XGI_40) && ivideo->haveXGIROM) {
+			} else if ((ivideo->chip == XGI_40) && ivideo->haveXGIROM) {
 				result = sisfb_post_xgi(pdev);
 				ivideo->sisfb_can_post = 1;
 			} else {
 				printk(KERN_INFO "sisfb: Card is not "
 					"POSTed and sisfb can't do this either.\n");
 			}
-			if(!result) {
+			if (!result) {
 				printk(KERN_ERR "sisfb: Failed to POST card\n");
 				ret = -ENODEV;
 				goto error_3;
diff --git a/drivers/video/fbdev/sm501fb.c b/drivers/video/fbdev/sm501fb.c
index 6a52eba64559..fce6cfbadfd6 100644
--- a/drivers/video/fbdev/sm501fb.c
+++ b/drivers/video/fbdev/sm501fb.c
@@ -1719,7 +1719,7 @@ static int sm501fb_init_fb(struct fb_info *fb, enum sm501_controller head,
 		enable = 0;
 	}
 
-	strlcpy(fb->fix.id, fbname, sizeof(fb->fix.id));
+	strscpy(fb->fix.id, fbname, sizeof(fb->fix.id));
 
 	memcpy(&par->ops,
 	       (head == HEAD_CRT) ? &sm501fb_ops_crt : &sm501fb_ops_pnl,
diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c
index 5c765655d000..52e4ed9da78c 100644
--- a/drivers/video/fbdev/ssd1307fb.c
+++ b/drivers/video/fbdev/ssd1307fb.c
@@ -450,7 +450,7 @@ static int ssd1307fb_init(struct ssd1307fb_par *par)
 	if (ret < 0)
 		return ret;
 
-	/* Set Set Area Color Mode ON/OFF & Low Power Display Mode */
+	/* Set Area Color Mode ON/OFF & Low Power Display Mode */
 	if (par->area_color_enable || par->low_power) {
 		u32 mode;
 
diff --git a/drivers/video/fbdev/sstfb.c b/drivers/video/fbdev/sstfb.c
index 27d4b0ace2d6..cd4d640f9477 100644
--- a/drivers/video/fbdev/sstfb.c
+++ b/drivers/video/fbdev/sstfb.c
@@ -1382,7 +1382,7 @@ static int sstfb_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto fail;
 	}
 	sst_get_memsize(info, &fix->smem_len);
-	strlcpy(fix->id, spec->name, sizeof(fix->id));
+	strscpy(fix->id, spec->name, sizeof(fix->id));
 
 	printk(KERN_INFO "%s (revision %d) with %s dac\n",
 		fix->id, par->revision, par->dac_sw.name);
diff --git a/drivers/video/fbdev/sunxvr1000.c b/drivers/video/fbdev/sunxvr1000.c
index 15b079505a00..490bd9a14763 100644
--- a/drivers/video/fbdev/sunxvr1000.c
+++ b/drivers/video/fbdev/sunxvr1000.c
@@ -80,7 +80,7 @@ static int gfb_set_fbinfo(struct gfb_info *gp)
 	info->pseudo_palette = gp->pseudo_palette;
 
 	/* Fill fix common fields */
-	strlcpy(info->fix.id, "gfb", sizeof(info->fix.id));
+	strscpy(info->fix.id, "gfb", sizeof(info->fix.id));
         info->fix.smem_start = gp->fb_base_phys;
         info->fix.smem_len = gp->fb_size;
         info->fix.type = FB_TYPE_PACKED_PIXELS;
diff --git a/drivers/video/fbdev/sunxvr2500.c b/drivers/video/fbdev/sunxvr2500.c
index 1d3bacd9d5ac..1279b02234f8 100644
--- a/drivers/video/fbdev/sunxvr2500.c
+++ b/drivers/video/fbdev/sunxvr2500.c
@@ -84,7 +84,7 @@ static int s3d_set_fbinfo(struct s3d_info *sp)
 	info->pseudo_palette = sp->pseudo_palette;
 
 	/* Fill fix common fields */
-	strlcpy(info->fix.id, "s3d", sizeof(info->fix.id));
+	strscpy(info->fix.id, "s3d", sizeof(info->fix.id));
         info->fix.smem_start = sp->fb_base_phys;
         info->fix.smem_len = sp->fb_size;
         info->fix.type = FB_TYPE_PACKED_PIXELS;
diff --git a/drivers/video/fbdev/sunxvr500.c b/drivers/video/fbdev/sunxvr500.c
index 9daf17b11106..f7b463633ba0 100644
--- a/drivers/video/fbdev/sunxvr500.c
+++ b/drivers/video/fbdev/sunxvr500.c
@@ -207,7 +207,7 @@ static int e3d_set_fbinfo(struct e3d_info *ep)
 	info->pseudo_palette = ep->pseudo_palette;
 
 	/* Fill fix common fields */
-	strlcpy(info->fix.id, "e3d", sizeof(info->fix.id));
+	strscpy(info->fix.id, "e3d", sizeof(info->fix.id));
         info->fix.smem_start = ep->fb_base_phys;
         info->fix.smem_len = ep->fb_size;
         info->fix.type = FB_TYPE_PACKED_PIXELS;
diff --git a/drivers/video/fbdev/tcx.c b/drivers/video/fbdev/tcx.c
index 1638a40fed22..01d87f53324d 100644
--- a/drivers/video/fbdev/tcx.c
+++ b/drivers/video/fbdev/tcx.c
@@ -333,7 +333,7 @@ tcx_init_fix(struct fb_info *info, int linebytes)
 	else
 		tcx_name = "TCX24";
 
-	strlcpy(info->fix.id, tcx_name, sizeof(info->fix.id));
+	strscpy(info->fix.id, tcx_name, sizeof(info->fix.id));
 
 	info->fix.type = FB_TYPE_PACKED_PIXELS;
 	info->fix.visual = FB_VISUAL_PSEUDOCOLOR;
diff --git a/drivers/video/fbdev/tdfxfb.c b/drivers/video/fbdev/tdfxfb.c
index 67e37a62b07c..8a8122f8bfeb 100644
--- a/drivers/video/fbdev/tdfxfb.c
+++ b/drivers/video/fbdev/tdfxfb.c
@@ -1264,7 +1264,7 @@ static int tdfxfb_setup_ddc_bus(struct tdfxfb_i2c_chan *chan, const char *name,
 {
 	int rc;
 
-	strlcpy(chan->adapter.name, name, sizeof(chan->adapter.name));
+	strscpy(chan->adapter.name, name, sizeof(chan->adapter.name));
 	chan->adapter.owner		= THIS_MODULE;
 	chan->adapter.class		= I2C_CLASS_DDC;
 	chan->adapter.algo_data		= &chan->algo;
@@ -1293,7 +1293,7 @@ static int tdfxfb_setup_i2c_bus(struct tdfxfb_i2c_chan *chan, const char *name,
 {
 	int rc;
 
-	strlcpy(chan->adapter.name, name, sizeof(chan->adapter.name));
+	strscpy(chan->adapter.name, name, sizeof(chan->adapter.name));
 	chan->adapter.owner		= THIS_MODULE;
 	chan->adapter.algo_data		= &chan->algo;
 	chan->adapter.dev.parent	= dev;
diff --git a/drivers/video/fbdev/tgafb.c b/drivers/video/fbdev/tgafb.c
index ae0cf5540636..1fff5fd7ab51 100644
--- a/drivers/video/fbdev/tgafb.c
+++ b/drivers/video/fbdev/tgafb.c
@@ -1344,7 +1344,7 @@ tgafb_init_fix(struct fb_info *info)
 		memory_size = 16777216;
 	}
 
-	strlcpy(info->fix.id, tga_type_name, sizeof(info->fix.id));
+	strscpy(info->fix.id, tga_type_name, sizeof(info->fix.id));
 
 	info->fix.type = FB_TYPE_PACKED_PIXELS;
 	info->fix.type_aux = 0;
diff --git a/drivers/video/fbdev/tridentfb.c b/drivers/video/fbdev/tridentfb.c
index 319131bd72cf..cda095420ee8 100644
--- a/drivers/video/fbdev/tridentfb.c
+++ b/drivers/video/fbdev/tridentfb.c
@@ -270,7 +270,7 @@ static int tridentfb_setup_ddc_bus(struct fb_info *info)
 {
 	struct tridentfb_par *par = info->par;
 
-	strlcpy(par->ddc_adapter.name, info->fix.id,
+	strscpy(par->ddc_adapter.name, info->fix.id,
 		sizeof(par->ddc_adapter.name));
 	par->ddc_adapter.owner		= THIS_MODULE;
 	par->ddc_adapter.class		= I2C_CLASS_DDC;
diff --git a/drivers/virt/nitro_enclaves/Kconfig b/drivers/virt/nitro_enclaves/Kconfig
index ce91add81401..dc4d25c26256 100644
--- a/drivers/virt/nitro_enclaves/Kconfig
+++ b/drivers/virt/nitro_enclaves/Kconfig
@@ -17,7 +17,7 @@ config NITRO_ENCLAVES
 
 config NITRO_ENCLAVES_MISC_DEV_TEST
 	bool "Tests for the misc device functionality of the Nitro Enclaves" if !KUNIT_ALL_TESTS
-	depends on NITRO_ENCLAVES && KUNIT
+	depends on NITRO_ENCLAVES && KUNIT=y
 	default KUNIT_ALL_TESTS
 	help
 	  Enable KUnit tests for the misc device functionality of the Nitro
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index c492a57531c6..3ff746e3f24a 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -360,7 +360,7 @@ static void vm_synchronize_cbs(struct virtio_device *vdev)
 
 static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int index,
 				  void (*callback)(struct virtqueue *vq),
-				  const char *name, u32 size, bool ctx)
+				  const char *name, bool ctx)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
 	struct virtio_mmio_vq_info *info;
@@ -395,11 +395,8 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int in
 		goto error_new_virtqueue;
 	}
 
-	if (!size || size > num)
-		size = num;
-
 	/* Create the vring */
-	vq = vring_create_virtqueue(index, size, VIRTIO_MMIO_VRING_ALIGN, vdev,
+	vq = vring_create_virtqueue(index, num, VIRTIO_MMIO_VRING_ALIGN, vdev,
 				 true, true, ctx, vm_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;
@@ -477,7 +474,6 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 		       struct virtqueue *vqs[],
 		       vq_callback_t *callbacks[],
 		       const char * const names[],
-		       u32 sizes[],
 		       const bool *ctx,
 		       struct irq_affinity *desc)
 {
@@ -503,7 +499,6 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 		}
 
 		vqs[i] = vm_setup_vq(vdev, queue_idx++, callbacks[i], names[i],
-				     sizes ? sizes[i] : 0,
 				     ctx ? ctx[i] : false);
 		if (IS_ERR(vqs[i])) {
 			vm_del_vqs(vdev);
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 00ad476a815d..ad258a9d3b9f 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -174,7 +174,6 @@ error:
 static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned int index,
 				     void (*callback)(struct virtqueue *vq),
 				     const char *name,
-				     u32 size,
 				     bool ctx,
 				     u16 msix_vec)
 {
@@ -187,7 +186,7 @@ static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned int in
 	if (!info)
 		return ERR_PTR(-ENOMEM);
 
-	vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, size, ctx,
+	vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, ctx,
 			      msix_vec);
 	if (IS_ERR(vq))
 		goto out_info;
@@ -284,7 +283,7 @@ void vp_del_vqs(struct virtio_device *vdev)
 
 static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], u32 sizes[], bool per_vq_vectors,
+		const char * const names[], bool per_vq_vectors,
 		const bool *ctx,
 		struct irq_affinity *desc)
 {
@@ -327,8 +326,8 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs,
 		else
 			msix_vec = VP_MSIX_VQ_VECTOR;
 		vqs[i] = vp_setup_vq(vdev, queue_idx++, callbacks[i], names[i],
-				     sizes ? sizes[i] : 0,
-				     ctx ? ctx[i] : false, msix_vec);
+				     ctx ? ctx[i] : false,
+				     msix_vec);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
 			goto error_find;
@@ -358,7 +357,7 @@ error_find:
 
 static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], u32 sizes[], const bool *ctx)
+		const char * const names[], const bool *ctx)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	int i, err, queue_idx = 0;
@@ -380,7 +379,6 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs,
 			continue;
 		}
 		vqs[i] = vp_setup_vq(vdev, queue_idx++, callbacks[i], names[i],
-				     sizes ? sizes[i] : 0,
 				     ctx ? ctx[i] : false,
 				     VIRTIO_MSI_NO_VECTOR);
 		if (IS_ERR(vqs[i])) {
@@ -398,21 +396,21 @@ out_del_vqs:
 /* the config->find_vqs() implementation */
 int vp_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], u32 sizes[], const bool *ctx,
+		const char * const names[], const bool *ctx,
 		struct irq_affinity *desc)
 {
 	int err;
 
 	/* Try MSI-X with one vector per queue. */
-	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, sizes, true, ctx, desc);
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, true, ctx, desc);
 	if (!err)
 		return 0;
 	/* Fallback: MSI-X with one vector for config, one shared for queues. */
-	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, sizes, false, ctx, desc);
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false, ctx, desc);
 	if (!err)
 		return 0;
 	/* Finally fall back to regular interrupts. */
-	return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names, sizes, ctx);
+	return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names, ctx);
 }
 
 const char *vp_bus_name(struct virtio_device *vdev)
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index c0448378b698..23112d84218f 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -80,7 +80,6 @@ struct virtio_pci_device {
 				      unsigned int idx,
 				      void (*callback)(struct virtqueue *vq),
 				      const char *name,
-				      u32 size,
 				      bool ctx,
 				      u16 msix_vec);
 	void (*del_vq)(struct virtio_pci_vq_info *info);
@@ -111,7 +110,7 @@ void vp_del_vqs(struct virtio_device *vdev);
 /* the config->find_vqs() implementation */
 int vp_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], u32 sizes[], const bool *ctx,
+		const char * const names[], const bool *ctx,
 		struct irq_affinity *desc);
 const char *vp_bus_name(struct virtio_device *vdev);
 
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index d75e5c4e637f..2257f1b3d8ae 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -112,7 +112,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 				  unsigned int index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
-				  u32 size,
 				  bool ctx,
 				  u16 msix_vec)
 {
@@ -126,13 +125,10 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	if (!num || vp_legacy_get_queue_enable(&vp_dev->ldev, index))
 		return ERR_PTR(-ENOENT);
 
-	if (!size || size > num)
-		size = num;
-
 	info->msix_vector = msix_vec;
 
 	/* create the vring */
-	vq = vring_create_virtqueue(index, size,
+	vq = vring_create_virtqueue(index, num,
 				    VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
 				    true, false, ctx,
 				    vp_notify, callback, name);
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index f7965c5dd36b..c3b9f2761849 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -293,7 +293,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 				  unsigned int index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
-				  u32 size,
 				  bool ctx,
 				  u16 msix_vec)
 {
@@ -311,18 +310,15 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	if (!num || vp_modern_get_queue_enable(mdev, index))
 		return ERR_PTR(-ENOENT);
 
-	if (!size || size > num)
-		size = num;
-
-	if (size & (size - 1)) {
-		dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", size);
+	if (num & (num - 1)) {
+		dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", num);
 		return ERR_PTR(-EINVAL);
 	}
 
 	info->msix_vector = msix_vec;
 
 	/* create the vring */
-	vq = vring_create_virtqueue(index, size,
+	vq = vring_create_virtqueue(index, num,
 				    SMP_CACHE_BYTES, &vp_dev->vdev,
 				    true, true, ctx,
 				    vp_notify, callback, name);
@@ -351,15 +347,12 @@ err:
 static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 			      struct virtqueue *vqs[],
 			      vq_callback_t *callbacks[],
-			      const char * const names[],
-			      u32 sizes[],
-			      const bool *ctx,
+			      const char * const names[], const bool *ctx,
 			      struct irq_affinity *desc)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	struct virtqueue *vq;
-	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, sizes, ctx,
-			     desc);
+	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, ctx, desc);
 
 	if (rc)
 		return rc;
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index d66c8e6d0ef3..4620e9d79dde 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -2426,6 +2426,14 @@ static inline bool more_used(const struct vring_virtqueue *vq)
 	return vq->packed_ring ? more_used_packed(vq) : more_used_split(vq);
 }
 
+/**
+ * vring_interrupt - notify a virtqueue on an interrupt
+ * @irq: the IRQ number (ignored)
+ * @_vq: the struct virtqueue to notify
+ *
+ * Calls the callback function of @_vq to process the virtqueue
+ * notification.
+ */
 irqreturn_t vring_interrupt(int irq, void *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c
index 9bc4d110b800..9670cc79371d 100644
--- a/drivers/virtio/virtio_vdpa.c
+++ b/drivers/virtio/virtio_vdpa.c
@@ -131,7 +131,7 @@ static irqreturn_t virtio_vdpa_virtqueue_cb(void *private)
 static struct virtqueue *
 virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index,
 		     void (*callback)(struct virtqueue *vq),
-		     const char *name, u32 size, bool ctx)
+		     const char *name, bool ctx)
 {
 	struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev);
 	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
@@ -168,17 +168,14 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index,
 		goto error_new_virtqueue;
 	}
 
-	if (!size || size > max_num)
-		size = max_num;
-
 	if (ops->get_vq_num_min)
 		min_num = ops->get_vq_num_min(vdpa);
 
-	may_reduce_num = (size == min_num) ? false : true;
+	may_reduce_num = (max_num == min_num) ? false : true;
 
 	/* Create the vring */
 	align = ops->get_vq_align(vdpa);
-	vq = vring_create_virtqueue(index, size, align, vdev,
+	vq = vring_create_virtqueue(index, max_num, align, vdev,
 				    true, may_reduce_num, ctx,
 				    virtio_vdpa_notify, callback, name);
 	if (!vq) {
@@ -272,7 +269,6 @@ static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 				struct virtqueue *vqs[],
 				vq_callback_t *callbacks[],
 				const char * const names[],
-				u32 sizes[],
 				const bool *ctx,
 				struct irq_affinity *desc)
 {
@@ -288,9 +284,9 @@ static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 			continue;
 		}
 
-		vqs[i] = virtio_vdpa_setup_vq(vdev, queue_idx++, callbacks[i],
-						  names[i], sizes ? sizes[i] : 0,
-						  ctx ? ctx[i] : false);
+		vqs[i] = virtio_vdpa_setup_vq(vdev, queue_idx++,
+					      callbacks[i], names[i], ctx ?
+					      ctx[i] : false);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
 			goto err_setup_vq;
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 738029de3c67..e1ec725c2819 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -1047,6 +1047,9 @@ int gnttab_dma_alloc_pages(struct gnttab_dma_alloc_args *args)
 	size_t size;
 	int i, ret;
 
+	if (args->nr_pages < 0 || args->nr_pages > (INT_MAX >> PAGE_SHIFT))
+		return -ENOMEM;
+
 	size = args->nr_pages << PAGE_SHIFT;
 	if (args->coherent)
 		args->vaddr = dma_alloc_coherent(args->dev, size,
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 3369734108af..e88e8f6f0a33 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -581,27 +581,30 @@ static int lock_pages(
 	struct privcmd_dm_op_buf kbufs[], unsigned int num,
 	struct page *pages[], unsigned int nr_pages, unsigned int *pinned)
 {
-	unsigned int i;
+	unsigned int i, off = 0;
 
-	for (i = 0; i < num; i++) {
+	for (i = 0; i < num; ) {
 		unsigned int requested;
 		int page_count;
 
 		requested = DIV_ROUND_UP(
 			offset_in_page(kbufs[i].uptr) + kbufs[i].size,
-			PAGE_SIZE);
+			PAGE_SIZE) - off;
 		if (requested > nr_pages)
 			return -ENOSPC;
 
 		page_count = pin_user_pages_fast(
-			(unsigned long) kbufs[i].uptr,
+			(unsigned long)kbufs[i].uptr + off * PAGE_SIZE,
 			requested, FOLL_WRITE, pages);
-		if (page_count < 0)
-			return page_count;
+		if (page_count <= 0)
+			return page_count ? : -EFAULT;
 
 		*pinned += page_count;
 		nr_pages -= page_count;
 		pages += page_count;
+
+		off = (requested == page_count) ? 0 : off + page_count;
+		i += !off;
 	}
 
 	return 0;
@@ -677,10 +680,8 @@ static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
 	}
 
 	rc = lock_pages(kbufs, kdata.num, pages, nr_pages, &pinned);
-	if (rc < 0) {
-		nr_pages = pinned;
+	if (rc < 0)
 		goto out;
-	}
 
 	for (i = 0; i < kdata.num; i++) {
 		set_xen_guest_handle(xbufs[i].h, kbufs[i].uptr);
@@ -692,7 +693,7 @@ static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
 	xen_preemptible_hcall_end();
 
 out:
-	unlock_pages(pages, nr_pages);
+	unlock_pages(pages, pinned);
 	kfree(xbufs);
 	kfree(pages);
 	kfree(kbufs);
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index 7a0c93acc2c5..d3dcda344989 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -1121,7 +1121,7 @@ static void scsiback_do_1lun_hotplug(struct vscsibk_info *info, int op,
 				"%s: writing %s", __func__, state);
 		return;
 	}
-	strlcpy(phy, val, VSCSI_NAMELEN);
+	strscpy(phy, val, VSCSI_NAMELEN);
 	kfree(val);
 
 	/* virtual SCSI device */
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index d5f3f763717e..d4b251925796 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -382,9 +382,10 @@ int xenbus_setup_ring(struct xenbus_device *dev, gfp_t gfp, void **vaddr,
 	unsigned long ring_size = nr_pages * XEN_PAGE_SIZE;
 	grant_ref_t gref_head;
 	unsigned int i;
+	void *addr;
 	int ret;
 
-	*vaddr = alloc_pages_exact(ring_size, gfp | __GFP_ZERO);
+	addr = *vaddr = alloc_pages_exact(ring_size, gfp | __GFP_ZERO);
 	if (!*vaddr) {
 		ret = -ENOMEM;
 		goto err;
@@ -401,13 +402,15 @@ int xenbus_setup_ring(struct xenbus_device *dev, gfp_t gfp, void **vaddr,
 		unsigned long gfn;
 
 		if (is_vmalloc_addr(*vaddr))
-			gfn = pfn_to_gfn(vmalloc_to_pfn(vaddr[i]));
+			gfn = pfn_to_gfn(vmalloc_to_pfn(addr));
 		else
-			gfn = virt_to_gfn(vaddr[i]);
+			gfn = virt_to_gfn(addr);
 
 		grefs[i] = gnttab_claim_grant_reference(&gref_head);
 		gnttab_grant_foreign_access_ref(grefs[i], dev->otherend_id,
 						gfn, 0);
+
+		addr += XEN_PAGE_SIZE;
 	}
 
 	return 0;
diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c
index 07b010a68fcf..f44d5a64351e 100644
--- a/drivers/xen/xenbus/xenbus_probe_frontend.c
+++ b/drivers/xen/xenbus/xenbus_probe_frontend.c
@@ -40,7 +40,7 @@ static int frontend_bus_id(char bus_id[XEN_BUS_ID_SIZE], const char *nodename)
 		return -EINVAL;
 	}
 
-	strlcpy(bus_id, nodename + 1, XEN_BUS_ID_SIZE);
+	strscpy(bus_id, nodename + 1, XEN_BUS_ID_SIZE);
 	if (!strchr(bus_id, '/')) {
 		pr_warn("bus_id %s no slash\n", bus_id);
 		return -EINVAL;
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 21e154516bf2..f14478643b91 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -142,39 +142,6 @@ config BINFMT_ZFLAT
 	help
 	  Support FLAT format compressed binaries
 
-config HAVE_AOUT
-       def_bool n
-
-config BINFMT_AOUT
-	tristate "Kernel support for a.out and ECOFF binaries"
-	depends on HAVE_AOUT
-	help
-	  A.out (Assembler.OUTput) is a set of formats for libraries and
-	  executables used in the earliest versions of UNIX.  Linux used
-	  the a.out formats QMAGIC and ZMAGIC until they were replaced
-	  with the ELF format.
-
-	  The conversion to ELF started in 1995.  This option is primarily
-	  provided for historical interest and for the benefit of those
-	  who need to run binaries from that era.
-
-	  Most people should answer N here.  If you think you may have
-	  occasional use for this format, enable module support above
-	  and answer M here to compile this support as a module called
-	  binfmt_aout.
-
-	  If any crucial components of your system (such as /sbin/init
-	  or /lib/ld.so) are still in a.out format, you will have to
-	  say Y here.
-
-config OSF4_COMPAT
-	bool "OSF/1 v4 readv/writev compatibility"
-	depends on ALPHA && BINFMT_AOUT
-	help
-	  Say Y if you are using OSF/1 binaries (like Netscape and Acrobat)
-	  with v4 shared libraries freely available from Compaq. If you're
-	  going to use shared libraries from Tru64 version 5.0 or later, say N.
-
 config BINFMT_MISC
 	tristate "Kernel support for MISC binaries"
 	help
diff --git a/fs/Makefile b/fs/Makefile
index 93b80529f8e8..4dea17840761 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -38,7 +38,6 @@ obj-$(CONFIG_FS_DAX)		+= dax.o
 obj-$(CONFIG_FS_ENCRYPTION)	+= crypto/
 obj-$(CONFIG_FS_VERITY)		+= verity/
 obj-$(CONFIG_FILE_LOCKING)      += locks.o
-obj-$(CONFIG_BINFMT_AOUT)	+= binfmt_aout.o
 obj-$(CONFIG_BINFMT_MISC)	+= binfmt_misc.o
 obj-$(CONFIG_BINFMT_SCRIPT)	+= binfmt_script.o
 obj-$(CONFIG_BINFMT_ELF)	+= binfmt_elf.o
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index c4210a3964d8..bbcc5afd1576 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -76,7 +76,7 @@ void afs_lock_op_done(struct afs_call *call)
 	if (call->error == 0) {
 		spin_lock(&vnode->lock);
 		trace_afs_flock_ev(vnode, NULL, afs_flock_timestamp, 0);
-		vnode->locked_at = call->reply_time;
+		vnode->locked_at = call->issue_time;
 		afs_schedule_lock_extension(vnode);
 		spin_unlock(&vnode->lock);
 	}
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 4943413d9c5f..7d37f63ef0f0 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -131,7 +131,7 @@ bad:
 
 static time64_t xdr_decode_expiry(struct afs_call *call, u32 expiry)
 {
-	return ktime_divns(call->reply_time, NSEC_PER_SEC) + expiry;
+	return ktime_divns(call->issue_time, NSEC_PER_SEC) + expiry;
 }
 
 static void xdr_decode_AFSCallBack(const __be32 **_bp,
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 64ad55494349..723d162078a3 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -137,7 +137,6 @@ struct afs_call {
 	bool			need_attention;	/* T if RxRPC poked us */
 	bool			async;		/* T if asynchronous */
 	bool			upgrade;	/* T to request service upgrade */
-	bool			have_reply_time; /* T if have got reply_time */
 	bool			intr;		/* T if interruptible */
 	bool			unmarshalling_error; /* T if an unmarshalling error occurred */
 	u16			service_id;	/* Actual service ID (after upgrade) */
@@ -151,7 +150,7 @@ struct afs_call {
 		} __attribute__((packed));
 		__be64		tmp64;
 	};
-	ktime_t			reply_time;	/* Time of first reply packet */
+	ktime_t			issue_time;	/* Time of issue of operation */
 };
 
 struct afs_call_type {
diff --git a/fs/afs/misc.c b/fs/afs/misc.c
index 933e67fcdab1..805328ca5428 100644
--- a/fs/afs/misc.c
+++ b/fs/afs/misc.c
@@ -69,6 +69,7 @@ int afs_abort_to_error(u32 abort_code)
 		/* Unified AFS error table */
 	case UAEPERM:			return -EPERM;
 	case UAENOENT:			return -ENOENT;
+	case UAEAGAIN:			return -EAGAIN;
 	case UAEACCES:			return -EACCES;
 	case UAEBUSY:			return -EBUSY;
 	case UAEEXIST:			return -EEXIST;
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index d5c4785c862d..eccc3cd0cb70 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -351,6 +351,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	if (call->max_lifespan)
 		rxrpc_kernel_set_max_life(call->net->socket, rxcall,
 					  call->max_lifespan);
+	call->issue_time = ktime_get_real();
 
 	/* send the request */
 	iov[0].iov_base	= call->request;
@@ -501,12 +502,6 @@ static void afs_deliver_to_call(struct afs_call *call)
 			return;
 		}
 
-		if (!call->have_reply_time &&
-		    rxrpc_kernel_get_reply_time(call->net->socket,
-						call->rxcall,
-						&call->reply_time))
-			call->have_reply_time = true;
-
 		ret = call->type->deliver(call);
 		state = READ_ONCE(call->state);
 		if (ret == 0 && call->unmarshalling_error)
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index fdc7d675b4b0..11571cca86c1 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -232,8 +232,7 @@ static void xdr_decode_YFSCallBack(const __be32 **_bp,
 	struct afs_callback *cb = &scb->callback;
 	ktime_t cb_expiry;
 
-	cb_expiry = call->reply_time;
-	cb_expiry = ktime_add(cb_expiry, xdr_to_u64(x->expiration_time) * 100);
+	cb_expiry = ktime_add(call->issue_time, xdr_to_u64(x->expiration_time) * 100);
 	cb->expires_at	= ktime_divns(cb_expiry, NSEC_PER_SEC);
 	scb->have_cb	= true;
 	*_bp += xdr_size(x);
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
deleted file mode 100644
index 0dcfc691e7e2..000000000000
--- a/fs/binfmt_aout.c
+++ /dev/null
@@ -1,342 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  linux/fs/binfmt_aout.c
- *
- *  Copyright (C) 1991, 1992, 1996  Linus Torvalds
- */
-
-#include <linux/module.h>
-
-#include <linux/time.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/mman.h>
-#include <linux/a.out.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/file.h>
-#include <linux/stat.h>
-#include <linux/fcntl.h>
-#include <linux/ptrace.h>
-#include <linux/user.h>
-#include <linux/binfmts.h>
-#include <linux/personality.h>
-#include <linux/init.h>
-#include <linux/coredump.h>
-#include <linux/slab.h>
-#include <linux/sched/task_stack.h>
-
-#include <linux/uaccess.h>
-#include <asm/cacheflush.h>
-
-static int load_aout_binary(struct linux_binprm *);
-static int load_aout_library(struct file*);
-
-static struct linux_binfmt aout_format = {
-	.module		= THIS_MODULE,
-	.load_binary	= load_aout_binary,
-	.load_shlib	= load_aout_library,
-};
-
-#define BAD_ADDR(x)	((unsigned long)(x) >= TASK_SIZE)
-
-static int set_brk(unsigned long start, unsigned long end)
-{
-	start = PAGE_ALIGN(start);
-	end = PAGE_ALIGN(end);
-	if (end > start)
-		return vm_brk(start, end - start);
-	return 0;
-}
-
-/*
- * create_aout_tables() parses the env- and arg-strings in new user
- * memory and creates the pointer tables from them, and puts their
- * addresses on the "stack", returning the new stack pointer value.
- */
-static unsigned long __user *create_aout_tables(char __user *p, struct linux_binprm * bprm)
-{
-	char __user * __user *argv;
-	char __user * __user *envp;
-	unsigned long __user *sp;
-	int argc = bprm->argc;
-	int envc = bprm->envc;
-
-	sp = (void __user *)((-(unsigned long)sizeof(char *)) & (unsigned long) p);
-#ifdef __alpha__
-/* whee.. test-programs are so much fun. */
-	put_user(0, --sp);
-	put_user(0, --sp);
-	if (bprm->loader) {
-		put_user(0, --sp);
-		put_user(1003, --sp);
-		put_user(bprm->loader, --sp);
-		put_user(1002, --sp);
-	}
-	put_user(bprm->exec, --sp);
-	put_user(1001, --sp);
-#endif
-	sp -= envc+1;
-	envp = (char __user * __user *) sp;
-	sp -= argc+1;
-	argv = (char __user * __user *) sp;
-#ifndef __alpha__
-	put_user((unsigned long) envp,--sp);
-	put_user((unsigned long) argv,--sp);
-#endif
-	put_user(argc,--sp);
-	current->mm->arg_start = (unsigned long) p;
-	while (argc-->0) {
-		char c;
-		put_user(p,argv++);
-		do {
-			get_user(c,p++);
-		} while (c);
-	}
-	put_user(NULL,argv);
-	current->mm->arg_end = current->mm->env_start = (unsigned long) p;
-	while (envc-->0) {
-		char c;
-		put_user(p,envp++);
-		do {
-			get_user(c,p++);
-		} while (c);
-	}
-	put_user(NULL,envp);
-	current->mm->env_end = (unsigned long) p;
-	return sp;
-}
-
-/*
- * These are the functions used to load a.out style executables and shared
- * libraries.  There is no binary dependent code anywhere else.
- */
-
-static int load_aout_binary(struct linux_binprm * bprm)
-{
-	struct pt_regs *regs = current_pt_regs();
-	struct exec ex;
-	unsigned long error;
-	unsigned long fd_offset;
-	unsigned long rlim;
-	int retval;
-
-	ex = *((struct exec *) bprm->buf);		/* exec-header */
-	if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != OMAGIC &&
-	     N_MAGIC(ex) != QMAGIC && N_MAGIC(ex) != NMAGIC) ||
-	    N_TRSIZE(ex) || N_DRSIZE(ex) ||
-	    i_size_read(file_inode(bprm->file)) < ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
-		return -ENOEXEC;
-	}
-
-	/*
-	 * Requires a mmap handler. This prevents people from using a.out
-	 * as part of an exploit attack against /proc-related vulnerabilities.
-	 */
-	if (!bprm->file->f_op->mmap)
-		return -ENOEXEC;
-
-	fd_offset = N_TXTOFF(ex);
-
-	/* Check initial limits. This avoids letting people circumvent
-	 * size limits imposed on them by creating programs with large
-	 * arrays in the data or bss.
-	 */
-	rlim = rlimit(RLIMIT_DATA);
-	if (rlim >= RLIM_INFINITY)
-		rlim = ~0;
-	if (ex.a_data + ex.a_bss > rlim)
-		return -ENOMEM;
-
-	/* Flush all traces of the currently running executable */
-	retval = begin_new_exec(bprm);
-	if (retval)
-		return retval;
-
-	/* OK, This is the point of no return */
-#ifdef __alpha__
-	SET_AOUT_PERSONALITY(bprm, ex);
-#else
-	set_personality(PER_LINUX);
-#endif
-	setup_new_exec(bprm);
-
-	current->mm->end_code = ex.a_text +
-		(current->mm->start_code = N_TXTADDR(ex));
-	current->mm->end_data = ex.a_data +
-		(current->mm->start_data = N_DATADDR(ex));
-	current->mm->brk = ex.a_bss +
-		(current->mm->start_brk = N_BSSADDR(ex));
-
-	retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT);
-	if (retval < 0)
-		return retval;
-
-
-	if (N_MAGIC(ex) == OMAGIC) {
-		unsigned long text_addr, map_size;
-		loff_t pos;
-
-		text_addr = N_TXTADDR(ex);
-
-#ifdef __alpha__
-		pos = fd_offset;
-		map_size = ex.a_text+ex.a_data + PAGE_SIZE - 1;
-#else
-		pos = 32;
-		map_size = ex.a_text+ex.a_data;
-#endif
-		error = vm_brk(text_addr & PAGE_MASK, map_size);
-		if (error)
-			return error;
-
-		error = read_code(bprm->file, text_addr, pos,
-				  ex.a_text+ex.a_data);
-		if ((signed long)error < 0)
-			return error;
-	} else {
-		if ((ex.a_text & 0xfff || ex.a_data & 0xfff) &&
-		    (N_MAGIC(ex) != NMAGIC) && printk_ratelimit())
-		{
-			printk(KERN_NOTICE "executable not page aligned\n");
-		}
-
-		if ((fd_offset & ~PAGE_MASK) != 0 && printk_ratelimit())
-		{
-			printk(KERN_WARNING 
-			       "fd_offset is not page aligned. Please convert program: %pD\n",
-			       bprm->file);
-		}
-
-		if (!bprm->file->f_op->mmap||((fd_offset & ~PAGE_MASK) != 0)) {
-			error = vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
-			if (error)
-				return error;
-
-			read_code(bprm->file, N_TXTADDR(ex), fd_offset,
-				  ex.a_text + ex.a_data);
-			goto beyond_if;
-		}
-
-		error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
-			PROT_READ | PROT_EXEC, MAP_FIXED | MAP_PRIVATE,
-			fd_offset);
-
-		if (error != N_TXTADDR(ex))
-			return error;
-
-		error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
-				PROT_READ | PROT_WRITE | PROT_EXEC,
-				MAP_FIXED | MAP_PRIVATE,
-				fd_offset + ex.a_text);
-		if (error != N_DATADDR(ex))
-			return error;
-	}
-beyond_if:
-	set_binfmt(&aout_format);
-
-	retval = set_brk(current->mm->start_brk, current->mm->brk);
-	if (retval < 0)
-		return retval;
-
-	current->mm->start_stack =
-		(unsigned long) create_aout_tables((char __user *) bprm->p, bprm);
-#ifdef __alpha__
-	regs->gp = ex.a_gpvalue;
-#endif
-	finalize_exec(bprm);
-	start_thread(regs, ex.a_entry, current->mm->start_stack);
-	return 0;
-}
-
-static int load_aout_library(struct file *file)
-{
-	struct inode * inode;
-	unsigned long bss, start_addr, len;
-	unsigned long error;
-	int retval;
-	struct exec ex;
-	loff_t pos = 0;
-
-	inode = file_inode(file);
-
-	retval = -ENOEXEC;
-	error = kernel_read(file, &ex, sizeof(ex), &pos);
-	if (error != sizeof(ex))
-		goto out;
-
-	/* We come in here for the regular a.out style of shared libraries */
-	if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != QMAGIC) || N_TRSIZE(ex) ||
-	    N_DRSIZE(ex) || ((ex.a_entry & 0xfff) && N_MAGIC(ex) == ZMAGIC) ||
-	    i_size_read(inode) < ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
-		goto out;
-	}
-
-	/*
-	 * Requires a mmap handler. This prevents people from using a.out
-	 * as part of an exploit attack against /proc-related vulnerabilities.
-	 */
-	if (!file->f_op->mmap)
-		goto out;
-
-	if (N_FLAGS(ex))
-		goto out;
-
-	/* For  QMAGIC, the starting address is 0x20 into the page.  We mask
-	   this off to get the starting address for the page */
-
-	start_addr =  ex.a_entry & 0xfffff000;
-
-	if ((N_TXTOFF(ex) & ~PAGE_MASK) != 0) {
-		if (printk_ratelimit())
-		{
-			printk(KERN_WARNING 
-			       "N_TXTOFF is not page aligned. Please convert library: %pD\n",
-			       file);
-		}
-		retval = vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
-		if (retval)
-			goto out;
-
-		read_code(file, start_addr, N_TXTOFF(ex),
-			  ex.a_text + ex.a_data);
-		retval = 0;
-		goto out;
-	}
-	/* Now use mmap to map the library into memory. */
-	error = vm_mmap(file, start_addr, ex.a_text + ex.a_data,
-			PROT_READ | PROT_WRITE | PROT_EXEC,
-			MAP_FIXED | MAP_PRIVATE,
-			N_TXTOFF(ex));
-	retval = error;
-	if (error != start_addr)
-		goto out;
-
-	len = PAGE_ALIGN(ex.a_text + ex.a_data);
-	bss = ex.a_text + ex.a_data + ex.a_bss;
-	if (bss > len) {
-		retval = vm_brk(start_addr + len, bss - len);
-		if (retval)
-			goto out;
-	}
-	retval = 0;
-out:
-	return retval;
-}
-
-static int __init init_aout_binfmt(void)
-{
-	register_binfmt(&aout_format);
-	return 0;
-}
-
-static void __exit exit_aout_binfmt(void)
-{
-	unregister_binfmt(&aout_format);
-}
-
-core_initcall(init_aout_binfmt);
-module_exit(exit_aout_binfmt);
-MODULE_LICENSE("GPL");
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index c3aecfb0a71d..e0375ba9d0fe 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -440,39 +440,26 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
 	btrfs_put_caching_control(caching_ctl);
 }
 
-int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache)
+static int btrfs_caching_ctl_wait_done(struct btrfs_block_group *cache,
+				       struct btrfs_caching_control *caching_ctl)
+{
+	wait_event(caching_ctl->wait, btrfs_block_group_done(cache));
+	return cache->cached == BTRFS_CACHE_ERROR ? -EIO : 0;
+}
+
+static int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache)
 {
 	struct btrfs_caching_control *caching_ctl;
-	int ret = 0;
+	int ret;
 
 	caching_ctl = btrfs_get_caching_control(cache);
 	if (!caching_ctl)
 		return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0;
-
-	wait_event(caching_ctl->wait, btrfs_block_group_done(cache));
-	if (cache->cached == BTRFS_CACHE_ERROR)
-		ret = -EIO;
+	ret = btrfs_caching_ctl_wait_done(cache, caching_ctl);
 	btrfs_put_caching_control(caching_ctl);
 	return ret;
 }
 
-static bool space_cache_v1_done(struct btrfs_block_group *cache)
-{
-	bool ret;
-
-	spin_lock(&cache->lock);
-	ret = cache->cached != BTRFS_CACHE_FAST;
-	spin_unlock(&cache->lock);
-
-	return ret;
-}
-
-void btrfs_wait_space_cache_v1_finished(struct btrfs_block_group *cache,
-				struct btrfs_caching_control *caching_ctl)
-{
-	wait_event(caching_ctl->wait, space_cache_v1_done(cache));
-}
-
 #ifdef CONFIG_BTRFS_DEBUG
 static void fragment_free_space(struct btrfs_block_group *block_group)
 {
@@ -750,9 +737,8 @@ done:
 	btrfs_put_block_group(block_group);
 }
 
-int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only)
+int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait)
 {
-	DEFINE_WAIT(wait);
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_caching_control *caching_ctl = NULL;
 	int ret = 0;
@@ -785,10 +771,7 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only
 	}
 	WARN_ON(cache->caching_ctl);
 	cache->caching_ctl = caching_ctl;
-	if (btrfs_test_opt(fs_info, SPACE_CACHE))
-		cache->cached = BTRFS_CACHE_FAST;
-	else
-		cache->cached = BTRFS_CACHE_STARTED;
+	cache->cached = BTRFS_CACHE_STARTED;
 	cache->has_caching_ctl = 1;
 	spin_unlock(&cache->lock);
 
@@ -801,8 +784,8 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only
 
 	btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work);
 out:
-	if (load_cache_only && caching_ctl)
-		btrfs_wait_space_cache_v1_finished(cache, caching_ctl);
+	if (wait && caching_ctl)
+		ret = btrfs_caching_ctl_wait_done(cache, caching_ctl);
 	if (caching_ctl)
 		btrfs_put_caching_control(caching_ctl);
 
@@ -1640,9 +1623,11 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 				div64_u64(zone_unusable * 100, bg->length));
 		trace_btrfs_reclaim_block_group(bg);
 		ret = btrfs_relocate_chunk(fs_info, bg->start);
-		if (ret)
+		if (ret) {
+			btrfs_dec_block_group_ro(bg);
 			btrfs_err(fs_info, "error relocating chunk %llu",
 				  bg->start);
+		}
 
 next:
 		btrfs_put_block_group(bg);
@@ -3310,7 +3295,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 		 * space back to the block group, otherwise we will leak space.
 		 */
 		if (!alloc && !btrfs_block_group_done(cache))
-			btrfs_cache_block_group(cache, 1);
+			btrfs_cache_block_group(cache, true);
 
 		byte_in_group = bytenr - cache->start;
 		WARN_ON(byte_in_group > cache->length);
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index 35e0e860cc0b..6b3cdc4cbc41 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -263,9 +263,7 @@ void btrfs_dec_nocow_writers(struct btrfs_block_group *bg);
 void btrfs_wait_nocow_writers(struct btrfs_block_group *bg);
 void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
 				           u64 num_bytes);
-int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache);
-int btrfs_cache_block_group(struct btrfs_block_group *cache,
-			    int load_cache_only);
+int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait);
 void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
 struct btrfs_caching_control *btrfs_get_caching_control(
 		struct btrfs_block_group *cache);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 6e556031a8f3..ebfa35fe1c38 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -2075,6 +2075,9 @@ cow_done:
 
 		if (!p->skip_locking) {
 			level = btrfs_header_level(b);
+
+			btrfs_maybe_reset_lockdep_class(root, b);
+
 			if (level <= write_lock_level) {
 				btrfs_tree_lock(b);
 				p->locks[level] = BTRFS_WRITE_LOCK;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 4db85b9dc7ed..df8c99c99df9 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -505,7 +505,6 @@ struct btrfs_free_cluster {
 enum btrfs_caching_type {
 	BTRFS_CACHE_NO,
 	BTRFS_CACHE_STARTED,
-	BTRFS_CACHE_FAST,
 	BTRFS_CACHE_FINISHED,
 	BTRFS_CACHE_ERROR,
 };
@@ -1089,8 +1088,6 @@ struct btrfs_fs_info {
 
 	spinlock_t zone_active_bgs_lock;
 	struct list_head zone_active_bgs;
-	/* Waiters when BTRFS_FS_NEED_ZONE_FINISH is set */
-	wait_queue_head_t zone_finish_wait;
 
 	/* Updates are not protected by any lock */
 	struct btrfs_commit_stats commit_stats;
@@ -1173,6 +1170,8 @@ enum {
 	BTRFS_ROOT_ORPHAN_CLEANUP,
 	/* This root has a drop operation that was started previously. */
 	BTRFS_ROOT_UNFINISHED_DROP,
+	/* This reloc root needs to have its buffers lockdep class reset. */
+	BTRFS_ROOT_RESET_LOCKDEP_CLASS,
 };
 
 static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index f43196a893ca..41cddd3ff059 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -165,7 +165,7 @@ no_valid_dev_replace_entry_found:
 		 */
 		if (btrfs_find_device(fs_info->fs_devices, &args)) {
 			btrfs_err(fs_info,
-			"replace devid present without an active replace item");
+"replace without active item, run 'device scan --forget' on the target device");
 			ret = -EUCLEAN;
 		} else {
 			dev_replace->srcdev = NULL;
@@ -1129,8 +1129,7 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 		up_write(&dev_replace->rwsem);
 
 		/* Scrub for replace must not be running in suspended state */
-		ret = btrfs_scrub_cancel(fs_info);
-		ASSERT(ret != -ENOTCONN);
+		btrfs_scrub_cancel(fs_info);
 
 		trans = btrfs_start_transaction(root, 0);
 		if (IS_ERR(trans)) {
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4c3166f3c725..2633137c3e9f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -87,88 +87,6 @@ struct async_submit_bio {
 };
 
 /*
- * Lockdep class keys for extent_buffer->lock's in this root.  For a given
- * eb, the lockdep key is determined by the btrfs_root it belongs to and
- * the level the eb occupies in the tree.
- *
- * Different roots are used for different purposes and may nest inside each
- * other and they require separate keysets.  As lockdep keys should be
- * static, assign keysets according to the purpose of the root as indicated
- * by btrfs_root->root_key.objectid.  This ensures that all special purpose
- * roots have separate keysets.
- *
- * Lock-nesting across peer nodes is always done with the immediate parent
- * node locked thus preventing deadlock.  As lockdep doesn't know this, use
- * subclass to avoid triggering lockdep warning in such cases.
- *
- * The key is set by the readpage_end_io_hook after the buffer has passed
- * csum validation but before the pages are unlocked.  It is also set by
- * btrfs_init_new_buffer on freshly allocated blocks.
- *
- * We also add a check to make sure the highest level of the tree is the
- * same as our lockdep setup here.  If BTRFS_MAX_LEVEL changes, this code
- * needs update as well.
- */
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# if BTRFS_MAX_LEVEL != 8
-#  error
-# endif
-
-#define DEFINE_LEVEL(stem, level)					\
-	.names[level] = "btrfs-" stem "-0" #level,
-
-#define DEFINE_NAME(stem)						\
-	DEFINE_LEVEL(stem, 0)						\
-	DEFINE_LEVEL(stem, 1)						\
-	DEFINE_LEVEL(stem, 2)						\
-	DEFINE_LEVEL(stem, 3)						\
-	DEFINE_LEVEL(stem, 4)						\
-	DEFINE_LEVEL(stem, 5)						\
-	DEFINE_LEVEL(stem, 6)						\
-	DEFINE_LEVEL(stem, 7)
-
-static struct btrfs_lockdep_keyset {
-	u64			id;		/* root objectid */
-	/* Longest entry: btrfs-free-space-00 */
-	char			names[BTRFS_MAX_LEVEL][20];
-	struct lock_class_key	keys[BTRFS_MAX_LEVEL];
-} btrfs_lockdep_keysets[] = {
-	{ .id = BTRFS_ROOT_TREE_OBJECTID,	DEFINE_NAME("root")	},
-	{ .id = BTRFS_EXTENT_TREE_OBJECTID,	DEFINE_NAME("extent")	},
-	{ .id = BTRFS_CHUNK_TREE_OBJECTID,	DEFINE_NAME("chunk")	},
-	{ .id = BTRFS_DEV_TREE_OBJECTID,	DEFINE_NAME("dev")	},
-	{ .id = BTRFS_CSUM_TREE_OBJECTID,	DEFINE_NAME("csum")	},
-	{ .id = BTRFS_QUOTA_TREE_OBJECTID,	DEFINE_NAME("quota")	},
-	{ .id = BTRFS_TREE_LOG_OBJECTID,	DEFINE_NAME("log")	},
-	{ .id = BTRFS_TREE_RELOC_OBJECTID,	DEFINE_NAME("treloc")	},
-	{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID,	DEFINE_NAME("dreloc")	},
-	{ .id = BTRFS_UUID_TREE_OBJECTID,	DEFINE_NAME("uuid")	},
-	{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID,	DEFINE_NAME("free-space") },
-	{ .id = 0,				DEFINE_NAME("tree")	},
-};
-
-#undef DEFINE_LEVEL
-#undef DEFINE_NAME
-
-void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
-				    int level)
-{
-	struct btrfs_lockdep_keyset *ks;
-
-	BUG_ON(level >= ARRAY_SIZE(ks->keys));
-
-	/* find the matching keyset, id 0 is the default entry */
-	for (ks = btrfs_lockdep_keysets; ks->id; ks++)
-		if (ks->id == objectid)
-			break;
-
-	lockdep_set_class_and_name(&eb->lock,
-				   &ks->keys[level], ks->names[level]);
-}
-
-#endif
-
-/*
  * Compute the csum of a btree block and store the result to provided buffer.
  */
 static void csum_tree_block(struct extent_buffer *buf, u8 *result)
@@ -3150,7 +3068,6 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	init_waitqueue_head(&fs_info->transaction_blocked_wait);
 	init_waitqueue_head(&fs_info->async_submit_wait);
 	init_waitqueue_head(&fs_info->delayed_iputs_wait);
-	init_waitqueue_head(&fs_info->zone_finish_wait);
 
 	/* Usable values until the real ones are cached from the superblock */
 	fs_info->nodesize = 4096;
@@ -4558,6 +4475,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags);
 
 	/*
+	 * If we had UNFINISHED_DROPS we could still be processing them, so
+	 * clear that bit and wake up relocation so it can stop.
+	 * We must do this before stopping the block group reclaim task, because
+	 * at btrfs_relocate_block_group() we wait for this bit, and after the
+	 * wait we stop with -EINTR if btrfs_fs_closing() returns non-zero - we
+	 * have just set BTRFS_FS_CLOSING_START, so btrfs_fs_closing() will
+	 * return 1.
+	 */
+	btrfs_wake_unfinished_drop(fs_info);
+
+	/*
 	 * We may have the reclaim task running and relocating a data block group,
 	 * in which case it may create delayed iputs. So stop it before we park
 	 * the cleaner kthread otherwise we can get new delayed iputs after
@@ -4575,12 +4503,6 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	 */
 	kthread_park(fs_info->cleaner_kthread);
 
-	/*
-	 * If we had UNFINISHED_DROPS we could still be processing them, so
-	 * clear that bit and wake up relocation so it can stop.
-	 */
-	btrfs_wake_unfinished_drop(fs_info);
-
 	/* wait for the qgroup rescan worker to stop */
 	btrfs_qgroup_wait_for_completion(fs_info, false);
 
@@ -4603,6 +4525,31 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	/* clear out the rbtree of defraggable inodes */
 	btrfs_cleanup_defrag_inodes(fs_info);
 
+	/*
+	 * After we parked the cleaner kthread, ordered extents may have
+	 * completed and created new delayed iputs. If one of the async reclaim
+	 * tasks is running and in the RUN_DELAYED_IPUTS flush state, then we
+	 * can hang forever trying to stop it, because if a delayed iput is
+	 * added after it ran btrfs_run_delayed_iputs() and before it called
+	 * btrfs_wait_on_delayed_iputs(), it will hang forever since there is
+	 * no one else to run iputs.
+	 *
+	 * So wait for all ongoing ordered extents to complete and then run
+	 * delayed iputs. This works because once we reach this point no one
+	 * can either create new ordered extents nor create delayed iputs
+	 * through some other means.
+	 *
+	 * Also note that btrfs_wait_ordered_roots() is not safe here, because
+	 * it waits for BTRFS_ORDERED_COMPLETE to be set on an ordered extent,
+	 * but the delayed iput for the respective inode is made only when doing
+	 * the final btrfs_put_ordered_extent() (which must happen at
+	 * btrfs_finish_ordered_io() when we are unmounting).
+	 */
+	btrfs_flush_workqueue(fs_info->endio_write_workers);
+	/* Ordered extents for free space inodes. */
+	btrfs_flush_workqueue(fs_info->endio_freespace_worker);
+	btrfs_run_delayed_iputs(fs_info);
+
 	cancel_work_sync(&fs_info->async_reclaim_work);
 	cancel_work_sync(&fs_info->async_data_reclaim_work);
 	cancel_work_sync(&fs_info->preempt_reclaim_work);
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 8993b428e09c..47ad8e0a2d33 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -137,14 +137,4 @@ int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags);
 int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid);
 int btrfs_init_root_free_objectid(struct btrfs_root *root);
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-void btrfs_set_buffer_lockdep_class(u64 objectid,
-			            struct extent_buffer *eb, int level);
-#else
-static inline void btrfs_set_buffer_lockdep_class(u64 objectid,
-					struct extent_buffer *eb, int level)
-{
-}
-#endif
-
 #endif
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index ea3ec1e761e8..6914cd8024ba 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2551,17 +2551,10 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
 		return -EINVAL;
 
 	/*
-	 * pull in the free space cache (if any) so that our pin
-	 * removes the free space from the cache.  We have load_only set
-	 * to one because the slow code to read in the free extents does check
-	 * the pinned extents.
+	 * Fully cache the free space first so that our pin removes the free space
+	 * from the cache.
 	 */
-	btrfs_cache_block_group(cache, 1);
-	/*
-	 * Make sure we wait until the cache is completely built in case it is
-	 * missing or is invalid and therefore needs to be rebuilt.
-	 */
-	ret = btrfs_wait_block_group_cache_done(cache);
+	ret = btrfs_cache_block_group(cache, true);
 	if (ret)
 		goto out;
 
@@ -2584,12 +2577,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
 	if (!block_group)
 		return -EINVAL;
 
-	btrfs_cache_block_group(block_group, 1);
-	/*
-	 * Make sure we wait until the cache is completely built in case it is
-	 * missing or is invalid and therefore needs to be rebuilt.
-	 */
-	ret = btrfs_wait_block_group_cache_done(block_group);
+	ret = btrfs_cache_block_group(block_group, true);
 	if (ret)
 		goto out;
 
@@ -4399,7 +4387,7 @@ have_block_group:
 		ffe_ctl->cached = btrfs_block_group_done(block_group);
 		if (unlikely(!ffe_ctl->cached)) {
 			ffe_ctl->have_caching_bg = true;
-			ret = btrfs_cache_block_group(block_group, 0);
+			ret = btrfs_cache_block_group(block_group, false);
 
 			/*
 			 * If we get ENOMEM here or something else we want to
@@ -4867,6 +4855,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *buf;
+	u64 lockdep_owner = owner;
 
 	buf = btrfs_find_create_tree_block(fs_info, bytenr, owner, level);
 	if (IS_ERR(buf))
@@ -4886,11 +4875,26 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	}
 
 	/*
+	 * The reloc trees are just snapshots, so we need them to appear to be
+	 * just like any other fs tree WRT lockdep.
+	 *
+	 * The exception however is in replace_path() in relocation, where we
+	 * hold the lock on the original fs root and then search for the reloc
+	 * root.  At that point we need to make sure any reloc root buffers are
+	 * set to the BTRFS_TREE_RELOC_OBJECTID lockdep class in order to make
+	 * lockdep happy.
+	 */
+	if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID &&
+	    !test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state))
+		lockdep_owner = BTRFS_FS_TREE_OBJECTID;
+
+	/*
 	 * This needs to stay, because we could allocate a freed block from an
 	 * old tree into a new tree, so we need to make sure this new block is
 	 * set to the appropriate level and owner.
 	 */
-	btrfs_set_buffer_lockdep_class(owner, buf, level);
+	btrfs_set_buffer_lockdep_class(lockdep_owner, buf, level);
+
 	__btrfs_tree_lock(buf, nest);
 	btrfs_clean_tree_block(buf);
 	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
@@ -6153,13 +6157,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 
 		if (end - start >= range->minlen) {
 			if (!btrfs_block_group_done(cache)) {
-				ret = btrfs_cache_block_group(cache, 0);
-				if (ret) {
-					bg_failed++;
-					bg_ret = ret;
-					continue;
-				}
-				ret = btrfs_wait_block_group_cache_done(cache);
+				ret = btrfs_cache_block_group(cache, true);
 				if (ret) {
 					bg_failed++;
 					bg_ret = ret;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index bfae67c593c5..cf4f19e80e2f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3233,7 +3233,7 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl,
 	u32 bio_size = bio->bi_iter.bi_size;
 	u32 real_size;
 	const sector_t sector = disk_bytenr >> SECTOR_SHIFT;
-	bool contig;
+	bool contig = false;
 	int ret;
 
 	ASSERT(bio);
@@ -3242,10 +3242,35 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl,
 	if (bio_ctrl->compress_type != compress_type)
 		return 0;
 
-	if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE)
+
+	if (bio->bi_iter.bi_size == 0) {
+		/* We can always add a page into an empty bio. */
+		contig = true;
+	} else if (bio_ctrl->compress_type == BTRFS_COMPRESS_NONE) {
+		struct bio_vec *bvec = bio_last_bvec_all(bio);
+
+		/*
+		 * The contig check requires the following conditions to be met:
+		 * 1) The pages are belonging to the same inode
+		 *    This is implied by the call chain.
+		 *
+		 * 2) The range has adjacent logical bytenr
+		 *
+		 * 3) The range has adjacent file offset
+		 *    This is required for the usage of btrfs_bio->file_offset.
+		 */
+		if (bio_end_sector(bio) == sector &&
+		    page_offset(bvec->bv_page) + bvec->bv_offset +
+		    bvec->bv_len == page_offset(page) + pg_offset)
+			contig = true;
+	} else {
+		/*
+		 * For compression, all IO should have its logical bytenr
+		 * set to the starting bytenr of the compressed extent.
+		 */
 		contig = bio->bi_iter.bi_sector == sector;
-	else
-		contig = bio_end_sector(bio) == sector;
+	}
+
 	if (!contig)
 		return 0;
 
@@ -6140,6 +6165,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	struct extent_buffer *exists = NULL;
 	struct page *p;
 	struct address_space *mapping = fs_info->btree_inode->i_mapping;
+	u64 lockdep_owner = owner_root;
 	int uptodate = 1;
 	int ret;
 
@@ -6164,7 +6190,15 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	eb = __alloc_extent_buffer(fs_info, start, len);
 	if (!eb)
 		return ERR_PTR(-ENOMEM);
-	btrfs_set_buffer_lockdep_class(owner_root, eb, level);
+
+	/*
+	 * The reloc trees are just snapshots, so we need them to appear to be
+	 * just like any other fs tree WRT lockdep.
+	 */
+	if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID)
+		lockdep_owner = BTRFS_FS_TREE_OBJECTID;
+
+	btrfs_set_buffer_lockdep_class(lockdep_owner, eb, level);
 
 	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++, index++) {
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 66c822182ecc..5a3f6e0d9688 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2482,6 +2482,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_offset(leaf, fi, 0);
+		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
 		btrfs_mark_buffer_dirty(leaf);
 		goto out;
 	}
@@ -2498,6 +2499,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_offset(leaf, fi, 0);
+		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
 		btrfs_mark_buffer_dirty(leaf);
 		goto out;
 	}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index f0c97d25b4a0..1372210869b1 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1644,10 +1644,9 @@ static noinline int run_delalloc_zoned(struct btrfs_inode *inode,
 			done_offset = end;
 
 		if (done_offset == start) {
-			struct btrfs_fs_info *info = inode->root->fs_info;
-
-			wait_var_event(&info->zone_finish_wait,
-				       !test_bit(BTRFS_FS_NEED_ZONE_FINISH, &info->flags));
+			wait_on_bit_io(&inode->root->fs_info->flags,
+				       BTRFS_FS_NEED_ZONE_FINISH,
+				       TASK_UNINTERRUPTIBLE);
 			continue;
 		}
 
@@ -7694,6 +7693,20 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	bool unlock_extents = false;
 
 	/*
+	 * We could potentially fault if we have a buffer > PAGE_SIZE, and if
+	 * we're NOWAIT we may submit a bio for a partial range and return
+	 * EIOCBQUEUED, which would result in an errant short read.
+	 *
+	 * The best way to handle this would be to allow for partial completions
+	 * of iocb's, so we could submit the partial bio, return and fault in
+	 * the rest of the pages, and then submit the io for the rest of the
+	 * range.  However we don't have that currently, so simply return
+	 * -EAGAIN at this point so that the normal path is used.
+	 */
+	if (!write && (flags & IOMAP_NOWAIT) && length > PAGE_SIZE)
+		return -EAGAIN;
+
+	/*
 	 * Cap the size of reads to that usually seen in buffered I/O as we need
 	 * to allocate a contiguous array for the checksums.
 	 */
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 33461b4f9c8b..9063072b399b 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -14,6 +14,93 @@
 #include "locking.h"
 
 /*
+ * Lockdep class keys for extent_buffer->lock's in this root.  For a given
+ * eb, the lockdep key is determined by the btrfs_root it belongs to and
+ * the level the eb occupies in the tree.
+ *
+ * Different roots are used for different purposes and may nest inside each
+ * other and they require separate keysets.  As lockdep keys should be
+ * static, assign keysets according to the purpose of the root as indicated
+ * by btrfs_root->root_key.objectid.  This ensures that all special purpose
+ * roots have separate keysets.
+ *
+ * Lock-nesting across peer nodes is always done with the immediate parent
+ * node locked thus preventing deadlock.  As lockdep doesn't know this, use
+ * subclass to avoid triggering lockdep warning in such cases.
+ *
+ * The key is set by the readpage_end_io_hook after the buffer has passed
+ * csum validation but before the pages are unlocked.  It is also set by
+ * btrfs_init_new_buffer on freshly allocated blocks.
+ *
+ * We also add a check to make sure the highest level of the tree is the
+ * same as our lockdep setup here.  If BTRFS_MAX_LEVEL changes, this code
+ * needs update as well.
+ */
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if BTRFS_MAX_LEVEL != 8
+#error
+#endif
+
+#define DEFINE_LEVEL(stem, level)					\
+	.names[level] = "btrfs-" stem "-0" #level,
+
+#define DEFINE_NAME(stem)						\
+	DEFINE_LEVEL(stem, 0)						\
+	DEFINE_LEVEL(stem, 1)						\
+	DEFINE_LEVEL(stem, 2)						\
+	DEFINE_LEVEL(stem, 3)						\
+	DEFINE_LEVEL(stem, 4)						\
+	DEFINE_LEVEL(stem, 5)						\
+	DEFINE_LEVEL(stem, 6)						\
+	DEFINE_LEVEL(stem, 7)
+
+static struct btrfs_lockdep_keyset {
+	u64			id;		/* root objectid */
+	/* Longest entry: btrfs-free-space-00 */
+	char			names[BTRFS_MAX_LEVEL][20];
+	struct lock_class_key	keys[BTRFS_MAX_LEVEL];
+} btrfs_lockdep_keysets[] = {
+	{ .id = BTRFS_ROOT_TREE_OBJECTID,	DEFINE_NAME("root")	},
+	{ .id = BTRFS_EXTENT_TREE_OBJECTID,	DEFINE_NAME("extent")	},
+	{ .id = BTRFS_CHUNK_TREE_OBJECTID,	DEFINE_NAME("chunk")	},
+	{ .id = BTRFS_DEV_TREE_OBJECTID,	DEFINE_NAME("dev")	},
+	{ .id = BTRFS_CSUM_TREE_OBJECTID,	DEFINE_NAME("csum")	},
+	{ .id = BTRFS_QUOTA_TREE_OBJECTID,	DEFINE_NAME("quota")	},
+	{ .id = BTRFS_TREE_LOG_OBJECTID,	DEFINE_NAME("log")	},
+	{ .id = BTRFS_TREE_RELOC_OBJECTID,	DEFINE_NAME("treloc")	},
+	{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID,	DEFINE_NAME("dreloc")	},
+	{ .id = BTRFS_UUID_TREE_OBJECTID,	DEFINE_NAME("uuid")	},
+	{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID,	DEFINE_NAME("free-space") },
+	{ .id = 0,				DEFINE_NAME("tree")	},
+};
+
+#undef DEFINE_LEVEL
+#undef DEFINE_NAME
+
+void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int level)
+{
+	struct btrfs_lockdep_keyset *ks;
+
+	BUG_ON(level >= ARRAY_SIZE(ks->keys));
+
+	/* Find the matching keyset, id 0 is the default entry */
+	for (ks = btrfs_lockdep_keysets; ks->id; ks++)
+		if (ks->id == objectid)
+			break;
+
+	lockdep_set_class_and_name(&eb->lock, &ks->keys[level], ks->names[level]);
+}
+
+void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, struct extent_buffer *eb)
+{
+	if (test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state))
+		btrfs_set_buffer_lockdep_class(root->root_key.objectid,
+					       eb, btrfs_header_level(eb));
+}
+
+#endif
+
+/*
  * Extent buffer locking
  * =====================
  *
@@ -164,6 +251,8 @@ struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root)
 
 	while (1) {
 		eb = btrfs_root_node(root);
+
+		btrfs_maybe_reset_lockdep_class(root, eb);
 		btrfs_tree_lock(eb);
 		if (eb == root->node)
 			break;
@@ -185,6 +274,8 @@ struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
 
 	while (1) {
 		eb = btrfs_root_node(root);
+
+		btrfs_maybe_reset_lockdep_class(root, eb);
 		btrfs_tree_read_lock(eb);
 		if (eb == root->node)
 			break;
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index bbc45534ae9a..ab268be09bb5 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -131,4 +131,18 @@ void btrfs_drew_write_unlock(struct btrfs_drew_lock *lock);
 void btrfs_drew_read_lock(struct btrfs_drew_lock *lock);
 void btrfs_drew_read_unlock(struct btrfs_drew_lock *lock);
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int level);
+void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, struct extent_buffer *eb);
+#else
+static inline void btrfs_set_buffer_lockdep_class(u64 objectid,
+					struct extent_buffer *eb, int level)
+{
+}
+static inline void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root,
+						   struct extent_buffer *eb)
+{
+}
+#endif
+
 #endif
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index a6dc827e75af..45c02aba2492 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1326,7 +1326,9 @@ again:
 		btrfs_release_path(path);
 
 		path->lowest_level = level;
+		set_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &src->state);
 		ret = btrfs_search_slot(trans, src, &key, path, 0, 1);
+		clear_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &src->state);
 		path->lowest_level = 0;
 		if (ret) {
 			if (ret > 0)
@@ -3573,7 +3575,12 @@ int prepare_to_relocate(struct reloc_control *rc)
 		 */
 		return PTR_ERR(trans);
 	}
-	return btrfs_commit_transaction(trans);
+
+	ret = btrfs_commit_transaction(trans);
+	if (ret)
+		unset_reloc_control(rc);
+
+	return ret;
 }
 
 static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index a64b26b16904..d647cb2938c0 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -349,9 +349,10 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
 	key.offset = ref_id;
 again:
 	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
-	if (ret < 0)
+	if (ret < 0) {
+		err = ret;
 		goto out;
-	if (ret == 0) {
+	} else if (ret == 0) {
 		leaf = path->nodes[0];
 		ref = btrfs_item_ptr(leaf, path->slots[0],
 				     struct btrfs_root_ref);
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index d0cbeb7ae81c..435559ba94fa 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -199,7 +199,7 @@ static u64 calc_chunk_size(const struct btrfs_fs_info *fs_info, u64 flags)
 	ASSERT(flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
 
 	if (flags & BTRFS_BLOCK_GROUP_DATA)
-		return SZ_1G;
+		return BTRFS_MAX_DATA_CHUNK_SIZE;
 	else if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
 		return SZ_32M;
 
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 9e0e0ae2288c..43f905ab0a18 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1233,7 +1233,8 @@ static void extent_err(const struct extent_buffer *eb, int slot,
 }
 
 static int check_extent_item(struct extent_buffer *leaf,
-			     struct btrfs_key *key, int slot)
+			     struct btrfs_key *key, int slot,
+			     struct btrfs_key *prev_key)
 {
 	struct btrfs_fs_info *fs_info = leaf->fs_info;
 	struct btrfs_extent_item *ei;
@@ -1453,6 +1454,26 @@ static int check_extent_item(struct extent_buffer *leaf,
 			   total_refs, inline_refs);
 		return -EUCLEAN;
 	}
+
+	if ((prev_key->type == BTRFS_EXTENT_ITEM_KEY) ||
+	    (prev_key->type == BTRFS_METADATA_ITEM_KEY)) {
+		u64 prev_end = prev_key->objectid;
+
+		if (prev_key->type == BTRFS_METADATA_ITEM_KEY)
+			prev_end += fs_info->nodesize;
+		else
+			prev_end += prev_key->offset;
+
+		if (unlikely(prev_end > key->objectid)) {
+			extent_err(leaf, slot,
+	"previous extent [%llu %u %llu] overlaps current extent [%llu %u %llu]",
+				   prev_key->objectid, prev_key->type,
+				   prev_key->offset, key->objectid, key->type,
+				   key->offset);
+			return -EUCLEAN;
+		}
+	}
+
 	return 0;
 }
 
@@ -1621,7 +1642,7 @@ static int check_leaf_item(struct extent_buffer *leaf,
 		break;
 	case BTRFS_EXTENT_ITEM_KEY:
 	case BTRFS_METADATA_ITEM_KEY:
-		ret = check_extent_item(leaf, key, slot);
+		ret = check_extent_item(leaf, key, slot, prev_key);
 		break;
 	case BTRFS_TREE_BLOCK_REF_KEY:
 	case BTRFS_SHARED_DATA_REF_KEY:
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index dcf75a8daa20..9205c4a5ca81 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1146,7 +1146,9 @@ again:
 	extref = btrfs_lookup_inode_extref(NULL, root, path, name, namelen,
 					   inode_objectid, parent_objectid, 0,
 					   0);
-	if (!IS_ERR_OR_NULL(extref)) {
+	if (IS_ERR(extref)) {
+		return PTR_ERR(extref);
+	} else if (extref) {
 		u32 item_size;
 		u32 cur_offset = 0;
 		unsigned long base;
@@ -1457,7 +1459,7 @@ static int add_link(struct btrfs_trans_handle *trans,
 	 * on the inode will not free it. We will fixup the link count later.
 	 */
 	if (other_inode->i_nlink == 0)
-		inc_nlink(other_inode);
+		set_nlink(other_inode, 1);
 add_link:
 	ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
 			     name, namelen, 0, ref_index);
@@ -1600,7 +1602,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 				 * free it. We will fixup the link count later.
 				 */
 				if (!ret && inode->i_nlink == 0)
-					inc_nlink(inode);
+					set_nlink(inode, 1);
 			}
 			if (ret < 0)
 				goto out;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 272901514b0c..f63ff91e2883 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2345,8 +2345,11 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 
 	ret = btrfs_get_bdev_and_sb(path, FMODE_READ, fs_info->bdev_holder, 0,
 				    &bdev, &disk_super);
-	if (ret)
+	if (ret) {
+		btrfs_put_dev_args_from_path(args);
 		return ret;
+	}
+
 	args->devid = btrfs_stack_device_id(&disk_super->dev_item);
 	memcpy(args->uuid, disk_super->dev_item.uuid, BTRFS_UUID_SIZE);
 	if (btrfs_fs_incompat(fs_info, METADATA_UUID))
@@ -5264,6 +5267,9 @@ static int decide_stripe_size_regular(struct alloc_chunk_ctl *ctl,
 				       ctl->stripe_size);
 	}
 
+	/* Stripe size should not go beyond 1G. */
+	ctl->stripe_size = min_t(u64, ctl->stripe_size, SZ_1G);
+
 	/* Align to BTRFS_STRIPE_LEN */
 	ctl->stripe_size = round_down(ctl->stripe_size, BTRFS_STRIPE_LEN);
 	ctl->chunk_size = ctl->stripe_size * data_stripes;
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 7421abcf325a..5bb8d8c86311 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -371,6 +371,9 @@ static int btrfs_xattr_handler_set(const struct xattr_handler *handler,
 				   const char *name, const void *buffer,
 				   size_t size, int flags)
 {
+	if (btrfs_root_readonly(BTRFS_I(inode)->root))
+		return -EROFS;
+
 	name = xattr_full_name(handler, name);
 	return btrfs_setxattr_trans(inode, name, buffer, size, flags);
 }
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index b150b07ba1a7..73c6929f7be6 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -421,10 +421,19 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
 	 * since btrfs adds the pages one by one to a bio, and btrfs cannot
 	 * increase the metadata reservation even if it increases the number of
 	 * extents, it is safe to stick with the limit.
+	 *
+	 * With the zoned emulation, we can have non-zoned device on the zoned
+	 * mode. In this case, we don't have a valid max zone append size. So,
+	 * use max_segments * PAGE_SIZE as the pseudo max_zone_append_size.
 	 */
-	zone_info->max_zone_append_size =
-		min_t(u64, (u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT,
-		      (u64)bdev_max_segments(bdev) << PAGE_SHIFT);
+	if (bdev_is_zoned(bdev)) {
+		zone_info->max_zone_append_size = min_t(u64,
+			(u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT,
+			(u64)bdev_max_segments(bdev) << PAGE_SHIFT);
+	} else {
+		zone_info->max_zone_append_size =
+			(u64)bdev_max_segments(bdev) << PAGE_SHIFT;
+	}
 	if (!IS_ALIGNED(nr_sectors, zone_sectors))
 		zone_info->nr_zones++;
 
@@ -1178,7 +1187,7 @@ int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size)
  * offset.
  */
 static int calculate_alloc_pointer(struct btrfs_block_group *cache,
-				   u64 *offset_ret)
+				   u64 *offset_ret, bool new)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_root *root;
@@ -1188,6 +1197,21 @@ static int calculate_alloc_pointer(struct btrfs_block_group *cache,
 	int ret;
 	u64 length;
 
+	/*
+	 * Avoid  tree lookups for a new block group, there's no use for it.
+	 * It must always be 0.
+	 *
+	 * Also, we have a lock chain of extent buffer lock -> chunk mutex.
+	 * For new a block group, this function is called from
+	 * btrfs_make_block_group() which is already taking the chunk mutex.
+	 * Thus, we cannot call calculate_alloc_pointer() which takes extent
+	 * buffer locks to avoid deadlock.
+	 */
+	if (new) {
+		*offset_ret = 0;
+		return 0;
+	}
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -1323,6 +1347,13 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		else
 			num_conventional++;
 
+		/*
+		 * Consider a zone as active if we can allow any number of
+		 * active zones.
+		 */
+		if (!device->zone_info->max_active_zones)
+			__set_bit(i, active);
+
 		if (!is_sequential) {
 			alloc_offsets[i] = WP_CONVENTIONAL;
 			continue;
@@ -1389,45 +1420,23 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 			__set_bit(i, active);
 			break;
 		}
-
-		/*
-		 * Consider a zone as active if we can allow any number of
-		 * active zones.
-		 */
-		if (!device->zone_info->max_active_zones)
-			__set_bit(i, active);
 	}
 
 	if (num_sequential > 0)
 		cache->seq_zone = true;
 
 	if (num_conventional > 0) {
-		/*
-		 * Avoid calling calculate_alloc_pointer() for new BG. It
-		 * is no use for new BG. It must be always 0.
-		 *
-		 * Also, we have a lock chain of extent buffer lock ->
-		 * chunk mutex.  For new BG, this function is called from
-		 * btrfs_make_block_group() which is already taking the
-		 * chunk mutex. Thus, we cannot call
-		 * calculate_alloc_pointer() which takes extent buffer
-		 * locks to avoid deadlock.
-		 */
-
 		/* Zone capacity is always zone size in emulation */
 		cache->zone_capacity = cache->length;
-		if (new) {
-			cache->alloc_offset = 0;
-			goto out;
-		}
-		ret = calculate_alloc_pointer(cache, &last_alloc);
-		if (ret || map->num_stripes == num_conventional) {
-			if (!ret)
-				cache->alloc_offset = last_alloc;
-			else
-				btrfs_err(fs_info,
+		ret = calculate_alloc_pointer(cache, &last_alloc, new);
+		if (ret) {
+			btrfs_err(fs_info,
 			"zoned: failed to determine allocation offset of bg %llu",
-					  cache->start);
+				  cache->start);
+			goto out;
+		} else if (map->num_stripes == num_conventional) {
+			cache->alloc_offset = last_alloc;
+			cache->zone_is_active = 1;
 			goto out;
 		}
 	}
@@ -1495,13 +1504,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		goto out;
 	}
 
-	if (cache->zone_is_active) {
-		btrfs_get_block_group(cache);
-		spin_lock(&fs_info->zone_active_bgs_lock);
-		list_add_tail(&cache->active_bg_list, &fs_info->zone_active_bgs);
-		spin_unlock(&fs_info->zone_active_bgs_lock);
-	}
-
 out:
 	if (cache->alloc_offset > fs_info->zone_size) {
 		btrfs_err(fs_info,
@@ -1526,10 +1528,16 @@ out:
 		ret = -EIO;
 	}
 
-	if (!ret)
+	if (!ret) {
 		cache->meta_write_pointer = cache->alloc_offset + cache->start;
-
-	if (ret) {
+		if (cache->zone_is_active) {
+			btrfs_get_block_group(cache);
+			spin_lock(&fs_info->zone_active_bgs_lock);
+			list_add_tail(&cache->active_bg_list,
+				      &fs_info->zone_active_bgs);
+			spin_unlock(&fs_info->zone_active_bgs_lock);
+		}
+	} else {
 		kfree(cache->physical_map);
 		cache->physical_map = NULL;
 	}
@@ -1910,10 +1918,44 @@ out_unlock:
 	return ret;
 }
 
+static void wait_eb_writebacks(struct btrfs_block_group *block_group)
+{
+	struct btrfs_fs_info *fs_info = block_group->fs_info;
+	const u64 end = block_group->start + block_group->length;
+	struct radix_tree_iter iter;
+	struct extent_buffer *eb;
+	void __rcu **slot;
+
+	rcu_read_lock();
+	radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter,
+				 block_group->start >> fs_info->sectorsize_bits) {
+		eb = radix_tree_deref_slot(slot);
+		if (!eb)
+			continue;
+		if (radix_tree_deref_retry(eb)) {
+			slot = radix_tree_iter_retry(&iter);
+			continue;
+		}
+
+		if (eb->start < block_group->start)
+			continue;
+		if (eb->start >= end)
+			break;
+
+		slot = radix_tree_iter_resume(slot, &iter);
+		rcu_read_unlock();
+		wait_on_extent_buffer_writeback(eb);
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
+}
+
 static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_written)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	struct map_lookup *map;
+	const bool is_metadata = (block_group->flags &
+			(BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM));
 	int ret = 0;
 	int i;
 
@@ -1924,8 +1966,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
 	}
 
 	/* Check if we have unwritten allocated space */
-	if ((block_group->flags &
-	     (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)) &&
+	if (is_metadata &&
 	    block_group->start + block_group->alloc_offset > block_group->meta_write_pointer) {
 		spin_unlock(&block_group->lock);
 		return -EAGAIN;
@@ -1950,6 +1991,9 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
 		/* No need to wait for NOCOW writers. Zoned mode does not allow that */
 		btrfs_wait_ordered_roots(fs_info, U64_MAX, block_group->start,
 					 block_group->length);
+		/* Wait for extent buffers to be written. */
+		if (is_metadata)
+			wait_eb_writebacks(block_group);
 
 		spin_lock(&block_group->lock);
 
@@ -2007,8 +2051,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
 	/* For active_bg_list */
 	btrfs_put_block_group(block_group);
 
-	clear_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags);
-	wake_up_all(&fs_info->zone_finish_wait);
+	clear_and_wake_up_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags);
 
 	return 0;
 }
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 6cba2c6de2f9..2ad58c465208 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -111,6 +111,7 @@ struct cachefiles_cache {
 	char				*tag;		/* cache binding tag */
 	refcount_t			unbind_pincount;/* refcount to do daemon unbind */
 	struct xarray			reqs;		/* xarray of pending on-demand requests */
+	unsigned long			req_id_next;
 	struct xarray			ondemand_ids;	/* xarray for ondemand_id allocation */
 	u32				ondemand_id_next;
 };
diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c
index 1fee702d5529..0254ed39f68c 100644
--- a/fs/cachefiles/ondemand.c
+++ b/fs/cachefiles/ondemand.c
@@ -158,9 +158,13 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args)
 
 	/* fail OPEN request if daemon reports an error */
 	if (size < 0) {
-		if (!IS_ERR_VALUE(size))
-			size = -EINVAL;
-		req->error = size;
+		if (!IS_ERR_VALUE(size)) {
+			req->error = -EINVAL;
+			ret = -EINVAL;
+		} else {
+			req->error = size;
+			ret = 0;
+		}
 		goto out;
 	}
 
@@ -238,14 +242,19 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 	unsigned long id = 0;
 	size_t n;
 	int ret = 0;
-	XA_STATE(xas, &cache->reqs, 0);
+	XA_STATE(xas, &cache->reqs, cache->req_id_next);
 
 	/*
-	 * Search for a request that has not ever been processed, to prevent
-	 * requests from being processed repeatedly.
+	 * Cyclically search for a request that has not ever been processed,
+	 * to prevent requests from being processed repeatedly, and make
+	 * request distribution fair.
 	 */
 	xa_lock(&cache->reqs);
 	req = xas_find_marked(&xas, UINT_MAX, CACHEFILES_REQ_NEW);
+	if (!req && cache->req_id_next > 0) {
+		xas_set(&xas, 0);
+		req = xas_find_marked(&xas, cache->req_id_next - 1, CACHEFILES_REQ_NEW);
+	}
 	if (!req) {
 		xa_unlock(&cache->reqs);
 		return 0;
@@ -260,6 +269,7 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 	}
 
 	xas_clear_mark(&xas, CACHEFILES_REQ_NEW);
+	cache->req_id_next = xas.xa_index + 1;
 	xa_unlock(&cache->reqs);
 
 	id = xas.xa_index;
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 11fd85de7217..c05477e28cff 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -42,7 +42,7 @@ void cifs_dump_detail(void *buf, struct TCP_Server_Info *server)
 		 smb->Command, smb->Status.CifsError,
 		 smb->Flags, smb->Flags2, smb->Mid, smb->Pid);
 	cifs_dbg(VFS, "smb buf %p len %u\n", smb,
-		 server->ops->calc_smb_size(smb, server));
+		 server->ops->calc_smb_size(smb));
 #endif /* CONFIG_CIFS_DEBUG2 */
 }
 
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 8f7835ccbca1..46f5718754f9 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -32,10 +32,9 @@ int __cifs_calc_signature(struct smb_rqst *rqst,
 	int rc;
 	struct kvec *iov = rqst->rq_iov;
 	int n_vec = rqst->rq_nvec;
-	int is_smb2 = server->vals->header_preamble_size == 0;
 
 	/* iov[0] is actual data and not the rfc1002 length for SMB2+ */
-	if (is_smb2) {
+	if (!is_smb1(server)) {
 		if (iov[0].iov_len <= 4)
 			return -EIO;
 		i = 0;
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index f54d8bf2732a..8042d7280dec 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -1248,6 +1248,12 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	lock_two_nondirectories(target_inode, src_inode);
 
 	cifs_dbg(FYI, "about to flush pages\n");
+
+	rc = filemap_write_and_wait_range(src_inode->i_mapping, off,
+					  off + len - 1);
+	if (rc)
+		goto out;
+
 	/* should we flush first and last page first */
 	truncate_inode_pages(&target_inode->i_data, 0);
 
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 81f4c15936d0..5b4a7a32bdc5 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -153,6 +153,6 @@ extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
 /* when changing internal version - update following two lines at same time */
-#define SMB3_PRODUCT_BUILD 38
-#define CIFS_VERSION   "2.38"
+#define SMB3_PRODUCT_BUILD 39
+#define CIFS_VERSION   "2.39"
 #endif				/* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index bc0ee2d4b47b..ae7f571a7dba 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -417,7 +417,7 @@ struct smb_version_operations {
 	int (*close_dir)(const unsigned int, struct cifs_tcon *,
 			 struct cifs_fid *);
 	/* calculate a size of SMB message */
-	unsigned int (*calc_smb_size)(void *buf, struct TCP_Server_Info *ptcpi);
+	unsigned int (*calc_smb_size)(void *buf);
 	/* check for STATUS_PENDING and process the response if yes */
 	bool (*is_status_pending)(char *buf, struct TCP_Server_Info *server);
 	/* check for STATUS_NETWORK_SESSION_EXPIRED */
@@ -557,6 +557,8 @@ struct smb_version_values {
 
 #define HEADER_SIZE(server) (server->vals->header_size)
 #define MAX_HEADER_SIZE(server) (server->vals->max_header_size)
+#define HEADER_PREAMBLE_SIZE(server) (server->vals->header_preamble_size)
+#define MID_HEADER_SIZE(server) (HEADER_SIZE(server) - 1 - HEADER_PREAMBLE_SIZE(server))
 
 /**
  * CIFS superblock mount flags (mnt_cifs_flags) to consider when
@@ -750,6 +752,11 @@ struct TCP_Server_Info {
 #endif
 };
 
+static inline bool is_smb1(struct TCP_Server_Info *server)
+{
+	return HEADER_PREAMBLE_SIZE(server) != 0;
+}
+
 static inline void cifs_server_lock(struct TCP_Server_Info *server)
 {
 	unsigned int nofs_flag = memalloc_nofs_save();
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 87a77a684339..3bc94bcc7177 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -151,7 +151,7 @@ extern int cifs_get_writable_path(struct cifs_tcon *tcon, const char *name,
 extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool);
 extern int cifs_get_readable_path(struct cifs_tcon *tcon, const char *name,
 				  struct cifsFileInfo **ret_file);
-extern unsigned int smbCalcSize(void *buf, struct TCP_Server_Info *server);
+extern unsigned int smbCalcSize(void *buf);
 extern int decode_negTokenInit(unsigned char *security_blob, int length,
 			struct TCP_Server_Info *server);
 extern int cifs_convert_address(struct sockaddr *dst, const char *src, int len);
diff --git a/fs/cifs/cifsroot.c b/fs/cifs/cifsroot.c
index 9e91a5a40aae..56ec1b233f52 100644
--- a/fs/cifs/cifsroot.c
+++ b/fs/cifs/cifsroot.c
@@ -59,7 +59,7 @@ static int __init cifs_root_setup(char *line)
 			pr_err("Root-CIFS: UNC path too long\n");
 			return 1;
 		}
-		strlcpy(root_dev, line, len);
+		strscpy(root_dev, line, len);
 		srvaddr = parse_srvaddr(&line[2], s);
 		if (*s) {
 			int n = snprintf(root_opts,
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 9111c025bcb8..7ae6f2c08153 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -702,9 +702,6 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg)
 	int length = 0;
 	int total_read;
 
-	smb_msg->msg_control = NULL;
-	smb_msg->msg_controllen = 0;
-
 	for (total_read = 0; msg_data_left(smb_msg); total_read += length) {
 		try_to_freeze();
 
@@ -760,7 +757,7 @@ int
 cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
 		      unsigned int to_read)
 {
-	struct msghdr smb_msg;
+	struct msghdr smb_msg = {};
 	struct kvec iov = {.iov_base = buf, .iov_len = to_read};
 	iov_iter_kvec(&smb_msg.msg_iter, READ, &iov, 1, to_read);
 
@@ -770,15 +767,13 @@ cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
 ssize_t
 cifs_discard_from_socket(struct TCP_Server_Info *server, size_t to_read)
 {
-	struct msghdr smb_msg;
+	struct msghdr smb_msg = {};
 
 	/*
 	 *  iov_iter_discard already sets smb_msg.type and count and iov_offset
 	 *  and cifs_readv_from_socket sets msg_control and msg_controllen
 	 *  so little to initialize in struct msghdr
 	 */
-	smb_msg.msg_name = NULL;
-	smb_msg.msg_namelen = 0;
 	iov_iter_discard(&smb_msg.msg_iter, READ, to_read);
 
 	return cifs_readv_from_socket(server, &smb_msg);
@@ -788,7 +783,7 @@ int
 cifs_read_page_from_socket(struct TCP_Server_Info *server, struct page *page,
 	unsigned int page_offset, unsigned int to_read)
 {
-	struct msghdr smb_msg;
+	struct msghdr smb_msg = {};
 	struct bio_vec bv = {
 		.bv_page = page, .bv_len = to_read, .bv_offset = page_offset};
 	iov_iter_bvec(&smb_msg.msg_iter, READ, &bv, 1, to_read);
@@ -871,7 +866,7 @@ smb2_get_credits_from_hdr(char *buffer, struct TCP_Server_Info *server)
 	/*
 	 * SMB1 does not use credits.
 	 */
-	if (server->vals->header_preamble_size)
+	if (is_smb1(server))
 		return 0;
 
 	return le16_to_cpu(shdr->CreditRequest);
@@ -1050,7 +1045,7 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 
 	/* make sure this will fit in a large buffer */
 	if (pdu_length > CIFSMaxBufSize + MAX_HEADER_SIZE(server) -
-		server->vals->header_preamble_size) {
+	    HEADER_PREAMBLE_SIZE(server)) {
 		cifs_server_dbg(VFS, "SMB response too long (%u bytes)\n", pdu_length);
 		cifs_reconnect(server, true);
 		return -ECONNABORTED;
@@ -1065,8 +1060,7 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 
 	/* now read the rest */
 	length = cifs_read_from_socket(server, buf + HEADER_SIZE(server) - 1,
-				       pdu_length - HEADER_SIZE(server) + 1
-				       + server->vals->header_preamble_size);
+				       pdu_length - MID_HEADER_SIZE(server));
 
 	if (length < 0)
 		return length;
@@ -1122,7 +1116,7 @@ smb2_add_credits_from_hdr(char *buffer, struct TCP_Server_Info *server)
 	/*
 	 * SMB1 does not use credits.
 	 */
-	if (server->vals->header_preamble_size)
+	if (is_smb1(server))
 		return;
 
 	if (shdr->CreditRequest) {
@@ -1180,10 +1174,10 @@ cifs_demultiplex_thread(void *p)
 		if (length < 0)
 			continue;
 
-		if (server->vals->header_preamble_size == 0)
-			server->total_read = 0;
-		else
+		if (is_smb1(server))
 			server->total_read = length;
+		else
+			server->total_read = 0;
 
 		/*
 		 * The right amount was read from socket - 4 bytes,
@@ -1198,8 +1192,7 @@ next_pdu:
 		server->pdu_size = pdu_length;
 
 		/* make sure we have enough to get to the MID */
-		if (server->pdu_size < HEADER_SIZE(server) - 1 -
-		    server->vals->header_preamble_size) {
+		if (server->pdu_size < MID_HEADER_SIZE(server)) {
 			cifs_server_dbg(VFS, "SMB response too short (%u bytes)\n",
 				 server->pdu_size);
 			cifs_reconnect(server, true);
@@ -1208,9 +1201,8 @@ next_pdu:
 
 		/* read down to the MID */
 		length = cifs_read_from_socket(server,
-			     buf + server->vals->header_preamble_size,
-			     HEADER_SIZE(server) - 1
-			     - server->vals->header_preamble_size);
+			     buf + HEADER_PREAMBLE_SIZE(server),
+			     MID_HEADER_SIZE(server));
 		if (length < 0)
 			continue;
 		server->total_read += length;
@@ -2353,7 +2345,9 @@ cifs_put_tcon(struct cifs_tcon *tcon)
 	ses = tcon->ses;
 	cifs_dbg(FYI, "%s: tc_count=%d\n", __func__, tcon->tc_count);
 	spin_lock(&cifs_tcp_ses_lock);
+	spin_lock(&tcon->tc_lock);
 	if (--tcon->tc_count > 0) {
+		spin_unlock(&tcon->tc_lock);
 		spin_unlock(&cifs_tcp_ses_lock);
 		return;
 	}
@@ -2362,6 +2356,7 @@ cifs_put_tcon(struct cifs_tcon *tcon)
 	WARN_ON(tcon->tc_count < 0);
 
 	list_del_init(&tcon->tcon_list);
+	spin_unlock(&tcon->tc_lock);
 	spin_unlock(&cifs_tcp_ses_lock);
 
 	/* cancel polling of interfaces */
@@ -3994,7 +3989,7 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses,
 		}
 		bcc_ptr += length + 1;
 		bytes_left -= (length + 1);
-		strlcpy(tcon->treeName, tree, sizeof(tcon->treeName));
+		strscpy(tcon->treeName, tree, sizeof(tcon->treeName));
 
 		/* mostly informational -- no need to fail on error here */
 		kfree(tcon->nativeFileSystem);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index fa738adc031f..6f38b134a346 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3575,6 +3575,9 @@ static ssize_t __cifs_writev(
 
 ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from)
 {
+	struct file *file = iocb->ki_filp;
+
+	cifs_revalidate_mapping(file->f_inode);
 	return __cifs_writev(iocb, from, true);
 }
 
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 34d990f06fd6..87f60f736731 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -354,7 +354,7 @@ checkSMB(char *buf, unsigned int total_read, struct TCP_Server_Info *server)
 	/* otherwise, there is enough to get to the BCC */
 	if (check_smb_hdr(smb))
 		return -EIO;
-	clc_len = smbCalcSize(smb, server);
+	clc_len = smbCalcSize(smb);
 
 	if (4 + rfclen != total_read) {
 		cifs_dbg(VFS, "Length read does not match RFC1001 length %d\n",
@@ -737,6 +737,8 @@ cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode)
 	list_for_each_entry(cfile, &cifs_inode->openFileList, flist) {
 		if (delayed_work_pending(&cfile->deferred)) {
 			if (cancel_delayed_work(&cfile->deferred)) {
+				cifs_del_deferred_close(cfile);
+
 				tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC);
 				if (tmp_list == NULL)
 					break;
@@ -766,6 +768,8 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon)
 	list_for_each_entry(cfile, &tcon->openFileList, tlist) {
 		if (delayed_work_pending(&cfile->deferred)) {
 			if (cancel_delayed_work(&cfile->deferred)) {
+				cifs_del_deferred_close(cfile);
+
 				tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC);
 				if (tmp_list == NULL)
 					break;
@@ -799,6 +803,8 @@ cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, const char *path)
 		if (strstr(full_path, path)) {
 			if (delayed_work_pending(&cfile->deferred)) {
 				if (cancel_delayed_work(&cfile->deferred)) {
+					cifs_del_deferred_close(cfile);
+
 					tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC);
 					if (tmp_list == NULL)
 						break;
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index 28caae7aed1b..1b52e6ac431c 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -909,7 +909,7 @@ map_and_check_smb_error(struct mid_q_entry *mid, bool logErr)
  * portion, the number of word parameters and the data portion of the message
  */
 unsigned int
-smbCalcSize(void *buf, struct TCP_Server_Info *server)
+smbCalcSize(void *buf)
 {
 	struct smb_hdr *ptr = buf;
 	return (sizeof(struct smb_hdr) + (2 * ptr->WordCount) +
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 2eece8a07c11..8e060c00c969 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -806,8 +806,7 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos,
 
 		end_of_smb = cfile->srch_inf.ntwrk_buf_start +
 			server->ops->calc_smb_size(
-					cfile->srch_inf.ntwrk_buf_start,
-					server);
+					cfile->srch_inf.ntwrk_buf_start);
 
 		cur_ent = cfile->srch_inf.srch_entries_start;
 		first_entry_in_buffer = cfile->srch_inf.index_of_last_entry
@@ -1161,8 +1160,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
 	cifs_dbg(FYI, "loop through %d times filling dir for net buf %p\n",
 		 num_to_fill, cifsFile->srch_inf.ntwrk_buf_start);
 	max_len = tcon->ses->server->ops->calc_smb_size(
-			cifsFile->srch_inf.ntwrk_buf_start,
-			tcon->ses->server);
+			cifsFile->srch_inf.ntwrk_buf_start);
 	end_of_smb = cifsFile->srch_inf.ntwrk_buf_start + max_len;
 
 	tmp_buf = kmalloc(UNICODE_NAME_MAX, GFP_KERNEL);
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index f5dcc4940b6d..9dfd2dd612c2 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -61,7 +61,6 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
 		nr_ioctl_req.Reserved = 0;
 		rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid,
 			fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY,
-			true /* is_fsctl */,
 			(char *)&nr_ioctl_req, sizeof(nr_ioctl_req),
 			CIFSMaxBufSize, NULL, NULL /* no return info */);
 		if (rc == -EOPNOTSUPP) {
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 6a6ec6efb45a..d73e5672aac4 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -222,7 +222,7 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server)
 		}
 	}
 
-	calc_len = smb2_calc_size(buf, server);
+	calc_len = smb2_calc_size(buf);
 
 	/* For SMB2_IOCTL, OutputOffset and OutputLength are optional, so might
 	 * be 0, and not a real miscalculation */
@@ -410,7 +410,7 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr)
  * portion, the number of word parameters and the data portion of the message.
  */
 unsigned int
-smb2_calc_size(void *buf, struct TCP_Server_Info *srvr)
+smb2_calc_size(void *buf)
 {
 	struct smb2_pdu *pdu = buf;
 	struct smb2_hdr *shdr = &pdu->hdr;
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index f406af596887..421be43af425 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -387,7 +387,7 @@ smb2_dump_detail(void *buf, struct TCP_Server_Info *server)
 		 shdr->Command, shdr->Status, shdr->Flags, shdr->MessageId,
 		 shdr->Id.SyncId.ProcessId);
 	cifs_server_dbg(VFS, "smb buf %p len %u\n", buf,
-		 server->ops->calc_smb_size(buf, server));
+		 server->ops->calc_smb_size(buf));
 #endif
 }
 
@@ -681,7 +681,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
 	struct cifs_ses *ses = tcon->ses;
 
 	rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
-			FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */,
+			FSCTL_QUERY_NETWORK_INTERFACE_INFO,
 			NULL /* no data input */, 0 /* no data input */,
 			CIFSMaxBufSize, (char **)&out_buf, &ret_data_len);
 	if (rc == -EOPNOTSUPP) {
@@ -1323,9 +1323,8 @@ SMB2_request_res_key(const unsigned int xid, struct cifs_tcon *tcon,
 	struct resume_key_req *res_key;
 
 	rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid,
-			FSCTL_SRV_REQUEST_RESUME_KEY, true /* is_fsctl */,
-			NULL, 0 /* no input */, CIFSMaxBufSize,
-			(char **)&res_key, &ret_data_len);
+			FSCTL_SRV_REQUEST_RESUME_KEY, NULL, 0 /* no input */,
+			CIFSMaxBufSize, (char **)&res_key, &ret_data_len);
 
 	if (rc == -EOPNOTSUPP) {
 		pr_warn_once("Server share %s does not support copy range\n", tcon->treeName);
@@ -1467,7 +1466,7 @@ smb2_ioctl_query_info(const unsigned int xid,
 		rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE;
 
 		rc = SMB2_ioctl_init(tcon, server, &rqst[1], COMPOUND_FID, COMPOUND_FID,
-				     qi.info_type, true, buffer, qi.output_buffer_length,
+				     qi.info_type, buffer, qi.output_buffer_length,
 				     CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE -
 				     MAX_SMB2_CLOSE_RESPONSE_SIZE);
 		free_req1_func = SMB2_ioctl_free;
@@ -1601,17 +1600,8 @@ smb2_copychunk_range(const unsigned int xid,
 	int chunks_copied = 0;
 	bool chunk_sizes_updated = false;
 	ssize_t bytes_written, total_bytes_written = 0;
-	struct inode *inode;
 
 	pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL);
-
-	/*
-	 * We need to flush all unwritten data before we can send the
-	 * copychunk ioctl to the server.
-	 */
-	inode = d_inode(trgtfile->dentry);
-	filemap_write_and_wait(inode->i_mapping);
-
 	if (pcchunk == NULL)
 		return -ENOMEM;
 
@@ -1643,9 +1633,8 @@ smb2_copychunk_range(const unsigned int xid,
 		retbuf = NULL;
 		rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
 			trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE,
-			true /* is_fsctl */, (char *)pcchunk,
-			sizeof(struct copychunk_ioctl),	CIFSMaxBufSize,
-			(char **)&retbuf, &ret_data_len);
+			(char *)pcchunk, sizeof(struct copychunk_ioctl),
+			CIFSMaxBufSize, (char **)&retbuf, &ret_data_len);
 		if (rc == 0) {
 			if (ret_data_len !=
 					sizeof(struct copychunk_ioctl_rsp)) {
@@ -1805,7 +1794,6 @@ static bool smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid, FSCTL_SET_SPARSE,
-			true /* is_fctl */,
 			&setsparse, 1, CIFSMaxBufSize, NULL, NULL);
 	if (rc) {
 		tcon->broken_sparse_sup = true;
@@ -1888,7 +1876,6 @@ smb2_duplicate_extents(const unsigned int xid,
 	rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
 			trgtfile->fid.volatile_fid,
 			FSCTL_DUPLICATE_EXTENTS_TO_FILE,
-			true /* is_fsctl */,
 			(char *)&dup_ext_buf,
 			sizeof(struct duplicate_extents_to_file),
 			CIFSMaxBufSize, NULL,
@@ -1923,7 +1910,6 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon,
 	return SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid,
 			FSCTL_SET_INTEGRITY_INFORMATION,
-			true /* is_fsctl */,
 			(char *)&integr_info,
 			sizeof(struct fsctl_set_integrity_information_req),
 			CIFSMaxBufSize, NULL,
@@ -1976,7 +1962,6 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon,
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid,
 			FSCTL_SRV_ENUMERATE_SNAPSHOTS,
-			true /* is_fsctl */,
 			NULL, 0 /* no input data */, max_response_size,
 			(char **)&retbuf,
 			&ret_data_len);
@@ -2699,7 +2684,6 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses,
 	do {
 		rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
 				FSCTL_DFS_GET_REFERRALS,
-				true /* is_fsctl */,
 				(char *)dfs_req, dfs_req_size, CIFSMaxBufSize,
 				(char **)&dfs_rsp, &dfs_rsp_size);
 		if (!is_retryable_error(rc))
@@ -2906,8 +2890,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl_init(tcon, server,
 			     &rqst[1], fid.persistent_fid,
-			     fid.volatile_fid, FSCTL_GET_REPARSE_POINT,
-			     true /* is_fctl */, NULL, 0,
+			     fid.volatile_fid, FSCTL_GET_REPARSE_POINT, NULL, 0,
 			     CIFSMaxBufSize -
 			     MAX_SMB2_CREATE_RESPONSE_SIZE -
 			     MAX_SMB2_CLOSE_RESPONSE_SIZE);
@@ -3087,8 +3070,7 @@ smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl_init(tcon, server,
 			     &rqst[1], COMPOUND_FID,
-			     COMPOUND_FID, FSCTL_GET_REPARSE_POINT,
-			     true /* is_fctl */, NULL, 0,
+			     COMPOUND_FID, FSCTL_GET_REPARSE_POINT, NULL, 0,
 			     CIFSMaxBufSize -
 			     MAX_SMB2_CREATE_RESPONSE_SIZE -
 			     MAX_SMB2_CLOSE_RESPONSE_SIZE);
@@ -3316,26 +3298,43 @@ get_smb2_acl(struct cifs_sb_info *cifs_sb,
 	return pntsd;
 }
 
+static long smb3_zero_data(struct file *file, struct cifs_tcon *tcon,
+			     loff_t offset, loff_t len, unsigned int xid)
+{
+	struct cifsFileInfo *cfile = file->private_data;
+	struct file_zero_data_information fsctl_buf;
+
+	cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len);
+
+	fsctl_buf.FileOffset = cpu_to_le64(offset);
+	fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len);
+
+	return SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
+			  cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA,
+			  (char *)&fsctl_buf,
+			  sizeof(struct file_zero_data_information),
+			  0, NULL, NULL);
+}
+
 static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 			    loff_t offset, loff_t len, bool keep_size)
 {
 	struct cifs_ses *ses = tcon->ses;
-	struct inode *inode;
-	struct cifsInodeInfo *cifsi;
+	struct inode *inode = file_inode(file);
+	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 	struct cifsFileInfo *cfile = file->private_data;
-	struct file_zero_data_information fsctl_buf;
 	long rc;
 	unsigned int xid;
 	__le64 eof;
 
 	xid = get_xid();
 
-	inode = d_inode(cfile->dentry);
-	cifsi = CIFS_I(inode);
-
 	trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid,
 			      ses->Suid, offset, len);
 
+	inode_lock(inode);
+	filemap_invalidate_lock(inode->i_mapping);
+
 	/*
 	 * We zero the range through ioctl, so we need remove the page caches
 	 * first, otherwise the data may be inconsistent with the server.
@@ -3343,26 +3342,12 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	truncate_pagecache_range(inode, offset, offset + len - 1);
 
 	/* if file not oplocked can't be sure whether asking to extend size */
-	if (!CIFS_CACHE_READ(cifsi))
-		if (keep_size == false) {
-			rc = -EOPNOTSUPP;
-			trace_smb3_zero_err(xid, cfile->fid.persistent_fid,
-				tcon->tid, ses->Suid, offset, len, rc);
-			free_xid(xid);
-			return rc;
-		}
-
-	cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len);
-
-	fsctl_buf.FileOffset = cpu_to_le64(offset);
-	fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len);
+	rc = -EOPNOTSUPP;
+	if (keep_size == false && !CIFS_CACHE_READ(cifsi))
+		goto zero_range_exit;
 
-	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
-			cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, true,
-			(char *)&fsctl_buf,
-			sizeof(struct file_zero_data_information),
-			0, NULL, NULL);
-	if (rc)
+	rc = smb3_zero_data(file, tcon, offset, len, xid);
+	if (rc < 0)
 		goto zero_range_exit;
 
 	/*
@@ -3375,6 +3360,8 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	}
 
  zero_range_exit:
+	filemap_invalidate_unlock(inode->i_mapping);
+	inode_unlock(inode);
 	free_xid(xid);
 	if (rc)
 		trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid,
@@ -3388,7 +3375,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 			    loff_t offset, loff_t len)
 {
-	struct inode *inode;
+	struct inode *inode = file_inode(file);
 	struct cifsFileInfo *cfile = file->private_data;
 	struct file_zero_data_information fsctl_buf;
 	long rc;
@@ -3397,14 +3384,12 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 
 	xid = get_xid();
 
-	inode = d_inode(cfile->dentry);
-
+	inode_lock(inode);
 	/* Need to make file sparse, if not already, before freeing range. */
 	/* Consider adding equivalent for compressed since it could also work */
 	if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse)) {
 		rc = -EOPNOTSUPP;
-		free_xid(xid);
-		return rc;
+		goto out;
 	}
 
 	filemap_invalidate_lock(inode->i_mapping);
@@ -3421,11 +3406,13 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA,
-			true /* is_fctl */, (char *)&fsctl_buf,
+			(char *)&fsctl_buf,
 			sizeof(struct file_zero_data_information),
 			CIFSMaxBufSize, NULL, NULL);
-	free_xid(xid);
 	filemap_invalidate_unlock(inode->i_mapping);
+out:
+	inode_unlock(inode);
+	free_xid(xid);
 	return rc;
 }
 
@@ -3481,7 +3468,7 @@ static int smb3_simple_fallocate_range(unsigned int xid,
 	in_data.length = cpu_to_le64(len);
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid,
-			FSCTL_QUERY_ALLOCATED_RANGES, true,
+			FSCTL_QUERY_ALLOCATED_RANGES,
 			(char *)&in_data, sizeof(in_data),
 			1024 * sizeof(struct file_allocated_range_buffer),
 			(char **)&out_data, &out_data_len);
@@ -3682,39 +3669,50 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon,
 {
 	int rc;
 	unsigned int xid;
-	struct inode *inode;
+	struct inode *inode = file_inode(file);
 	struct cifsFileInfo *cfile = file->private_data;
-	struct cifsInodeInfo *cifsi;
+	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 	__le64 eof;
+	loff_t old_eof;
 
 	xid = get_xid();
 
-	inode = d_inode(cfile->dentry);
-	cifsi = CIFS_I(inode);
+	inode_lock(inode);
 
-	if (off >= i_size_read(inode) ||
-	    off + len >= i_size_read(inode)) {
+	old_eof = i_size_read(inode);
+	if ((off >= old_eof) ||
+	    off + len >= old_eof) {
 		rc = -EINVAL;
 		goto out;
 	}
 
+	filemap_invalidate_lock(inode->i_mapping);
+	rc = filemap_write_and_wait_range(inode->i_mapping, off, old_eof - 1);
+	if (rc < 0)
+		goto out_2;
+
+	truncate_pagecache_range(inode, off, old_eof);
+
 	rc = smb2_copychunk_range(xid, cfile, cfile, off + len,
-				  i_size_read(inode) - off - len, off);
+				  old_eof - off - len, off);
 	if (rc < 0)
-		goto out;
+		goto out_2;
 
-	eof = cpu_to_le64(i_size_read(inode) - len);
+	eof = cpu_to_le64(old_eof - len);
 	rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
 			  cfile->fid.volatile_fid, cfile->pid, &eof);
 	if (rc < 0)
-		goto out;
+		goto out_2;
 
 	rc = 0;
 
 	cifsi->server_eof = i_size_read(inode) - len;
 	truncate_setsize(inode, cifsi->server_eof);
 	fscache_resize_cookie(cifs_inode_cookie(inode), cifsi->server_eof);
+out_2:
+	filemap_invalidate_unlock(inode->i_mapping);
  out:
+	inode_unlock(inode);
 	free_xid(xid);
 	return rc;
 }
@@ -3725,34 +3723,47 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon,
 	int rc;
 	unsigned int xid;
 	struct cifsFileInfo *cfile = file->private_data;
+	struct inode *inode = file_inode(file);
 	__le64 eof;
-	__u64  count;
+	__u64  count, old_eof;
 
 	xid = get_xid();
 
-	if (off >= i_size_read(file->f_inode)) {
+	inode_lock(inode);
+
+	old_eof = i_size_read(inode);
+	if (off >= old_eof) {
 		rc = -EINVAL;
 		goto out;
 	}
 
-	count = i_size_read(file->f_inode) - off;
-	eof = cpu_to_le64(i_size_read(file->f_inode) + len);
+	count = old_eof - off;
+	eof = cpu_to_le64(old_eof + len);
+
+	filemap_invalidate_lock(inode->i_mapping);
+	rc = filemap_write_and_wait_range(inode->i_mapping, off, old_eof + len - 1);
+	if (rc < 0)
+		goto out_2;
+	truncate_pagecache_range(inode, off, old_eof);
 
 	rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
 			  cfile->fid.volatile_fid, cfile->pid, &eof);
 	if (rc < 0)
-		goto out;
+		goto out_2;
 
 	rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len);
 	if (rc < 0)
-		goto out;
+		goto out_2;
 
-	rc = smb3_zero_range(file, tcon, off, len, 1);
+	rc = smb3_zero_data(file, tcon, off, len, xid);
 	if (rc < 0)
-		goto out;
+		goto out_2;
 
 	rc = 0;
+out_2:
+	filemap_invalidate_unlock(inode->i_mapping);
  out:
+	inode_unlock(inode);
 	free_xid(xid);
 	return rc;
 }
@@ -3802,7 +3813,7 @@ static loff_t smb3_llseek(struct file *file, struct cifs_tcon *tcon, loff_t offs
 
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid,
-			FSCTL_QUERY_ALLOCATED_RANGES, true,
+			FSCTL_QUERY_ALLOCATED_RANGES,
 			(char *)&in_data, sizeof(in_data),
 			sizeof(struct file_allocated_range_buffer),
 			(char **)&out_data, &out_data_len);
@@ -3862,7 +3873,7 @@ static int smb3_fiemap(struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid,
-			FSCTL_QUERY_ALLOCATED_RANGES, true,
+			FSCTL_QUERY_ALLOCATED_RANGES,
 			(char *)&in_data, sizeof(in_data),
 			1024 * sizeof(struct file_allocated_range_buffer),
 			(char **)&out_data, &out_data_len);
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 9b31ea946d45..6352ab32c7e7 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -965,16 +965,17 @@ SMB2_negotiate(const unsigned int xid,
 	} else if (rc != 0)
 		goto neg_exit;
 
+	rc = -EIO;
 	if (strcmp(server->vals->version_string,
 		   SMB3ANY_VERSION_STRING) == 0) {
 		if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) {
 			cifs_server_dbg(VFS,
 				"SMB2 dialect returned but not requested\n");
-			return -EIO;
+			goto neg_exit;
 		} else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) {
 			cifs_server_dbg(VFS,
 				"SMB2.1 dialect returned but not requested\n");
-			return -EIO;
+			goto neg_exit;
 		} else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) {
 			/* ops set to 3.0 by default for default so update */
 			server->ops = &smb311_operations;
@@ -985,7 +986,7 @@ SMB2_negotiate(const unsigned int xid,
 		if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) {
 			cifs_server_dbg(VFS,
 				"SMB2 dialect returned but not requested\n");
-			return -EIO;
+			goto neg_exit;
 		} else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) {
 			/* ops set to 3.0 by default for default so update */
 			server->ops = &smb21_operations;
@@ -999,7 +1000,7 @@ SMB2_negotiate(const unsigned int xid,
 		/* if requested single dialect ensure returned dialect matched */
 		cifs_server_dbg(VFS, "Invalid 0x%x dialect returned: not requested\n",
 				le16_to_cpu(rsp->DialectRevision));
-		return -EIO;
+		goto neg_exit;
 	}
 
 	cifs_dbg(FYI, "mode 0x%x\n", rsp->SecurityMode);
@@ -1017,9 +1018,10 @@ SMB2_negotiate(const unsigned int xid,
 	else {
 		cifs_server_dbg(VFS, "Invalid dialect returned by server 0x%x\n",
 				le16_to_cpu(rsp->DialectRevision));
-		rc = -EIO;
 		goto neg_exit;
 	}
+
+	rc = 0;
 	server->dialect = le16_to_cpu(rsp->DialectRevision);
 
 	/*
@@ -1173,7 +1175,7 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
 	}
 
 	rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
-		FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */,
+		FSCTL_VALIDATE_NEGOTIATE_INFO,
 		(char *)pneg_inbuf, inbuflen, CIFSMaxBufSize,
 		(char **)&pneg_rsp, &rsplen);
 	if (rc == -EOPNOTSUPP) {
@@ -1928,7 +1930,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	tcon->capabilities = rsp->Capabilities; /* we keep caps little endian */
 	tcon->maximal_access = le32_to_cpu(rsp->MaximalAccess);
 	tcon->tid = le32_to_cpu(rsp->hdr.Id.SyncId.TreeId);
-	strlcpy(tcon->treeName, tree, sizeof(tcon->treeName));
+	strscpy(tcon->treeName, tree, sizeof(tcon->treeName));
 
 	if ((rsp->Capabilities & SMB2_SHARE_CAP_DFS) &&
 	    ((tcon->share_flags & SHI1005_FLAGS_DFS) == 0))
@@ -2572,19 +2574,15 @@ alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len,
 
 	path_len = UniStrnlen((wchar_t *)path, PATH_MAX);
 
-	/*
-	 * make room for one path separator between the treename and
-	 * path
-	 */
-	*out_len = treename_len + 1 + path_len;
+	/* make room for one path separator only if @path isn't empty */
+	*out_len = treename_len + (path[0] ? 1 : 0) + path_len;
 
 	/*
-	 * final path needs to be null-terminated UTF16 with a
-	 * size aligned to 8
+	 * final path needs to be 8-byte aligned as specified in
+	 * MS-SMB2 2.2.13 SMB2 CREATE Request.
 	 */
-
-	*out_size = roundup((*out_len+1)*2, 8);
-	*out_path = kzalloc(*out_size, GFP_KERNEL);
+	*out_size = roundup(*out_len * sizeof(__le16), 8);
+	*out_path = kzalloc(*out_size + sizeof(__le16) /* null */, GFP_KERNEL);
 	if (!*out_path)
 		return -ENOMEM;
 
@@ -3056,7 +3054,7 @@ int
 SMB2_ioctl_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server,
 		struct smb_rqst *rqst,
 		u64 persistent_fid, u64 volatile_fid, u32 opcode,
-		bool is_fsctl, char *in_data, u32 indatalen,
+		char *in_data, u32 indatalen,
 		__u32 max_response_size)
 {
 	struct smb2_ioctl_req *req;
@@ -3131,10 +3129,8 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server,
 	req->hdr.CreditCharge =
 		cpu_to_le16(DIV_ROUND_UP(max(indatalen, max_response_size),
 					 SMB2_MAX_BUFFER_SIZE));
-	if (is_fsctl)
-		req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL);
-	else
-		req->Flags = 0;
+	/* always an FSCTL (for now) */
+	req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL);
 
 	/* validate negotiate request must be signed - see MS-SMB2 3.2.5.5 */
 	if (opcode == FSCTL_VALIDATE_NEGOTIATE_INFO)
@@ -3161,9 +3157,9 @@ SMB2_ioctl_free(struct smb_rqst *rqst)
  */
 int
 SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
-	   u64 volatile_fid, u32 opcode, bool is_fsctl,
-	   char *in_data, u32 indatalen, u32 max_out_data_len,
-	   char **out_data, u32 *plen /* returned data len */)
+	   u64 volatile_fid, u32 opcode, char *in_data, u32 indatalen,
+	   u32 max_out_data_len, char **out_data,
+	   u32 *plen /* returned data len */)
 {
 	struct smb_rqst rqst;
 	struct smb2_ioctl_rsp *rsp = NULL;
@@ -3205,7 +3201,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 
 	rc = SMB2_ioctl_init(tcon, server,
 			     &rqst, persistent_fid, volatile_fid, opcode,
-			     is_fsctl, in_data, indatalen, max_out_data_len);
+			     in_data, indatalen, max_out_data_len);
 	if (rc)
 		goto ioctl_exit;
 
@@ -3297,7 +3293,7 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 			cpu_to_le16(COMPRESSION_FORMAT_DEFAULT);
 
 	rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid,
-			FSCTL_SET_COMPRESSION, true /* is_fsctl */,
+			FSCTL_SET_COMPRESSION,
 			(char *)&fsctl_input /* data input */,
 			2 /* in data len */, CIFSMaxBufSize /* max out data */,
 			&ret_data /* out data */, NULL);
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 51c5bf4a338a..3f740f24b96a 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -23,7 +23,7 @@ struct smb_rqst;
 extern int map_smb2_to_linux_error(char *buf, bool log_err);
 extern int smb2_check_message(char *buf, unsigned int length,
 			      struct TCP_Server_Info *server);
-extern unsigned int smb2_calc_size(void *buf, struct TCP_Server_Info *server);
+extern unsigned int smb2_calc_size(void *buf);
 extern char *smb2_get_data_area_len(int *off, int *len,
 				    struct smb2_hdr *shdr);
 extern __le16 *cifs_convert_path_to_utf16(const char *from,
@@ -137,13 +137,13 @@ extern int SMB2_open_init(struct cifs_tcon *tcon,
 extern void SMB2_open_free(struct smb_rqst *rqst);
 extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon,
 		     u64 persistent_fid, u64 volatile_fid, u32 opcode,
-		     bool is_fsctl, char *in_data, u32 indatalen, u32 maxoutlen,
+		     char *in_data, u32 indatalen, u32 maxoutlen,
 		     char **out_data, u32 *plen /* returned data len */);
 extern int SMB2_ioctl_init(struct cifs_tcon *tcon,
 			   struct TCP_Server_Info *server,
 			   struct smb_rqst *rqst,
 			   u64 persistent_fid, u64 volatile_fid, u32 opcode,
-			   bool is_fsctl, char *in_data, u32 indatalen,
+			   char *in_data, u32 indatalen,
 			   __u32 max_response_size);
 extern void SMB2_ioctl_free(struct smb_rqst *rqst);
 extern int SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon,
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index de7aeced7e16..9a2753e21170 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -194,10 +194,6 @@ smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg,
 
 	*sent = 0;
 
-	smb_msg->msg_name = (struct sockaddr *) &server->dstaddr;
-	smb_msg->msg_namelen = sizeof(struct sockaddr);
-	smb_msg->msg_control = NULL;
-	smb_msg->msg_controllen = 0;
 	if (server->noblocksnd)
 		smb_msg->msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL;
 	else
@@ -261,8 +257,8 @@ smb_rqst_len(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 	int nvec;
 	unsigned long buflen = 0;
 
-	if (server->vals->header_preamble_size == 0 &&
-	    rqst->rq_nvec >= 2 && rqst->rq_iov[0].iov_len == 4) {
+	if (!is_smb1(server) && rqst->rq_nvec >= 2 &&
+	    rqst->rq_iov[0].iov_len == 4) {
 		iov = &rqst->rq_iov[1];
 		nvec = rqst->rq_nvec - 1;
 	} else {
@@ -309,7 +305,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 	sigset_t mask, oldmask;
 	size_t total_len = 0, sent, size;
 	struct socket *ssocket = server->ssocket;
-	struct msghdr smb_msg;
+	struct msghdr smb_msg = {};
 	__be32 rfc1002_marker;
 
 	if (cifs_rdma_enabled(server)) {
@@ -346,7 +342,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 	sigprocmask(SIG_BLOCK, &mask, &oldmask);
 
 	/* Generate a rfc1002 marker for SMB2+ */
-	if (server->vals->header_preamble_size == 0) {
+	if (!is_smb1(server)) {
 		struct kvec hiov = {
 			.iov_base = &rfc1002_marker,
 			.iov_len  = 4
@@ -1238,7 +1234,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
 		buf = (char *)midQ[i]->resp_buf;
 		resp_iov[i].iov_base = buf;
 		resp_iov[i].iov_len = midQ[i]->resp_buf_size +
-			server->vals->header_preamble_size;
+			HEADER_PREAMBLE_SIZE(server);
 
 		if (midQ[i]->large_buf)
 			resp_buf_type[i] = CIFS_LARGE_BUFFER;
@@ -1643,7 +1639,7 @@ int
 cifs_discard_remaining_data(struct TCP_Server_Info *server)
 {
 	unsigned int rfclen = server->pdu_size;
-	int remaining = rfclen + server->vals->header_preamble_size -
+	int remaining = rfclen + HEADER_PREAMBLE_SIZE(server) -
 		server->total_read;
 
 	while (remaining > 0) {
@@ -1689,8 +1685,7 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	unsigned int data_offset, data_len;
 	struct cifs_readdata *rdata = mid->callback_data;
 	char *buf = server->smallbuf;
-	unsigned int buflen = server->pdu_size +
-		server->vals->header_preamble_size;
+	unsigned int buflen = server->pdu_size + HEADER_PREAMBLE_SIZE(server);
 	bool use_rdma_mr = false;
 
 	cifs_dbg(FYI, "%s: mid=%llu offset=%llu bytes=%u\n",
@@ -1724,10 +1719,10 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 
 	/* set up first two iov for signature check and to get credits */
 	rdata->iov[0].iov_base = buf;
-	rdata->iov[0].iov_len = server->vals->header_preamble_size;
-	rdata->iov[1].iov_base = buf + server->vals->header_preamble_size;
+	rdata->iov[0].iov_len = HEADER_PREAMBLE_SIZE(server);
+	rdata->iov[1].iov_base = buf + HEADER_PREAMBLE_SIZE(server);
 	rdata->iov[1].iov_len =
-		server->total_read - server->vals->header_preamble_size;
+		server->total_read - HEADER_PREAMBLE_SIZE(server);
 	cifs_dbg(FYI, "0: iov_base=%p iov_len=%zu\n",
 		 rdata->iov[0].iov_base, rdata->iov[0].iov_len);
 	cifs_dbg(FYI, "1: iov_base=%p iov_len=%zu\n",
@@ -1752,7 +1747,7 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	}
 
 	data_offset = server->ops->read_data_offset(buf) +
-		server->vals->header_preamble_size;
+		HEADER_PREAMBLE_SIZE(server);
 	if (data_offset < server->total_read) {
 		/*
 		 * win2k8 sometimes sends an offset of 0 when the read
diff --git a/fs/coredump.c b/fs/coredump.c
index 9f4aae202109..3538f3a63965 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -832,6 +832,39 @@ static int __dump_skip(struct coredump_params *cprm, size_t nr)
 	}
 }
 
+static int dump_emit_page(struct coredump_params *cprm, struct page *page)
+{
+	struct bio_vec bvec = {
+		.bv_page	= page,
+		.bv_offset	= 0,
+		.bv_len		= PAGE_SIZE,
+	};
+	struct iov_iter iter;
+	struct file *file = cprm->file;
+	loff_t pos;
+	ssize_t n;
+
+	if (cprm->to_skip) {
+		if (!__dump_skip(cprm, cprm->to_skip))
+			return 0;
+		cprm->to_skip = 0;
+	}
+	if (cprm->written + PAGE_SIZE > cprm->limit)
+		return 0;
+	if (dump_interrupted())
+		return 0;
+	pos = file->f_pos;
+	iov_iter_bvec(&iter, WRITE, &bvec, 1, PAGE_SIZE);
+	n = __kernel_write_iter(cprm->file, &iter, &pos);
+	if (n != PAGE_SIZE)
+		return 0;
+	file->f_pos = pos;
+	cprm->written += PAGE_SIZE;
+	cprm->pos += PAGE_SIZE;
+
+	return 1;
+}
+
 int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
 {
 	if (cprm->to_skip) {
@@ -863,7 +896,6 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start,
 
 	for (addr = start; addr < start + len; addr += PAGE_SIZE) {
 		struct page *page;
-		int stop;
 
 		/*
 		 * To avoid having to allocate page tables for virtual address
@@ -874,10 +906,7 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start,
 		 */
 		page = get_dump_page(addr);
 		if (page) {
-			void *kaddr = kmap_local_page(page);
-
-			stop = !dump_emit(cprm, kaddr, PAGE_SIZE);
-			kunmap_local(kaddr);
+			int stop = !dump_emit_page(cprm, page);
 			put_page(page);
 			if (stop)
 				return 0;
diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c
index 2217fe5ece6f..1b4403136d05 100644
--- a/fs/crypto/bio.c
+++ b/fs/crypto/bio.c
@@ -25,21 +25,25 @@
  * then this function isn't applicable.  This function may sleep, so it must be
  * called from a workqueue rather than from the bio's bi_end_io callback.
  *
- * This function sets PG_error on any pages that contain any blocks that failed
- * to be decrypted.  The filesystem must not mark such pages uptodate.
+ * Return: %true on success; %false on failure.  On failure, bio->bi_status is
+ *	   also set to an error status.
  */
-void fscrypt_decrypt_bio(struct bio *bio)
+bool fscrypt_decrypt_bio(struct bio *bio)
 {
 	struct bio_vec *bv;
 	struct bvec_iter_all iter_all;
 
 	bio_for_each_segment_all(bv, bio, iter_all) {
 		struct page *page = bv->bv_page;
-		int ret = fscrypt_decrypt_pagecache_blocks(page, bv->bv_len,
+		int err = fscrypt_decrypt_pagecache_blocks(page, bv->bv_len,
 							   bv->bv_offset);
-		if (ret)
-			SetPageError(page);
+
+		if (err) {
+			bio->bi_status = errno_to_blk_status(err);
+			return false;
+		}
 	}
+	return true;
 }
 EXPORT_SYMBOL(fscrypt_decrypt_bio);
 
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index 3afdaa084773..d5f68a0c5d15 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -184,7 +184,7 @@ struct fscrypt_symlink_data {
 struct fscrypt_prepared_key {
 	struct crypto_skcipher *tfm;
 #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
-	struct fscrypt_blk_crypto_key *blk_key;
+	struct blk_crypto_key *blk_key;
 #endif
 };
 
@@ -225,7 +225,7 @@ struct fscrypt_info {
 	 * will be NULL if the master key was found in a process-subscribed
 	 * keyring rather than in the filesystem-level keyring.
 	 */
-	struct key *ci_master_key;
+	struct fscrypt_master_key *ci_master_key;
 
 	/*
 	 * Link in list of inodes that were unlocked with the master key.
@@ -344,7 +344,8 @@ int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key,
 				     const u8 *raw_key,
 				     const struct fscrypt_info *ci);
 
-void fscrypt_destroy_inline_crypt_key(struct fscrypt_prepared_key *prep_key);
+void fscrypt_destroy_inline_crypt_key(struct super_block *sb,
+				      struct fscrypt_prepared_key *prep_key);
 
 /*
  * Check whether the crypto transform or blk-crypto key has been allocated in
@@ -390,7 +391,8 @@ fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key,
 }
 
 static inline void
-fscrypt_destroy_inline_crypt_key(struct fscrypt_prepared_key *prep_key)
+fscrypt_destroy_inline_crypt_key(struct super_block *sb,
+				 struct fscrypt_prepared_key *prep_key)
 {
 }
 
@@ -437,6 +439,40 @@ struct fscrypt_master_key_secret {
 struct fscrypt_master_key {
 
 	/*
+	 * Back-pointer to the super_block of the filesystem to which this
+	 * master key has been added.  Only valid if ->mk_active_refs > 0.
+	 */
+	struct super_block			*mk_sb;
+
+	/*
+	 * Link in ->mk_sb->s_master_keys->key_hashtable.
+	 * Only valid if ->mk_active_refs > 0.
+	 */
+	struct hlist_node			mk_node;
+
+	/* Semaphore that protects ->mk_secret and ->mk_users */
+	struct rw_semaphore			mk_sem;
+
+	/*
+	 * Active and structural reference counts.  An active ref guarantees
+	 * that the struct continues to exist, continues to be in the keyring
+	 * ->mk_sb->s_master_keys, and that any embedded subkeys (e.g.
+	 * ->mk_direct_keys) that have been prepared continue to exist.
+	 * A structural ref only guarantees that the struct continues to exist.
+	 *
+	 * There is one active ref associated with ->mk_secret being present,
+	 * and one active ref for each inode in ->mk_decrypted_inodes.
+	 *
+	 * There is one structural ref associated with the active refcount being
+	 * nonzero.  Finding a key in the keyring also takes a structural ref,
+	 * which is then held temporarily while the key is operated on.
+	 */
+	refcount_t				mk_active_refs;
+	refcount_t				mk_struct_refs;
+
+	struct rcu_head				mk_rcu_head;
+
+	/*
 	 * The secret key material.  After FS_IOC_REMOVE_ENCRYPTION_KEY is
 	 * executed, this is wiped and no new inodes can be unlocked with this
 	 * key; however, there may still be inodes in ->mk_decrypted_inodes
@@ -444,7 +480,10 @@ struct fscrypt_master_key {
 	 * FS_IOC_REMOVE_ENCRYPTION_KEY can be retried, or
 	 * FS_IOC_ADD_ENCRYPTION_KEY can add the secret again.
 	 *
-	 * Locking: protected by this master key's key->sem.
+	 * While ->mk_secret is present, one ref in ->mk_active_refs is held.
+	 *
+	 * Locking: protected by ->mk_sem.  The manipulation of ->mk_active_refs
+	 *	    associated with this field is protected by ->mk_sem as well.
 	 */
 	struct fscrypt_master_key_secret	mk_secret;
 
@@ -465,23 +504,13 @@ struct fscrypt_master_key {
 	 *
 	 * This is NULL for v1 policy keys; those can only be added by root.
 	 *
-	 * Locking: in addition to this keyring's own semaphore, this is
-	 * protected by this master key's key->sem, so we can do atomic
-	 * search+insert.  It can also be searched without taking any locks, but
-	 * in that case the returned key may have already been removed.
+	 * Locking: protected by ->mk_sem.  (We don't just rely on the keyrings
+	 * subsystem semaphore ->mk_users->sem, as we need support for atomic
+	 * search+insert along with proper synchronization with ->mk_secret.)
 	 */
 	struct key		*mk_users;
 
 	/*
-	 * Length of ->mk_decrypted_inodes, plus one if mk_secret is present.
-	 * Once this goes to 0, the master key is removed from ->s_master_keys.
-	 * The 'struct fscrypt_master_key' will continue to live as long as the
-	 * 'struct key' whose payload it is, but we won't let this reference
-	 * count rise again.
-	 */
-	refcount_t		mk_refcount;
-
-	/*
 	 * List of inodes that were unlocked using this key.  This allows the
 	 * inodes to be evicted efficiently if the key is removed.
 	 */
@@ -506,10 +535,10 @@ static inline bool
 is_master_key_secret_present(const struct fscrypt_master_key_secret *secret)
 {
 	/*
-	 * The READ_ONCE() is only necessary for fscrypt_drop_inode() and
-	 * fscrypt_key_describe().  These run in atomic context, so they can't
-	 * take the key semaphore and thus 'secret' can change concurrently
-	 * which would be a data race.  But they only need to know whether the
+	 * The READ_ONCE() is only necessary for fscrypt_drop_inode().
+	 * fscrypt_drop_inode() runs in atomic context, so it can't take the key
+	 * semaphore and thus 'secret' can change concurrently which would be a
+	 * data race.  But fscrypt_drop_inode() only need to know whether the
 	 * secret *was* present at the time of check, so READ_ONCE() suffices.
 	 */
 	return READ_ONCE(secret->size) != 0;
@@ -538,7 +567,11 @@ static inline int master_key_spec_len(const struct fscrypt_key_specifier *spec)
 	return 0;
 }
 
-struct key *
+void fscrypt_put_master_key(struct fscrypt_master_key *mk);
+
+void fscrypt_put_master_key_activeref(struct fscrypt_master_key *mk);
+
+struct fscrypt_master_key *
 fscrypt_find_master_key(struct super_block *sb,
 			const struct fscrypt_key_specifier *mk_spec);
 
@@ -569,7 +602,8 @@ extern struct fscrypt_mode fscrypt_modes[];
 int fscrypt_prepare_key(struct fscrypt_prepared_key *prep_key,
 			const u8 *raw_key, const struct fscrypt_info *ci);
 
-void fscrypt_destroy_prepared_key(struct fscrypt_prepared_key *prep_key);
+void fscrypt_destroy_prepared_key(struct super_block *sb,
+				  struct fscrypt_prepared_key *prep_key);
 
 int fscrypt_set_per_file_enc_key(struct fscrypt_info *ci, const u8 *raw_key);
 
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index 7c01025879b3..7b8c5a1104b5 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -5,8 +5,6 @@
  * Encryption hooks for higher-level filesystem operations.
  */
 
-#include <linux/key.h>
-
 #include "fscrypt_private.h"
 
 /**
@@ -142,7 +140,6 @@ int fscrypt_prepare_setflags(struct inode *inode,
 			     unsigned int oldflags, unsigned int flags)
 {
 	struct fscrypt_info *ci;
-	struct key *key;
 	struct fscrypt_master_key *mk;
 	int err;
 
@@ -158,14 +155,13 @@ int fscrypt_prepare_setflags(struct inode *inode,
 		ci = inode->i_crypt_info;
 		if (ci->ci_policy.version != FSCRYPT_POLICY_V2)
 			return -EINVAL;
-		key = ci->ci_master_key;
-		mk = key->payload.data[0];
-		down_read(&key->sem);
+		mk = ci->ci_master_key;
+		down_read(&mk->mk_sem);
 		if (is_master_key_secret_present(&mk->mk_secret))
 			err = fscrypt_derive_dirhash_key(ci, mk);
 		else
 			err = -ENOKEY;
-		up_read(&key->sem);
+		up_read(&mk->mk_sem);
 		return err;
 	}
 	return 0;
diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c
index 90f3e68f166e..cea8b14007e6 100644
--- a/fs/crypto/inline_crypt.c
+++ b/fs/crypto/inline_crypt.c
@@ -21,26 +21,22 @@
 
 #include "fscrypt_private.h"
 
-struct fscrypt_blk_crypto_key {
-	struct blk_crypto_key base;
-	int num_devs;
-	struct request_queue *devs[];
-};
-
-static int fscrypt_get_num_devices(struct super_block *sb)
+static struct block_device **fscrypt_get_devices(struct super_block *sb,
+						 unsigned int *num_devs)
 {
-	if (sb->s_cop->get_num_devices)
-		return sb->s_cop->get_num_devices(sb);
-	return 1;
-}
+	struct block_device **devs;
 
-static void fscrypt_get_devices(struct super_block *sb, int num_devs,
-				struct request_queue **devs)
-{
-	if (num_devs == 1)
-		devs[0] = bdev_get_queue(sb->s_bdev);
-	else
-		sb->s_cop->get_devices(sb, devs);
+	if (sb->s_cop->get_devices) {
+		devs = sb->s_cop->get_devices(sb, num_devs);
+		if (devs)
+			return devs;
+	}
+	devs = kmalloc(sizeof(*devs), GFP_KERNEL);
+	if (!devs)
+		return ERR_PTR(-ENOMEM);
+	devs[0] = sb->s_bdev;
+	*num_devs = 1;
+	return devs;
 }
 
 static unsigned int fscrypt_get_dun_bytes(const struct fscrypt_info *ci)
@@ -74,15 +70,17 @@ static unsigned int fscrypt_get_dun_bytes(const struct fscrypt_info *ci)
  * helpful for debugging problems where the "wrong" implementation is used.
  */
 static void fscrypt_log_blk_crypto_impl(struct fscrypt_mode *mode,
-					struct request_queue **devs,
-					int num_devs,
+					struct block_device **devs,
+					unsigned int num_devs,
 					const struct blk_crypto_config *cfg)
 {
-	int i;
+	unsigned int i;
 
 	for (i = 0; i < num_devs; i++) {
+		struct request_queue *q = bdev_get_queue(devs[i]);
+
 		if (!IS_ENABLED(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) ||
-		    __blk_crypto_cfg_supported(devs[i]->crypto_profile, cfg)) {
+		    __blk_crypto_cfg_supported(q->crypto_profile, cfg)) {
 			if (!xchg(&mode->logged_blk_crypto_native, 1))
 				pr_info("fscrypt: %s using blk-crypto (native)\n",
 					mode->friendly_name);
@@ -99,9 +97,9 @@ int fscrypt_select_encryption_impl(struct fscrypt_info *ci)
 	const struct inode *inode = ci->ci_inode;
 	struct super_block *sb = inode->i_sb;
 	struct blk_crypto_config crypto_cfg;
-	int num_devs;
-	struct request_queue **devs;
-	int i;
+	struct block_device **devs;
+	unsigned int num_devs;
+	unsigned int i;
 
 	/* The file must need contents encryption, not filenames encryption */
 	if (!S_ISREG(inode->i_mode))
@@ -129,20 +127,20 @@ int fscrypt_select_encryption_impl(struct fscrypt_info *ci)
 		return 0;
 
 	/*
-	 * On all the filesystem's devices, blk-crypto must support the crypto
-	 * configuration that the file would use.
+	 * On all the filesystem's block devices, blk-crypto must support the
+	 * crypto configuration that the file would use.
 	 */
 	crypto_cfg.crypto_mode = ci->ci_mode->blk_crypto_mode;
 	crypto_cfg.data_unit_size = sb->s_blocksize;
 	crypto_cfg.dun_bytes = fscrypt_get_dun_bytes(ci);
-	num_devs = fscrypt_get_num_devices(sb);
-	devs = kmalloc_array(num_devs, sizeof(*devs), GFP_KERNEL);
-	if (!devs)
-		return -ENOMEM;
-	fscrypt_get_devices(sb, num_devs, devs);
+
+	devs = fscrypt_get_devices(sb, &num_devs);
+	if (IS_ERR(devs))
+		return PTR_ERR(devs);
 
 	for (i = 0; i < num_devs; i++) {
-		if (!blk_crypto_config_supported(devs[i], &crypto_cfg))
+		if (!blk_crypto_config_supported(bdev_get_queue(devs[i]),
+						 &crypto_cfg))
 			goto out_free_devs;
 	}
 
@@ -162,49 +160,41 @@ int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key,
 	const struct inode *inode = ci->ci_inode;
 	struct super_block *sb = inode->i_sb;
 	enum blk_crypto_mode_num crypto_mode = ci->ci_mode->blk_crypto_mode;
-	int num_devs = fscrypt_get_num_devices(sb);
-	int queue_refs = 0;
-	struct fscrypt_blk_crypto_key *blk_key;
+	struct blk_crypto_key *blk_key;
+	struct block_device **devs;
+	unsigned int num_devs;
+	unsigned int i;
 	int err;
-	int i;
 
-	blk_key = kzalloc(struct_size(blk_key, devs, num_devs), GFP_KERNEL);
+	blk_key = kmalloc(sizeof(*blk_key), GFP_KERNEL);
 	if (!blk_key)
 		return -ENOMEM;
 
-	blk_key->num_devs = num_devs;
-	fscrypt_get_devices(sb, num_devs, blk_key->devs);
-
-	err = blk_crypto_init_key(&blk_key->base, raw_key, crypto_mode,
+	err = blk_crypto_init_key(blk_key, raw_key, crypto_mode,
 				  fscrypt_get_dun_bytes(ci), sb->s_blocksize);
 	if (err) {
 		fscrypt_err(inode, "error %d initializing blk-crypto key", err);
 		goto fail;
 	}
 
-	/*
-	 * We have to start using blk-crypto on all the filesystem's devices.
-	 * We also have to save all the request_queue's for later so that the
-	 * key can be evicted from them.  This is needed because some keys
-	 * aren't destroyed until after the filesystem was already unmounted
-	 * (namely, the per-mode keys in struct fscrypt_master_key).
-	 */
+	/* Start using blk-crypto on all the filesystem's block devices. */
+	devs = fscrypt_get_devices(sb, &num_devs);
+	if (IS_ERR(devs)) {
+		err = PTR_ERR(devs);
+		goto fail;
+	}
 	for (i = 0; i < num_devs; i++) {
-		if (!blk_get_queue(blk_key->devs[i])) {
-			fscrypt_err(inode, "couldn't get request_queue");
-			err = -EAGAIN;
-			goto fail;
-		}
-		queue_refs++;
-
-		err = blk_crypto_start_using_key(&blk_key->base,
-						 blk_key->devs[i]);
-		if (err) {
-			fscrypt_err(inode,
-				    "error %d starting to use blk-crypto", err);
-			goto fail;
-		}
+		err = blk_crypto_start_using_key(blk_key,
+						 bdev_get_queue(devs[i]));
+		if (err)
+			break;
 	}
+	kfree(devs);
+	if (err) {
+		fscrypt_err(inode, "error %d starting to use blk-crypto", err);
+		goto fail;
+	}
+
 	/*
 	 * Pairs with the smp_load_acquire() in fscrypt_is_key_prepared().
 	 * I.e., here we publish ->blk_key with a RELEASE barrier so that
@@ -215,24 +205,29 @@ int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key,
 	return 0;
 
 fail:
-	for (i = 0; i < queue_refs; i++)
-		blk_put_queue(blk_key->devs[i]);
 	kfree_sensitive(blk_key);
 	return err;
 }
 
-void fscrypt_destroy_inline_crypt_key(struct fscrypt_prepared_key *prep_key)
+void fscrypt_destroy_inline_crypt_key(struct super_block *sb,
+				      struct fscrypt_prepared_key *prep_key)
 {
-	struct fscrypt_blk_crypto_key *blk_key = prep_key->blk_key;
-	int i;
+	struct blk_crypto_key *blk_key = prep_key->blk_key;
+	struct block_device **devs;
+	unsigned int num_devs;
+	unsigned int i;
 
-	if (blk_key) {
-		for (i = 0; i < blk_key->num_devs; i++) {
-			blk_crypto_evict_key(blk_key->devs[i], &blk_key->base);
-			blk_put_queue(blk_key->devs[i]);
-		}
-		kfree_sensitive(blk_key);
+	if (!blk_key)
+		return;
+
+	/* Evict the key from all the filesystem's block devices. */
+	devs = fscrypt_get_devices(sb, &num_devs);
+	if (!IS_ERR(devs)) {
+		for (i = 0; i < num_devs; i++)
+			blk_crypto_evict_key(bdev_get_queue(devs[i]), blk_key);
+		kfree(devs);
 	}
+	kfree_sensitive(blk_key);
 }
 
 bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode)
@@ -282,7 +277,7 @@ void fscrypt_set_bio_crypt_ctx(struct bio *bio, const struct inode *inode,
 	ci = inode->i_crypt_info;
 
 	fscrypt_generate_dun(ci, first_lblk, dun);
-	bio_crypt_set_ctx(bio, &ci->ci_enc_key.blk_key->base, dun, gfp_mask);
+	bio_crypt_set_ctx(bio, ci->ci_enc_key.blk_key, dun, gfp_mask);
 }
 EXPORT_SYMBOL_GPL(fscrypt_set_bio_crypt_ctx);
 
@@ -369,7 +364,7 @@ bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode,
 	 * uses the same pointer.  I.e., there's currently no need to support
 	 * merging requests where the keys are the same but the pointers differ.
 	 */
-	if (bc->bc_key != &inode->i_crypt_info->ci_enc_key.blk_key->base)
+	if (bc->bc_key != inode->i_crypt_info->ci_enc_key.blk_key)
 		return false;
 
 	fscrypt_generate_dun(inode->i_crypt_info, next_lblk, next_dun);
@@ -401,46 +396,45 @@ bool fscrypt_mergeable_bio_bh(struct bio *bio,
 EXPORT_SYMBOL_GPL(fscrypt_mergeable_bio_bh);
 
 /**
- * fscrypt_dio_supported() - check whether a DIO (direct I/O) request is
- *			     supported as far as encryption is concerned
- * @iocb: the file and position the I/O is targeting
- * @iter: the I/O data segment(s)
+ * fscrypt_dio_supported() - check whether DIO (direct I/O) is supported on an
+ *			     inode, as far as encryption is concerned
+ * @inode: the inode in question
  *
  * Return: %true if there are no encryption constraints that prevent DIO from
  *	   being supported; %false if DIO is unsupported.  (Note that in the
  *	   %true case, the filesystem might have other, non-encryption-related
- *	   constraints that prevent DIO from actually being supported.)
+ *	   constraints that prevent DIO from actually being supported.  Also, on
+ *	   encrypted files the filesystem is still responsible for only allowing
+ *	   DIO when requests are filesystem-block-aligned.)
  */
-bool fscrypt_dio_supported(struct kiocb *iocb, struct iov_iter *iter)
+bool fscrypt_dio_supported(struct inode *inode)
 {
-	const struct inode *inode = file_inode(iocb->ki_filp);
-	const unsigned int blocksize = i_blocksize(inode);
+	int err;
 
 	/* If the file is unencrypted, no veto from us. */
 	if (!fscrypt_needs_contents_encryption(inode))
 		return true;
 
-	/* We only support DIO with inline crypto, not fs-layer crypto. */
-	if (!fscrypt_inode_uses_inline_crypto(inode))
-		return false;
-
 	/*
-	 * Since the granularity of encryption is filesystem blocks, the file
-	 * position and total I/O length must be aligned to the filesystem block
-	 * size -- not just to the block device's logical block size as is
-	 * traditionally the case for DIO on many filesystems.
+	 * We only support DIO with inline crypto, not fs-layer crypto.
 	 *
-	 * We require that the user-provided memory buffers be filesystem block
-	 * aligned too.  It is simpler to have a single alignment value required
-	 * for all properties of the I/O, as is normally the case for DIO.
-	 * Also, allowing less aligned buffers would imply that data units could
-	 * cross bvecs, which would greatly complicate the I/O stack, which
-	 * assumes that bios can be split at any bvec boundary.
+	 * To determine whether the inode is using inline crypto, we have to set
+	 * up the key if it wasn't already done.  This is because in the current
+	 * design of fscrypt, the decision of whether to use inline crypto or
+	 * not isn't made until the inode's encryption key is being set up.  In
+	 * the DIO read/write case, the key will always be set up already, since
+	 * the file will be open.  But in the case of statx(), the key might not
+	 * be set up yet, as the file might not have been opened yet.
 	 */
-	if (!IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(iter), blocksize))
+	err = fscrypt_require_key(inode);
+	if (err) {
+		/*
+		 * Key unavailable or couldn't be set up.  This edge case isn't
+		 * worth worrying about; just report that DIO is unsupported.
+		 */
 		return false;
-
-	return true;
+	}
+	return fscrypt_inode_uses_inline_crypto(inode);
 }
 EXPORT_SYMBOL_GPL(fscrypt_dio_supported);
 
diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c
index caee9f8620dd..1cca09aa43f8 100644
--- a/fs/crypto/keyring.c
+++ b/fs/crypto/keyring.c
@@ -18,6 +18,7 @@
  * information about these ioctls.
  */
 
+#include <asm/unaligned.h>
 #include <crypto/skcipher.h>
 #include <linux/key-type.h>
 #include <linux/random.h>
@@ -25,6 +26,18 @@
 
 #include "fscrypt_private.h"
 
+/* The master encryption keys for a filesystem (->s_master_keys) */
+struct fscrypt_keyring {
+	/*
+	 * Lock that protects ->key_hashtable.  It does *not* protect the
+	 * fscrypt_master_key structs themselves.
+	 */
+	spinlock_t lock;
+
+	/* Hash table that maps fscrypt_key_specifier to fscrypt_master_key */
+	struct hlist_head key_hashtable[128];
+};
+
 static void wipe_master_key_secret(struct fscrypt_master_key_secret *secret)
 {
 	fscrypt_destroy_hkdf(&secret->hkdf);
@@ -38,66 +51,81 @@ static void move_master_key_secret(struct fscrypt_master_key_secret *dst,
 	memzero_explicit(src, sizeof(*src));
 }
 
-static void free_master_key(struct fscrypt_master_key *mk)
+static void fscrypt_free_master_key(struct rcu_head *head)
 {
-	size_t i;
-
-	wipe_master_key_secret(&mk->mk_secret);
-
-	for (i = 0; i <= FSCRYPT_MODE_MAX; i++) {
-		fscrypt_destroy_prepared_key(&mk->mk_direct_keys[i]);
-		fscrypt_destroy_prepared_key(&mk->mk_iv_ino_lblk_64_keys[i]);
-		fscrypt_destroy_prepared_key(&mk->mk_iv_ino_lblk_32_keys[i]);
-	}
-
-	key_put(mk->mk_users);
+	struct fscrypt_master_key *mk =
+		container_of(head, struct fscrypt_master_key, mk_rcu_head);
+	/*
+	 * The master key secret and any embedded subkeys should have already
+	 * been wiped when the last active reference to the fscrypt_master_key
+	 * struct was dropped; doing it here would be unnecessarily late.
+	 * Nevertheless, use kfree_sensitive() in case anything was missed.
+	 */
 	kfree_sensitive(mk);
 }
 
-static inline bool valid_key_spec(const struct fscrypt_key_specifier *spec)
+void fscrypt_put_master_key(struct fscrypt_master_key *mk)
 {
-	if (spec->__reserved)
-		return false;
-	return master_key_spec_len(spec) != 0;
+	if (!refcount_dec_and_test(&mk->mk_struct_refs))
+		return;
+	/*
+	 * No structural references left, so free ->mk_users, and also free the
+	 * fscrypt_master_key struct itself after an RCU grace period ensures
+	 * that concurrent keyring lookups can no longer find it.
+	 */
+	WARN_ON(refcount_read(&mk->mk_active_refs) != 0);
+	key_put(mk->mk_users);
+	mk->mk_users = NULL;
+	call_rcu(&mk->mk_rcu_head, fscrypt_free_master_key);
 }
 
-static int fscrypt_key_instantiate(struct key *key,
-				   struct key_preparsed_payload *prep)
+void fscrypt_put_master_key_activeref(struct fscrypt_master_key *mk)
 {
-	key->payload.data[0] = (struct fscrypt_master_key *)prep->data;
-	return 0;
-}
+	struct super_block *sb = mk->mk_sb;
+	struct fscrypt_keyring *keyring = sb->s_master_keys;
+	size_t i;
 
-static void fscrypt_key_destroy(struct key *key)
-{
-	free_master_key(key->payload.data[0]);
-}
+	if (!refcount_dec_and_test(&mk->mk_active_refs))
+		return;
+	/*
+	 * No active references left, so complete the full removal of this
+	 * fscrypt_master_key struct by removing it from the keyring and
+	 * destroying any subkeys embedded in it.
+	 */
 
-static void fscrypt_key_describe(const struct key *key, struct seq_file *m)
-{
-	seq_puts(m, key->description);
+	spin_lock(&keyring->lock);
+	hlist_del_rcu(&mk->mk_node);
+	spin_unlock(&keyring->lock);
 
-	if (key_is_positive(key)) {
-		const struct fscrypt_master_key *mk = key->payload.data[0];
+	/*
+	 * ->mk_active_refs == 0 implies that ->mk_secret is not present and
+	 * that ->mk_decrypted_inodes is empty.
+	 */
+	WARN_ON(is_master_key_secret_present(&mk->mk_secret));
+	WARN_ON(!list_empty(&mk->mk_decrypted_inodes));
 
-		if (!is_master_key_secret_present(&mk->mk_secret))
-			seq_puts(m, ": secret removed");
+	for (i = 0; i <= FSCRYPT_MODE_MAX; i++) {
+		fscrypt_destroy_prepared_key(
+				sb, &mk->mk_direct_keys[i]);
+		fscrypt_destroy_prepared_key(
+				sb, &mk->mk_iv_ino_lblk_64_keys[i]);
+		fscrypt_destroy_prepared_key(
+				sb, &mk->mk_iv_ino_lblk_32_keys[i]);
 	}
+	memzero_explicit(&mk->mk_ino_hash_key,
+			 sizeof(mk->mk_ino_hash_key));
+	mk->mk_ino_hash_key_initialized = false;
+
+	/* Drop the structural ref associated with the active refs. */
+	fscrypt_put_master_key(mk);
 }
 
-/*
- * Type of key in ->s_master_keys.  Each key of this type represents a master
- * key which has been added to the filesystem.  Its payload is a
- * 'struct fscrypt_master_key'.  The "." prefix in the key type name prevents
- * users from adding keys of this type via the keyrings syscalls rather than via
- * the intended method of FS_IOC_ADD_ENCRYPTION_KEY.
- */
-static struct key_type key_type_fscrypt = {
-	.name			= "._fscrypt",
-	.instantiate		= fscrypt_key_instantiate,
-	.destroy		= fscrypt_key_destroy,
-	.describe		= fscrypt_key_describe,
-};
+static inline bool valid_key_spec(const struct fscrypt_key_specifier *spec)
+{
+	if (spec->__reserved)
+		return false;
+	return master_key_spec_len(spec) != 0;
+}
 
 static int fscrypt_user_key_instantiate(struct key *key,
 					struct key_preparsed_payload *prep)
@@ -131,32 +159,6 @@ static struct key_type key_type_fscrypt_user = {
 	.describe		= fscrypt_user_key_describe,
 };
 
-/* Search ->s_master_keys or ->mk_users */
-static struct key *search_fscrypt_keyring(struct key *keyring,
-					  struct key_type *type,
-					  const char *description)
-{
-	/*
-	 * We need to mark the keyring reference as "possessed" so that we
-	 * acquire permission to search it, via the KEY_POS_SEARCH permission.
-	 */
-	key_ref_t keyref = make_key_ref(keyring, true /* possessed */);
-
-	keyref = keyring_search(keyref, type, description, false);
-	if (IS_ERR(keyref)) {
-		if (PTR_ERR(keyref) == -EAGAIN || /* not found */
-		    PTR_ERR(keyref) == -EKEYREVOKED) /* recently invalidated */
-			keyref = ERR_PTR(-ENOKEY);
-		return ERR_CAST(keyref);
-	}
-	return key_ref_to_ptr(keyref);
-}
-
-#define FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE	\
-	(CONST_STRLEN("fscrypt-") + sizeof_field(struct super_block, s_id))
-
-#define FSCRYPT_MK_DESCRIPTION_SIZE	(2 * FSCRYPT_KEY_IDENTIFIER_SIZE + 1)
-
 #define FSCRYPT_MK_USERS_DESCRIPTION_SIZE	\
 	(CONST_STRLEN("fscrypt-") + 2 * FSCRYPT_KEY_IDENTIFIER_SIZE + \
 	 CONST_STRLEN("-users") + 1)
@@ -164,21 +166,6 @@ static struct key *search_fscrypt_keyring(struct key *keyring,
 #define FSCRYPT_MK_USER_DESCRIPTION_SIZE	\
 	(2 * FSCRYPT_KEY_IDENTIFIER_SIZE + CONST_STRLEN(".uid.") + 10 + 1)
 
-static void format_fs_keyring_description(
-			char description[FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE],
-			const struct super_block *sb)
-{
-	sprintf(description, "fscrypt-%s", sb->s_id);
-}
-
-static void format_mk_description(
-			char description[FSCRYPT_MK_DESCRIPTION_SIZE],
-			const struct fscrypt_key_specifier *mk_spec)
-{
-	sprintf(description, "%*phN",
-		master_key_spec_len(mk_spec), (u8 *)&mk_spec->u);
-}
-
 static void format_mk_users_keyring_description(
 			char description[FSCRYPT_MK_USERS_DESCRIPTION_SIZE],
 			const u8 mk_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE])
@@ -199,20 +186,15 @@ static void format_mk_user_description(
 /* Create ->s_master_keys if needed.  Synchronized by fscrypt_add_key_mutex. */
 static int allocate_filesystem_keyring(struct super_block *sb)
 {
-	char description[FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE];
-	struct key *keyring;
+	struct fscrypt_keyring *keyring;
 
 	if (sb->s_master_keys)
 		return 0;
 
-	format_fs_keyring_description(description, sb);
-	keyring = keyring_alloc(description, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
-				current_cred(), KEY_POS_SEARCH |
-				  KEY_USR_SEARCH | KEY_USR_READ | KEY_USR_VIEW,
-				KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL);
-	if (IS_ERR(keyring))
-		return PTR_ERR(keyring);
-
+	keyring = kzalloc(sizeof(*keyring), GFP_KERNEL);
+	if (!keyring)
+		return -ENOMEM;
+	spin_lock_init(&keyring->lock);
 	/*
 	 * Pairs with the smp_load_acquire() in fscrypt_find_master_key().
 	 * I.e., here we publish ->s_master_keys with a RELEASE barrier so that
@@ -222,21 +204,75 @@ static int allocate_filesystem_keyring(struct super_block *sb)
 	return 0;
 }
 
-void fscrypt_sb_free(struct super_block *sb)
+/*
+ * This is called at unmount time to release all encryption keys that have been
+ * added to the filesystem, along with the keyring that contains them.
+ *
+ * Note that besides clearing and freeing memory, this might need to evict keys
+ * from the keyslots of an inline crypto engine.  Therefore, this must be called
+ * while the filesystem's underlying block device(s) are still available.
+ */
+void fscrypt_sb_delete(struct super_block *sb)
 {
-	key_put(sb->s_master_keys);
+	struct fscrypt_keyring *keyring = sb->s_master_keys;
+	size_t i;
+
+	if (!keyring)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(keyring->key_hashtable); i++) {
+		struct hlist_head *bucket = &keyring->key_hashtable[i];
+		struct fscrypt_master_key *mk;
+		struct hlist_node *tmp;
+
+		hlist_for_each_entry_safe(mk, tmp, bucket, mk_node) {
+			/*
+			 * Since all inodes were already evicted, every key
+			 * remaining in the keyring should have an empty inode
+			 * list, and should only still be in the keyring due to
+			 * the single active ref associated with ->mk_secret.
+			 * There should be no structural refs beyond the one
+			 * associated with the active ref.
+			 */
+			WARN_ON(refcount_read(&mk->mk_active_refs) != 1);
+			WARN_ON(refcount_read(&mk->mk_struct_refs) != 1);
+			WARN_ON(!is_master_key_secret_present(&mk->mk_secret));
+			wipe_master_key_secret(&mk->mk_secret);
+			fscrypt_put_master_key_activeref(mk);
+		}
+	}
+	kfree_sensitive(keyring);
 	sb->s_master_keys = NULL;
 }
 
+static struct hlist_head *
+fscrypt_mk_hash_bucket(struct fscrypt_keyring *keyring,
+		       const struct fscrypt_key_specifier *mk_spec)
+{
+	/*
+	 * Since key specifiers should be "random" values, it is sufficient to
+	 * use a trivial hash function that just takes the first several bits of
+	 * the key specifier.
+	 */
+	unsigned long i = get_unaligned((unsigned long *)&mk_spec->u);
+
+	return &keyring->key_hashtable[i % ARRAY_SIZE(keyring->key_hashtable)];
+}
+
 /*
- * Find the specified master key in ->s_master_keys.
- * Returns ERR_PTR(-ENOKEY) if not found.
+ * Find the specified master key struct in ->s_master_keys and take a structural
+ * ref to it.  The structural ref guarantees that the key struct continues to
+ * exist, but it does *not* guarantee that ->s_master_keys continues to contain
+ * the key struct.  The structural ref needs to be dropped by
+ * fscrypt_put_master_key().  Returns NULL if the key struct is not found.
  */
-struct key *fscrypt_find_master_key(struct super_block *sb,
-				    const struct fscrypt_key_specifier *mk_spec)
+struct fscrypt_master_key *
+fscrypt_find_master_key(struct super_block *sb,
+			const struct fscrypt_key_specifier *mk_spec)
 {
-	struct key *keyring;
-	char description[FSCRYPT_MK_DESCRIPTION_SIZE];
+	struct fscrypt_keyring *keyring;
+	struct hlist_head *bucket;
+	struct fscrypt_master_key *mk;
 
 	/*
 	 * Pairs with the smp_store_release() in allocate_filesystem_keyring().
@@ -246,10 +282,38 @@ struct key *fscrypt_find_master_key(struct super_block *sb,
 	 */
 	keyring = smp_load_acquire(&sb->s_master_keys);
 	if (keyring == NULL)
-		return ERR_PTR(-ENOKEY); /* No keyring yet, so no keys yet. */
-
-	format_mk_description(description, mk_spec);
-	return search_fscrypt_keyring(keyring, &key_type_fscrypt, description);
+		return NULL; /* No keyring yet, so no keys yet. */
+
+	bucket = fscrypt_mk_hash_bucket(keyring, mk_spec);
+	rcu_read_lock();
+	switch (mk_spec->type) {
+	case FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR:
+		hlist_for_each_entry_rcu(mk, bucket, mk_node) {
+			if (mk->mk_spec.type ==
+				FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR &&
+			    memcmp(mk->mk_spec.u.descriptor,
+				   mk_spec->u.descriptor,
+				   FSCRYPT_KEY_DESCRIPTOR_SIZE) == 0 &&
+			    refcount_inc_not_zero(&mk->mk_struct_refs))
+				goto out;
+		}
+		break;
+	case FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER:
+		hlist_for_each_entry_rcu(mk, bucket, mk_node) {
+			if (mk->mk_spec.type ==
+				FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER &&
+			    memcmp(mk->mk_spec.u.identifier,
+				   mk_spec->u.identifier,
+				   FSCRYPT_KEY_IDENTIFIER_SIZE) == 0 &&
+			    refcount_inc_not_zero(&mk->mk_struct_refs))
+				goto out;
+		}
+		break;
+	}
+	mk = NULL;
+out:
+	rcu_read_unlock();
+	return mk;
 }
 
 static int allocate_master_key_users_keyring(struct fscrypt_master_key *mk)
@@ -277,17 +341,30 @@ static int allocate_master_key_users_keyring(struct fscrypt_master_key *mk)
 static struct key *find_master_key_user(struct fscrypt_master_key *mk)
 {
 	char description[FSCRYPT_MK_USER_DESCRIPTION_SIZE];
+	key_ref_t keyref;
 
 	format_mk_user_description(description, mk->mk_spec.u.identifier);
-	return search_fscrypt_keyring(mk->mk_users, &key_type_fscrypt_user,
-				      description);
+
+	/*
+	 * We need to mark the keyring reference as "possessed" so that we
+	 * acquire permission to search it, via the KEY_POS_SEARCH permission.
+	 */
+	keyref = keyring_search(make_key_ref(mk->mk_users, true /*possessed*/),
+				&key_type_fscrypt_user, description, false);
+	if (IS_ERR(keyref)) {
+		if (PTR_ERR(keyref) == -EAGAIN || /* not found */
+		    PTR_ERR(keyref) == -EKEYREVOKED) /* recently invalidated */
+			keyref = ERR_PTR(-ENOKEY);
+		return ERR_CAST(keyref);
+	}
+	return key_ref_to_ptr(keyref);
 }
 
 /*
  * Give the current user a "key" in ->mk_users.  This charges the user's quota
  * and marks the master key as added by the current user, so that it cannot be
- * removed by another user with the key.  Either the master key's key->sem must
- * be held for write, or the master key must be still undergoing initialization.
+ * removed by another user with the key.  Either ->mk_sem must be held for
+ * write, or the master key must be still undergoing initialization.
  */
 static int add_master_key_user(struct fscrypt_master_key *mk)
 {
@@ -309,7 +386,7 @@ static int add_master_key_user(struct fscrypt_master_key *mk)
 
 /*
  * Remove the current user's "key" from ->mk_users.
- * The master key's key->sem must be held for write.
+ * ->mk_sem must be held for write.
  *
  * Returns 0 if removed, -ENOKEY if not found, or another -errno code.
  */
@@ -327,63 +404,49 @@ static int remove_master_key_user(struct fscrypt_master_key *mk)
 }
 
 /*
- * Allocate a new fscrypt_master_key which contains the given secret, set it as
- * the payload of a new 'struct key' of type fscrypt, and link the 'struct key'
- * into the given keyring.  Synchronized by fscrypt_add_key_mutex.
+ * Allocate a new fscrypt_master_key, transfer the given secret over to it, and
+ * insert it into sb->s_master_keys.
  */
-static int add_new_master_key(struct fscrypt_master_key_secret *secret,
-			      const struct fscrypt_key_specifier *mk_spec,
-			      struct key *keyring)
+static int add_new_master_key(struct super_block *sb,
+			      struct fscrypt_master_key_secret *secret,
+			      const struct fscrypt_key_specifier *mk_spec)
 {
+	struct fscrypt_keyring *keyring = sb->s_master_keys;
 	struct fscrypt_master_key *mk;
-	char description[FSCRYPT_MK_DESCRIPTION_SIZE];
-	struct key *key;
 	int err;
 
 	mk = kzalloc(sizeof(*mk), GFP_KERNEL);
 	if (!mk)
 		return -ENOMEM;
 
+	mk->mk_sb = sb;
+	init_rwsem(&mk->mk_sem);
+	refcount_set(&mk->mk_struct_refs, 1);
 	mk->mk_spec = *mk_spec;
 
-	move_master_key_secret(&mk->mk_secret, secret);
-
-	refcount_set(&mk->mk_refcount, 1); /* secret is present */
 	INIT_LIST_HEAD(&mk->mk_decrypted_inodes);
 	spin_lock_init(&mk->mk_decrypted_inodes_lock);
 
 	if (mk_spec->type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) {
 		err = allocate_master_key_users_keyring(mk);
 		if (err)
-			goto out_free_mk;
+			goto out_put;
 		err = add_master_key_user(mk);
 		if (err)
-			goto out_free_mk;
+			goto out_put;
 	}
 
-	/*
-	 * Note that we don't charge this key to anyone's quota, since when
-	 * ->mk_users is in use those keys are charged instead, and otherwise
-	 * (when ->mk_users isn't in use) only root can add these keys.
-	 */
-	format_mk_description(description, mk_spec);
-	key = key_alloc(&key_type_fscrypt, description,
-			GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, current_cred(),
-			KEY_POS_SEARCH | KEY_USR_SEARCH | KEY_USR_VIEW,
-			KEY_ALLOC_NOT_IN_QUOTA, NULL);
-	if (IS_ERR(key)) {
-		err = PTR_ERR(key);
-		goto out_free_mk;
-	}
-	err = key_instantiate_and_link(key, mk, sizeof(*mk), keyring, NULL);
-	key_put(key);
-	if (err)
-		goto out_free_mk;
+	move_master_key_secret(&mk->mk_secret, secret);
+	refcount_set(&mk->mk_active_refs, 1); /* ->mk_secret is present */
 
+	spin_lock(&keyring->lock);
+	hlist_add_head_rcu(&mk->mk_node,
+			   fscrypt_mk_hash_bucket(keyring, mk_spec));
+	spin_unlock(&keyring->lock);
 	return 0;
 
-out_free_mk:
-	free_master_key(mk);
+out_put:
+	fscrypt_put_master_key(mk);
 	return err;
 }
 
@@ -392,42 +455,34 @@ out_free_mk:
 static int add_existing_master_key(struct fscrypt_master_key *mk,
 				   struct fscrypt_master_key_secret *secret)
 {
-	struct key *mk_user;
-	bool rekey;
 	int err;
 
 	/*
 	 * If the current user is already in ->mk_users, then there's nothing to
-	 * do.  (Not applicable for v1 policy keys, which have NULL ->mk_users.)
+	 * do.  Otherwise, we need to add the user to ->mk_users.  (Neither is
+	 * applicable for v1 policy keys, which have NULL ->mk_users.)
 	 */
 	if (mk->mk_users) {
-		mk_user = find_master_key_user(mk);
+		struct key *mk_user = find_master_key_user(mk);
+
 		if (mk_user != ERR_PTR(-ENOKEY)) {
 			if (IS_ERR(mk_user))
 				return PTR_ERR(mk_user);
 			key_put(mk_user);
 			return 0;
 		}
-	}
-
-	/* If we'll be re-adding ->mk_secret, try to take the reference. */
-	rekey = !is_master_key_secret_present(&mk->mk_secret);
-	if (rekey && !refcount_inc_not_zero(&mk->mk_refcount))
-		return KEY_DEAD;
-
-	/* Add the current user to ->mk_users, if applicable. */
-	if (mk->mk_users) {
 		err = add_master_key_user(mk);
-		if (err) {
-			if (rekey && refcount_dec_and_test(&mk->mk_refcount))
-				return KEY_DEAD;
+		if (err)
 			return err;
-		}
 	}
 
 	/* Re-add the secret if needed. */
-	if (rekey)
+	if (!is_master_key_secret_present(&mk->mk_secret)) {
+		if (!refcount_inc_not_zero(&mk->mk_active_refs))
+			return KEY_DEAD;
 		move_master_key_secret(&mk->mk_secret, secret);
+	}
+
 	return 0;
 }
 
@@ -436,38 +491,36 @@ static int do_add_master_key(struct super_block *sb,
 			     const struct fscrypt_key_specifier *mk_spec)
 {
 	static DEFINE_MUTEX(fscrypt_add_key_mutex);
-	struct key *key;
+	struct fscrypt_master_key *mk;
 	int err;
 
 	mutex_lock(&fscrypt_add_key_mutex); /* serialize find + link */
-retry:
-	key = fscrypt_find_master_key(sb, mk_spec);
-	if (IS_ERR(key)) {
-		err = PTR_ERR(key);
-		if (err != -ENOKEY)
-			goto out_unlock;
+
+	mk = fscrypt_find_master_key(sb, mk_spec);
+	if (!mk) {
 		/* Didn't find the key in ->s_master_keys.  Add it. */
 		err = allocate_filesystem_keyring(sb);
-		if (err)
-			goto out_unlock;
-		err = add_new_master_key(secret, mk_spec, sb->s_master_keys);
+		if (!err)
+			err = add_new_master_key(sb, secret, mk_spec);
 	} else {
 		/*
 		 * Found the key in ->s_master_keys.  Re-add the secret if
 		 * needed, and add the user to ->mk_users if needed.
 		 */
-		down_write(&key->sem);
-		err = add_existing_master_key(key->payload.data[0], secret);
-		up_write(&key->sem);
+		down_write(&mk->mk_sem);
+		err = add_existing_master_key(mk, secret);
+		up_write(&mk->mk_sem);
 		if (err == KEY_DEAD) {
-			/* Key being removed or needs to be removed */
-			key_invalidate(key);
-			key_put(key);
-			goto retry;
+			/*
+			 * We found a key struct, but it's already been fully
+			 * removed.  Ignore the old struct and add a new one.
+			 * fscrypt_add_key_mutex means we don't need to worry
+			 * about concurrent adds.
+			 */
+			err = add_new_master_key(sb, secret, mk_spec);
 		}
-		key_put(key);
+		fscrypt_put_master_key(mk);
 	}
-out_unlock:
 	mutex_unlock(&fscrypt_add_key_mutex);
 	return err;
 }
@@ -771,19 +824,19 @@ int fscrypt_verify_key_added(struct super_block *sb,
 			     const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE])
 {
 	struct fscrypt_key_specifier mk_spec;
-	struct key *key, *mk_user;
 	struct fscrypt_master_key *mk;
+	struct key *mk_user;
 	int err;
 
 	mk_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER;
 	memcpy(mk_spec.u.identifier, identifier, FSCRYPT_KEY_IDENTIFIER_SIZE);
 
-	key = fscrypt_find_master_key(sb, &mk_spec);
-	if (IS_ERR(key)) {
-		err = PTR_ERR(key);
+	mk = fscrypt_find_master_key(sb, &mk_spec);
+	if (!mk) {
+		err = -ENOKEY;
 		goto out;
 	}
-	mk = key->payload.data[0];
+	down_read(&mk->mk_sem);
 	mk_user = find_master_key_user(mk);
 	if (IS_ERR(mk_user)) {
 		err = PTR_ERR(mk_user);
@@ -791,7 +844,8 @@ int fscrypt_verify_key_added(struct super_block *sb,
 		key_put(mk_user);
 		err = 0;
 	}
-	key_put(key);
+	up_read(&mk->mk_sem);
+	fscrypt_put_master_key(mk);
 out:
 	if (err == -ENOKEY && capable(CAP_FOWNER))
 		err = 0;
@@ -953,11 +1007,10 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users)
 	struct super_block *sb = file_inode(filp)->i_sb;
 	struct fscrypt_remove_key_arg __user *uarg = _uarg;
 	struct fscrypt_remove_key_arg arg;
-	struct key *key;
 	struct fscrypt_master_key *mk;
 	u32 status_flags = 0;
 	int err;
-	bool dead;
+	bool inodes_remain;
 
 	if (copy_from_user(&arg, uarg, sizeof(arg)))
 		return -EFAULT;
@@ -977,12 +1030,10 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users)
 		return -EACCES;
 
 	/* Find the key being removed. */
-	key = fscrypt_find_master_key(sb, &arg.key_spec);
-	if (IS_ERR(key))
-		return PTR_ERR(key);
-	mk = key->payload.data[0];
-
-	down_write(&key->sem);
+	mk = fscrypt_find_master_key(sb, &arg.key_spec);
+	if (!mk)
+		return -ENOKEY;
+	down_write(&mk->mk_sem);
 
 	/* If relevant, remove current user's (or all users) claim to the key */
 	if (mk->mk_users && mk->mk_users->keys.nr_leaves_on_tree != 0) {
@@ -991,7 +1042,7 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users)
 		else
 			err = remove_master_key_user(mk);
 		if (err) {
-			up_write(&key->sem);
+			up_write(&mk->mk_sem);
 			goto out_put_key;
 		}
 		if (mk->mk_users->keys.nr_leaves_on_tree != 0) {
@@ -1003,26 +1054,22 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users)
 			status_flags |=
 				FSCRYPT_KEY_REMOVAL_STATUS_FLAG_OTHER_USERS;
 			err = 0;
-			up_write(&key->sem);
+			up_write(&mk->mk_sem);
 			goto out_put_key;
 		}
 	}
 
 	/* No user claims remaining.  Go ahead and wipe the secret. */
-	dead = false;
+	err = -ENOKEY;
 	if (is_master_key_secret_present(&mk->mk_secret)) {
 		wipe_master_key_secret(&mk->mk_secret);
-		dead = refcount_dec_and_test(&mk->mk_refcount);
-	}
-	up_write(&key->sem);
-	if (dead) {
-		/*
-		 * No inodes reference the key, and we wiped the secret, so the
-		 * key object is free to be removed from the keyring.
-		 */
-		key_invalidate(key);
+		fscrypt_put_master_key_activeref(mk);
 		err = 0;
-	} else {
+	}
+	inodes_remain = refcount_read(&mk->mk_active_refs) > 0;
+	up_write(&mk->mk_sem);
+
+	if (inodes_remain) {
 		/* Some inodes still reference this key; try to evict them. */
 		err = try_to_lock_encrypted_files(sb, mk);
 		if (err == -EBUSY) {
@@ -1038,7 +1085,7 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users)
 	 * has been fully removed including all files locked.
 	 */
 out_put_key:
-	key_put(key);
+	fscrypt_put_master_key(mk);
 	if (err == 0)
 		err = put_user(status_flags, &uarg->removal_status_flags);
 	return err;
@@ -1085,7 +1132,6 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg)
 {
 	struct super_block *sb = file_inode(filp)->i_sb;
 	struct fscrypt_get_key_status_arg arg;
-	struct key *key;
 	struct fscrypt_master_key *mk;
 	int err;
 
@@ -1102,19 +1148,18 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg)
 	arg.user_count = 0;
 	memset(arg.__out_reserved, 0, sizeof(arg.__out_reserved));
 
-	key = fscrypt_find_master_key(sb, &arg.key_spec);
-	if (IS_ERR(key)) {
-		if (key != ERR_PTR(-ENOKEY))
-			return PTR_ERR(key);
+	mk = fscrypt_find_master_key(sb, &arg.key_spec);
+	if (!mk) {
 		arg.status = FSCRYPT_KEY_STATUS_ABSENT;
 		err = 0;
 		goto out;
 	}
-	mk = key->payload.data[0];
-	down_read(&key->sem);
+	down_read(&mk->mk_sem);
 
 	if (!is_master_key_secret_present(&mk->mk_secret)) {
-		arg.status = FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED;
+		arg.status = refcount_read(&mk->mk_active_refs) > 0 ?
+			FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED :
+			FSCRYPT_KEY_STATUS_ABSENT /* raced with full removal */;
 		err = 0;
 		goto out_release_key;
 	}
@@ -1136,8 +1181,8 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg)
 	}
 	err = 0;
 out_release_key:
-	up_read(&key->sem);
-	key_put(key);
+	up_read(&mk->mk_sem);
+	fscrypt_put_master_key(mk);
 out:
 	if (!err && copy_to_user(uarg, &arg, sizeof(arg)))
 		err = -EFAULT;
@@ -1149,13 +1194,9 @@ int __init fscrypt_init_keyring(void)
 {
 	int err;
 
-	err = register_key_type(&key_type_fscrypt);
-	if (err)
-		return err;
-
 	err = register_key_type(&key_type_fscrypt_user);
 	if (err)
-		goto err_unregister_fscrypt;
+		return err;
 
 	err = register_key_type(&key_type_fscrypt_provisioning);
 	if (err)
@@ -1165,7 +1206,5 @@ int __init fscrypt_init_keyring(void)
 
 err_unregister_fscrypt_user:
 	unregister_key_type(&key_type_fscrypt_user);
-err_unregister_fscrypt:
-	unregister_key_type(&key_type_fscrypt);
 	return err;
 }
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index fbc71abdabe3..f7407071a952 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -9,7 +9,6 @@
  */
 
 #include <crypto/skcipher.h>
-#include <linux/key.h>
 #include <linux/random.h>
 
 #include "fscrypt_private.h"
@@ -155,10 +154,12 @@ int fscrypt_prepare_key(struct fscrypt_prepared_key *prep_key,
 }
 
 /* Destroy a crypto transform object and/or blk-crypto key. */
-void fscrypt_destroy_prepared_key(struct fscrypt_prepared_key *prep_key)
+void fscrypt_destroy_prepared_key(struct super_block *sb,
+				  struct fscrypt_prepared_key *prep_key)
 {
 	crypto_free_skcipher(prep_key->tfm);
-	fscrypt_destroy_inline_crypt_key(prep_key);
+	fscrypt_destroy_inline_crypt_key(sb, prep_key);
+	memzero_explicit(prep_key, sizeof(*prep_key));
 }
 
 /* Given a per-file encryption key, set up the file's crypto transform object */
@@ -412,20 +413,18 @@ static bool fscrypt_valid_master_key_size(const struct fscrypt_master_key *mk,
 /*
  * Find the master key, then set up the inode's actual encryption key.
  *
- * If the master key is found in the filesystem-level keyring, then the
- * corresponding 'struct key' is returned in *master_key_ret with its semaphore
- * read-locked.  This is needed to ensure that only one task links the
- * fscrypt_info into ->mk_decrypted_inodes (as multiple tasks may race to create
- * an fscrypt_info for the same inode), and to synchronize the master key being
- * removed with a new inode starting to use it.
+ * If the master key is found in the filesystem-level keyring, then it is
+ * returned in *mk_ret with its semaphore read-locked.  This is needed to ensure
+ * that only one task links the fscrypt_info into ->mk_decrypted_inodes (as
+ * multiple tasks may race to create an fscrypt_info for the same inode), and to
+ * synchronize the master key being removed with a new inode starting to use it.
  */
 static int setup_file_encryption_key(struct fscrypt_info *ci,
 				     bool need_dirhash_key,
-				     struct key **master_key_ret)
+				     struct fscrypt_master_key **mk_ret)
 {
-	struct key *key;
-	struct fscrypt_master_key *mk = NULL;
 	struct fscrypt_key_specifier mk_spec;
+	struct fscrypt_master_key *mk;
 	int err;
 
 	err = fscrypt_select_encryption_impl(ci);
@@ -436,11 +435,10 @@ static int setup_file_encryption_key(struct fscrypt_info *ci,
 	if (err)
 		return err;
 
-	key = fscrypt_find_master_key(ci->ci_inode->i_sb, &mk_spec);
-	if (IS_ERR(key)) {
-		if (key != ERR_PTR(-ENOKEY) ||
-		    ci->ci_policy.version != FSCRYPT_POLICY_V1)
-			return PTR_ERR(key);
+	mk = fscrypt_find_master_key(ci->ci_inode->i_sb, &mk_spec);
+	if (!mk) {
+		if (ci->ci_policy.version != FSCRYPT_POLICY_V1)
+			return -ENOKEY;
 
 		/*
 		 * As a legacy fallback for v1 policies, search for the key in
@@ -450,9 +448,7 @@ static int setup_file_encryption_key(struct fscrypt_info *ci,
 		 */
 		return fscrypt_setup_v1_file_key_via_subscribed_keyrings(ci);
 	}
-
-	mk = key->payload.data[0];
-	down_read(&key->sem);
+	down_read(&mk->mk_sem);
 
 	/* Has the secret been removed (via FS_IOC_REMOVE_ENCRYPTION_KEY)? */
 	if (!is_master_key_secret_present(&mk->mk_secret)) {
@@ -480,18 +476,18 @@ static int setup_file_encryption_key(struct fscrypt_info *ci,
 	if (err)
 		goto out_release_key;
 
-	*master_key_ret = key;
+	*mk_ret = mk;
 	return 0;
 
 out_release_key:
-	up_read(&key->sem);
-	key_put(key);
+	up_read(&mk->mk_sem);
+	fscrypt_put_master_key(mk);
 	return err;
 }
 
 static void put_crypt_info(struct fscrypt_info *ci)
 {
-	struct key *key;
+	struct fscrypt_master_key *mk;
 
 	if (!ci)
 		return;
@@ -499,26 +495,21 @@ static void put_crypt_info(struct fscrypt_info *ci)
 	if (ci->ci_direct_key)
 		fscrypt_put_direct_key(ci->ci_direct_key);
 	else if (ci->ci_owns_key)
-		fscrypt_destroy_prepared_key(&ci->ci_enc_key);
-
-	key = ci->ci_master_key;
-	if (key) {
-		struct fscrypt_master_key *mk = key->payload.data[0];
+		fscrypt_destroy_prepared_key(ci->ci_inode->i_sb,
+					     &ci->ci_enc_key);
 
+	mk = ci->ci_master_key;
+	if (mk) {
 		/*
 		 * Remove this inode from the list of inodes that were unlocked
-		 * with the master key.
-		 *
-		 * In addition, if we're removing the last inode from a key that
-		 * already had its secret removed, invalidate the key so that it
-		 * gets removed from ->s_master_keys.
+		 * with the master key.  In addition, if we're removing the last
+		 * inode from a master key struct that already had its secret
+		 * removed, then complete the full removal of the struct.
 		 */
 		spin_lock(&mk->mk_decrypted_inodes_lock);
 		list_del(&ci->ci_master_key_link);
 		spin_unlock(&mk->mk_decrypted_inodes_lock);
-		if (refcount_dec_and_test(&mk->mk_refcount))
-			key_invalidate(key);
-		key_put(key);
+		fscrypt_put_master_key_activeref(mk);
 	}
 	memzero_explicit(ci, sizeof(*ci));
 	kmem_cache_free(fscrypt_info_cachep, ci);
@@ -532,7 +523,7 @@ fscrypt_setup_encryption_info(struct inode *inode,
 {
 	struct fscrypt_info *crypt_info;
 	struct fscrypt_mode *mode;
-	struct key *master_key = NULL;
+	struct fscrypt_master_key *mk = NULL;
 	int res;
 
 	res = fscrypt_initialize(inode->i_sb->s_cop->flags);
@@ -555,8 +546,7 @@ fscrypt_setup_encryption_info(struct inode *inode,
 	WARN_ON(mode->ivsize > FSCRYPT_MAX_IV_SIZE);
 	crypt_info->ci_mode = mode;
 
-	res = setup_file_encryption_key(crypt_info, need_dirhash_key,
-					&master_key);
+	res = setup_file_encryption_key(crypt_info, need_dirhash_key, &mk);
 	if (res)
 		goto out;
 
@@ -571,12 +561,9 @@ fscrypt_setup_encryption_info(struct inode *inode,
 		 * We won the race and set ->i_crypt_info to our crypt_info.
 		 * Now link it into the master key's inode list.
 		 */
-		if (master_key) {
-			struct fscrypt_master_key *mk =
-				master_key->payload.data[0];
-
-			refcount_inc(&mk->mk_refcount);
-			crypt_info->ci_master_key = key_get(master_key);
+		if (mk) {
+			crypt_info->ci_master_key = mk;
+			refcount_inc(&mk->mk_active_refs);
 			spin_lock(&mk->mk_decrypted_inodes_lock);
 			list_add(&crypt_info->ci_master_key_link,
 				 &mk->mk_decrypted_inodes);
@@ -586,9 +573,9 @@ fscrypt_setup_encryption_info(struct inode *inode,
 	}
 	res = 0;
 out:
-	if (master_key) {
-		up_read(&master_key->sem);
-		key_put(master_key);
+	if (mk) {
+		up_read(&mk->mk_sem);
+		fscrypt_put_master_key(mk);
 	}
 	put_crypt_info(crypt_info);
 	return res;
@@ -753,7 +740,6 @@ EXPORT_SYMBOL(fscrypt_free_inode);
 int fscrypt_drop_inode(struct inode *inode)
 {
 	const struct fscrypt_info *ci = fscrypt_get_info(inode);
-	const struct fscrypt_master_key *mk;
 
 	/*
 	 * If ci is NULL, then the inode doesn't have an encryption key set up
@@ -763,7 +749,6 @@ int fscrypt_drop_inode(struct inode *inode)
 	 */
 	if (!ci || !ci->ci_master_key)
 		return 0;
-	mk = ci->ci_master_key->payload.data[0];
 
 	/*
 	 * With proper, non-racy use of FS_IOC_REMOVE_ENCRYPTION_KEY, all inodes
@@ -782,6 +767,6 @@ int fscrypt_drop_inode(struct inode *inode)
 	 * then the thread removing the key will either evict the inode itself
 	 * or will correctly detect that it wasn't evicted due to the race.
 	 */
-	return !is_master_key_secret_present(&mk->mk_secret);
+	return !is_master_key_secret_present(&ci->ci_master_key->mk_secret);
 }
 EXPORT_SYMBOL_GPL(fscrypt_drop_inode);
diff --git a/fs/crypto/keysetup_v1.c b/fs/crypto/keysetup_v1.c
index 2762c5350432..75dabd9b27f9 100644
--- a/fs/crypto/keysetup_v1.c
+++ b/fs/crypto/keysetup_v1.c
@@ -143,6 +143,7 @@ invalid:
 
 /* Master key referenced by DIRECT_KEY policy */
 struct fscrypt_direct_key {
+	struct super_block		*dk_sb;
 	struct hlist_node		dk_node;
 	refcount_t			dk_refcount;
 	const struct fscrypt_mode	*dk_mode;
@@ -154,7 +155,7 @@ struct fscrypt_direct_key {
 static void free_direct_key(struct fscrypt_direct_key *dk)
 {
 	if (dk) {
-		fscrypt_destroy_prepared_key(&dk->dk_key);
+		fscrypt_destroy_prepared_key(dk->dk_sb, &dk->dk_key);
 		kfree_sensitive(dk);
 	}
 }
@@ -231,6 +232,7 @@ fscrypt_get_direct_key(const struct fscrypt_info *ci, const u8 *raw_key)
 	dk = kzalloc(sizeof(*dk), GFP_KERNEL);
 	if (!dk)
 		return ERR_PTR(-ENOMEM);
+	dk->dk_sb = ci->ci_inode->i_sb;
 	refcount_set(&dk->dk_refcount, 1);
 	dk->dk_mode = ci->ci_mode;
 	err = fscrypt_prepare_key(&dk->dk_key, raw_key, ci);
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 80b8ca0f340b..46757c3052ef 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -744,12 +744,8 @@ int fscrypt_set_context(struct inode *inode, void *fs_data)
 	 * delayed key setup that requires the inode number.
 	 */
 	if (ci->ci_policy.version == FSCRYPT_POLICY_V2 &&
-	    (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) {
-		const struct fscrypt_master_key *mk =
-			ci->ci_master_key->payload.data[0];
-
-		fscrypt_hash_inode_number(ci, mk);
-	}
+	    (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32))
+		fscrypt_hash_inode_number(ci, ci->ci_master_key);
 
 	return inode->i_sb->s_cop->set_context(inode, &ctx, ctxsize, fs_data);
 }
@@ -833,19 +829,6 @@ bool fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1,
 }
 EXPORT_SYMBOL_GPL(fscrypt_dummy_policies_equal);
 
-/* Deprecated, do not use */
-int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg,
-				      struct fscrypt_dummy_policy *dummy_policy)
-{
-	struct fs_parameter param = {
-		.type = fs_value_is_string,
-		.string = arg ? (char *)arg : "",
-	};
-	return fscrypt_parse_test_dummy_encryption(&param, dummy_policy) ?:
-		fscrypt_add_test_dummy_key(sb, dummy_policy);
-}
-EXPORT_SYMBOL_GPL(fscrypt_set_test_dummy_encryption);
-
 /**
  * fscrypt_show_test_dummy_encryption() - show '-o test_dummy_encryption'
  * @seq: the seq_file to print the option to
diff --git a/fs/dax.c b/fs/dax.c
index c440dcef4b1b..1c6867810cbd 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1445,6 +1445,9 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 	loff_t done = 0;
 	int ret;
 
+	if (!iomi.len)
+		return 0;
+
 	if (iov_iter_rw(iter) == WRITE) {
 		lockdep_assert_held_write(&iomi.inode->i_rwsem);
 		iomi.flags |= IOMAP_WRITE;
diff --git a/fs/dcache.c b/fs/dcache.c
index c5dc32a59c76..bb0c4d0038db 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2270,6 +2270,48 @@ bool d_same_name(const struct dentry *dentry, const struct dentry *parent,
 }
 EXPORT_SYMBOL_GPL(d_same_name);
 
+/*
+ * This is __d_lookup_rcu() when the parent dentry has
+ * DCACHE_OP_COMPARE, which makes things much nastier.
+ */
+static noinline struct dentry *__d_lookup_rcu_op_compare(
+	const struct dentry *parent,
+	const struct qstr *name,
+	unsigned *seqp)
+{
+	u64 hashlen = name->hash_len;
+	struct hlist_bl_head *b = d_hash(hashlen_hash(hashlen));
+	struct hlist_bl_node *node;
+	struct dentry *dentry;
+
+	hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
+		int tlen;
+		const char *tname;
+		unsigned seq;
+
+seqretry:
+		seq = raw_seqcount_begin(&dentry->d_seq);
+		if (dentry->d_parent != parent)
+			continue;
+		if (d_unhashed(dentry))
+			continue;
+		if (dentry->d_name.hash != hashlen_hash(hashlen))
+			continue;
+		tlen = dentry->d_name.len;
+		tname = dentry->d_name.name;
+		/* we want a consistent (name,len) pair */
+		if (read_seqcount_retry(&dentry->d_seq, seq)) {
+			cpu_relax();
+			goto seqretry;
+		}
+		if (parent->d_op->d_compare(dentry, tlen, tname, name) != 0)
+			continue;
+		*seqp = seq;
+		return dentry;
+	}
+	return NULL;
+}
+
 /**
  * __d_lookup_rcu - search for a dentry (racy, store-free)
  * @parent: parent dentry
@@ -2316,6 +2358,9 @@ struct dentry *__d_lookup_rcu(const struct dentry *parent,
 	 * Keep the two functions in sync.
 	 */
 
+	if (unlikely(parent->d_flags & DCACHE_OP_COMPARE))
+		return __d_lookup_rcu_op_compare(parent, name, seqp);
+
 	/*
 	 * The hash list is protected using RCU.
 	 *
@@ -2332,7 +2377,6 @@ struct dentry *__d_lookup_rcu(const struct dentry *parent,
 	hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
 		unsigned seq;
 
-seqretry:
 		/*
 		 * The dentry sequence count protects us from concurrent
 		 * renames, and thus protects parent and name fields.
@@ -2355,28 +2399,10 @@ seqretry:
 			continue;
 		if (d_unhashed(dentry))
 			continue;
-
-		if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) {
-			int tlen;
-			const char *tname;
-			if (dentry->d_name.hash != hashlen_hash(hashlen))
-				continue;
-			tlen = dentry->d_name.len;
-			tname = dentry->d_name.name;
-			/* we want a consistent (name,len) pair */
-			if (read_seqcount_retry(&dentry->d_seq, seq)) {
-				cpu_relax();
-				goto seqretry;
-			}
-			if (parent->d_op->d_compare(dentry,
-						    tlen, tname, name) != 0)
-				continue;
-		} else {
-			if (dentry->d_name.hash_len != hashlen)
-				continue;
-			if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0)
-				continue;
-		}
+		if (dentry->d_name.hash_len != hashlen)
+			continue;
+		if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0)
+			continue;
 		*seqp = seq;
 		return dentry;
 	}
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 3dcf0b8b4e93..232cfdf095ae 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -745,6 +745,28 @@ void debugfs_remove(struct dentry *dentry)
 EXPORT_SYMBOL_GPL(debugfs_remove);
 
 /**
+ * debugfs_lookup_and_remove - lookup a directory or file and recursively remove it
+ * @name: a pointer to a string containing the name of the item to look up.
+ * @parent: a pointer to the parent dentry of the item.
+ *
+ * This is the equlivant of doing something like
+ * debugfs_remove(debugfs_lookup(..)) but with the proper reference counting
+ * handled for the directory being looked up.
+ */
+void debugfs_lookup_and_remove(const char *name, struct dentry *parent)
+{
+	struct dentry *dentry;
+
+	dentry = debugfs_lookup(name, parent);
+	if (!dentry)
+		return;
+
+	debugfs_remove(dentry);
+	dput(dentry);
+}
+EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove);
+
+/**
  * debugfs_rename - rename a file/directory in the debugfs filesystem
  * @old_dir: a pointer to the parent dentry for the renamed object. This
  *          should be a directory dentry.
diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c
index 19ef136f9e4f..d60a8d8f109d 100644
--- a/fs/dlm/ast.c
+++ b/fs/dlm/ast.c
@@ -200,13 +200,13 @@ void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status,
 	if (!prev_seq) {
 		kref_get(&lkb->lkb_ref);
 
+		mutex_lock(&ls->ls_cb_mutex);
 		if (test_bit(LSFL_CB_DELAY, &ls->ls_flags)) {
-			mutex_lock(&ls->ls_cb_mutex);
 			list_add(&lkb->lkb_cb_list, &ls->ls_cb_delay);
-			mutex_unlock(&ls->ls_cb_mutex);
 		} else {
 			queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work);
 		}
+		mutex_unlock(&ls->ls_cb_mutex);
 	}
  out:
 	mutex_unlock(&lkb->lkb_cb_mutex);
@@ -288,10 +288,13 @@ void dlm_callback_stop(struct dlm_ls *ls)
 
 void dlm_callback_suspend(struct dlm_ls *ls)
 {
-	set_bit(LSFL_CB_DELAY, &ls->ls_flags);
+	if (ls->ls_callback_wq) {
+		mutex_lock(&ls->ls_cb_mutex);
+		set_bit(LSFL_CB_DELAY, &ls->ls_flags);
+		mutex_unlock(&ls->ls_cb_mutex);
 
-	if (ls->ls_callback_wq)
 		flush_workqueue(ls->ls_callback_wq);
+	}
 }
 
 #define MAX_CB_QUEUE 25
@@ -302,11 +305,11 @@ void dlm_callback_resume(struct dlm_ls *ls)
 	int count = 0, sum = 0;
 	bool empty;
 
-	clear_bit(LSFL_CB_DELAY, &ls->ls_flags);
-
 	if (!ls->ls_callback_wq)
 		return;
 
+	clear_bit(LSFL_CB_DELAY, &ls->ls_flags);
+
 more:
 	mutex_lock(&ls->ls_cb_mutex);
 	list_for_each_entry_safe(lkb, safe, &ls->ls_cb_delay, lkb_cb_list) {
diff --git a/fs/dlm/ast.h b/fs/dlm/ast.h
index 181ad7d20c4d..e5e05fcc5813 100644
--- a/fs/dlm/ast.h
+++ b/fs/dlm/ast.h
@@ -11,7 +11,6 @@
 #ifndef __ASTD_DOT_H__
 #define __ASTD_DOT_H__
 
-void dlm_del_ast(struct dlm_lkb *lkb);
 int dlm_add_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
                          int status, uint32_t sbflags, uint64_t seq);
 int dlm_rem_lkb_callback(struct dlm_ls *ls, struct dlm_lkb *lkb,
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index 8aca8085d24e..e34c3d2639a5 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -661,7 +661,7 @@ struct dlm_ls {
 	spinlock_t		ls_recover_idr_lock;
 	wait_queue_head_t	ls_wait_general;
 	wait_queue_head_t	ls_recover_lock_wait;
-	struct mutex		ls_clear_proc_locks;
+	spinlock_t		ls_clear_proc_locks;
 
 	struct list_head	ls_root_list;	/* root resources */
 	struct rw_semaphore	ls_root_sem;	/* protect root_list */
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index dac7eb75dba9..94a72ede5764 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -401,7 +401,7 @@ static int pre_rsb_struct(struct dlm_ls *ls)
    unlock any spinlocks, go back and call pre_rsb_struct again.
    Otherwise, take an rsb off the list and return it. */
 
-static int get_rsb_struct(struct dlm_ls *ls, char *name, int len,
+static int get_rsb_struct(struct dlm_ls *ls, const void *name, int len,
 			  struct dlm_rsb **r_ret)
 {
 	struct dlm_rsb *r;
@@ -412,7 +412,8 @@ static int get_rsb_struct(struct dlm_ls *ls, char *name, int len,
 		count = ls->ls_new_rsb_count;
 		spin_unlock(&ls->ls_new_rsb_spin);
 		log_debug(ls, "find_rsb retry %d %d %s",
-			  count, dlm_config.ci_new_rsb_count, name);
+			  count, dlm_config.ci_new_rsb_count,
+			  (const char *)name);
 		return -EAGAIN;
 	}
 
@@ -448,7 +449,7 @@ static int rsb_cmp(struct dlm_rsb *r, const char *name, int nlen)
 	return memcmp(r->res_name, maxname, DLM_RESNAME_MAXLEN);
 }
 
-int dlm_search_rsb_tree(struct rb_root *tree, char *name, int len,
+int dlm_search_rsb_tree(struct rb_root *tree, const void *name, int len,
 			struct dlm_rsb **r_ret)
 {
 	struct rb_node *node = tree->rb_node;
@@ -546,7 +547,7 @@ static int rsb_insert(struct dlm_rsb *rsb, struct rb_root *tree)
  * while that rsb has a potentially stale master.)
  */
 
-static int find_rsb_dir(struct dlm_ls *ls, char *name, int len,
+static int find_rsb_dir(struct dlm_ls *ls, const void *name, int len,
 			uint32_t hash, uint32_t b,
 			int dir_nodeid, int from_nodeid,
 			unsigned int flags, struct dlm_rsb **r_ret)
@@ -724,7 +725,7 @@ static int find_rsb_dir(struct dlm_ls *ls, char *name, int len,
    dlm_recover_locks) before we've made ourself master (in
    dlm_recover_masters). */
 
-static int find_rsb_nodir(struct dlm_ls *ls, char *name, int len,
+static int find_rsb_nodir(struct dlm_ls *ls, const void *name, int len,
 			  uint32_t hash, uint32_t b,
 			  int dir_nodeid, int from_nodeid,
 			  unsigned int flags, struct dlm_rsb **r_ret)
@@ -818,8 +819,9 @@ static int find_rsb_nodir(struct dlm_ls *ls, char *name, int len,
 	return error;
 }
 
-static int find_rsb(struct dlm_ls *ls, char *name, int len, int from_nodeid,
-		    unsigned int flags, struct dlm_rsb **r_ret)
+static int find_rsb(struct dlm_ls *ls, const void *name, int len,
+		    int from_nodeid, unsigned int flags,
+		    struct dlm_rsb **r_ret)
 {
 	uint32_t hash, b;
 	int dir_nodeid;
@@ -2864,17 +2866,9 @@ static int set_unlock_args(uint32_t flags, void *astarg, struct dlm_args *args)
 static int validate_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
 			      struct dlm_args *args)
 {
-	int rv = -EINVAL;
+	int rv = -EBUSY;
 
 	if (args->flags & DLM_LKF_CONVERT) {
-		if (lkb->lkb_flags & DLM_IFL_MSTCPY)
-			goto out;
-
-		if (args->flags & DLM_LKF_QUECVT &&
-		    !__quecvt_compat_matrix[lkb->lkb_grmode+1][args->mode+1])
-			goto out;
-
-		rv = -EBUSY;
 		if (lkb->lkb_status != DLM_LKSTS_GRANTED)
 			goto out;
 
@@ -2884,6 +2878,14 @@ static int validate_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
 
 		if (is_overlap(lkb))
 			goto out;
+
+		rv = -EINVAL;
+		if (lkb->lkb_flags & DLM_IFL_MSTCPY)
+			goto out;
+
+		if (args->flags & DLM_LKF_QUECVT &&
+		    !__quecvt_compat_matrix[lkb->lkb_grmode+1][args->mode+1])
+			goto out;
 	}
 
 	lkb->lkb_exflags = args->flags;
@@ -2900,11 +2902,25 @@ static int validate_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
 #endif
 	rv = 0;
  out:
-	if (rv)
-		log_debug(ls, "validate_lock_args %d %x %x %x %d %d %s",
+	switch (rv) {
+	case 0:
+		break;
+	case -EINVAL:
+		/* annoy the user because dlm usage is wrong */
+		WARN_ON(1);
+		log_error(ls, "%s %d %x %x %x %d %d %s", __func__,
+			  rv, lkb->lkb_id, lkb->lkb_flags, args->flags,
+			  lkb->lkb_status, lkb->lkb_wait_type,
+			  lkb->lkb_resource->res_name);
+		break;
+	default:
+		log_debug(ls, "%s %d %x %x %x %d %d %s", __func__,
 			  rv, lkb->lkb_id, lkb->lkb_flags, args->flags,
 			  lkb->lkb_status, lkb->lkb_wait_type,
 			  lkb->lkb_resource->res_name);
+		break;
+	}
+
 	return rv;
 }
 
@@ -2918,23 +2934,12 @@ static int validate_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
 static int validate_unlock_args(struct dlm_lkb *lkb, struct dlm_args *args)
 {
 	struct dlm_ls *ls = lkb->lkb_resource->res_ls;
-	int rv = -EINVAL;
-
-	if (lkb->lkb_flags & DLM_IFL_MSTCPY) {
-		log_error(ls, "unlock on MSTCPY %x", lkb->lkb_id);
-		dlm_print_lkb(lkb);
-		goto out;
-	}
-
-	/* an lkb may still exist even though the lock is EOL'ed due to a
-	   cancel, unlock or failed noqueue request; an app can't use these
-	   locks; return same error as if the lkid had not been found at all */
+	int rv = -EBUSY;
 
-	if (lkb->lkb_flags & DLM_IFL_ENDOFLIFE) {
-		log_debug(ls, "unlock on ENDOFLIFE %x", lkb->lkb_id);
-		rv = -ENOENT;
+	/* normal unlock not allowed if there's any op in progress */
+	if (!(args->flags & (DLM_LKF_CANCEL | DLM_LKF_FORCEUNLOCK)) &&
+	    (lkb->lkb_wait_type || lkb->lkb_wait_count))
 		goto out;
-	}
 
 	/* an lkb may be waiting for an rsb lookup to complete where the
 	   lookup was initiated by another lock */
@@ -2949,7 +2954,24 @@ static int validate_unlock_args(struct dlm_lkb *lkb, struct dlm_args *args)
 			unhold_lkb(lkb); /* undoes create_lkb() */
 		}
 		/* caller changes -EBUSY to 0 for CANCEL and FORCEUNLOCK */
-		rv = -EBUSY;
+		goto out;
+	}
+
+	rv = -EINVAL;
+	if (lkb->lkb_flags & DLM_IFL_MSTCPY) {
+		log_error(ls, "unlock on MSTCPY %x", lkb->lkb_id);
+		dlm_print_lkb(lkb);
+		goto out;
+	}
+
+	/* an lkb may still exist even though the lock is EOL'ed due to a
+	 * cancel, unlock or failed noqueue request; an app can't use these
+	 * locks; return same error as if the lkid had not been found at all
+	 */
+
+	if (lkb->lkb_flags & DLM_IFL_ENDOFLIFE) {
+		log_debug(ls, "unlock on ENDOFLIFE %x", lkb->lkb_id);
+		rv = -ENOENT;
 		goto out;
 	}
 
@@ -3022,14 +3044,8 @@ static int validate_unlock_args(struct dlm_lkb *lkb, struct dlm_args *args)
 			goto out;
 		}
 		/* add_to_waiters() will set OVERLAP_UNLOCK */
-		goto out_ok;
 	}
 
-	/* normal unlock not allowed if there's any op in progress */
-	rv = -EBUSY;
-	if (lkb->lkb_wait_type || lkb->lkb_wait_count)
-		goto out;
-
  out_ok:
 	/* an overlapping op shouldn't blow away exflags from other op */
 	lkb->lkb_exflags |= args->flags;
@@ -3037,11 +3053,25 @@ static int validate_unlock_args(struct dlm_lkb *lkb, struct dlm_args *args)
 	lkb->lkb_astparam = args->astparam;
 	rv = 0;
  out:
-	if (rv)
-		log_debug(ls, "validate_unlock_args %d %x %x %x %x %d %s", rv,
+	switch (rv) {
+	case 0:
+		break;
+	case -EINVAL:
+		/* annoy the user because dlm usage is wrong */
+		WARN_ON(1);
+		log_error(ls, "%s %d %x %x %x %x %d %s", __func__, rv,
+			  lkb->lkb_id, lkb->lkb_flags, lkb->lkb_exflags,
+			  args->flags, lkb->lkb_wait_type,
+			  lkb->lkb_resource->res_name);
+		break;
+	default:
+		log_debug(ls, "%s %d %x %x %x %x %d %s", __func__, rv,
 			  lkb->lkb_id, lkb->lkb_flags, lkb->lkb_exflags,
 			  args->flags, lkb->lkb_wait_type,
 			  lkb->lkb_resource->res_name);
+		break;
+	}
+
 	return rv;
 }
 
@@ -3292,8 +3322,9 @@ static int _cancel_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
  * request_lock(), convert_lock(), unlock_lock(), cancel_lock()
  */
 
-static int request_lock(struct dlm_ls *ls, struct dlm_lkb *lkb, char *name,
-			int len, struct dlm_args *args)
+static int request_lock(struct dlm_ls *ls, struct dlm_lkb *lkb,
+			const void *name, int len,
+			struct dlm_args *args)
 {
 	struct dlm_rsb *r;
 	int error;
@@ -3392,7 +3423,7 @@ int dlm_lock(dlm_lockspace_t *lockspace,
 	     int mode,
 	     struct dlm_lksb *lksb,
 	     uint32_t flags,
-	     void *name,
+	     const void *name,
 	     unsigned int namelen,
 	     uint32_t parent_lkid,
 	     void (*ast) (void *astarg),
@@ -3438,7 +3469,7 @@ int dlm_lock(dlm_lockspace_t *lockspace,
 	if (error == -EINPROGRESS)
 		error = 0;
  out_put:
-	trace_dlm_lock_end(ls, lkb, name, namelen, mode, flags, error);
+	trace_dlm_lock_end(ls, lkb, name, namelen, mode, flags, error, true);
 
 	if (convert || error)
 		__put_lkb(ls, lkb);
@@ -3623,7 +3654,7 @@ static void send_args(struct dlm_rsb *r, struct dlm_lkb *lkb,
 	case cpu_to_le32(DLM_MSG_REQUEST_REPLY):
 	case cpu_to_le32(DLM_MSG_CONVERT_REPLY):
 	case cpu_to_le32(DLM_MSG_GRANT):
-		if (!lkb->lkb_lvbptr)
+		if (!lkb->lkb_lvbptr || !(lkb->lkb_exflags & DLM_LKF_VALBLK))
 			break;
 		memcpy(ms->m_extra, lkb->lkb_lvbptr, r->res_ls->ls_lvblen);
 		break;
@@ -5080,8 +5111,11 @@ void dlm_receive_buffer(union dlm_packet *p, int nodeid)
 	down_read(&ls->ls_recv_active);
 	if (hd->h_cmd == DLM_MSG)
 		dlm_receive_message(ls, &p->message, nodeid);
-	else
+	else if (hd->h_cmd == DLM_RCOM)
 		dlm_receive_rcom(ls, &p->rcom, nodeid);
+	else
+		log_error(ls, "invalid h_cmd %d from %d lockspace %x",
+			  hd->h_cmd, nodeid, le32_to_cpu(hd->u.h_lockspace));
 	up_read(&ls->ls_recv_active);
 
 	dlm_put_lockspace(ls);
@@ -5801,6 +5835,7 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
 {
 	struct dlm_lkb *lkb;
 	struct dlm_args args;
+	bool do_put = true;
 	int error;
 
 	dlm_lock_recovery(ls);
@@ -5811,13 +5846,14 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
 		goto out;
 	}
 
+	trace_dlm_lock_start(ls, lkb, name, namelen, mode, flags);
+
 	if (flags & DLM_LKF_VALBLK) {
 		ua->lksb.sb_lvbptr = kzalloc(DLM_USER_LVB_LEN, GFP_NOFS);
 		if (!ua->lksb.sb_lvbptr) {
 			kfree(ua);
-			__put_lkb(ls, lkb);
 			error = -ENOMEM;
-			goto out;
+			goto out_put;
 		}
 	}
 #ifdef CONFIG_DLM_DEPRECATED_API
@@ -5831,8 +5867,7 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
 		kfree(ua->lksb.sb_lvbptr);
 		ua->lksb.sb_lvbptr = NULL;
 		kfree(ua);
-		__put_lkb(ls, lkb);
-		goto out;
+		goto out_put;
 	}
 
 	/* After ua is attached to lkb it will be freed by dlm_free_lkb().
@@ -5851,8 +5886,7 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
 		error = 0;
 		fallthrough;
 	default:
-		__put_lkb(ls, lkb);
-		goto out;
+		goto out_put;
 	}
 
 	/* add this new lkb to the per-process list of locks */
@@ -5860,6 +5894,11 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
 	hold_lkb(lkb);
 	list_add_tail(&lkb->lkb_ownqueue, &ua->proc->locks);
 	spin_unlock(&ua->proc->locks_spin);
+	do_put = false;
+ out_put:
+	trace_dlm_lock_end(ls, lkb, name, namelen, mode, flags, error, false);
+	if (do_put)
+		__put_lkb(ls, lkb);
  out:
 	dlm_unlock_recovery(ls);
 	return error;
@@ -5885,6 +5924,8 @@ int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
 	if (error)
 		goto out;
 
+	trace_dlm_lock_start(ls, lkb, NULL, 0, mode, flags);
+
 	/* user can change the params on its lock when it converts it, or
 	   add an lvb that didn't exist before */
 
@@ -5922,6 +5963,7 @@ int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
 	if (error == -EINPROGRESS || error == -EAGAIN || error == -EDEADLK)
 		error = 0;
  out_put:
+	trace_dlm_lock_end(ls, lkb, NULL, 0, mode, flags, error, false);
 	dlm_put_lkb(lkb);
  out:
 	dlm_unlock_recovery(ls);
@@ -6014,6 +6056,8 @@ int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
 	if (error)
 		goto out;
 
+	trace_dlm_unlock_start(ls, lkb, flags);
+
 	ua = lkb->lkb_ua;
 
 	if (lvb_in && ua->lksb.sb_lvbptr)
@@ -6042,6 +6086,7 @@ int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
 		list_move(&lkb->lkb_ownqueue, &ua->proc->unlocking);
 	spin_unlock(&ua->proc->locks_spin);
  out_put:
+	trace_dlm_unlock_end(ls, lkb, flags, error);
 	dlm_put_lkb(lkb);
  out:
 	dlm_unlock_recovery(ls);
@@ -6063,6 +6108,8 @@ int dlm_user_cancel(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
 	if (error)
 		goto out;
 
+	trace_dlm_unlock_start(ls, lkb, flags);
+
 	ua = lkb->lkb_ua;
 	if (ua_tmp->castparam)
 		ua->castparam = ua_tmp->castparam;
@@ -6080,6 +6127,7 @@ int dlm_user_cancel(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
 	if (error == -EBUSY)
 		error = 0;
  out_put:
+	trace_dlm_unlock_end(ls, lkb, flags, error);
 	dlm_put_lkb(lkb);
  out:
 	dlm_unlock_recovery(ls);
@@ -6101,6 +6149,8 @@ int dlm_user_deadlock(struct dlm_ls *ls, uint32_t flags, uint32_t lkid)
 	if (error)
 		goto out;
 
+	trace_dlm_unlock_start(ls, lkb, flags);
+
 	ua = lkb->lkb_ua;
 
 	error = set_unlock_args(flags, ua, &args);
@@ -6129,6 +6179,7 @@ int dlm_user_deadlock(struct dlm_ls *ls, uint32_t flags, uint32_t lkid)
 	if (error == -EBUSY)
 		error = 0;
  out_put:
+	trace_dlm_unlock_end(ls, lkb, flags, error);
 	dlm_put_lkb(lkb);
  out:
 	dlm_unlock_recovery(ls);
@@ -6184,7 +6235,7 @@ static struct dlm_lkb *del_proc_lock(struct dlm_ls *ls,
 {
 	struct dlm_lkb *lkb = NULL;
 
-	mutex_lock(&ls->ls_clear_proc_locks);
+	spin_lock(&ls->ls_clear_proc_locks);
 	if (list_empty(&proc->locks))
 		goto out;
 
@@ -6196,7 +6247,7 @@ static struct dlm_lkb *del_proc_lock(struct dlm_ls *ls,
 	else
 		lkb->lkb_flags |= DLM_IFL_DEAD;
  out:
-	mutex_unlock(&ls->ls_clear_proc_locks);
+	spin_unlock(&ls->ls_clear_proc_locks);
 	return lkb;
 }
 
@@ -6233,7 +6284,7 @@ void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc)
 		dlm_put_lkb(lkb);
 	}
 
-	mutex_lock(&ls->ls_clear_proc_locks);
+	spin_lock(&ls->ls_clear_proc_locks);
 
 	/* in-progress unlocks */
 	list_for_each_entry_safe(lkb, safe, &proc->unlocking, lkb_ownqueue) {
@@ -6249,7 +6300,7 @@ void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc)
 		dlm_put_lkb(lkb);
 	}
 
-	mutex_unlock(&ls->ls_clear_proc_locks);
+	spin_unlock(&ls->ls_clear_proc_locks);
 	dlm_unlock_recovery(ls);
 }
 
diff --git a/fs/dlm/lock.h b/fs/dlm/lock.h
index a7b6474f009d..40c76b5544da 100644
--- a/fs/dlm/lock.h
+++ b/fs/dlm/lock.h
@@ -36,7 +36,7 @@ static inline void dlm_adjust_timeouts(struct dlm_ls *ls) { }
 int dlm_master_lookup(struct dlm_ls *ls, int nodeid, char *name, int len,
 		      unsigned int flags, int *r_nodeid, int *result);
 
-int dlm_search_rsb_tree(struct rb_root *tree, char *name, int len,
+int dlm_search_rsb_tree(struct rb_root *tree, const void *name, int len,
 			struct dlm_rsb **r_ret);
 
 void dlm_recover_purge(struct dlm_ls *ls);
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 3972f4d86c75..bae050df7abf 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -416,7 +416,7 @@ static int new_lockspace(const char *name, const char *cluster,
 	if (namelen > DLM_LOCKSPACE_LEN || namelen == 0)
 		return -EINVAL;
 
-	if (!lvblen || (lvblen % 8))
+	if (lvblen % 8)
 		return -EINVAL;
 
 	if (!try_module_get(THIS_MODULE))
@@ -584,7 +584,7 @@ static int new_lockspace(const char *name, const char *cluster,
 	atomic_set(&ls->ls_requestqueue_cnt, 0);
 	init_waitqueue_head(&ls->ls_requestqueue_wait);
 	mutex_init(&ls->ls_requestqueue_mutex);
-	mutex_init(&ls->ls_clear_proc_locks);
+	spin_lock_init(&ls->ls_clear_proc_locks);
 
 	/* Due backwards compatibility with 3.1 we need to use maximum
 	 * possible dlm message size to be sure the message will fit and
@@ -703,10 +703,11 @@ static int new_lockspace(const char *name, const char *cluster,
 	return error;
 }
 
-int dlm_new_lockspace(const char *name, const char *cluster,
-		      uint32_t flags, int lvblen,
-		      const struct dlm_lockspace_ops *ops, void *ops_arg,
-		      int *ops_result, dlm_lockspace_t **lockspace)
+static int __dlm_new_lockspace(const char *name, const char *cluster,
+			       uint32_t flags, int lvblen,
+			       const struct dlm_lockspace_ops *ops,
+			       void *ops_arg, int *ops_result,
+			       dlm_lockspace_t **lockspace)
 {
 	int error = 0;
 
@@ -732,6 +733,25 @@ int dlm_new_lockspace(const char *name, const char *cluster,
 	return error;
 }
 
+int dlm_new_lockspace(const char *name, const char *cluster, uint32_t flags,
+		      int lvblen, const struct dlm_lockspace_ops *ops,
+		      void *ops_arg, int *ops_result,
+		      dlm_lockspace_t **lockspace)
+{
+	return __dlm_new_lockspace(name, cluster, flags | DLM_LSFL_FS, lvblen,
+				   ops, ops_arg, ops_result, lockspace);
+}
+
+int dlm_new_user_lockspace(const char *name, const char *cluster,
+			   uint32_t flags, int lvblen,
+			   const struct dlm_lockspace_ops *ops,
+			   void *ops_arg, int *ops_result,
+			   dlm_lockspace_t **lockspace)
+{
+	return __dlm_new_lockspace(name, cluster, flags, lvblen, ops,
+				   ops_arg, ops_result, lockspace);
+}
+
 static int lkb_idr_is_local(int id, void *p, void *data)
 {
 	struct dlm_lkb *lkb = p;
diff --git a/fs/dlm/lockspace.h b/fs/dlm/lockspace.h
index 306fc4f4ea15..03f4a4a3a871 100644
--- a/fs/dlm/lockspace.h
+++ b/fs/dlm/lockspace.h
@@ -12,6 +12,14 @@
 #ifndef __LOCKSPACE_DOT_H__
 #define __LOCKSPACE_DOT_H__
 
+/* DLM_LSFL_FS
+ *   The lockspace user is in the kernel (i.e. filesystem).  Enables
+ *   direct bast/cast callbacks.
+ *
+ * internal lockspace flag - will be removed in future
+ */
+#define DLM_LSFL_FS	0x00000004
+
 int dlm_lockspace_init(void);
 void dlm_lockspace_exit(void);
 struct dlm_ls *dlm_find_lockspace_global(uint32_t id);
@@ -20,6 +28,11 @@ struct dlm_ls *dlm_find_lockspace_device(int minor);
 void dlm_put_lockspace(struct dlm_ls *ls);
 void dlm_stop_lockspaces(void);
 void dlm_stop_lockspaces_check(void);
+int dlm_new_user_lockspace(const char *name, const char *cluster,
+			   uint32_t flags, int lvblen,
+			   const struct dlm_lockspace_ops *ops,
+			   void *ops_arg, int *ops_result,
+			   dlm_lockspace_t **lockspace);
 
 #endif				/* __LOCKSPACE_DOT_H__ */
 
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index a4e84e8d94c8..59f64c596233 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1336,6 +1336,8 @@ struct dlm_msg *dlm_lowcomms_new_msg(int nodeid, int len, gfp_t allocation,
 		return NULL;
 	}
 
+	/* for dlm_lowcomms_commit_msg() */
+	kref_get(&msg->ref);
 	/* we assume if successful commit must called */
 	msg->idx = idx;
 	return msg;
@@ -1375,6 +1377,8 @@ void dlm_lowcomms_commit_msg(struct dlm_msg *msg)
 {
 	_dlm_lowcomms_commit_msg(msg);
 	srcu_read_unlock(&connections_srcu, msg->idx);
+	/* because dlm_lowcomms_new_msg() */
+	kref_put(&msg->ref, dlm_msg_release);
 }
 #endif
 
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 99e8f0744513..c5d27bccc3dc 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -16,6 +16,8 @@
 #include <linux/slab.h>
 #include <linux/sched/signal.h>
 
+#include <trace/events/dlm.h>
+
 #include "dlm_internal.h"
 #include "lockspace.h"
 #include "lock.h"
@@ -184,7 +186,7 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,
 		return;
 
 	ls = lkb->lkb_resource->res_ls;
-	mutex_lock(&ls->ls_clear_proc_locks);
+	spin_lock(&ls->ls_clear_proc_locks);
 
 	/* If ORPHAN/DEAD flag is set, it means the process is dead so an ast
 	   can't be delivered.  For ORPHAN's, dlm_clear_proc_locks() freed
@@ -230,7 +232,7 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,
 		spin_unlock(&proc->locks_spin);
 	}
  out:
-	mutex_unlock(&ls->ls_clear_proc_locks);
+	spin_unlock(&ls->ls_clear_proc_locks);
 }
 
 static int device_user_lock(struct dlm_user_proc *proc,
@@ -421,9 +423,9 @@ static int device_create_lockspace(struct dlm_lspace_params *params)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	error = dlm_new_lockspace(params->name, dlm_config.ci_cluster_name, params->flags,
-				  DLM_USER_LVB_LEN, NULL, NULL, NULL,
-				  &lockspace);
+	error = dlm_new_user_lockspace(params->name, dlm_config.ci_cluster_name,
+				       params->flags, DLM_USER_LVB_LEN, NULL,
+				       NULL, NULL, &lockspace);
 	if (error)
 		return error;
 
@@ -882,7 +884,9 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count,
 		goto try_another;
 	}
 
-	if (cb.flags & DLM_CB_CAST) {
+	if (cb.flags & DLM_CB_BAST) {
+		trace_dlm_bast(lkb->lkb_resource->res_ls, lkb, cb.mode);
+	} else if (cb.flags & DLM_CB_CAST) {
 		new_mode = cb.mode;
 
 		if (!cb.sb_status && lkb->lkb_lksb->sb_lvbptr &&
@@ -891,6 +895,7 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count,
 
 		lkb->lkb_lksb->sb_status = cb.sb_status;
 		lkb->lkb_lksb->sb_flags = cb.sb_flags;
+		trace_dlm_ast(lkb->lkb_resource->res_ls, lkb);
 	}
 
 	rv = copy_result_to_user(lkb->lkb_ua,
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 2d55569f96ac..51b7ac7166d9 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -317,52 +317,61 @@ dstmap_out:
 	return ret;
 }
 
-static int z_erofs_shifted_transform(struct z_erofs_decompress_req *rq,
-				     struct page **pagepool)
+static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq,
+				   struct page **pagepool)
 {
-	const unsigned int nrpages_out =
+	const unsigned int inpages = PAGE_ALIGN(rq->inputsize) >> PAGE_SHIFT;
+	const unsigned int outpages =
 		PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
 	const unsigned int righthalf = min_t(unsigned int, rq->outputsize,
 					     PAGE_SIZE - rq->pageofs_out);
 	const unsigned int lefthalf = rq->outputsize - righthalf;
+	const unsigned int interlaced_offset =
+		rq->alg == Z_EROFS_COMPRESSION_SHIFTED ? 0 : rq->pageofs_out;
 	unsigned char *src, *dst;
 
-	if (nrpages_out > 2) {
+	if (outpages > 2 && rq->alg == Z_EROFS_COMPRESSION_SHIFTED) {
 		DBG_BUGON(1);
-		return -EIO;
+		return -EFSCORRUPTED;
 	}
 
 	if (rq->out[0] == *rq->in) {
-		DBG_BUGON(nrpages_out != 1);
+		DBG_BUGON(rq->pageofs_out);
 		return 0;
 	}
 
-	src = kmap_atomic(*rq->in) + rq->pageofs_in;
+	src = kmap_local_page(rq->in[inpages - 1]) + rq->pageofs_in;
 	if (rq->out[0]) {
-		dst = kmap_atomic(rq->out[0]);
-		memcpy(dst + rq->pageofs_out, src, righthalf);
-		kunmap_atomic(dst);
+		dst = kmap_local_page(rq->out[0]);
+		memcpy(dst + rq->pageofs_out, src + interlaced_offset,
+		       righthalf);
+		kunmap_local(dst);
 	}
 
-	if (nrpages_out == 2) {
-		DBG_BUGON(!rq->out[1]);
-		if (rq->out[1] == *rq->in) {
+	if (outpages > inpages) {
+		DBG_BUGON(!rq->out[outpages - 1]);
+		if (rq->out[outpages - 1] != rq->in[inpages - 1]) {
+			dst = kmap_local_page(rq->out[outpages - 1]);
+			memcpy(dst, interlaced_offset ? src :
+					(src + righthalf), lefthalf);
+			kunmap_local(dst);
+		} else if (!interlaced_offset) {
 			memmove(src, src + righthalf, lefthalf);
-		} else {
-			dst = kmap_atomic(rq->out[1]);
-			memcpy(dst, src + righthalf, lefthalf);
-			kunmap_atomic(dst);
 		}
 	}
-	kunmap_atomic(src);
+	kunmap_local(src);
 	return 0;
 }
 
 static struct z_erofs_decompressor decompressors[] = {
 	[Z_EROFS_COMPRESSION_SHIFTED] = {
-		.decompress = z_erofs_shifted_transform,
+		.decompress = z_erofs_transform_plain,
 		.name = "shifted"
 	},
+	[Z_EROFS_COMPRESSION_INTERLACED] = {
+		.decompress = z_erofs_transform_plain,
+		.name = "interlaced"
+	},
 	[Z_EROFS_COMPRESSION_LZ4] = {
 		.decompress = z_erofs_lz4_decompress,
 		.name = "lz4"
diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c
index 5e59b3f523eb..091fd5adf818 100644
--- a/fs/erofs/decompressor_lzma.c
+++ b/fs/erofs/decompressor_lzma.c
@@ -217,6 +217,9 @@ again:
 			strm->buf.out_size = min_t(u32, outlen,
 						   PAGE_SIZE - pageofs);
 			outlen -= strm->buf.out_size;
+			if (!rq->out[no] && rq->fillgaps)	/* deduped */
+				rq->out[no] = erofs_allocpage(pagepool,
+						GFP_KERNEL | __GFP_NOFAIL);
 			if (rq->out[no])
 				strm->buf.out = kmap(rq->out[no]) + pageofs;
 			pageofs = 0;
diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index 2b48373f690b..dbcd24371002 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -25,6 +25,8 @@
 #define EROFS_FEATURE_INCOMPAT_DEVICE_TABLE	0x00000008
 #define EROFS_FEATURE_INCOMPAT_COMPR_HEAD2	0x00000008
 #define EROFS_FEATURE_INCOMPAT_ZTAILPACKING	0x00000010
+#define EROFS_FEATURE_INCOMPAT_FRAGMENTS	0x00000020
+#define EROFS_FEATURE_INCOMPAT_DEDUPE		0x00000020
 #define EROFS_ALL_FEATURE_INCOMPAT		\
 	(EROFS_FEATURE_INCOMPAT_ZERO_PADDING | \
 	 EROFS_FEATURE_INCOMPAT_COMPR_CFGS | \
@@ -32,7 +34,9 @@
 	 EROFS_FEATURE_INCOMPAT_CHUNKED_FILE | \
 	 EROFS_FEATURE_INCOMPAT_DEVICE_TABLE | \
 	 EROFS_FEATURE_INCOMPAT_COMPR_HEAD2 | \
-	 EROFS_FEATURE_INCOMPAT_ZTAILPACKING)
+	 EROFS_FEATURE_INCOMPAT_ZTAILPACKING | \
+	 EROFS_FEATURE_INCOMPAT_FRAGMENTS | \
+	 EROFS_FEATURE_INCOMPAT_DEDUPE)
 
 #define EROFS_SB_EXTSLOT_SIZE	16
 
@@ -71,7 +75,9 @@ struct erofs_super_block {
 	} __packed u1;
 	__le16 extra_devices;	/* # of devices besides the primary device */
 	__le16 devt_slotoff;	/* startoff = devt_slotoff * devt_slotsize */
-	__u8 reserved2[38];
+	__u8 reserved[6];
+	__le64 packed_nid;	/* nid of the special packed inode */
+	__u8 reserved2[24];
 };
 
 /*
@@ -295,16 +301,27 @@ struct z_erofs_lzma_cfgs {
  * bit 1 : HEAD1 big pcluster (0 - off; 1 - on)
  * bit 2 : HEAD2 big pcluster (0 - off; 1 - on)
  * bit 3 : tailpacking inline pcluster (0 - off; 1 - on)
+ * bit 4 : interlaced plain pcluster (0 - off; 1 - on)
+ * bit 5 : fragment pcluster (0 - off; 1 - on)
  */
 #define Z_EROFS_ADVISE_COMPACTED_2B		0x0001
 #define Z_EROFS_ADVISE_BIG_PCLUSTER_1		0x0002
 #define Z_EROFS_ADVISE_BIG_PCLUSTER_2		0x0004
 #define Z_EROFS_ADVISE_INLINE_PCLUSTER		0x0008
+#define Z_EROFS_ADVISE_INTERLACED_PCLUSTER	0x0010
+#define Z_EROFS_ADVISE_FRAGMENT_PCLUSTER	0x0020
 
+#define Z_EROFS_FRAGMENT_INODE_BIT              7
 struct z_erofs_map_header {
-	__le16	h_reserved1;
-	/* indicates the encoded size of tailpacking data */
-	__le16  h_idata_size;
+	union {
+		/* fragment data offset in the packed inode */
+		__le32  h_fragmentoff;
+		struct {
+			__le16  h_reserved1;
+			/* indicates the encoded size of tailpacking data */
+			__le16  h_idata_size;
+		};
+	};
 	__le16	h_advise;
 	/*
 	 * bit 0-3 : algorithm type of head 1 (logical cluster type 01);
@@ -313,7 +330,8 @@ struct z_erofs_map_header {
 	__u8	h_algorithmtype;
 	/*
 	 * bit 0-2 : logical cluster bits - 12, e.g. 0 for 4096;
-	 * bit 3-7 : reserved.
+	 * bit 3-6 : reserved;
+	 * bit 7   : move the whole file into packed inode or not.
 	 */
 	__u8	h_clusterbits;
 };
@@ -355,6 +373,9 @@ enum {
 #define Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS        2
 #define Z_EROFS_VLE_DI_CLUSTER_TYPE_BIT         0
 
+/* (noncompact only, HEAD) This pcluster refers to partial decompressed data */
+#define Z_EROFS_VLE_DI_PARTIAL_REF		(1 << 15)
+
 /*
  * D0_CBLKCNT will be marked _only_ at the 1st non-head lcluster to store the
  * compressed block count of a compressed extent (in logical clusters, aka.
@@ -402,6 +423,10 @@ struct erofs_dirent {
 /* check the EROFS on-disk layout strictly at compile time */
 static inline void erofs_check_ondisk_layout_definitions(void)
 {
+	const __le64 fmh = *(__le64 *)&(struct z_erofs_map_header) {
+		.h_clusterbits = 1 << Z_EROFS_FRAGMENT_INODE_BIT
+	};
+
 	BUILD_BUG_ON(sizeof(struct erofs_super_block) != 128);
 	BUILD_BUG_ON(sizeof(struct erofs_inode_compact) != 32);
 	BUILD_BUG_ON(sizeof(struct erofs_inode_extended) != 64);
@@ -419,6 +444,9 @@ static inline void erofs_check_ondisk_layout_definitions(void)
 
 	BUILD_BUG_ON(BIT(Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS) <
 		     Z_EROFS_VLE_CLUSTER_TYPE_MAX - 1);
+	/* exclude old compiler versions like gcc 7.5.0 */
+	BUILD_BUG_ON(__builtin_constant_p(fmh) ?
+		     fmh != cpu_to_le64(1ULL << 63) : 0);
 }
 
 #endif
diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
index 8e01d89c3319..998cd26a1b3b 100644
--- a/fs/erofs/fscache.c
+++ b/fs/erofs/fscache.c
@@ -1,10 +1,16 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2022, Alibaba Cloud
+ * Copyright (C) 2022, Bytedance Inc. All rights reserved.
  */
 #include <linux/fscache.h>
 #include "internal.h"
 
+static DEFINE_MUTEX(erofs_domain_list_lock);
+static DEFINE_MUTEX(erofs_domain_cookies_lock);
+static LIST_HEAD(erofs_domain_list);
+static struct vfsmount *erofs_pseudo_mnt;
+
 static struct netfs_io_request *erofs_fscache_alloc_request(struct address_space *mapping,
 					     loff_t start, size_t len)
 {
@@ -222,8 +228,10 @@ static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio)
 
 	rreq = erofs_fscache_alloc_request(folio_mapping(folio),
 				folio_pos(folio), folio_size(folio));
-	if (IS_ERR(rreq))
+	if (IS_ERR(rreq)) {
+		ret = PTR_ERR(rreq);
 		goto out;
+	}
 
 	return erofs_fscache_read_folios_async(mdev.m_fscache->cookie,
 				rreq, mdev.m_pa);
@@ -232,111 +240,111 @@ out:
 	return ret;
 }
 
-static int erofs_fscache_read_folio_inline(struct folio *folio,
-					 struct erofs_map_blocks *map)
-{
-	struct super_block *sb = folio_mapping(folio)->host->i_sb;
-	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
-	erofs_blk_t blknr;
-	size_t offset, len;
-	void *src, *dst;
-
-	/* For tail packing layout, the offset may be non-zero. */
-	offset = erofs_blkoff(map->m_pa);
-	blknr = erofs_blknr(map->m_pa);
-	len = map->m_llen;
-
-	src = erofs_read_metabuf(&buf, sb, blknr, EROFS_KMAP);
-	if (IS_ERR(src))
-		return PTR_ERR(src);
-
-	dst = kmap_local_folio(folio, 0);
-	memcpy(dst, src + offset, len);
-	memset(dst + len, 0, PAGE_SIZE - len);
-	kunmap_local(dst);
-
-	erofs_put_metabuf(&buf);
-	return 0;
-}
-
-static int erofs_fscache_read_folio(struct file *file, struct folio *folio)
+/*
+ * Read into page cache in the range described by (@pos, @len).
+ *
+ * On return, the caller is responsible for page unlocking if the output @unlock
+ * is true, or the callee will take this responsibility through netfs_io_request
+ * interface.
+ *
+ * The return value is the number of bytes successfully handled, or negative
+ * error code on failure. The only exception is that, the length of the range
+ * instead of the error code is returned on failure after netfs_io_request is
+ * allocated, so that .readahead() could advance rac accordingly.
+ */
+static int erofs_fscache_data_read(struct address_space *mapping,
+				   loff_t pos, size_t len, bool *unlock)
 {
-	struct inode *inode = folio_mapping(folio)->host;
+	struct inode *inode = mapping->host;
 	struct super_block *sb = inode->i_sb;
+	struct netfs_io_request *rreq;
 	struct erofs_map_blocks map;
 	struct erofs_map_dev mdev;
-	struct netfs_io_request *rreq;
-	erofs_off_t pos;
-	loff_t pstart;
+	struct iov_iter iter;
+	size_t count;
 	int ret;
 
-	DBG_BUGON(folio_size(folio) != EROFS_BLKSIZ);
+	*unlock = true;
 
-	pos = folio_pos(folio);
 	map.m_la = pos;
-
 	ret = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
-	if (!(map.m_flags & EROFS_MAP_MAPPED)) {
-		folio_zero_range(folio, 0, folio_size(folio));
-		goto out_uptodate;
+	if (map.m_flags & EROFS_MAP_META) {
+		struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
+		erofs_blk_t blknr;
+		size_t offset, size;
+		void *src;
+
+		/* For tail packing layout, the offset may be non-zero. */
+		offset = erofs_blkoff(map.m_pa);
+		blknr = erofs_blknr(map.m_pa);
+		size = map.m_llen;
+
+		src = erofs_read_metabuf(&buf, sb, blknr, EROFS_KMAP);
+		if (IS_ERR(src))
+			return PTR_ERR(src);
+
+		iov_iter_xarray(&iter, READ, &mapping->i_pages, pos, PAGE_SIZE);
+		if (copy_to_iter(src + offset, size, &iter) != size)
+			return -EFAULT;
+		iov_iter_zero(PAGE_SIZE - size, &iter);
+		erofs_put_metabuf(&buf);
+		return PAGE_SIZE;
 	}
 
-	if (map.m_flags & EROFS_MAP_META) {
-		ret = erofs_fscache_read_folio_inline(folio, &map);
-		goto out_uptodate;
+	count = min_t(size_t, map.m_llen - (pos - map.m_la), len);
+	DBG_BUGON(!count || count % PAGE_SIZE);
+
+	if (!(map.m_flags & EROFS_MAP_MAPPED)) {
+		iov_iter_xarray(&iter, READ, &mapping->i_pages, pos, count);
+		iov_iter_zero(count, &iter);
+		return count;
 	}
 
 	mdev = (struct erofs_map_dev) {
 		.m_deviceid = map.m_deviceid,
 		.m_pa = map.m_pa,
 	};
-
 	ret = erofs_map_dev(sb, &mdev);
 	if (ret)
-		goto out_unlock;
-
+		return ret;
 
-	rreq = erofs_fscache_alloc_request(folio_mapping(folio),
-				folio_pos(folio), folio_size(folio));
+	rreq = erofs_fscache_alloc_request(mapping, pos, count);
 	if (IS_ERR(rreq))
-		goto out_unlock;
-
-	pstart = mdev.m_pa + (pos - map.m_la);
-	return erofs_fscache_read_folios_async(mdev.m_fscache->cookie,
-				rreq, pstart);
+		return PTR_ERR(rreq);
 
-out_uptodate:
-	if (!ret)
-		folio_mark_uptodate(folio);
-out_unlock:
-	folio_unlock(folio);
-	return ret;
+	*unlock = false;
+	erofs_fscache_read_folios_async(mdev.m_fscache->cookie,
+			rreq, mdev.m_pa + (pos - map.m_la));
+	return count;
 }
 
-static void erofs_fscache_advance_folios(struct readahead_control *rac,
-					 size_t len, bool unlock)
+static int erofs_fscache_read_folio(struct file *file, struct folio *folio)
 {
-	while (len) {
-		struct folio *folio = readahead_folio(rac);
-		len -= folio_size(folio);
-		if (unlock) {
+	bool unlock;
+	int ret;
+
+	DBG_BUGON(folio_size(folio) != EROFS_BLKSIZ);
+
+	ret = erofs_fscache_data_read(folio_mapping(folio), folio_pos(folio),
+				      folio_size(folio), &unlock);
+	if (unlock) {
+		if (ret > 0)
 			folio_mark_uptodate(folio);
-			folio_unlock(folio);
-		}
+		folio_unlock(folio);
 	}
+	return ret < 0 ? ret : 0;
 }
 
 static void erofs_fscache_readahead(struct readahead_control *rac)
 {
-	struct inode *inode = rac->mapping->host;
-	struct super_block *sb = inode->i_sb;
-	size_t len, count, done = 0;
-	erofs_off_t pos;
-	loff_t start, offset;
-	int ret;
+	struct folio *folio;
+	size_t len, done = 0;
+	loff_t start, pos;
+	bool unlock;
+	int ret, size;
 
 	if (!readahead_count(rac))
 		return;
@@ -345,67 +353,22 @@ static void erofs_fscache_readahead(struct readahead_control *rac)
 	len = readahead_length(rac);
 
 	do {
-		struct erofs_map_blocks map;
-		struct erofs_map_dev mdev;
-		struct netfs_io_request *rreq;
-
 		pos = start + done;
-		map.m_la = pos;
-
-		ret = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
-		if (ret)
+		ret = erofs_fscache_data_read(rac->mapping, pos,
+					      len - done, &unlock);
+		if (ret <= 0)
 			return;
 
-		offset = start + done;
-		count = min_t(size_t, map.m_llen - (pos - map.m_la),
-			      len - done);
-
-		if (!(map.m_flags & EROFS_MAP_MAPPED)) {
-			struct iov_iter iter;
-
-			iov_iter_xarray(&iter, READ, &rac->mapping->i_pages,
-					offset, count);
-			iov_iter_zero(count, &iter);
-
-			erofs_fscache_advance_folios(rac, count, true);
-			ret = count;
-			continue;
-		}
-
-		if (map.m_flags & EROFS_MAP_META) {
-			struct folio *folio = readahead_folio(rac);
-
-			ret = erofs_fscache_read_folio_inline(folio, &map);
-			if (!ret) {
+		size = ret;
+		while (size) {
+			folio = readahead_folio(rac);
+			size -= folio_size(folio);
+			if (unlock) {
 				folio_mark_uptodate(folio);
-				ret = folio_size(folio);
+				folio_unlock(folio);
 			}
-
-			folio_unlock(folio);
-			continue;
 		}
-
-		mdev = (struct erofs_map_dev) {
-			.m_deviceid = map.m_deviceid,
-			.m_pa = map.m_pa,
-		};
-		ret = erofs_map_dev(sb, &mdev);
-		if (ret)
-			return;
-
-		rreq = erofs_fscache_alloc_request(rac->mapping, offset, count);
-		if (IS_ERR(rreq))
-			return;
-		/*
-		 * Drop the ref of folios here. Unlock them in
-		 * rreq_unlock_folios() when rreq complete.
-		 */
-		erofs_fscache_advance_folios(rac, count, false);
-		ret = erofs_fscache_read_folios_async(mdev.m_fscache->cookie,
-					rreq, mdev.m_pa + (pos - map.m_la));
-		if (!ret)
-			ret = count;
-	} while (ret > 0 && ((done += ret) < len));
+	} while ((done += ret) < len);
 }
 
 static const struct address_space_operations erofs_fscache_meta_aops = {
@@ -417,9 +380,114 @@ const struct address_space_operations erofs_fscache_access_aops = {
 	.readahead = erofs_fscache_readahead,
 };
 
-int erofs_fscache_register_cookie(struct super_block *sb,
-				  struct erofs_fscache **fscache,
-				  char *name, bool need_inode)
+static void erofs_fscache_domain_put(struct erofs_domain *domain)
+{
+	if (!domain)
+		return;
+	mutex_lock(&erofs_domain_list_lock);
+	if (refcount_dec_and_test(&domain->ref)) {
+		list_del(&domain->list);
+		if (list_empty(&erofs_domain_list)) {
+			kern_unmount(erofs_pseudo_mnt);
+			erofs_pseudo_mnt = NULL;
+		}
+		mutex_unlock(&erofs_domain_list_lock);
+		fscache_relinquish_volume(domain->volume, NULL, false);
+		kfree(domain->domain_id);
+		kfree(domain);
+		return;
+	}
+	mutex_unlock(&erofs_domain_list_lock);
+}
+
+static int erofs_fscache_register_volume(struct super_block *sb)
+{
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
+	char *domain_id = sbi->opt.domain_id;
+	struct fscache_volume *volume;
+	char *name;
+	int ret = 0;
+
+	name = kasprintf(GFP_KERNEL, "erofs,%s",
+			 domain_id ? domain_id : sbi->opt.fsid);
+	if (!name)
+		return -ENOMEM;
+
+	volume = fscache_acquire_volume(name, NULL, NULL, 0);
+	if (IS_ERR_OR_NULL(volume)) {
+		erofs_err(sb, "failed to register volume for %s", name);
+		ret = volume ? PTR_ERR(volume) : -EOPNOTSUPP;
+		volume = NULL;
+	}
+
+	sbi->volume = volume;
+	kfree(name);
+	return ret;
+}
+
+static int erofs_fscache_init_domain(struct super_block *sb)
+{
+	int err;
+	struct erofs_domain *domain;
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
+
+	domain = kzalloc(sizeof(struct erofs_domain), GFP_KERNEL);
+	if (!domain)
+		return -ENOMEM;
+
+	domain->domain_id = kstrdup(sbi->opt.domain_id, GFP_KERNEL);
+	if (!domain->domain_id) {
+		kfree(domain);
+		return -ENOMEM;
+	}
+
+	err = erofs_fscache_register_volume(sb);
+	if (err)
+		goto out;
+
+	if (!erofs_pseudo_mnt) {
+		erofs_pseudo_mnt = kern_mount(&erofs_fs_type);
+		if (IS_ERR(erofs_pseudo_mnt)) {
+			err = PTR_ERR(erofs_pseudo_mnt);
+			goto out;
+		}
+	}
+
+	domain->volume = sbi->volume;
+	refcount_set(&domain->ref, 1);
+	list_add(&domain->list, &erofs_domain_list);
+	sbi->domain = domain;
+	return 0;
+out:
+	kfree(domain->domain_id);
+	kfree(domain);
+	return err;
+}
+
+static int erofs_fscache_register_domain(struct super_block *sb)
+{
+	int err;
+	struct erofs_domain *domain;
+	struct erofs_sb_info *sbi = EROFS_SB(sb);
+
+	mutex_lock(&erofs_domain_list_lock);
+	list_for_each_entry(domain, &erofs_domain_list, list) {
+		if (!strcmp(domain->domain_id, sbi->opt.domain_id)) {
+			sbi->domain = domain;
+			sbi->volume = domain->volume;
+			refcount_inc(&domain->ref);
+			mutex_unlock(&erofs_domain_list_lock);
+			return 0;
+		}
+	}
+	err = erofs_fscache_init_domain(sb);
+	mutex_unlock(&erofs_domain_list_lock);
+	return err;
+}
+
+static
+struct erofs_fscache *erofs_fscache_acquire_cookie(struct super_block *sb,
+						    char *name, bool need_inode)
 {
 	struct fscache_volume *volume = EROFS_SB(sb)->volume;
 	struct erofs_fscache *ctx;
@@ -428,7 +496,7 @@ int erofs_fscache_register_cookie(struct super_block *sb,
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	cookie = fscache_acquire_cookie(volume, FSCACHE_ADV_WANT_CACHE_SIZE,
 					name, strlen(name), NULL, 0, 0);
@@ -458,63 +526,146 @@ int erofs_fscache_register_cookie(struct super_block *sb,
 		ctx->inode = inode;
 	}
 
-	*fscache = ctx;
-	return 0;
+	return ctx;
 
 err_cookie:
 	fscache_unuse_cookie(ctx->cookie, NULL, NULL);
 	fscache_relinquish_cookie(ctx->cookie, false);
-	ctx->cookie = NULL;
 err:
 	kfree(ctx);
-	return ret;
+	return ERR_PTR(ret);
 }
 
-void erofs_fscache_unregister_cookie(struct erofs_fscache **fscache)
+static void erofs_fscache_relinquish_cookie(struct erofs_fscache *ctx)
 {
-	struct erofs_fscache *ctx = *fscache;
-
-	if (!ctx)
-		return;
-
 	fscache_unuse_cookie(ctx->cookie, NULL, NULL);
 	fscache_relinquish_cookie(ctx->cookie, false);
-	ctx->cookie = NULL;
-
 	iput(ctx->inode);
-	ctx->inode = NULL;
-
+	kfree(ctx->name);
 	kfree(ctx);
-	*fscache = NULL;
+}
+
+static
+struct erofs_fscache *erofs_fscache_domain_init_cookie(struct super_block *sb,
+		char *name, bool need_inode)
+{
+	int err;
+	struct inode *inode;
+	struct erofs_fscache *ctx;
+	struct erofs_domain *domain = EROFS_SB(sb)->domain;
+
+	ctx = erofs_fscache_acquire_cookie(sb, name, need_inode);
+	if (IS_ERR(ctx))
+		return ctx;
+
+	ctx->name = kstrdup(name, GFP_KERNEL);
+	if (!ctx->name) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	inode = new_inode(erofs_pseudo_mnt->mnt_sb);
+	if (!inode) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	ctx->domain = domain;
+	ctx->anon_inode = inode;
+	inode->i_private = ctx;
+	refcount_inc(&domain->ref);
+	return ctx;
+out:
+	erofs_fscache_relinquish_cookie(ctx);
+	return ERR_PTR(err);
+}
+
+static
+struct erofs_fscache *erofs_domain_register_cookie(struct super_block *sb,
+						   char *name, bool need_inode)
+{
+	struct inode *inode;
+	struct erofs_fscache *ctx;
+	struct erofs_domain *domain = EROFS_SB(sb)->domain;
+	struct super_block *psb = erofs_pseudo_mnt->mnt_sb;
+
+	mutex_lock(&erofs_domain_cookies_lock);
+	list_for_each_entry(inode, &psb->s_inodes, i_sb_list) {
+		ctx = inode->i_private;
+		if (!ctx || ctx->domain != domain || strcmp(ctx->name, name))
+			continue;
+		igrab(inode);
+		mutex_unlock(&erofs_domain_cookies_lock);
+		return ctx;
+	}
+	ctx = erofs_fscache_domain_init_cookie(sb, name, need_inode);
+	mutex_unlock(&erofs_domain_cookies_lock);
+	return ctx;
+}
+
+struct erofs_fscache *erofs_fscache_register_cookie(struct super_block *sb,
+						    char *name, bool need_inode)
+{
+	if (EROFS_SB(sb)->opt.domain_id)
+		return erofs_domain_register_cookie(sb, name, need_inode);
+	return erofs_fscache_acquire_cookie(sb, name, need_inode);
+}
+
+void erofs_fscache_unregister_cookie(struct erofs_fscache *ctx)
+{
+	bool drop;
+	struct erofs_domain *domain;
+
+	if (!ctx)
+		return;
+	domain = ctx->domain;
+	if (domain) {
+		mutex_lock(&erofs_domain_cookies_lock);
+		drop = atomic_read(&ctx->anon_inode->i_count) == 1;
+		iput(ctx->anon_inode);
+		mutex_unlock(&erofs_domain_cookies_lock);
+		if (!drop)
+			return;
+	}
+
+	erofs_fscache_relinquish_cookie(ctx);
+	erofs_fscache_domain_put(domain);
 }
 
 int erofs_fscache_register_fs(struct super_block *sb)
 {
+	int ret;
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
-	struct fscache_volume *volume;
-	char *name;
-	int ret = 0;
+	struct erofs_fscache *fscache;
 
-	name = kasprintf(GFP_KERNEL, "erofs,%s", sbi->opt.fsid);
-	if (!name)
-		return -ENOMEM;
+	if (sbi->opt.domain_id)
+		ret = erofs_fscache_register_domain(sb);
+	else
+		ret = erofs_fscache_register_volume(sb);
+	if (ret)
+		return ret;
 
-	volume = fscache_acquire_volume(name, NULL, NULL, 0);
-	if (IS_ERR_OR_NULL(volume)) {
-		erofs_err(sb, "failed to register volume for %s", name);
-		ret = volume ? PTR_ERR(volume) : -EOPNOTSUPP;
-		volume = NULL;
-	}
+	/* acquired domain/volume will be relinquished in kill_sb() on error */
+	fscache = erofs_fscache_register_cookie(sb, sbi->opt.fsid, true);
+	if (IS_ERR(fscache))
+		return PTR_ERR(fscache);
 
-	sbi->volume = volume;
-	kfree(name);
-	return ret;
+	sbi->s_fscache = fscache;
+	return 0;
 }
 
 void erofs_fscache_unregister_fs(struct super_block *sb)
 {
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
 
-	fscache_relinquish_volume(sbi->volume, NULL, false);
+	erofs_fscache_unregister_cookie(sbi->s_fscache);
+
+	if (sbi->domain)
+		erofs_fscache_domain_put(sbi->domain);
+	else
+		fscache_relinquish_volume(sbi->volume, NULL, false);
+
+	sbi->s_fscache = NULL;
 	sbi->volume = NULL;
+	sbi->domain = NULL;
 }
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 95a403720e8c..ad2a82f2eb4c 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -214,7 +214,7 @@ static int erofs_fill_symlink(struct inode *inode, void *kaddr,
 
 	/* if it cannot be handled with fast symlink scheme */
 	if (vi->datalayout != EROFS_INODE_FLAT_INLINE ||
-	    inode->i_size >= EROFS_BLKSIZ) {
+	    inode->i_size >= EROFS_BLKSIZ || inode->i_size < 0) {
 		inode->i_op = &erofs_symlink_iops;
 		return 0;
 	}
@@ -241,7 +241,7 @@ static int erofs_fill_symlink(struct inode *inode, void *kaddr,
 	return 0;
 }
 
-static int erofs_fill_inode(struct inode *inode, int isdir)
+static int erofs_fill_inode(struct inode *inode)
 {
 	struct erofs_inode *vi = EROFS_I(inode);
 	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
@@ -249,7 +249,7 @@ static int erofs_fill_inode(struct inode *inode, int isdir)
 	unsigned int ofs;
 	int err = 0;
 
-	trace_erofs_fill_inode(inode, isdir);
+	trace_erofs_fill_inode(inode);
 
 	/* read inode base data from disk */
 	kaddr = erofs_read_inode(&buf, inode, &ofs);
@@ -324,21 +324,13 @@ static int erofs_iget_set_actor(struct inode *inode, void *opaque)
 	return 0;
 }
 
-static inline struct inode *erofs_iget_locked(struct super_block *sb,
-					      erofs_nid_t nid)
+struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid)
 {
 	const unsigned long hashval = erofs_inode_hash(nid);
+	struct inode *inode;
 
-	return iget5_locked(sb, hashval, erofs_ilookup_test_actor,
+	inode = iget5_locked(sb, hashval, erofs_ilookup_test_actor,
 		erofs_iget_set_actor, &nid);
-}
-
-struct inode *erofs_iget(struct super_block *sb,
-			 erofs_nid_t nid,
-			 bool isdir)
-{
-	struct inode *inode = erofs_iget_locked(sb, nid);
-
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 
@@ -348,10 +340,10 @@ struct inode *erofs_iget(struct super_block *sb,
 
 		vi->nid = nid;
 
-		err = erofs_fill_inode(inode, isdir);
-		if (!err)
+		err = erofs_fill_inode(inode);
+		if (!err) {
 			unlock_new_inode(inode);
-		else {
+		} else {
 			iget_failed(inode);
 			inode = ERR_PTR(err);
 		}
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index cfee49d33b95..1701df48c446 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -76,6 +76,7 @@ struct erofs_mount_opts {
 #endif
 	unsigned int mount_opt;
 	char *fsid;
+	char *domain_id;
 };
 
 struct erofs_dev_context {
@@ -98,9 +99,19 @@ struct erofs_sb_lz4_info {
 	u16 max_pclusterblks;
 };
 
+struct erofs_domain {
+	refcount_t ref;
+	struct list_head list;
+	struct fscache_volume *volume;
+	char *domain_id;
+};
+
 struct erofs_fscache {
 	struct fscache_cookie *cookie;
 	struct inode *inode;
+	struct inode *anon_inode;
+	struct erofs_domain *domain;
+	char *name;
 };
 
 struct erofs_sb_info {
@@ -120,6 +131,7 @@ struct erofs_sb_info {
 	struct inode *managed_cache;
 
 	struct erofs_sb_lz4_info lz4;
+	struct inode *packed_inode;
 #endif	/* CONFIG_EROFS_FS_ZIP */
 	struct erofs_dev_context *devs;
 	struct dax_device *dax_dev;
@@ -157,6 +169,7 @@ struct erofs_sb_info {
 	/* fscache support */
 	struct fscache_volume *volume;
 	struct erofs_fscache *s_fscache;
+	struct erofs_domain *domain;
 };
 
 #define EROFS_SB(sb) ((struct erofs_sb_info *)(sb)->s_fs_info)
@@ -183,7 +196,6 @@ enum {
 	EROFS_ZIP_CACHE_READAROUND
 };
 
-#ifdef CONFIG_EROFS_FS_ZIP
 #define EROFS_LOCKED_MAGIC     (INT_MIN | 0xE0F510CCL)
 
 /* basic unit of the workstation of a super_block */
@@ -195,7 +207,6 @@ struct erofs_workgroup {
 	atomic_t refcount;
 };
 
-#if defined(CONFIG_SMP)
 static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
 						 int val)
 {
@@ -224,35 +235,6 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
 	return atomic_cond_read_relaxed(&grp->refcount,
 					VAL != EROFS_LOCKED_MAGIC);
 }
-#else
-static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
-						 int val)
-{
-	preempt_disable();
-	/* no need to spin on UP platforms, let's just disable preemption. */
-	if (val != atomic_read(&grp->refcount)) {
-		preempt_enable();
-		return false;
-	}
-	return true;
-}
-
-static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp,
-					    int orig_val)
-{
-	preempt_enable();
-}
-
-static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
-{
-	int v = atomic_read(&grp->refcount);
-
-	/* workgroup is never freezed on uniprocessor systems */
-	DBG_BUGON(v == EROFS_LOCKED_MAGIC);
-	return v;
-}
-#endif	/* !CONFIG_SMP */
-#endif	/* !CONFIG_EROFS_FS_ZIP */
 
 /* we strictly follow PAGE_SIZE and no buffer head yet */
 #define LOG_BLOCK_SIZE		PAGE_SHIFT
@@ -306,6 +288,8 @@ EROFS_FEATURE_FUNCS(chunked_file, incompat, INCOMPAT_CHUNKED_FILE)
 EROFS_FEATURE_FUNCS(device_table, incompat, INCOMPAT_DEVICE_TABLE)
 EROFS_FEATURE_FUNCS(compr_head2, incompat, INCOMPAT_COMPR_HEAD2)
 EROFS_FEATURE_FUNCS(ztailpacking, incompat, INCOMPAT_ZTAILPACKING)
+EROFS_FEATURE_FUNCS(fragments, incompat, INCOMPAT_FRAGMENTS)
+EROFS_FEATURE_FUNCS(dedupe, incompat, INCOMPAT_DEDUPE)
 EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM)
 
 /* atomic flag definitions */
@@ -341,8 +325,13 @@ struct erofs_inode {
 			unsigned char  z_algorithmtype[2];
 			unsigned char  z_logical_clusterbits;
 			unsigned long  z_tailextent_headlcn;
-			erofs_off_t    z_idataoff;
-			unsigned short z_idata_size;
+			union {
+				struct {
+					erofs_off_t    z_idataoff;
+					unsigned short z_idata_size;
+				};
+				erofs_off_t z_fragmentoff;
+			};
 		};
 #endif	/* CONFIG_EROFS_FS_ZIP */
 	};
@@ -393,6 +382,7 @@ struct page *erofs_grab_cache_page_nowait(struct address_space *mapping,
 }
 
 extern const struct super_operations erofs_sops;
+extern struct file_system_type erofs_fs_type;
 
 extern const struct address_space_operations erofs_raw_access_aops;
 extern const struct address_space_operations z_erofs_aops;
@@ -400,6 +390,8 @@ extern const struct address_space_operations z_erofs_aops;
 enum {
 	BH_Encoded = BH_PrivateStart,
 	BH_FullMapped,
+	BH_Fragment,
+	BH_Partialref,
 };
 
 /* Has a disk mapping */
@@ -410,6 +402,10 @@ enum {
 #define EROFS_MAP_ENCODED	(1 << BH_Encoded)
 /* The length of extent is full */
 #define EROFS_MAP_FULL_MAPPED	(1 << BH_FullMapped)
+/* Located in the special packed inode */
+#define EROFS_MAP_FRAGMENT	(1 << BH_Fragment)
+/* The extent refers to partial decompressed data */
+#define EROFS_MAP_PARTIAL_REF	(1 << BH_Partialref)
 
 struct erofs_map_blocks {
 	struct erofs_buf buf;
@@ -431,11 +427,12 @@ struct erofs_map_blocks {
 #define EROFS_GET_BLOCKS_FIEMAP	0x0002
 /* Used to map the whole extent if non-negligible data is requested for LZMA */
 #define EROFS_GET_BLOCKS_READMORE	0x0004
-/* Used to map tail extent for tailpacking inline pcluster */
+/* Used to map tail extent for tailpacking inline or fragment pcluster */
 #define EROFS_GET_BLOCKS_FINDTAIL	0x0008
 
 enum {
 	Z_EROFS_COMPRESSION_SHIFTED = Z_EROFS_COMPRESSION_MAX,
+	Z_EROFS_COMPRESSION_INTERLACED,
 	Z_EROFS_COMPRESSION_RUNTIME_MAX
 };
 
@@ -495,7 +492,7 @@ extern const struct inode_operations erofs_generic_iops;
 extern const struct inode_operations erofs_symlink_iops;
 extern const struct inode_operations erofs_fast_symlink_iops;
 
-struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid, bool dir);
+struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid);
 int erofs_getattr(struct user_namespace *mnt_userns, const struct path *path,
 		  struct kstat *stat, u32 request_mask,
 		  unsigned int query_flags);
@@ -610,27 +607,26 @@ static inline int z_erofs_load_lzma_config(struct super_block *sb,
 int erofs_fscache_register_fs(struct super_block *sb);
 void erofs_fscache_unregister_fs(struct super_block *sb);
 
-int erofs_fscache_register_cookie(struct super_block *sb,
-				  struct erofs_fscache **fscache,
-				  char *name, bool need_inode);
-void erofs_fscache_unregister_cookie(struct erofs_fscache **fscache);
+struct erofs_fscache *erofs_fscache_register_cookie(struct super_block *sb,
+						     char *name, bool need_inode);
+void erofs_fscache_unregister_cookie(struct erofs_fscache *fscache);
 
 extern const struct address_space_operations erofs_fscache_access_aops;
 #else
 static inline int erofs_fscache_register_fs(struct super_block *sb)
 {
-	return 0;
+	return -EOPNOTSUPP;
 }
 static inline void erofs_fscache_unregister_fs(struct super_block *sb) {}
 
-static inline int erofs_fscache_register_cookie(struct super_block *sb,
-						struct erofs_fscache **fscache,
-						char *name, bool need_inode)
+static inline
+struct erofs_fscache *erofs_fscache_register_cookie(struct super_block *sb,
+						     char *name, bool need_inode)
 {
-	return -EOPNOTSUPP;
+	return ERR_PTR(-EOPNOTSUPP);
 }
 
-static inline void erofs_fscache_unregister_cookie(struct erofs_fscache **fscache)
+static inline void erofs_fscache_unregister_cookie(struct erofs_fscache *fscache)
 {
 }
 #endif
diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c
index fd75506799c4..0dc34721080c 100644
--- a/fs/erofs/namei.c
+++ b/fs/erofs/namei.c
@@ -185,7 +185,6 @@ int erofs_namei(struct inode *dir, const struct qstr *name, erofs_nid_t *nid,
 	if (IS_ERR(de))
 		return PTR_ERR(de);
 
-	/* the target page has been mapped */
 	if (ndirents)
 		de = find_target_dirent(&qn, (u8 *)de, EROFS_BLKSIZ, ndirents);
 
@@ -197,9 +196,7 @@ int erofs_namei(struct inode *dir, const struct qstr *name, erofs_nid_t *nid,
 	return PTR_ERR_OR_ZERO(de);
 }
 
-/* NOTE: i_mutex is already held by vfs */
-static struct dentry *erofs_lookup(struct inode *dir,
-				   struct dentry *dentry,
+static struct dentry *erofs_lookup(struct inode *dir, struct dentry *dentry,
 				   unsigned int flags)
 {
 	int err;
@@ -207,17 +204,11 @@ static struct dentry *erofs_lookup(struct inode *dir,
 	unsigned int d_type;
 	struct inode *inode;
 
-	DBG_BUGON(!d_really_is_negative(dentry));
-	/* dentry must be unhashed in lookup, no need to worry about */
-	DBG_BUGON(!d_unhashed(dentry));
-
 	trace_erofs_lookup(dir, dentry, flags);
 
-	/* file name exceeds fs limit */
 	if (dentry->d_name.len > EROFS_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
-	/* false uninitialized warnings on gcc 4.8.x */
 	err = erofs_namei(dir, &dentry->d_name, &nid, &d_type);
 
 	if (err == -ENOENT) {
@@ -228,7 +219,7 @@ static struct dentry *erofs_lookup(struct inode *dir,
 	} else {
 		erofs_dbg("%s, %pd (nid %llu) found, d_type %u", __func__,
 			  dentry, nid, d_type);
-		inode = erofs_iget(dir->i_sb, nid, d_type == FT_DIR);
+		inode = erofs_iget(dir->i_sb, nid);
 	}
 	return d_splice_alias(inode, dentry);
 }
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 3173debeaa5a..2cf96ce1c32e 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -224,10 +224,10 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 			     struct erofs_device_info *dif, erofs_off_t *pos)
 {
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
+	struct erofs_fscache *fscache;
 	struct erofs_deviceslot *dis;
 	struct block_device *bdev;
 	void *ptr;
-	int ret;
 
 	ptr = erofs_read_metabuf(buf, sb, erofs_blknr(*pos), EROFS_KMAP);
 	if (IS_ERR(ptr))
@@ -245,10 +245,10 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 	}
 
 	if (erofs_is_fscache_mode(sb)) {
-		ret = erofs_fscache_register_cookie(sb, &dif->fscache,
-				dif->path, false);
-		if (ret)
-			return ret;
+		fscache = erofs_fscache_register_cookie(sb, dif->path, false);
+		if (IS_ERR(fscache))
+			return PTR_ERR(fscache);
+		dif->fscache = fscache;
 	} else {
 		bdev = blkdev_get_by_path(dif->path, FMODE_READ | FMODE_EXCL,
 					  sb->s_type);
@@ -381,6 +381,17 @@ static int erofs_read_superblock(struct super_block *sb)
 #endif
 	sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact));
 	sbi->root_nid = le16_to_cpu(dsb->root_nid);
+#ifdef CONFIG_EROFS_FS_ZIP
+	sbi->packed_inode = NULL;
+	if (erofs_sb_has_fragments(sbi) && dsb->packed_nid) {
+		sbi->packed_inode =
+			erofs_iget(sb, le64_to_cpu(dsb->packed_nid));
+		if (IS_ERR(sbi->packed_inode)) {
+			ret = PTR_ERR(sbi->packed_inode);
+			goto out;
+		}
+	}
+#endif
 	sbi->inos = le64_to_cpu(dsb->inos);
 
 	sbi->build_time = le64_to_cpu(dsb->build_time);
@@ -411,6 +422,10 @@ static int erofs_read_superblock(struct super_block *sb)
 		erofs_info(sb, "EXPERIMENTAL compressed inline data feature in use. Use at your own risk!");
 	if (erofs_is_fscache_mode(sb))
 		erofs_info(sb, "EXPERIMENTAL fscache-based on-demand read feature in use. Use at your own risk!");
+	if (erofs_sb_has_fragments(sbi))
+		erofs_info(sb, "EXPERIMENTAL compressed fragments feature in use. Use at your own risk!");
+	if (erofs_sb_has_dedupe(sbi))
+		erofs_info(sb, "EXPERIMENTAL global deduplication feature in use. Use at your own risk!");
 out:
 	erofs_put_metabuf(&buf);
 	return ret;
@@ -440,6 +455,7 @@ enum {
 	Opt_dax_enum,
 	Opt_device,
 	Opt_fsid,
+	Opt_domain_id,
 	Opt_err
 };
 
@@ -465,6 +481,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = {
 	fsparam_enum("dax",		Opt_dax_enum, erofs_dax_param_enums),
 	fsparam_string("device",	Opt_device),
 	fsparam_string("fsid",		Opt_fsid),
+	fsparam_string("domain_id",	Opt_domain_id),
 	{}
 };
 
@@ -570,6 +587,16 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 		errorfc(fc, "fsid option not supported");
 #endif
 		break;
+	case Opt_domain_id:
+#ifdef CONFIG_EROFS_FS_ONDEMAND
+		kfree(ctx->opt.domain_id);
+		ctx->opt.domain_id = kstrdup(param->string, GFP_KERNEL);
+		if (!ctx->opt.domain_id)
+			return -ENOMEM;
+#else
+		errorfc(fc, "domain_id option not supported");
+#endif
+		break;
 	default:
 		return -ENOPARAM;
 	}
@@ -641,7 +668,7 @@ static int erofs_init_managed_cache(struct super_block *sb) { return 0; }
 static struct inode *erofs_nfs_get_inode(struct super_block *sb,
 					 u64 ino, u32 generation)
 {
-	return erofs_iget(sb, ino, false);
+	return erofs_iget(sb, ino);
 }
 
 static struct dentry *erofs_fh_to_dentry(struct super_block *sb,
@@ -667,7 +694,7 @@ static struct dentry *erofs_get_parent(struct dentry *child)
 	err = erofs_namei(d_inode(child), &dotdot_name, &nid, &d_type);
 	if (err)
 		return ERR_PTR(err);
-	return d_obtain_alias(erofs_iget(child->d_sb, nid, d_type == FT_DIR));
+	return d_obtain_alias(erofs_iget(child->d_sb, nid));
 }
 
 static const struct export_operations erofs_export_ops = {
@@ -676,6 +703,13 @@ static const struct export_operations erofs_export_ops = {
 	.get_parent = erofs_get_parent,
 };
 
+static int erofs_fc_fill_pseudo_super(struct super_block *sb, struct fs_context *fc)
+{
+	static const struct tree_descr empty_descr = {""};
+
+	return simple_fill_super(sb, EROFS_SUPER_MAGIC, &empty_descr);
+}
+
 static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 {
 	struct inode *inode;
@@ -695,6 +729,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_fs_info = sbi;
 	sbi->opt = ctx->opt;
 	ctx->opt.fsid = NULL;
+	ctx->opt.domain_id = NULL;
 	sbi->devs = ctx->devs;
 	ctx->devs = NULL;
 
@@ -706,11 +741,6 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 		if (err)
 			return err;
 
-		err = erofs_fscache_register_cookie(sb, &sbi->s_fscache,
-						    sbi->opt.fsid, true);
-		if (err)
-			return err;
-
 		err = super_setup_bdi(sb);
 		if (err)
 			return err;
@@ -752,7 +782,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 #endif
 
 	/* get the root inode */
-	inode = erofs_iget(sb, ROOT_NID(sbi), true);
+	inode = erofs_iget(sb, ROOT_NID(sbi));
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
@@ -781,6 +811,11 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 	return 0;
 }
 
+static int erofs_fc_anon_get_tree(struct fs_context *fc)
+{
+	return get_tree_nodev(fc, erofs_fc_fill_pseudo_super);
+}
+
 static int erofs_fc_get_tree(struct fs_context *fc)
 {
 	struct erofs_fs_context *ctx = fc->fs_private;
@@ -817,7 +852,8 @@ static int erofs_release_device_info(int id, void *ptr, void *data)
 	fs_put_dax(dif->dax_dev, NULL);
 	if (dif->bdev)
 		blkdev_put(dif->bdev, FMODE_READ | FMODE_EXCL);
-	erofs_fscache_unregister_cookie(&dif->fscache);
+	erofs_fscache_unregister_cookie(dif->fscache);
+	dif->fscache = NULL;
 	kfree(dif->path);
 	kfree(dif);
 	return 0;
@@ -838,6 +874,7 @@ static void erofs_fc_free(struct fs_context *fc)
 
 	erofs_free_dev_context(ctx->devs);
 	kfree(ctx->opt.fsid);
+	kfree(ctx->opt.domain_id);
 	kfree(ctx);
 }
 
@@ -848,10 +885,21 @@ static const struct fs_context_operations erofs_context_ops = {
 	.free		= erofs_fc_free,
 };
 
+static const struct fs_context_operations erofs_anon_context_ops = {
+	.get_tree       = erofs_fc_anon_get_tree,
+};
+
 static int erofs_init_fs_context(struct fs_context *fc)
 {
-	struct erofs_fs_context *ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	struct erofs_fs_context *ctx;
+
+	/* pseudo mount for anon inodes */
+	if (fc->sb_flags & SB_KERNMOUNT) {
+		fc->ops = &erofs_anon_context_ops;
+		return 0;
+	}
 
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 	ctx->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL);
@@ -878,8 +926,14 @@ static void erofs_kill_sb(struct super_block *sb)
 
 	WARN_ON(sb->s_magic != EROFS_SUPER_MAGIC);
 
+	/* pseudo mount for anon inodes */
+	if (sb->s_flags & SB_KERNMOUNT) {
+		kill_anon_super(sb);
+		return;
+	}
+
 	if (erofs_is_fscache_mode(sb))
-		generic_shutdown_super(sb);
+		kill_anon_super(sb);
 	else
 		kill_block_super(sb);
 
@@ -889,9 +943,9 @@ static void erofs_kill_sb(struct super_block *sb)
 
 	erofs_free_dev_context(sbi->devs);
 	fs_put_dax(sbi->dax_dev, NULL);
-	erofs_fscache_unregister_cookie(&sbi->s_fscache);
 	erofs_fscache_unregister_fs(sb);
 	kfree(sbi->opt.fsid);
+	kfree(sbi->opt.domain_id);
 	kfree(sbi);
 	sb->s_fs_info = NULL;
 }
@@ -908,11 +962,13 @@ static void erofs_put_super(struct super_block *sb)
 #ifdef CONFIG_EROFS_FS_ZIP
 	iput(sbi->managed_cache);
 	sbi->managed_cache = NULL;
+	iput(sbi->packed_inode);
+	sbi->packed_inode = NULL;
 #endif
-	erofs_fscache_unregister_cookie(&sbi->s_fscache);
+	erofs_fscache_unregister_fs(sb);
 }
 
-static struct file_system_type erofs_fs_type = {
+struct file_system_type erofs_fs_type = {
 	.owner          = THIS_MODULE,
 	.name           = "erofs",
 	.init_fs_context = erofs_init_fs_context,
@@ -1044,6 +1100,8 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root)
 #ifdef CONFIG_EROFS_FS_ONDEMAND
 	if (opt->fsid)
 		seq_printf(seq, ",fsid=%s", opt->fsid);
+	if (opt->domain_id)
+		seq_printf(seq, ",domain_id=%s", opt->domain_id);
 #endif
 	return 0;
 }
diff --git a/fs/erofs/sysfs.c b/fs/erofs/sysfs.c
index c1383e508bbe..783bb7b21b51 100644
--- a/fs/erofs/sysfs.c
+++ b/fs/erofs/sysfs.c
@@ -76,6 +76,8 @@ EROFS_ATTR_FEATURE(device_table);
 EROFS_ATTR_FEATURE(compr_head2);
 EROFS_ATTR_FEATURE(sb_chksum);
 EROFS_ATTR_FEATURE(ztailpacking);
+EROFS_ATTR_FEATURE(fragments);
+EROFS_ATTR_FEATURE(dedupe);
 
 static struct attribute *erofs_feat_attrs[] = {
 	ATTR_LIST(zero_padding),
@@ -86,6 +88,8 @@ static struct attribute *erofs_feat_attrs[] = {
 	ATTR_LIST(compr_head2),
 	ATTR_LIST(sb_chksum),
 	ATTR_LIST(ztailpacking),
+	ATTR_LIST(fragments),
+	ATTR_LIST(dedupe),
 	NULL,
 };
 ATTRIBUTE_GROUPS(erofs_feat);
@@ -201,12 +205,27 @@ static struct kobject erofs_feat = {
 int erofs_register_sysfs(struct super_block *sb)
 {
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
+	char *name;
+	char *str = NULL;
 	int err;
 
+	if (erofs_is_fscache_mode(sb)) {
+		if (sbi->opt.domain_id) {
+			str = kasprintf(GFP_KERNEL, "%s,%s", sbi->opt.domain_id,
+					sbi->opt.fsid);
+			if (!str)
+				return -ENOMEM;
+			name = str;
+		} else {
+			name = sbi->opt.fsid;
+		}
+	} else {
+		name = sb->s_id;
+	}
 	sbi->s_kobj.kset = &erofs_root;
 	init_completion(&sbi->s_kobj_unregister);
-	err = kobject_init_and_add(&sbi->s_kobj, &erofs_sb_ktype, NULL, "%s",
-			erofs_is_fscache_mode(sb) ? sbi->opt.fsid : sb->s_id);
+	err = kobject_init_and_add(&sbi->s_kobj, &erofs_sb_ktype, NULL, "%s", name);
+	kfree(str);
 	if (err)
 		goto put_sb_kobj;
 	return 0;
diff --git a/fs/erofs/xattr.h b/fs/erofs/xattr.h
index 332462c59f11..0a43c9ee9f8f 100644
--- a/fs/erofs/xattr.h
+++ b/fs/erofs/xattr.h
@@ -39,9 +39,7 @@ static inline unsigned int xattrblock_offset(struct erofs_sb_info *sbi,
 #ifdef CONFIG_EROFS_FS_XATTR
 extern const struct xattr_handler erofs_xattr_user_handler;
 extern const struct xattr_handler erofs_xattr_trusted_handler;
-#ifdef CONFIG_EROFS_FS_SECURITY
 extern const struct xattr_handler erofs_xattr_security_handler;
-#endif
 
 static inline const struct xattr_handler *erofs_xattr_handler(unsigned int idx)
 {
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 5792ca9e0d5e..cce56dde135c 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -650,6 +650,35 @@ static bool should_alloc_managed_pages(struct z_erofs_decompress_frontend *fe,
 		la < fe->headoffset;
 }
 
+static int z_erofs_read_fragment(struct inode *inode, erofs_off_t pos,
+				 struct page *page, unsigned int pageofs,
+				 unsigned int len)
+{
+	struct inode *packed_inode = EROFS_I_SB(inode)->packed_inode;
+	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
+	u8 *src, *dst;
+	unsigned int i, cnt;
+
+	pos += EROFS_I(inode)->z_fragmentoff;
+	for (i = 0; i < len; i += cnt) {
+		cnt = min_t(unsigned int, len - i,
+			    EROFS_BLKSIZ - erofs_blkoff(pos));
+		src = erofs_bread(&buf, packed_inode,
+				  erofs_blknr(pos), EROFS_KMAP);
+		if (IS_ERR(src)) {
+			erofs_put_metabuf(&buf);
+			return PTR_ERR(src);
+		}
+
+		dst = kmap_local_page(page);
+		memcpy(dst + pageofs + i, src + erofs_blkoff(pos), cnt);
+		kunmap_local(dst);
+		pos += cnt;
+	}
+	erofs_put_metabuf(&buf);
+	return 0;
+}
+
 static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
 				struct page *page, struct page **pagepool)
 {
@@ -688,7 +717,8 @@ repeat:
 		/* didn't get a valid pcluster previously (very rare) */
 	}
 
-	if (!(map->m_flags & EROFS_MAP_MAPPED))
+	if (!(map->m_flags & EROFS_MAP_MAPPED) ||
+	    map->m_flags & EROFS_MAP_FRAGMENT)
 		goto hitted;
 
 	err = z_erofs_collector_begin(fe);
@@ -735,6 +765,24 @@ hitted:
 		zero_user_segment(page, cur, end);
 		goto next_part;
 	}
+	if (map->m_flags & EROFS_MAP_FRAGMENT) {
+		unsigned int pageofs, skip, len;
+
+		if (offset > map->m_la) {
+			pageofs = 0;
+			skip = offset - map->m_la;
+		} else {
+			pageofs = map->m_la & ~PAGE_MASK;
+			skip = 0;
+		}
+		len = min_t(unsigned int, map->m_llen - skip, end - cur);
+		err = z_erofs_read_fragment(inode, skip, page, pageofs, len);
+		if (err)
+			goto out;
+		++spiltted;
+		tight = false;
+		goto next_part;
+	}
 
 	exclusive = (!cur && (!spiltted || tight));
 	if (cur)
@@ -766,6 +814,7 @@ retry:
 		fe->pcl->multibases = true;
 
 	if ((map->m_flags & EROFS_MAP_FULL_MAPPED) &&
+	    !(map->m_flags & EROFS_MAP_PARTIAL_REF) &&
 	    fe->pcl->length == map->m_llen)
 		fe->pcl->partial = false;
 	if (fe->pcl->length < offset + end - map->m_la) {
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 572f0b8151ba..44c27ef39c43 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -17,7 +17,7 @@ int z_erofs_fill_inode(struct inode *inode)
 	struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);
 
 	if (!erofs_sb_has_big_pcluster(sbi) &&
-	    !erofs_sb_has_ztailpacking(sbi) &&
+	    !erofs_sb_has_ztailpacking(sbi) && !erofs_sb_has_fragments(sbi) &&
 	    vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY) {
 		vi->z_advise = 0;
 		vi->z_algorithmtype[0] = 0;
@@ -55,10 +55,6 @@ static int z_erofs_fill_inode_lazy(struct inode *inode)
 	if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags))
 		goto out_unlock;
 
-	DBG_BUGON(!erofs_sb_has_big_pcluster(EROFS_SB(sb)) &&
-		  !erofs_sb_has_ztailpacking(EROFS_SB(sb)) &&
-		  vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY);
-
 	pos = ALIGN(iloc(EROFS_SB(sb), vi->nid) + vi->inode_isize +
 		    vi->xattr_isize, 8);
 	kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos),
@@ -69,6 +65,16 @@ static int z_erofs_fill_inode_lazy(struct inode *inode)
 	}
 
 	h = kaddr + erofs_blkoff(pos);
+	/*
+	 * if the highest bit of the 8-byte map header is set, the whole file
+	 * is stored in the packed inode. The rest bits keeps z_fragmentoff.
+	 */
+	if (h->h_clusterbits >> Z_EROFS_FRAGMENT_INODE_BIT) {
+		vi->z_advise = Z_EROFS_ADVISE_FRAGMENT_PCLUSTER;
+		vi->z_fragmentoff = le64_to_cpu(*(__le64 *)h) ^ (1ULL << 63);
+		vi->z_tailextent_headlcn = 0;
+		goto unmap_done;
+	}
 	vi->z_advise = le16_to_cpu(h->h_advise);
 	vi->z_algorithmtype[0] = h->h_algorithmtype & 15;
 	vi->z_algorithmtype[1] = h->h_algorithmtype >> 4;
@@ -123,6 +129,20 @@ unmap_done:
 		if (err < 0)
 			goto out_unlock;
 	}
+
+	if (vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER &&
+	    !(h->h_clusterbits >> Z_EROFS_FRAGMENT_INODE_BIT)) {
+		struct erofs_map_blocks map = {
+			.buf = __EROFS_BUF_INITIALIZER
+		};
+
+		vi->z_fragmentoff = le32_to_cpu(h->h_fragmentoff);
+		err = z_erofs_do_map_blocks(inode, &map,
+					    EROFS_GET_BLOCKS_FINDTAIL);
+		erofs_put_metabuf(&map.buf);
+		if (err < 0)
+			goto out_unlock;
+	}
 	/* paired with smp_mb() at the beginning of the function */
 	smp_mb();
 	set_bit(EROFS_I_Z_INITED_BIT, &vi->flags);
@@ -141,22 +161,11 @@ struct z_erofs_maprecorder {
 	u8  type, headtype;
 	u16 clusterofs;
 	u16 delta[2];
-	erofs_blk_t pblk, compressedlcs;
+	erofs_blk_t pblk, compressedblks;
 	erofs_off_t nextpackoff;
+	bool partialref;
 };
 
-static int z_erofs_reload_indexes(struct z_erofs_maprecorder *m,
-				  erofs_blk_t eblk)
-{
-	struct super_block *const sb = m->inode->i_sb;
-
-	m->kaddr = erofs_read_metabuf(&m->map->buf, sb, eblk,
-				      EROFS_KMAP_ATOMIC);
-	if (IS_ERR(m->kaddr))
-		return PTR_ERR(m->kaddr);
-	return 0;
-}
-
 static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
 					 unsigned long lcn)
 {
@@ -169,11 +178,11 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
 		lcn * sizeof(struct z_erofs_vle_decompressed_index);
 	struct z_erofs_vle_decompressed_index *di;
 	unsigned int advise, type;
-	int err;
 
-	err = z_erofs_reload_indexes(m, erofs_blknr(pos));
-	if (err)
-		return err;
+	m->kaddr = erofs_read_metabuf(&m->map->buf, inode->i_sb,
+				      erofs_blknr(pos), EROFS_KMAP_ATOMIC);
+	if (IS_ERR(m->kaddr))
+		return PTR_ERR(m->kaddr);
 
 	m->nextpackoff = pos + sizeof(struct z_erofs_vle_decompressed_index);
 	m->lcn = lcn;
@@ -192,7 +201,7 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
 				DBG_BUGON(1);
 				return -EFSCORRUPTED;
 			}
-			m->compressedlcs = m->delta[0] &
+			m->compressedblks = m->delta[0] &
 				~Z_EROFS_VLE_DI_D0_CBLKCNT;
 			m->delta[0] = 1;
 		}
@@ -201,6 +210,8 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
 	case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
 	case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1:
 	case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2:
+		if (advise & Z_EROFS_VLE_DI_PARTIAL_REF)
+			m->partialref = true;
 		m->clusterofs = le16_to_cpu(di->di_clusterofs);
 		m->pblk = le32_to_cpu(di->di_u.blkaddr);
 		break;
@@ -293,7 +304,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 				DBG_BUGON(1);
 				return -EFSCORRUPTED;
 			}
-			m->compressedlcs = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT;
+			m->compressedblks = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT;
 			m->delta[0] = 1;
 			return 0;
 		} else if (i + 1 != (int)vcnt) {
@@ -370,7 +381,6 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m,
 	unsigned int compacted_4b_initial, compacted_2b;
 	unsigned int amortizedshift;
 	erofs_off_t pos;
-	int err;
 
 	if (lclusterbits != 12)
 		return -EOPNOTSUPP;
@@ -407,9 +417,10 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m,
 	amortizedshift = 2;
 out:
 	pos += lcn * (1 << amortizedshift);
-	err = z_erofs_reload_indexes(m, erofs_blknr(pos));
-	if (err)
-		return err;
+	m->kaddr = erofs_read_metabuf(&m->map->buf, inode->i_sb,
+				      erofs_blknr(pos), EROFS_KMAP_ATOMIC);
+	if (IS_ERR(m->kaddr))
+		return PTR_ERR(m->kaddr);
 	return unpack_compacted_index(m, amortizedshift, pos, lookahead);
 }
 
@@ -497,7 +508,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 		return 0;
 	}
 	lcn = m->lcn + 1;
-	if (m->compressedlcs)
+	if (m->compressedblks)
 		goto out;
 
 	err = z_erofs_load_cluster_from_disk(m, lcn, false);
@@ -506,7 +517,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 
 	/*
 	 * If the 1st NONHEAD lcluster has already been handled initially w/o
-	 * valid compressedlcs, which means at least it mustn't be CBLKCNT, or
+	 * valid compressedblks, which means at least it mustn't be CBLKCNT, or
 	 * an internal implemenatation error is detected.
 	 *
 	 * The following code can also handle it properly anyway, but let's
@@ -523,12 +534,12 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 		 * if the 1st NONHEAD lcluster is actually PLAIN or HEAD type
 		 * rather than CBLKCNT, it's a 1 lcluster-sized pcluster.
 		 */
-		m->compressedlcs = 1;
+		m->compressedblks = 1 << (lclusterbits - LOG_BLOCK_SIZE);
 		break;
 	case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
 		if (m->delta[0] != 1)
 			goto err_bonus_cblkcnt;
-		if (m->compressedlcs)
+		if (m->compressedblks)
 			break;
 		fallthrough;
 	default:
@@ -539,7 +550,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 		return -EFSCORRUPTED;
 	}
 out:
-	map->m_plen = (u64)m->compressedlcs << lclusterbits;
+	map->m_plen = (u64)m->compressedblks << LOG_BLOCK_SIZE;
 	return 0;
 err_bonus_cblkcnt:
 	erofs_err(m->inode->i_sb,
@@ -598,6 +609,7 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 {
 	struct erofs_inode *const vi = EROFS_I(inode);
 	bool ztailpacking = vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER;
+	bool fragment = vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER;
 	struct z_erofs_maprecorder m = {
 		.inode = inode,
 		.map = map,
@@ -663,15 +675,23 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 		err = -EOPNOTSUPP;
 		goto unmap_out;
 	}
-
+	if (m.partialref)
+		map->m_flags |= EROFS_MAP_PARTIAL_REF;
 	map->m_llen = end - map->m_la;
 
-	if (flags & EROFS_GET_BLOCKS_FINDTAIL)
+	if (flags & EROFS_GET_BLOCKS_FINDTAIL) {
 		vi->z_tailextent_headlcn = m.lcn;
+		/* for non-compact indexes, fragmentoff is 64 bits */
+		if (fragment &&
+		    vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY)
+			vi->z_fragmentoff |= (u64)m.pblk << 32;
+	}
 	if (ztailpacking && m.lcn == vi->z_tailextent_headlcn) {
 		map->m_flags |= EROFS_MAP_META;
 		map->m_pa = vi->z_idataoff;
 		map->m_plen = vi->z_idata_size;
+	} else if (fragment && m.lcn == vi->z_tailextent_headlcn) {
+		map->m_flags |= EROFS_MAP_FRAGMENT;
 	} else {
 		map->m_pa = blknr_to_addr(m.pblk);
 		err = z_erofs_get_extent_compressedlen(&m, initial_lcn);
@@ -679,12 +699,18 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 			goto out;
 	}
 
-	if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN)
-		map->m_algorithmformat = Z_EROFS_COMPRESSION_SHIFTED;
-	else if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2)
+	if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN) {
+		if (vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER)
+			map->m_algorithmformat =
+				Z_EROFS_COMPRESSION_INTERLACED;
+		else
+			map->m_algorithmformat =
+				Z_EROFS_COMPRESSION_SHIFTED;
+	} else if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) {
 		map->m_algorithmformat = vi->z_algorithmtype[1];
-	else
+	} else {
 		map->m_algorithmformat = vi->z_algorithmtype[0];
+	}
 
 	if ((flags & EROFS_GET_BLOCKS_FIEMAP) ||
 	    ((flags & EROFS_GET_BLOCKS_READMORE) &&
@@ -705,10 +731,10 @@ out:
 	return err;
 }
 
-int z_erofs_map_blocks_iter(struct inode *inode,
-			    struct erofs_map_blocks *map,
+int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map,
 			    int flags)
 {
+	struct erofs_inode *const vi = EROFS_I(inode);
 	int err = 0;
 
 	trace_z_erofs_map_blocks_iter_enter(inode, map, flags);
@@ -725,6 +751,15 @@ int z_erofs_map_blocks_iter(struct inode *inode,
 	if (err)
 		goto out;
 
+	if ((vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER) &&
+	    !vi->z_tailextent_headlcn) {
+		map->m_la = 0;
+		map->m_llen = inode->i_size;
+		map->m_flags = EROFS_MAP_MAPPED | EROFS_MAP_FULL_MAPPED |
+				EROFS_MAP_FRAGMENT;
+		goto out;
+	}
+
 	err = z_erofs_do_map_blocks(inode, map, flags);
 out:
 	trace_z_erofs_map_blocks_iter_exit(inode, map, flags, err);
@@ -751,7 +786,8 @@ static int z_erofs_iomap_begin_report(struct inode *inode, loff_t offset,
 	iomap->length = map.m_llen;
 	if (map.m_flags & EROFS_MAP_MAPPED) {
 		iomap->type = IOMAP_MAPPED;
-		iomap->addr = map.m_pa;
+		iomap->addr = map.m_flags & EROFS_MAP_FRAGMENT ?
+			      IOMAP_NULL_ADDR : map.m_pa;
 	} else {
 		iomap->type = IOMAP_HOLE;
 		iomap->addr = IOMAP_NULL_ADDR;
diff --git a/fs/exec.c b/fs/exec.c
index f793221f4eb6..69a572fc57db 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -65,7 +65,6 @@
 #include <linux/io_uring.h>
 #include <linux/syscall_user_dispatch.h>
 #include <linux/coredump.h>
-#include <linux/time_namespace.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
@@ -584,11 +583,11 @@ static int copy_strings(int argc, struct user_arg_ptr argv,
 
 				if (kmapped_page) {
 					flush_dcache_page(kmapped_page);
-					kunmap(kmapped_page);
+					kunmap_local(kaddr);
 					put_arg_page(kmapped_page);
 				}
 				kmapped_page = page;
-				kaddr = kmap(kmapped_page);
+				kaddr = kmap_local_page(kmapped_page);
 				kpos = pos & PAGE_MASK;
 				flush_arg_page(bprm, kpos, kmapped_page);
 			}
@@ -602,7 +601,7 @@ static int copy_strings(int argc, struct user_arg_ptr argv,
 out:
 	if (kmapped_page) {
 		flush_dcache_page(kmapped_page);
-		kunmap(kmapped_page);
+		kunmap_local(kaddr);
 		put_arg_page(kmapped_page);
 	}
 	return ret;
@@ -880,11 +879,11 @@ int transfer_args_to_stack(struct linux_binprm *bprm,
 
 	for (index = MAX_ARG_PAGES - 1; index >= stop; index--) {
 		unsigned int offset = index == stop ? bprm->p & ~PAGE_MASK : 0;
-		char *src = kmap(bprm->page[index]) + offset;
+		char *src = kmap_local_page(bprm->page[index]) + offset;
 		sp -= PAGE_SIZE - offset;
 		if (copy_to_user((void *) sp, src, PAGE_SIZE - offset) != 0)
 			ret = -EFAULT;
-		kunmap(bprm->page[index]);
+		kunmap_local(src);
 		if (ret)
 			goto out;
 	}
@@ -958,8 +957,7 @@ struct file *open_exec(const char *name)
 }
 EXPORT_SYMBOL(open_exec);
 
-#if defined(CONFIG_HAVE_AOUT) || defined(CONFIG_BINFMT_FLAT) || \
-    defined(CONFIG_BINFMT_ELF_FDPIC)
+#if defined(CONFIG_BINFMT_FLAT) || defined(CONFIG_BINFMT_ELF_FDPIC)
 ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len)
 {
 	ssize_t res = vfs_read(file, (void __user *)addr, len, &pos);
@@ -979,12 +977,10 @@ static int exec_mmap(struct mm_struct *mm)
 {
 	struct task_struct *tsk;
 	struct mm_struct *old_mm, *active_mm;
-	bool vfork;
 	int ret;
 
 	/* Notify parent that we're no longer interested in the old VM */
 	tsk = current;
-	vfork = !!tsk->vfork_done;
 	old_mm = current->mm;
 	exec_mm_release(tsk, old_mm);
 	if (old_mm)
@@ -1029,10 +1025,6 @@ static int exec_mmap(struct mm_struct *mm)
 	tsk->mm->vmacache_seqnum = 0;
 	vmacache_flush(tsk);
 	task_unlock(tsk);
-
-	if (vfork)
-		timens_on_fork(tsk->nsproxy, tsk);
-
 	if (old_mm) {
 		mmap_read_unlock(old_mm);
 		BUG_ON(active_mm != old_mm);
@@ -1686,13 +1678,13 @@ int remove_arg_zero(struct linux_binprm *bprm)
 			ret = -EFAULT;
 			goto out;
 		}
-		kaddr = kmap_atomic(page);
+		kaddr = kmap_local_page(page);
 
 		for (; offset < PAGE_SIZE && kaddr[offset];
 				offset++, bprm->p++)
 			;
 
-		kunmap_atomic(kaddr);
+		kunmap_local(kaddr);
 		put_arg_page(page);
 	} while (offset == PAGE_SIZE);
 
diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c
index ee0b7cf51157..41ae4cce1f42 100644
--- a/fs/exfat/fatent.c
+++ b/fs/exfat/fatent.c
@@ -270,8 +270,7 @@ int exfat_zeroed_cluster(struct inode *dir, unsigned int clu)
 	struct super_block *sb = dir->i_sb;
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
 	struct buffer_head *bh;
-	sector_t blknr, last_blknr;
-	int i;
+	sector_t blknr, last_blknr, i;
 
 	blknr = exfat_cluster_to_sector(sbi, clu);
 	last_blknr = blknr + sbi->sect_per_clus;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 9bca5565547b..e5f2f5ca5120 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -167,8 +167,6 @@ enum SHIFT_DIRECTION {
 #define EXT4_MB_CR0_OPTIMIZED		0x8000
 /* Avg fragment size rb tree lookup succeeded at least once for cr = 1 */
 #define EXT4_MB_CR1_OPTIMIZED		0x00010000
-/* Perform linear traversal for one group */
-#define EXT4_MB_SEARCH_NEXT_LINEAR	0x00020000
 struct ext4_allocation_request {
 	/* target inode for block we're allocating */
 	struct inode *inode;
@@ -1600,8 +1598,8 @@ struct ext4_sb_info {
 	struct list_head s_discard_list;
 	struct work_struct s_discard_work;
 	atomic_t s_retry_alloc_pending;
-	struct rb_root s_mb_avg_fragment_size_root;
-	rwlock_t s_mb_rb_lock;
+	struct list_head *s_mb_avg_fragment_size;
+	rwlock_t *s_mb_avg_fragment_size_locks;
 	struct list_head *s_mb_largest_free_orders;
 	rwlock_t *s_mb_largest_free_orders_locks;
 
@@ -2979,6 +2977,7 @@ extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 extern int  ext4_write_inode(struct inode *, struct writeback_control *);
 extern int  ext4_setattr(struct user_namespace *, struct dentry *,
 			 struct iattr *);
+extern u32  ext4_dio_alignment(struct inode *inode);
 extern int  ext4_getattr(struct user_namespace *, const struct path *,
 			 struct kstat *, u32, unsigned int);
 extern void ext4_evict_inode(struct inode *);
@@ -3413,6 +3412,8 @@ struct ext4_group_info {
 	ext4_grpblk_t	bb_first_free;	/* first free block */
 	ext4_grpblk_t	bb_free;	/* total free blocks */
 	ext4_grpblk_t	bb_fragments;	/* nr of freespace fragments */
+	int		bb_avg_fragment_size_order;	/* order of average
+							   fragment in BG */
 	ext4_grpblk_t	bb_largest_free_order;/* order of largest frag in BG */
 	ext4_group_t	bb_group;	/* Group number */
 	struct          list_head bb_prealloc_list;
@@ -3420,7 +3421,7 @@ struct ext4_group_info {
 	void            *bb_bitmap;
 #endif
 	struct rw_semaphore alloc_sem;
-	struct rb_node	bb_avg_fragment_size_rb;
+	struct list_head bb_avg_fragment_size_node;
 	struct list_head bb_largest_free_order_node;
 	ext4_grpblk_t	bb_counters[];	/* Nr of free power-of-two-block
 					 * regions, index is order.
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index c148bb97b527..5235974126bd 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -460,6 +460,10 @@ static int __ext4_ext_check(const char *function, unsigned int line,
 		error_msg = "invalid eh_entries";
 		goto corrupted;
 	}
+	if (unlikely((eh->eh_entries == 0) && (depth > 0))) {
+		error_msg = "eh_entries is 0 but eh_depth is > 0";
+		goto corrupted;
+	}
 	if (!ext4_valid_extent_entries(inode, eh, lblk, &pblk, depth)) {
 		error_msg = "invalid extent entries";
 		goto corrupted;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 109d07629f81..8bb1c35fd6dd 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -36,19 +36,34 @@
 #include "acl.h"
 #include "truncate.h"
 
-static bool ext4_dio_supported(struct kiocb *iocb, struct iov_iter *iter)
+/*
+ * Returns %true if the given DIO request should be attempted with DIO, or
+ * %false if it should fall back to buffered I/O.
+ *
+ * DIO isn't well specified; when it's unsupported (either due to the request
+ * being misaligned, or due to the file not supporting DIO at all), filesystems
+ * either fall back to buffered I/O or return EINVAL.  For files that don't use
+ * any special features like encryption or verity, ext4 has traditionally
+ * returned EINVAL for misaligned DIO.  iomap_dio_rw() uses this convention too.
+ * In this case, we should attempt the DIO, *not* fall back to buffered I/O.
+ *
+ * In contrast, in cases where DIO is unsupported due to ext4 features, ext4
+ * traditionally falls back to buffered I/O.
+ *
+ * This function implements the traditional ext4 behavior in all these cases.
+ */
+static bool ext4_should_use_dio(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
+	u32 dio_align = ext4_dio_alignment(inode);
 
-	if (!fscrypt_dio_supported(iocb, iter))
-		return false;
-	if (fsverity_active(inode))
+	if (dio_align == 0)
 		return false;
-	if (ext4_should_journal_data(inode))
-		return false;
-	if (ext4_has_inline_data(inode))
-		return false;
-	return true;
+
+	if (dio_align == 1)
+		return true;
+
+	return IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(iter), dio_align);
 }
 
 static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
@@ -63,7 +78,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		inode_lock_shared(inode);
 	}
 
-	if (!ext4_dio_supported(iocb, to)) {
+	if (!ext4_should_use_dio(iocb, to)) {
 		inode_unlock_shared(inode);
 		/*
 		 * Fallback to buffered I/O if the operation being performed on
@@ -511,7 +526,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	}
 
 	/* Fallback to buffered I/O if the inode does not support direct I/O. */
-	if (!ext4_dio_supported(iocb, from)) {
+	if (!ext4_should_use_dio(iocb, from)) {
 		if (ilock_shared)
 			inode_unlock_shared(inode);
 		else
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f73e5eb43eae..208b87ce8858 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -510,7 +510,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 		goto fallback;
 	}
 
-	max_dirs = ndirs / ngroups + inodes_per_group / 16;
+	max_dirs = ndirs / ngroups + inodes_per_group*flex_size / 16;
 	min_inodes = avefreei - inodes_per_group*flex_size / 4;
 	if (min_inodes < 1)
 		min_inodes = 1;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 601214453c3a..364774230d87 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5550,6 +5550,22 @@ err_out:
 	return error;
 }
 
+u32 ext4_dio_alignment(struct inode *inode)
+{
+	if (fsverity_active(inode))
+		return 0;
+	if (ext4_should_journal_data(inode))
+		return 0;
+	if (ext4_has_inline_data(inode))
+		return 0;
+	if (IS_ENCRYPTED(inode)) {
+		if (!fscrypt_dio_supported(inode))
+			return 0;
+		return i_blocksize(inode);
+	}
+	return 1; /* use the iomap defaults */
+}
+
 int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path,
 		 struct kstat *stat, u32 request_mask, unsigned int query_flags)
 {
@@ -5565,6 +5581,27 @@ int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path,
 		stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
 	}
 
+	/*
+	 * Return the DIO alignment restrictions if requested.  We only return
+	 * this information when requested, since on encrypted files it might
+	 * take a fair bit of work to get if the file wasn't opened recently.
+	 */
+	if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) {
+		u32 dio_align = ext4_dio_alignment(inode);
+
+		stat->result_mask |= STATX_DIOALIGN;
+		if (dio_align == 1) {
+			struct block_device *bdev = inode->i_sb->s_bdev;
+
+			/* iomap defaults */
+			stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
+			stat->dio_offset_align = bdev_logical_block_size(bdev);
+		} else {
+			stat->dio_mem_align = dio_align;
+			stat->dio_offset_align = dio_align;
+		}
+	}
+
 	flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
 	if (flags & EXT4_APPEND_FL)
 		stat->attributes |= STATX_ATTR_APPEND;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index bd8f8b5c3d30..9dad93059945 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -140,13 +140,15 @@
  *    number of buddy bitmap orders possible) number of lists. Group-infos are
  *    placed in appropriate lists.
  *
- * 2) Average fragment size rb tree (sbi->s_mb_avg_fragment_size_root)
+ * 2) Average fragment size lists (sbi->s_mb_avg_fragment_size)
  *
- *    Locking: sbi->s_mb_rb_lock (rwlock)
+ *    Locking: sbi->s_mb_avg_fragment_size_locks(array of rw locks)
  *
- *    This is a red black tree consisting of group infos and the tree is sorted
- *    by average fragment sizes (which is calculated as ext4_group_info->bb_free
- *    / ext4_group_info->bb_fragments).
+ *    This is an array of lists where in the i-th list there are groups with
+ *    average fragment size >= 2^i and < 2^(i+1). The average fragment size
+ *    is computed as ext4_group_info->bb_free / ext4_group_info->bb_fragments.
+ *    Note that we don't bother with a special list for completely empty groups
+ *    so we only have MB_NUM_ORDERS(sb) lists.
  *
  * When "mb_optimize_scan" mount option is set, mballoc consults the above data
  * structures to decide the order in which groups are to be traversed for
@@ -160,7 +162,8 @@
  *
  * At CR = 1, we only consider groups where average fragment size > request
  * size. So, we lookup a group which has average fragment size just above or
- * equal to request size using our rb tree (data structure 2) in O(log N) time.
+ * equal to request size using our average fragment size group lists (data
+ * structure 2) in O(1) time.
  *
  * If "mb_optimize_scan" mount option is not set, mballoc traverses groups in
  * linear order which requires O(N) search time for each CR 0 and CR 1 phase.
@@ -802,65 +805,51 @@ static void ext4_mb_mark_free_simple(struct super_block *sb,
 	}
 }
 
-static void ext4_mb_rb_insert(struct rb_root *root, struct rb_node *new,
-			int (*cmp)(struct rb_node *, struct rb_node *))
+static int mb_avg_fragment_size_order(struct super_block *sb, ext4_grpblk_t len)
 {
-	struct rb_node **iter = &root->rb_node, *parent = NULL;
+	int order;
 
-	while (*iter) {
-		parent = *iter;
-		if (cmp(new, *iter) > 0)
-			iter = &((*iter)->rb_left);
-		else
-			iter = &((*iter)->rb_right);
-	}
-
-	rb_link_node(new, parent, iter);
-	rb_insert_color(new, root);
-}
-
-static int
-ext4_mb_avg_fragment_size_cmp(struct rb_node *rb1, struct rb_node *rb2)
-{
-	struct ext4_group_info *grp1 = rb_entry(rb1,
-						struct ext4_group_info,
-						bb_avg_fragment_size_rb);
-	struct ext4_group_info *grp2 = rb_entry(rb2,
-						struct ext4_group_info,
-						bb_avg_fragment_size_rb);
-	int num_frags_1, num_frags_2;
-
-	num_frags_1 = grp1->bb_fragments ?
-		grp1->bb_free / grp1->bb_fragments : 0;
-	num_frags_2 = grp2->bb_fragments ?
-		grp2->bb_free / grp2->bb_fragments : 0;
-
-	return (num_frags_2 - num_frags_1);
+	/*
+	 * We don't bother with a special lists groups with only 1 block free
+	 * extents and for completely empty groups.
+	 */
+	order = fls(len) - 2;
+	if (order < 0)
+		return 0;
+	if (order == MB_NUM_ORDERS(sb))
+		order--;
+	return order;
 }
 
-/*
- * Reinsert grpinfo into the avg_fragment_size tree with new average
- * fragment size.
- */
+/* Move group to appropriate avg_fragment_size list */
 static void
 mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int new_order;
 
 	if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0)
 		return;
 
-	write_lock(&sbi->s_mb_rb_lock);
-	if (!RB_EMPTY_NODE(&grp->bb_avg_fragment_size_rb)) {
-		rb_erase(&grp->bb_avg_fragment_size_rb,
-				&sbi->s_mb_avg_fragment_size_root);
-		RB_CLEAR_NODE(&grp->bb_avg_fragment_size_rb);
-	}
+	new_order = mb_avg_fragment_size_order(sb,
+					grp->bb_free / grp->bb_fragments);
+	if (new_order == grp->bb_avg_fragment_size_order)
+		return;
 
-	ext4_mb_rb_insert(&sbi->s_mb_avg_fragment_size_root,
-		&grp->bb_avg_fragment_size_rb,
-		ext4_mb_avg_fragment_size_cmp);
-	write_unlock(&sbi->s_mb_rb_lock);
+	if (grp->bb_avg_fragment_size_order != -1) {
+		write_lock(&sbi->s_mb_avg_fragment_size_locks[
+					grp->bb_avg_fragment_size_order]);
+		list_del(&grp->bb_avg_fragment_size_node);
+		write_unlock(&sbi->s_mb_avg_fragment_size_locks[
+					grp->bb_avg_fragment_size_order]);
+	}
+	grp->bb_avg_fragment_size_order = new_order;
+	write_lock(&sbi->s_mb_avg_fragment_size_locks[
+					grp->bb_avg_fragment_size_order]);
+	list_add_tail(&grp->bb_avg_fragment_size_node,
+		&sbi->s_mb_avg_fragment_size[grp->bb_avg_fragment_size_order]);
+	write_unlock(&sbi->s_mb_avg_fragment_size_locks[
+					grp->bb_avg_fragment_size_order]);
 }
 
 /*
@@ -909,86 +898,55 @@ static void ext4_mb_choose_next_group_cr0(struct ext4_allocation_context *ac,
 		*new_cr = 1;
 	} else {
 		*group = grp->bb_group;
-		ac->ac_last_optimal_group = *group;
 		ac->ac_flags |= EXT4_MB_CR0_OPTIMIZED;
 	}
 }
 
 /*
- * Choose next group by traversing average fragment size tree. Updates *new_cr
- * if cr lvel needs an update. Sets EXT4_MB_SEARCH_NEXT_LINEAR to indicate that
- * the linear search should continue for one iteration since there's lock
- * contention on the rb tree lock.
+ * Choose next group by traversing average fragment size list of suitable
+ * order. Updates *new_cr if cr level needs an update.
  */
 static void ext4_mb_choose_next_group_cr1(struct ext4_allocation_context *ac,
 		int *new_cr, ext4_group_t *group, ext4_group_t ngroups)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
-	int avg_fragment_size, best_so_far;
-	struct rb_node *node, *found;
-	struct ext4_group_info *grp;
-
-	/*
-	 * If there is contention on the lock, instead of waiting for the lock
-	 * to become available, just continue searching lineraly. We'll resume
-	 * our rb tree search later starting at ac->ac_last_optimal_group.
-	 */
-	if (!read_trylock(&sbi->s_mb_rb_lock)) {
-		ac->ac_flags |= EXT4_MB_SEARCH_NEXT_LINEAR;
-		return;
-	}
+	struct ext4_group_info *grp = NULL, *iter;
+	int i;
 
 	if (unlikely(ac->ac_flags & EXT4_MB_CR1_OPTIMIZED)) {
 		if (sbi->s_mb_stats)
 			atomic_inc(&sbi->s_bal_cr1_bad_suggestions);
-		/* We have found something at CR 1 in the past */
-		grp = ext4_get_group_info(ac->ac_sb, ac->ac_last_optimal_group);
-		for (found = rb_next(&grp->bb_avg_fragment_size_rb); found != NULL;
-		     found = rb_next(found)) {
-			grp = rb_entry(found, struct ext4_group_info,
-				       bb_avg_fragment_size_rb);
+	}
+
+	for (i = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len);
+	     i < MB_NUM_ORDERS(ac->ac_sb); i++) {
+		if (list_empty(&sbi->s_mb_avg_fragment_size[i]))
+			continue;
+		read_lock(&sbi->s_mb_avg_fragment_size_locks[i]);
+		if (list_empty(&sbi->s_mb_avg_fragment_size[i])) {
+			read_unlock(&sbi->s_mb_avg_fragment_size_locks[i]);
+			continue;
+		}
+		list_for_each_entry(iter, &sbi->s_mb_avg_fragment_size[i],
+				    bb_avg_fragment_size_node) {
 			if (sbi->s_mb_stats)
 				atomic64_inc(&sbi->s_bal_cX_groups_considered[1]);
-			if (likely(ext4_mb_good_group(ac, grp->bb_group, 1)))
+			if (likely(ext4_mb_good_group(ac, iter->bb_group, 1))) {
+				grp = iter;
 				break;
-		}
-		goto done;
-	}
-
-	node = sbi->s_mb_avg_fragment_size_root.rb_node;
-	best_so_far = 0;
-	found = NULL;
-
-	while (node) {
-		grp = rb_entry(node, struct ext4_group_info,
-			       bb_avg_fragment_size_rb);
-		avg_fragment_size = 0;
-		if (ext4_mb_good_group(ac, grp->bb_group, 1)) {
-			avg_fragment_size = grp->bb_fragments ?
-				grp->bb_free / grp->bb_fragments : 0;
-			if (!best_so_far || avg_fragment_size < best_so_far) {
-				best_so_far = avg_fragment_size;
-				found = node;
 			}
 		}
-		if (avg_fragment_size > ac->ac_g_ex.fe_len)
-			node = node->rb_right;
-		else
-			node = node->rb_left;
+		read_unlock(&sbi->s_mb_avg_fragment_size_locks[i]);
+		if (grp)
+			break;
 	}
 
-done:
-	if (found) {
-		grp = rb_entry(found, struct ext4_group_info,
-			       bb_avg_fragment_size_rb);
+	if (grp) {
 		*group = grp->bb_group;
 		ac->ac_flags |= EXT4_MB_CR1_OPTIMIZED;
 	} else {
 		*new_cr = 2;
 	}
-
-	read_unlock(&sbi->s_mb_rb_lock);
-	ac->ac_last_optimal_group = *group;
 }
 
 static inline int should_optimize_scan(struct ext4_allocation_context *ac)
@@ -1017,11 +975,6 @@ next_linear_group(struct ext4_allocation_context *ac, int group, int ngroups)
 		goto inc_and_return;
 	}
 
-	if (ac->ac_flags & EXT4_MB_SEARCH_NEXT_LINEAR) {
-		ac->ac_flags &= ~EXT4_MB_SEARCH_NEXT_LINEAR;
-		goto inc_and_return;
-	}
-
 	return group;
 inc_and_return:
 	/*
@@ -1049,8 +1002,10 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac,
 {
 	*new_cr = ac->ac_criteria;
 
-	if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining)
+	if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining) {
+		*group = next_linear_group(ac, *group, ngroups);
 		return;
+	}
 
 	if (*new_cr == 0) {
 		ext4_mb_choose_next_group_cr0(ac, new_cr, group, ngroups);
@@ -1075,23 +1030,25 @@ mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp)
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	int i;
 
-	if (test_opt2(sb, MB_OPTIMIZE_SCAN) && grp->bb_largest_free_order >= 0) {
+	for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--)
+		if (grp->bb_counters[i] > 0)
+			break;
+	/* No need to move between order lists? */
+	if (!test_opt2(sb, MB_OPTIMIZE_SCAN) ||
+	    i == grp->bb_largest_free_order) {
+		grp->bb_largest_free_order = i;
+		return;
+	}
+
+	if (grp->bb_largest_free_order >= 0) {
 		write_lock(&sbi->s_mb_largest_free_orders_locks[
 					      grp->bb_largest_free_order]);
 		list_del_init(&grp->bb_largest_free_order_node);
 		write_unlock(&sbi->s_mb_largest_free_orders_locks[
 					      grp->bb_largest_free_order]);
 	}
-	grp->bb_largest_free_order = -1; /* uninit */
-
-	for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) {
-		if (grp->bb_counters[i] > 0) {
-			grp->bb_largest_free_order = i;
-			break;
-		}
-	}
-	if (test_opt2(sb, MB_OPTIMIZE_SCAN) &&
-	    grp->bb_largest_free_order >= 0 && grp->bb_free) {
+	grp->bb_largest_free_order = i;
+	if (grp->bb_largest_free_order >= 0 && grp->bb_free) {
 		write_lock(&sbi->s_mb_largest_free_orders_locks[
 					      grp->bb_largest_free_order]);
 		list_add_tail(&grp->bb_largest_free_order_node,
@@ -1148,13 +1105,13 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 	}
 	mb_set_largest_free_order(sb, grp);
+	mb_update_avg_fragment_size(sb, grp);
 
 	clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
 
 	period = get_cycles() - period;
 	atomic_inc(&sbi->s_mb_buddies_generated);
 	atomic64_add(period, &sbi->s_mb_generation_time);
-	mb_update_avg_fragment_size(sb, grp);
 }
 
 /* The buddy information is attached the buddy cache inode
@@ -2636,7 +2593,7 @@ static noinline_for_stack int
 ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 {
 	ext4_group_t prefetch_grp = 0, ngroups, group, i;
-	int cr = -1;
+	int cr = -1, new_cr;
 	int err = 0, first_err = 0;
 	unsigned int nr = 0, prefetch_ios = 0;
 	struct ext4_sb_info *sbi;
@@ -2707,17 +2664,14 @@ repeat:
 		 * from the goal value specified
 		 */
 		group = ac->ac_g_ex.fe_group;
-		ac->ac_last_optimal_group = group;
 		ac->ac_groups_linear_remaining = sbi->s_mb_max_linear_groups;
 		prefetch_grp = group;
 
-		for (i = 0; i < ngroups; group = next_linear_group(ac, group, ngroups),
-			     i++) {
-			int ret = 0, new_cr;
+		for (i = 0, new_cr = cr; i < ngroups; i++,
+		     ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups)) {
+			int ret = 0;
 
 			cond_resched();
-
-			ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups);
 			if (new_cr != cr) {
 				cr = new_cr;
 				goto repeat;
@@ -2991,9 +2945,7 @@ __acquires(&EXT4_SB(sb)->s_mb_rb_lock)
 	struct super_block *sb = pde_data(file_inode(seq->file));
 	unsigned long position;
 
-	read_lock(&EXT4_SB(sb)->s_mb_rb_lock);
-
-	if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1)
+	if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb))
 		return NULL;
 	position = *pos + 1;
 	return (void *) ((unsigned long) position);
@@ -3005,7 +2957,7 @@ static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, lof
 	unsigned long position;
 
 	++*pos;
-	if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1)
+	if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb))
 		return NULL;
 	position = *pos + 1;
 	return (void *) ((unsigned long) position);
@@ -3017,29 +2969,22 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v)
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	unsigned long position = ((unsigned long) v);
 	struct ext4_group_info *grp;
-	struct rb_node *n;
-	unsigned int count, min, max;
+	unsigned int count;
 
 	position--;
 	if (position >= MB_NUM_ORDERS(sb)) {
-		seq_puts(seq, "fragment_size_tree:\n");
-		n = rb_first(&sbi->s_mb_avg_fragment_size_root);
-		if (!n) {
-			seq_puts(seq, "\ttree_min: 0\n\ttree_max: 0\n\ttree_nodes: 0\n");
-			return 0;
-		}
-		grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb);
-		min = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0;
-		count = 1;
-		while (rb_next(n)) {
-			count++;
-			n = rb_next(n);
-		}
-		grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb);
-		max = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0;
+		position -= MB_NUM_ORDERS(sb);
+		if (position == 0)
+			seq_puts(seq, "avg_fragment_size_lists:\n");
 
-		seq_printf(seq, "\ttree_min: %u\n\ttree_max: %u\n\ttree_nodes: %u\n",
-			   min, max, count);
+		count = 0;
+		read_lock(&sbi->s_mb_avg_fragment_size_locks[position]);
+		list_for_each_entry(grp, &sbi->s_mb_avg_fragment_size[position],
+				    bb_avg_fragment_size_node)
+			count++;
+		read_unlock(&sbi->s_mb_avg_fragment_size_locks[position]);
+		seq_printf(seq, "\tlist_order_%u_groups: %u\n",
+					(unsigned int)position, count);
 		return 0;
 	}
 
@@ -3049,9 +2994,11 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v)
 		seq_puts(seq, "max_free_order_lists:\n");
 	}
 	count = 0;
+	read_lock(&sbi->s_mb_largest_free_orders_locks[position]);
 	list_for_each_entry(grp, &sbi->s_mb_largest_free_orders[position],
 			    bb_largest_free_order_node)
 		count++;
+	read_unlock(&sbi->s_mb_largest_free_orders_locks[position]);
 	seq_printf(seq, "\tlist_order_%u_groups: %u\n",
 		   (unsigned int)position, count);
 
@@ -3059,11 +3006,7 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v)
 }
 
 static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v)
-__releases(&EXT4_SB(sb)->s_mb_rb_lock)
 {
-	struct super_block *sb = pde_data(file_inode(seq->file));
-
-	read_unlock(&EXT4_SB(sb)->s_mb_rb_lock);
 }
 
 const struct seq_operations ext4_mb_seq_structs_summary_ops = {
@@ -3176,8 +3119,9 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
 	init_rwsem(&meta_group_info[i]->alloc_sem);
 	meta_group_info[i]->bb_free_root = RB_ROOT;
 	INIT_LIST_HEAD(&meta_group_info[i]->bb_largest_free_order_node);
-	RB_CLEAR_NODE(&meta_group_info[i]->bb_avg_fragment_size_rb);
+	INIT_LIST_HEAD(&meta_group_info[i]->bb_avg_fragment_size_node);
 	meta_group_info[i]->bb_largest_free_order = -1;  /* uninit */
+	meta_group_info[i]->bb_avg_fragment_size_order = -1;  /* uninit */
 	meta_group_info[i]->bb_group = group;
 
 	mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group);
@@ -3426,7 +3370,24 @@ int ext4_mb_init(struct super_block *sb)
 		i++;
 	} while (i < MB_NUM_ORDERS(sb));
 
-	sbi->s_mb_avg_fragment_size_root = RB_ROOT;
+	sbi->s_mb_avg_fragment_size =
+		kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head),
+			GFP_KERNEL);
+	if (!sbi->s_mb_avg_fragment_size) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	sbi->s_mb_avg_fragment_size_locks =
+		kmalloc_array(MB_NUM_ORDERS(sb), sizeof(rwlock_t),
+			GFP_KERNEL);
+	if (!sbi->s_mb_avg_fragment_size_locks) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	for (i = 0; i < MB_NUM_ORDERS(sb); i++) {
+		INIT_LIST_HEAD(&sbi->s_mb_avg_fragment_size[i]);
+		rwlock_init(&sbi->s_mb_avg_fragment_size_locks[i]);
+	}
 	sbi->s_mb_largest_free_orders =
 		kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head),
 			GFP_KERNEL);
@@ -3445,7 +3406,6 @@ int ext4_mb_init(struct super_block *sb)
 		INIT_LIST_HEAD(&sbi->s_mb_largest_free_orders[i]);
 		rwlock_init(&sbi->s_mb_largest_free_orders_locks[i]);
 	}
-	rwlock_init(&sbi->s_mb_rb_lock);
 
 	spin_lock_init(&sbi->s_md_lock);
 	sbi->s_mb_free_pending = 0;
@@ -3516,6 +3476,8 @@ out_free_locality_groups:
 	free_percpu(sbi->s_locality_groups);
 	sbi->s_locality_groups = NULL;
 out:
+	kfree(sbi->s_mb_avg_fragment_size);
+	kfree(sbi->s_mb_avg_fragment_size_locks);
 	kfree(sbi->s_mb_largest_free_orders);
 	kfree(sbi->s_mb_largest_free_orders_locks);
 	kfree(sbi->s_mb_offsets);
@@ -3582,6 +3544,8 @@ int ext4_mb_release(struct super_block *sb)
 		kvfree(group_info);
 		rcu_read_unlock();
 	}
+	kfree(sbi->s_mb_avg_fragment_size);
+	kfree(sbi->s_mb_avg_fragment_size_locks);
 	kfree(sbi->s_mb_largest_free_orders);
 	kfree(sbi->s_mb_largest_free_orders_locks);
 	kfree(sbi->s_mb_offsets);
@@ -5193,6 +5157,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	int bsbits = ac->ac_sb->s_blocksize_bits;
 	loff_t size, isize;
+	bool inode_pa_eligible, group_pa_eligible;
 
 	if (!(ac->ac_flags & EXT4_MB_HINT_DATA))
 		return;
@@ -5200,25 +5165,27 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
 	if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))
 		return;
 
+	group_pa_eligible = sbi->s_mb_group_prealloc > 0;
+	inode_pa_eligible = true;
 	size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len);
 	isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1)
 		>> bsbits;
 
+	/* No point in using inode preallocation for closed files */
 	if ((size == isize) && !ext4_fs_is_busy(sbi) &&
-	    !inode_is_open_for_write(ac->ac_inode)) {
-		ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC;
-		return;
-	}
+	    !inode_is_open_for_write(ac->ac_inode))
+		inode_pa_eligible = false;
 
-	if (sbi->s_mb_group_prealloc <= 0) {
-		ac->ac_flags |= EXT4_MB_STREAM_ALLOC;
-		return;
-	}
-
-	/* don't use group allocation for large files */
 	size = max(size, isize);
-	if (size > sbi->s_mb_stream_request) {
-		ac->ac_flags |= EXT4_MB_STREAM_ALLOC;
+	/* Don't use group allocation for large files */
+	if (size > sbi->s_mb_stream_request)
+		group_pa_eligible = false;
+
+	if (!group_pa_eligible) {
+		if (inode_pa_eligible)
+			ac->ac_flags |= EXT4_MB_STREAM_ALLOC;
+		else
+			ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC;
 		return;
 	}
 
@@ -5565,6 +5532,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 	ext4_fsblk_t block = 0;
 	unsigned int inquota = 0;
 	unsigned int reserv_clstrs = 0;
+	int retries = 0;
 	u64 seq;
 
 	might_sleep();
@@ -5667,7 +5635,8 @@ repeat:
 			ar->len = ac->ac_b_ex.fe_len;
 		}
 	} else {
-		if (ext4_mb_discard_preallocations_should_retry(sb, ac, &seq))
+		if (++retries < 3 &&
+		    ext4_mb_discard_preallocations_should_retry(sb, ac, &seq))
 			goto repeat;
 		/*
 		 * If block allocation fails then the pa allocated above
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 39da92ceabf8..dcda2a943cee 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -178,7 +178,6 @@ struct ext4_allocation_context {
 	/* copy of the best found extent taken before preallocation efforts */
 	struct ext4_free_extent ac_f_ex;
 
-	ext4_group_t ac_last_optimal_group;
 	__u32 ac_groups_considered;
 	__u32 ac_flags;		/* allocation hints */
 	__u16 ac_groups_scanned;
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index e02a5f14e021..3d21eae267fc 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -75,7 +75,7 @@ static void __read_end_io(struct bio *bio)
 	bio_for_each_segment_all(bv, bio, iter_all) {
 		page = bv->bv_page;
 
-		/* PG_error was set if any post_read step failed */
+		/* PG_error was set if verity failed. */
 		if (bio->bi_status || PageError(page)) {
 			ClearPageUptodate(page);
 			/* will re-read again later */
@@ -96,10 +96,12 @@ static void decrypt_work(struct work_struct *work)
 {
 	struct bio_post_read_ctx *ctx =
 		container_of(work, struct bio_post_read_ctx, work);
+	struct bio *bio = ctx->bio;
 
-	fscrypt_decrypt_bio(ctx->bio);
-
-	bio_post_read_processing(ctx);
+	if (fscrypt_decrypt_bio(bio))
+		bio_post_read_processing(ctx);
+	else
+		__read_end_io(bio);
 }
 
 static void verity_work(struct work_struct *work)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index aa3ccddfa037..93cc2ec51c2a 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -139,7 +139,7 @@ static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
 			continue;
 		}
 
-		/* PG_error was set if decryption or verity failed. */
+		/* PG_error was set if verity failed. */
 		if (bio->bi_status || PageError(page)) {
 			ClearPageUptodate(page);
 			/* will re-read again later */
@@ -185,7 +185,7 @@ static void f2fs_verify_bio(struct work_struct *work)
 			struct page *page = bv->bv_page;
 
 			if (!f2fs_is_compressed_page(page) &&
-			    !PageError(page) && !fsverity_verify_page(page))
+			    !fsverity_verify_page(page))
 				SetPageError(page);
 		}
 	} else {
@@ -236,10 +236,9 @@ static void f2fs_handle_step_decompress(struct bio_post_read_ctx *ctx,
 	bio_for_each_segment_all(bv, ctx->bio, iter_all) {
 		struct page *page = bv->bv_page;
 
-		/* PG_error was set if decryption failed. */
 		if (f2fs_is_compressed_page(page))
-			f2fs_end_read_compressed_page(page, PageError(page),
-						blkaddr, in_task);
+			f2fs_end_read_compressed_page(page, false, blkaddr,
+						      in_task);
 		else
 			all_compressed = false;
 
@@ -259,14 +258,17 @@ static void f2fs_post_read_work(struct work_struct *work)
 {
 	struct bio_post_read_ctx *ctx =
 		container_of(work, struct bio_post_read_ctx, work);
+	struct bio *bio = ctx->bio;
 
-	if (ctx->enabled_steps & STEP_DECRYPT)
-		fscrypt_decrypt_bio(ctx->bio);
+	if ((ctx->enabled_steps & STEP_DECRYPT) && !fscrypt_decrypt_bio(bio)) {
+		f2fs_finish_read_bio(bio, true);
+		return;
+	}
 
 	if (ctx->enabled_steps & STEP_DECOMPRESS)
 		f2fs_handle_step_decompress(ctx, true);
 
-	f2fs_verify_and_finish_bio(ctx->bio, true);
+	f2fs_verify_and_finish_bio(bio, true);
 }
 
 static void f2fs_read_end_io(struct bio *bio)
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 3c7cdb70fe2e..aea816a133a8 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -4471,17 +4471,6 @@ static inline void f2fs_i_compr_blocks_update(struct inode *inode,
 	f2fs_mark_inode_dirty_sync(inode, true);
 }
 
-static inline int block_unaligned_IO(struct inode *inode,
-				struct kiocb *iocb, struct iov_iter *iter)
-{
-	unsigned int i_blkbits = READ_ONCE(inode->i_blkbits);
-	unsigned int blocksize_mask = (1 << i_blkbits) - 1;
-	loff_t offset = iocb->ki_pos;
-	unsigned long align = offset | iov_iter_alignment(iter);
-
-	return align & blocksize_mask;
-}
-
 static inline bool f2fs_allow_multi_device_dio(struct f2fs_sb_info *sbi,
 								int flag)
 {
@@ -4492,35 +4481,6 @@ static inline bool f2fs_allow_multi_device_dio(struct f2fs_sb_info *sbi,
 	return sbi->aligned_blksize;
 }
 
-static inline bool f2fs_force_buffered_io(struct inode *inode,
-				struct kiocb *iocb, struct iov_iter *iter)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	int rw = iov_iter_rw(iter);
-
-	if (!fscrypt_dio_supported(iocb, iter))
-		return true;
-	if (fsverity_active(inode))
-		return true;
-	if (f2fs_compressed_file(inode))
-		return true;
-
-	/* disallow direct IO if any of devices has unaligned blksize */
-	if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize)
-		return true;
-
-	if (f2fs_lfs_mode(sbi) && (rw == WRITE)) {
-		if (block_unaligned_IO(inode, iocb, iter))
-			return true;
-		if (F2FS_IO_ALIGNED(sbi))
-			return true;
-	}
-	if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED))
-		return true;
-
-	return false;
-}
-
 static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx)
 {
 	return fsverity_active(inode) &&
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index ce4905a073b3..791770507328 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -808,6 +808,29 @@ int f2fs_truncate(struct inode *inode)
 	return 0;
 }
 
+static bool f2fs_force_buffered_io(struct inode *inode, int rw)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+	if (!fscrypt_dio_supported(inode))
+		return true;
+	if (fsverity_active(inode))
+		return true;
+	if (f2fs_compressed_file(inode))
+		return true;
+
+	/* disallow direct IO if any of devices has unaligned blksize */
+	if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize)
+		return true;
+
+	if (f2fs_lfs_mode(sbi) && rw == WRITE && F2FS_IO_ALIGNED(sbi))
+		return true;
+	if (is_sbi_flag_set(sbi, SBI_CP_DISABLED))
+		return true;
+
+	return false;
+}
+
 int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path,
 		 struct kstat *stat, u32 request_mask, unsigned int query_flags)
 {
@@ -824,6 +847,24 @@ int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path,
 		stat->btime.tv_nsec = fi->i_crtime.tv_nsec;
 	}
 
+	/*
+	 * Return the DIO alignment restrictions if requested.  We only return
+	 * this information when requested, since on encrypted files it might
+	 * take a fair bit of work to get if the file wasn't opened recently.
+	 *
+	 * f2fs sometimes supports DIO reads but not DIO writes.  STATX_DIOALIGN
+	 * cannot represent that, so in that case we report no DIO support.
+	 */
+	if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) {
+		unsigned int bsize = i_blocksize(inode);
+
+		stat->result_mask |= STATX_DIOALIGN;
+		if (!f2fs_force_buffered_io(inode, WRITE)) {
+			stat->dio_mem_align = bsize;
+			stat->dio_offset_align = bsize;
+		}
+	}
+
 	flags = fi->i_flags;
 	if (flags & F2FS_COMPR_FL)
 		stat->attributes |= STATX_ATTR_COMPRESSED;
@@ -4182,7 +4223,7 @@ static bool f2fs_should_use_dio(struct inode *inode, struct kiocb *iocb,
 	if (!(iocb->ki_flags & IOCB_DIRECT))
 		return false;
 
-	if (f2fs_force_buffered_io(inode, iocb, iter))
+	if (f2fs_force_buffered_io(inode, iov_iter_rw(iter)))
 		return false;
 
 	/*
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 2451623c05a7..26817b5aeac7 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -3039,23 +3039,24 @@ static void f2fs_get_ino_and_lblk_bits(struct super_block *sb,
 	*lblk_bits_ret = 8 * sizeof(block_t);
 }
 
-static int f2fs_get_num_devices(struct super_block *sb)
+static struct block_device **f2fs_get_devices(struct super_block *sb,
+					      unsigned int *num_devs)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	struct block_device **devs;
+	int i;
 
-	if (f2fs_is_multi_device(sbi))
-		return sbi->s_ndevs;
-	return 1;
-}
+	if (!f2fs_is_multi_device(sbi))
+		return NULL;
 
-static void f2fs_get_devices(struct super_block *sb,
-			     struct request_queue **devs)
-{
-	struct f2fs_sb_info *sbi = F2FS_SB(sb);
-	int i;
+	devs = kmalloc_array(sbi->s_ndevs, sizeof(*devs), GFP_KERNEL);
+	if (!devs)
+		return ERR_PTR(-ENOMEM);
 
 	for (i = 0; i < sbi->s_ndevs; i++)
-		devs[i] = bdev_get_queue(FDEV(i).bdev);
+		devs[i] = FDEV(i).bdev;
+	*num_devs = sbi->s_ndevs;
+	return devs;
 }
 
 static const struct fscrypt_operations f2fs_cryptops = {
@@ -3066,7 +3067,6 @@ static const struct fscrypt_operations f2fs_cryptops = {
 	.empty_dir		= f2fs_empty_dir,
 	.has_stable_inodes	= f2fs_has_stable_inodes,
 	.get_ino_and_lblk_bits	= f2fs_get_ino_and_lblk_bits,
-	.get_num_devices	= f2fs_get_num_devices,
 	.get_devices		= f2fs_get_devices,
 };
 #endif
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 3e4eb3467cb4..8a6b493b5b5f 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -461,8 +461,9 @@ static int fat_allow_set_time(struct user_namespace *mnt_userns,
 {
 	umode_t allow_utime = sbi->options.allow_utime;
 
-	if (!uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode))) {
-		if (in_group_p(i_gid_into_mnt(mnt_userns, inode)))
+	if (!vfsuid_eq_kuid(i_uid_into_vfsuid(mnt_userns, inode),
+			    current_fsuid())) {
+		if (vfsgid_in_group_p(i_gid_into_vfsgid(mnt_userns, inode)))
 			allow_utime >>= 3;
 		if (allow_utime & MAY_WRITE)
 			return 1;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 05221366a16d..08a1993ab7fd 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -134,10 +134,10 @@ static bool inode_io_list_move_locked(struct inode *inode,
 
 static void wb_wakeup(struct bdi_writeback *wb)
 {
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 	if (test_bit(WB_registered, &wb->state))
 		mod_delayed_work(bdi_wq, &wb->dwork, 0);
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 }
 
 static void finish_writeback_work(struct bdi_writeback *wb,
@@ -164,7 +164,7 @@ static void wb_queue_work(struct bdi_writeback *wb,
 	if (work->done)
 		atomic_inc(&work->done->cnt);
 
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 
 	if (test_bit(WB_registered, &wb->state)) {
 		list_add_tail(&work->list, &wb->work_list);
@@ -172,7 +172,7 @@ static void wb_queue_work(struct bdi_writeback *wb,
 	} else
 		finish_writeback_work(wb, work);
 
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 }
 
 /**
@@ -2082,13 +2082,13 @@ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb)
 {
 	struct wb_writeback_work *work = NULL;
 
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 	if (!list_empty(&wb->work_list)) {
 		work = list_entry(wb->work_list.next,
 				  struct wb_writeback_work, list);
 		list_del_init(&work->list);
 	}
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 	return work;
 }
 
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 6ce369b096d4..71911bf9ab34 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -1302,7 +1302,7 @@ static int gdlm_mount(struct gfs2_sbd *sdp, const char *table)
 	memcpy(cluster, table, strlen(table) - strlen(fsname));
 	fsname++;
 
-	flags = DLM_LSFL_FS | DLM_LSFL_NEWEXCL;
+	flags = DLM_LSFL_NEWEXCL;
 
 	/*
 	 * create/join lockspace
diff --git a/fs/inode.c b/fs/inode.c
index 6462276dfdf0..ba1de23c13c1 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -2018,23 +2018,25 @@ static int __file_remove_privs(struct file *file, unsigned int flags)
 {
 	struct dentry *dentry = file_dentry(file);
 	struct inode *inode = file_inode(file);
-	int error;
+	int error = 0;
 	int kill;
 
 	if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode))
 		return 0;
 
 	kill = dentry_needs_remove_privs(dentry);
-	if (kill <= 0)
+	if (kill < 0)
 		return kill;
 
-	if (flags & IOCB_NOWAIT)
-		return -EAGAIN;
+	if (kill) {
+		if (flags & IOCB_NOWAIT)
+			return -EAGAIN;
+
+		error = __remove_privs(file_mnt_user_ns(file), dentry, kill);
+	}
 
-	error = __remove_privs(file_mnt_user_ns(file), dentry, kill);
 	if (!error)
 		inode_has_no_xattr(inode);
-
 	return error;
 }
 
diff --git a/fs/internal.h b/fs/internal.h
index 87e96b9024ce..3e206d3e317c 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -16,6 +16,7 @@ struct shrink_control;
 struct fs_context;
 struct user_namespace;
 struct pipe_inode_info;
+struct iov_iter;
 
 /*
  * block/bdev.c
@@ -221,3 +222,5 @@ ssize_t do_getxattr(struct user_namespace *mnt_userns,
 int setxattr_copy(const char __user *name, struct xattr_ctx *ctx);
 int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 		struct xattr_ctx *ctx);
+
+ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos);
diff --git a/fs/ksmbd/ksmbd_netlink.h b/fs/ksmbd/ksmbd_netlink.h
index 52aa0adeb951..e0cbcfa98c7e 100644
--- a/fs/ksmbd/ksmbd_netlink.h
+++ b/fs/ksmbd/ksmbd_netlink.h
@@ -349,6 +349,7 @@ enum KSMBD_TREE_CONN_STATUS {
 #define KSMBD_SHARE_FLAG_STREAMS		BIT(11)
 #define KSMBD_SHARE_FLAG_FOLLOW_SYMLINKS	BIT(12)
 #define KSMBD_SHARE_FLAG_ACL_XATTR		BIT(13)
+#define KSMBD_SHARE_FLAG_UPDATE		BIT(14)
 
 /*
  * Tree connect request flags.
@@ -364,6 +365,7 @@ enum KSMBD_TREE_CONN_STATUS {
 #define KSMBD_TREE_CONN_FLAG_READ_ONLY		BIT(1)
 #define KSMBD_TREE_CONN_FLAG_WRITABLE		BIT(2)
 #define KSMBD_TREE_CONN_FLAG_ADMIN_ACCOUNT	BIT(3)
+#define KSMBD_TREE_CONN_FLAG_UPDATE		BIT(4)
 
 /*
  * RPC over IPC.
diff --git a/fs/ksmbd/mgmt/share_config.c b/fs/ksmbd/mgmt/share_config.c
index 70655af93b44..c9bca1c2c834 100644
--- a/fs/ksmbd/mgmt/share_config.c
+++ b/fs/ksmbd/mgmt/share_config.c
@@ -51,12 +51,16 @@ static void kill_share(struct ksmbd_share_config *share)
 	kfree(share);
 }
 
-void __ksmbd_share_config_put(struct ksmbd_share_config *share)
+void ksmbd_share_config_del(struct ksmbd_share_config *share)
 {
 	down_write(&shares_table_lock);
 	hash_del(&share->hlist);
 	up_write(&shares_table_lock);
+}
 
+void __ksmbd_share_config_put(struct ksmbd_share_config *share)
+{
+	ksmbd_share_config_del(share);
 	kill_share(share);
 }
 
diff --git a/fs/ksmbd/mgmt/share_config.h b/fs/ksmbd/mgmt/share_config.h
index 28bf3511763f..902f2cb1963a 100644
--- a/fs/ksmbd/mgmt/share_config.h
+++ b/fs/ksmbd/mgmt/share_config.h
@@ -64,6 +64,7 @@ static inline int test_share_config_flag(struct ksmbd_share_config *share,
 	return share->flags & flag;
 }
 
+void ksmbd_share_config_del(struct ksmbd_share_config *share);
 void __ksmbd_share_config_put(struct ksmbd_share_config *share);
 
 static inline void ksmbd_share_config_put(struct ksmbd_share_config *share)
diff --git a/fs/ksmbd/mgmt/tree_connect.c b/fs/ksmbd/mgmt/tree_connect.c
index b35ea6a6abc5..97ab7987df6e 100644
--- a/fs/ksmbd/mgmt/tree_connect.c
+++ b/fs/ksmbd/mgmt/tree_connect.c
@@ -19,7 +19,7 @@ struct ksmbd_tree_conn_status
 ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess,
 			char *share_name)
 {
-	struct ksmbd_tree_conn_status status = {-EINVAL, NULL};
+	struct ksmbd_tree_conn_status status = {-ENOENT, NULL};
 	struct ksmbd_tree_connect_response *resp = NULL;
 	struct ksmbd_share_config *sc;
 	struct ksmbd_tree_connect *tree_conn = NULL;
@@ -57,6 +57,20 @@ ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess,
 		goto out_error;
 
 	tree_conn->flags = resp->connection_flags;
+	if (test_tree_conn_flag(tree_conn, KSMBD_TREE_CONN_FLAG_UPDATE)) {
+		struct ksmbd_share_config *new_sc;
+
+		ksmbd_share_config_del(sc);
+		new_sc = ksmbd_share_config_get(share_name);
+		if (!new_sc) {
+			pr_err("Failed to update stale share config\n");
+			status.ret = -ESTALE;
+			goto out_error;
+		}
+		ksmbd_share_config_put(sc);
+		sc = new_sc;
+	}
+
 	tree_conn->user = sess->user;
 	tree_conn->share_conf = sc;
 	status.tree_conn = tree_conn;
diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c
index 9751cc92c111..19412ac701a6 100644
--- a/fs/ksmbd/smb2pdu.c
+++ b/fs/ksmbd/smb2pdu.c
@@ -1944,8 +1944,10 @@ out_err1:
 		rsp->hdr.Status = STATUS_SUCCESS;
 		rc = 0;
 		break;
+	case -ESTALE:
+	case -ENOENT:
 	case KSMBD_TREE_CONN_STATUS_NO_SHARE:
-		rsp->hdr.Status = STATUS_BAD_NETWORK_PATH;
+		rsp->hdr.Status = STATUS_BAD_NETWORK_NAME;
 		break;
 	case -ENOMEM:
 	case KSMBD_TREE_CONN_STATUS_NOMEM:
@@ -2328,15 +2330,15 @@ static int smb2_remove_smb_xattrs(struct path *path)
 			name += strlen(name) + 1) {
 		ksmbd_debug(SMB, "%s, len %zd\n", name, strlen(name));
 
-		if (strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) &&
-		    strncmp(&name[XATTR_USER_PREFIX_LEN], DOS_ATTRIBUTE_PREFIX,
-			    DOS_ATTRIBUTE_PREFIX_LEN) &&
-		    strncmp(&name[XATTR_USER_PREFIX_LEN], STREAM_PREFIX, STREAM_PREFIX_LEN))
-			continue;
-
-		err = ksmbd_vfs_remove_xattr(user_ns, path->dentry, name);
-		if (err)
-			ksmbd_debug(SMB, "remove xattr failed : %s\n", name);
+		if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) &&
+		    !strncmp(&name[XATTR_USER_PREFIX_LEN], STREAM_PREFIX,
+			     STREAM_PREFIX_LEN)) {
+			err = ksmbd_vfs_remove_xattr(user_ns, path->dentry,
+						     name);
+			if (err)
+				ksmbd_debug(SMB, "remove xattr failed : %s\n",
+					    name);
+		}
 	}
 out:
 	kvfree(xattr_list);
@@ -3042,12 +3044,6 @@ int smb2_open(struct ksmbd_work *work)
 	list_add(&fp->node, &fp->f_ci->m_fp_list);
 	write_unlock(&fp->f_ci->m_lock);
 
-	rc = ksmbd_vfs_getattr(&path, &stat);
-	if (rc) {
-		generic_fillattr(user_ns, d_inode(path.dentry), &stat);
-		rc = 0;
-	}
-
 	/* Check delete pending among previous fp before oplock break */
 	if (ksmbd_inode_pending_delete(fp)) {
 		rc = -EBUSY;
@@ -3134,6 +3130,10 @@ int smb2_open(struct ksmbd_work *work)
 		}
 	}
 
+	rc = ksmbd_vfs_getattr(&path, &stat);
+	if (rc)
+		goto err_out;
+
 	if (stat.result_mask & STATX_BTIME)
 		fp->create_time = ksmbd_UnixTimeToNT(stat.btime);
 	else
@@ -3149,9 +3149,6 @@ int smb2_open(struct ksmbd_work *work)
 
 	memcpy(fp->client_guid, conn->ClientGUID, SMB2_CLIENT_GUID_SIZE);
 
-	generic_fillattr(user_ns, file_inode(fp->filp),
-			 &stat);
-
 	rsp->StructureSize = cpu_to_le16(89);
 	rcu_read_lock();
 	opinfo = rcu_dereference(fp->f_opinfo);
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index f802223e71ab..cdc8e12cdac4 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -164,7 +164,7 @@ static struct nlm_host *nlm_alloc_host(struct nlm_lookup_host_info *ni,
 	host->h_addrbuf    = nsm->sm_addrbuf;
 	host->net	   = ni->net;
 	host->h_cred	   = get_cred(ni->cred);
-	strlcpy(host->nodename, utsname()->nodename, sizeof(host->nodename));
+	strscpy(host->nodename, utsname()->nodename, sizeof(host->nodename));
 
 out:
 	return host;
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index bf274f23969b..284b019cb652 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -521,6 +521,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_void,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_void),
+		.pc_argzero = sizeof(struct nlm_void),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "NULL",
@@ -530,6 +531,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_testargs,
 		.pc_encode = nlm4svc_encode_testres,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St+2+No+Rg,
 		.pc_name = "TEST",
@@ -539,6 +541,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_lockargs,
 		.pc_encode = nlm4svc_encode_res,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St,
 		.pc_name = "LOCK",
@@ -548,6 +551,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_cancargs,
 		.pc_encode = nlm4svc_encode_res,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St,
 		.pc_name = "CANCEL",
@@ -557,6 +561,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_unlockargs,
 		.pc_encode = nlm4svc_encode_res,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St,
 		.pc_name = "UNLOCK",
@@ -566,6 +571,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_testargs,
 		.pc_encode = nlm4svc_encode_res,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St,
 		.pc_name = "GRANTED",
@@ -575,6 +581,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_testargs,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "TEST_MSG",
@@ -584,6 +591,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_lockargs,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "LOCK_MSG",
@@ -593,6 +601,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_cancargs,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "CANCEL_MSG",
@@ -602,6 +611,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_unlockargs,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "UNLOCK_MSG",
@@ -611,6 +621,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_testargs,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "GRANTED_MSG",
@@ -620,6 +631,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_void,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_res),
+		.pc_argzero = sizeof(struct nlm_res),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "TEST_RES",
@@ -629,6 +641,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_void,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_res),
+		.pc_argzero = sizeof(struct nlm_res),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "LOCK_RES",
@@ -638,6 +651,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_void,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_res),
+		.pc_argzero = sizeof(struct nlm_res),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "CANCEL_RES",
@@ -647,6 +661,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_void,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_res),
+		.pc_argzero = sizeof(struct nlm_res),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "UNLOCK_RES",
@@ -656,6 +671,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_res,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_res),
+		.pc_argzero = sizeof(struct nlm_res),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "GRANTED_RES",
@@ -665,6 +681,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_reboot,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_reboot),
+		.pc_argzero = sizeof(struct nlm_reboot),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "SM_NOTIFY",
@@ -674,6 +691,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_void,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_void),
+		.pc_argzero = sizeof(struct nlm_void),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = 0,
 		.pc_name = "UNUSED",
@@ -683,6 +701,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_void,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_void),
+		.pc_argzero = sizeof(struct nlm_void),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = 0,
 		.pc_name = "UNUSED",
@@ -692,6 +711,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_void,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_void),
+		.pc_argzero = sizeof(struct nlm_void),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = 0,
 		.pc_name = "UNUSED",
@@ -701,6 +721,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_shareargs,
 		.pc_encode = nlm4svc_encode_shareres,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St+1,
 		.pc_name = "SHARE",
@@ -710,6 +731,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_shareargs,
 		.pc_encode = nlm4svc_encode_shareres,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St+1,
 		.pc_name = "UNSHARE",
@@ -719,6 +741,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_lockargs,
 		.pc_encode = nlm4svc_encode_res,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St,
 		.pc_name = "NM_LOCK",
@@ -728,6 +751,7 @@ const struct svc_procedure nlmsvc_procedures4[24] = {
 		.pc_decode = nlm4svc_decode_notify,
 		.pc_encode = nlm4svc_encode_void,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "FREE_ALL",
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index b09ca35b527c..e35c05e27806 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -555,6 +555,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_void,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_void),
+		.pc_argzero = sizeof(struct nlm_void),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "NULL",
@@ -564,6 +565,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_testargs,
 		.pc_encode = nlmsvc_encode_testres,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St+2+No+Rg,
 		.pc_name = "TEST",
@@ -573,6 +575,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_lockargs,
 		.pc_encode = nlmsvc_encode_res,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St,
 		.pc_name = "LOCK",
@@ -582,6 +585,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_cancargs,
 		.pc_encode = nlmsvc_encode_res,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St,
 		.pc_name = "CANCEL",
@@ -591,6 +595,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_unlockargs,
 		.pc_encode = nlmsvc_encode_res,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St,
 		.pc_name = "UNLOCK",
@@ -600,6 +605,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_testargs,
 		.pc_encode = nlmsvc_encode_res,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St,
 		.pc_name = "GRANTED",
@@ -609,6 +615,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_testargs,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "TEST_MSG",
@@ -618,6 +625,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_lockargs,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "LOCK_MSG",
@@ -627,6 +635,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_cancargs,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "CANCEL_MSG",
@@ -636,6 +645,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_unlockargs,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "UNLOCK_MSG",
@@ -645,6 +655,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_testargs,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "GRANTED_MSG",
@@ -654,6 +665,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_void,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_res),
+		.pc_argzero = sizeof(struct nlm_res),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "TEST_RES",
@@ -663,6 +675,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_void,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_res),
+		.pc_argzero = sizeof(struct nlm_res),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "LOCK_RES",
@@ -672,6 +685,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_void,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_res),
+		.pc_argzero = sizeof(struct nlm_res),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "CANCEL_RES",
@@ -681,6 +695,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_void,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_res),
+		.pc_argzero = sizeof(struct nlm_res),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "UNLOCK_RES",
@@ -690,6 +705,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_res,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_res),
+		.pc_argzero = sizeof(struct nlm_res),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "GRANTED_RES",
@@ -699,6 +715,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_reboot,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_reboot),
+		.pc_argzero = sizeof(struct nlm_reboot),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "SM_NOTIFY",
@@ -708,6 +725,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_void,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_void),
+		.pc_argzero = sizeof(struct nlm_void),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "UNUSED",
@@ -717,6 +735,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_void,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_void),
+		.pc_argzero = sizeof(struct nlm_void),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "UNUSED",
@@ -726,6 +745,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_void,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_void),
+		.pc_argzero = sizeof(struct nlm_void),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = St,
 		.pc_name = "UNUSED",
@@ -735,6 +755,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_shareargs,
 		.pc_encode = nlmsvc_encode_shareres,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St+1,
 		.pc_name = "SHARE",
@@ -744,6 +765,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_shareargs,
 		.pc_encode = nlmsvc_encode_shareres,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St+1,
 		.pc_name = "UNSHARE",
@@ -753,6 +775,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_lockargs,
 		.pc_encode = nlmsvc_encode_res,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_res),
 		.pc_xdrressize = Ck+St,
 		.pc_name = "NM_LOCK",
@@ -762,6 +785,7 @@ const struct svc_procedure nlmsvc_procedures[24] = {
 		.pc_decode = nlmsvc_decode_notify,
 		.pc_encode = nlmsvc_encode_void,
 		.pc_argsize = sizeof(struct nlm_args),
+		.pc_argzero = sizeof(struct nlm_args),
 		.pc_ressize = sizeof(struct nlm_void),
 		.pc_xdrressize = 0,
 		.pc_name = "FREE_ALL",
diff --git a/fs/locks.c b/fs/locks.c
index c266cfdc3291..607f94a0e789 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2129,6 +2129,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
 	else
 		error = locks_lock_file_wait(f.file, &fl);
 
+	locks_release_private(&fl);
  out_putf:
 	fdput(f);
 
diff --git a/fs/namespace.c b/fs/namespace.c
index 68789f896f08..df137ba19d37 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -4238,6 +4238,13 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
 		err = -EPERM;
 		goto out_fput;
 	}
+
+	/* We're not controlling the target namespace. */
+	if (!ns_capable(mnt_userns, CAP_SYS_ADMIN)) {
+		err = -EPERM;
+		goto out_fput;
+	}
+
 	kattr->mnt_userns = get_user_ns(mnt_userns);
 
 out_fput:
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 8dcb08e1a885..d0cccddb7d08 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -1065,6 +1065,7 @@ static const struct svc_procedure nfs4_callback_procedures1[] = {
 		.pc_func = nfs4_callback_compound,
 		.pc_encode = nfs4_encode_void,
 		.pc_argsize = 256,
+		.pc_argzero = 256,
 		.pc_ressize = 256,
 		.pc_xdrressize = NFS4_CALLBACK_BUFSIZE,
 		.pc_name = "COMPOUND",
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index dbab3caa15ed..5d6c2ddc7ea6 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2382,7 +2382,8 @@ static void nfs_dentry_remove_handle_error(struct inode *dir,
 {
 	switch (error) {
 	case -ENOENT:
-		d_delete(dentry);
+		if (d_really_is_positive(dentry))
+			d_delete(dentry);
 		nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 		break;
 	case 0:
@@ -2484,8 +2485,10 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry)
 	 */
 	error = -ETXTBSY;
 	if (WARN_ON(dentry->d_flags & DCACHE_NFSFS_RENAMED) ||
-	    WARN_ON(dentry->d_fsdata == NFS_FSDATA_BLOCKED))
+	    WARN_ON(dentry->d_fsdata == NFS_FSDATA_BLOCKED)) {
+		spin_unlock(&dentry->d_lock);
 		goto out;
+	}
 	if (dentry->d_fsdata)
 		/* old devname */
 		kfree(dentry->d_fsdata);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index d2bcd4834c0e..e032fe201a36 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -221,8 +221,10 @@ nfs_file_fsync_commit(struct file *file, int datasync)
 int
 nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
-	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	struct inode *inode = file_inode(file);
+	struct nfs_inode *nfsi = NFS_I(inode);
+	long save_nredirtied = atomic_long_read(&nfsi->redirtied_pages);
+	long nredirtied;
 	int ret;
 
 	trace_nfs_fsync_enter(inode);
@@ -237,15 +239,10 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		ret = pnfs_sync_inode(inode, !!datasync);
 		if (ret != 0)
 			break;
-		if (!test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags))
+		nredirtied = atomic_long_read(&nfsi->redirtied_pages);
+		if (nredirtied == save_nredirtied)
 			break;
-		/*
-		 * If nfs_file_fsync_commit detected a server reboot, then
-		 * resend all dirty pages that might have been covered by
-		 * the NFS_CONTEXT_RESEND_WRITES flag
-		 */
-		start = 0;
-		end = LLONG_MAX;
+		save_nredirtied = nredirtied;
 	}
 
 	trace_nfs_fsync_exit(inode, ret);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index b4e46b0ffa2d..bea7c005119c 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -426,6 +426,7 @@ nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh)
 static void nfs_inode_init_regular(struct nfs_inode *nfsi)
 {
 	atomic_long_set(&nfsi->nrequests, 0);
+	atomic_long_set(&nfsi->redirtied_pages, 0);
 	INIT_LIST_HEAD(&nfsi->commit_info.list);
 	atomic_long_set(&nfsi->commit_info.ncommit, 0);
 	atomic_set(&nfsi->commit_info.rpcs_out, 0);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 27c720d71b4e..898dd95bc7a7 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -606,6 +606,31 @@ static inline gfp_t nfs_io_gfp_mask(void)
 	return GFP_KERNEL;
 }
 
+/*
+ * Special version of should_remove_suid() that ignores capabilities.
+ */
+static inline int nfs_should_remove_suid(const struct inode *inode)
+{
+	umode_t mode = inode->i_mode;
+	int kill = 0;
+
+	/* suid always must be killed */
+	if (unlikely(mode & S_ISUID))
+		kill = ATTR_KILL_SUID;
+
+	/*
+	 * sgid without any exec bits is just a mandatory locking mark; leave
+	 * it alone.  If some exec bits are set, it's a real sgid; kill it.
+	 */
+	if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
+		kill |= ATTR_KILL_SGID;
+
+	if (unlikely(kill && S_ISREG(mode)))
+		return kill;
+
+	return 0;
+}
+
 /* unlink.c */
 extern struct rpc_task *
 nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 068c45b3bc1a..6dab9e408372 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -78,10 +78,15 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 
 	status = nfs4_call_sync(server->client, server, msg,
 				&args.seq_args, &res.seq_res, 0);
-	if (status == 0)
+	if (status == 0) {
+		if (nfs_should_remove_suid(inode)) {
+			spin_lock(&inode->i_lock);
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE);
+			spin_unlock(&inode->i_lock);
+		}
 		status = nfs_post_op_update_inode_force_wcc(inode,
 							    res.falloc_fattr);
-
+	}
 	if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE])
 		trace_nfs4_fallocate(inode, &args, status);
 	else
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index e88f6b18445e..9eb181287879 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -340,6 +340,11 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 		goto out;
 	}
 
+	if (!S_ISREG(fattr->mode)) {
+		res = ERR_PTR(-EBADF);
+		goto out;
+	}
+
 	res = ERR_PTR(-ENOMEM);
 	len = strlen(SSC_READ_NAME_BODY) + 16;
 	read_name = kzalloc(len, GFP_KERNEL);
@@ -357,6 +362,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 				     r_ino->i_fop);
 	if (IS_ERR(filep)) {
 		res = ERR_CAST(filep);
+		iput(r_ino);
 		goto out_free_name;
 	}
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 41a9b6b58fb9..2613b7e36eb9 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -2817,7 +2817,6 @@ int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *hdr)
 	/* Resend all requests through the MDS */
 	nfs_pageio_init_write(&pgio, hdr->inode, FLUSH_STABLE, true,
 			      hdr->completion_ops);
-	set_bit(NFS_CONTEXT_RESEND_WRITES, &hdr->args.context->flags);
 	return nfs_pageio_resend(&pgio, hdr);
 }
 EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 82944e14fcea..ee66ffdb985e 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1051,22 +1051,31 @@ static void nfs_fill_super(struct super_block *sb, struct nfs_fs_context *ctx)
 	if (ctx->bsize)
 		sb->s_blocksize = nfs_block_size(ctx->bsize, &sb->s_blocksize_bits);
 
-	if (server->nfs_client->rpc_ops->version != 2) {
-		/* The VFS shouldn't apply the umask to mode bits. We will do
-		 * so ourselves when necessary.
+	switch (server->nfs_client->rpc_ops->version) {
+	case 2:
+		sb->s_time_gran = 1000;
+		sb->s_time_min = 0;
+		sb->s_time_max = U32_MAX;
+		break;
+	case 3:
+		/*
+		 * The VFS shouldn't apply the umask to mode bits.
+		 * We will do so ourselves when necessary.
 		 */
 		sb->s_flags |= SB_POSIXACL;
 		sb->s_time_gran = 1;
-		sb->s_export_op = &nfs_export_ops;
-	} else
-		sb->s_time_gran = 1000;
-
-	if (server->nfs_client->rpc_ops->version != 4) {
 		sb->s_time_min = 0;
 		sb->s_time_max = U32_MAX;
-	} else {
+		sb->s_export_op = &nfs_export_ops;
+		break;
+	case 4:
+		sb->s_flags |= SB_POSIXACL;
+		sb->s_time_gran = 1;
 		sb->s_time_min = S64_MIN;
 		sb->s_time_max = S64_MAX;
+		if (server->caps & NFS_CAP_ATOMIC_OPEN_V1)
+			sb->s_export_op = &nfs_export_ops;
+		break;
 	}
 
 	sb->s_magic = NFS_SUPER_MAGIC;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 51a7e202d6e5..f41d24b54fd1 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1420,10 +1420,12 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr,
  */
 static void nfs_redirty_request(struct nfs_page *req)
 {
+	struct nfs_inode *nfsi = NFS_I(page_file_mapping(req->wb_page)->host);
+
 	/* Bump the transmission count */
 	req->wb_nio++;
 	nfs_mark_request_dirty(req);
-	set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags);
+	atomic_long_inc(&nfsi->redirtied_pages);
 	nfs_end_page_writeback(req);
 	nfs_release_request(req);
 }
@@ -1494,31 +1496,6 @@ void nfs_commit_prepare(struct rpc_task *task, void *calldata)
 	NFS_PROTO(data->inode)->commit_rpc_prepare(task, data);
 }
 
-/*
- * Special version of should_remove_suid() that ignores capabilities.
- */
-static int nfs_should_remove_suid(const struct inode *inode)
-{
-	umode_t mode = inode->i_mode;
-	int kill = 0;
-
-	/* suid always must be killed */
-	if (unlikely(mode & S_ISUID))
-		kill = ATTR_KILL_SUID;
-
-	/*
-	 * sgid without any exec bits is just a mandatory locking mark; leave
-	 * it alone.  If some exec bits are set, it's a real sgid; kill it.
-	 */
-	if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
-		kill |= ATTR_KILL_SGID;
-
-	if (unlikely(kill && S_ISREG(mode)))
-		return kill;
-
-	return 0;
-}
-
 static void nfs_writeback_check_extend(struct nfs_pgio_header *hdr,
 		struct nfs_fattr *fattr)
 {
@@ -1904,7 +1881,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 		/* We have a mismatch. Write the page again */
 		dprintk_cont(" mismatch\n");
 		nfs_mark_request_dirty(req);
-		set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags);
+		atomic_long_inc(&NFS_I(data->inode)->redirtied_pages);
 	next:
 		nfs_unlock_and_release_request(req);
 		/* Latency breaker */
diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h
index 65c331f75e9c..f21259ead64b 100644
--- a/fs/nfsd/cache.h
+++ b/fs/nfsd/cache.h
@@ -84,6 +84,6 @@ int	nfsd_reply_cache_init(struct nfsd_net *);
 void	nfsd_reply_cache_shutdown(struct nfsd_net *);
 int	nfsd_cache_lookup(struct svc_rqst *);
 void	nfsd_cache_update(struct svc_rqst *, int, __be32 *);
-int	nfsd_reply_cache_stats_open(struct inode *, struct file *);
+int	nfsd_reply_cache_stats_show(struct seq_file *m, void *v);
 
 #endif /* NFSCACHE_H */
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index eeed4ae5b4ad..d5c57360b418 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -1212,7 +1212,7 @@ nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
  * scraping this file for info should test the labels to ensure they're
  * getting the correct field.
  */
-static int nfsd_file_cache_stats_show(struct seq_file *m, void *v)
+int nfsd_file_cache_stats_show(struct seq_file *m, void *v)
 {
 	unsigned long releases = 0, pages_flushed = 0, evictions = 0;
 	unsigned long hits = 0, acquisitions = 0;
@@ -1259,8 +1259,3 @@ static int nfsd_file_cache_stats_show(struct seq_file *m, void *v)
 	seq_printf(m, "pages flushed: %lu\n", pages_flushed);
 	return 0;
 }
-
-int nfsd_file_cache_stats_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, nfsd_file_cache_stats_show, NULL);
-}
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index 8e8c0c47d67d..357832bac736 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -60,5 +60,5 @@ __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		  unsigned int may_flags, struct nfsd_file **nfp);
 __be32 nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		  unsigned int may_flags, struct nfsd_file **nfp);
-int	nfsd_file_cache_stats_open(struct inode *, struct file *);
+int nfsd_file_cache_stats_show(struct seq_file *m, void *v);
 #endif /* _FS_NFSD_FILECACHE_H */
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index ffe17743cc74..8c854ba3285b 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -192,6 +192,10 @@ struct nfsd_net {
 
 	atomic_t		nfs4_client_count;
 	int			nfs4_max_clients;
+
+	atomic_t		nfsd_courtesy_clients;
+	struct shrinker		nfsd_client_shrinker;
+	struct delayed_work	nfsd_shrinker_work;
 };
 
 /* Simple check to find out if a given net was properly initialized */
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 9edd3c1a30fb..13e6e6897f6c 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -331,6 +331,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = {
 		.pc_decode = nfssvc_decode_voidarg,
 		.pc_encode = nfssvc_encode_voidres,
 		.pc_argsize = sizeof(struct nfsd_voidargs),
+		.pc_argzero = sizeof(struct nfsd_voidargs),
 		.pc_ressize = sizeof(struct nfsd_voidres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST,
@@ -342,6 +343,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = {
 		.pc_encode = nfsaclsvc_encode_getaclres,
 		.pc_release = nfsaclsvc_release_getacl,
 		.pc_argsize = sizeof(struct nfsd3_getaclargs),
+		.pc_argzero = sizeof(struct nfsd3_getaclargs),
 		.pc_ressize = sizeof(struct nfsd3_getaclres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+1+2*(1+ACL),
@@ -353,6 +355,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = {
 		.pc_encode = nfssvc_encode_attrstatres,
 		.pc_release = nfssvc_release_attrstat,
 		.pc_argsize = sizeof(struct nfsd3_setaclargs),
+		.pc_argzero = sizeof(struct nfsd3_setaclargs),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+AT,
@@ -364,6 +367,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = {
 		.pc_encode = nfssvc_encode_attrstatres,
 		.pc_release = nfssvc_release_attrstat,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
+		.pc_argzero = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+AT,
@@ -375,6 +379,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = {
 		.pc_encode = nfsaclsvc_encode_accessres,
 		.pc_release = nfsaclsvc_release_access,
 		.pc_argsize = sizeof(struct nfsd3_accessargs),
+		.pc_argzero = sizeof(struct nfsd3_accessargs),
 		.pc_ressize = sizeof(struct nfsd3_accessres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+AT+1,
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 9446c6743664..2fb9ee356455 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -252,6 +252,7 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = {
 		.pc_decode = nfssvc_decode_voidarg,
 		.pc_encode = nfssvc_encode_voidres,
 		.pc_argsize = sizeof(struct nfsd_voidargs),
+		.pc_argzero = sizeof(struct nfsd_voidargs),
 		.pc_ressize = sizeof(struct nfsd_voidres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST,
@@ -263,6 +264,7 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = {
 		.pc_encode = nfs3svc_encode_getaclres,
 		.pc_release = nfs3svc_release_getacl,
 		.pc_argsize = sizeof(struct nfsd3_getaclargs),
+		.pc_argzero = sizeof(struct nfsd3_getaclargs),
 		.pc_ressize = sizeof(struct nfsd3_getaclres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+1+2*(1+ACL),
@@ -274,6 +276,7 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = {
 		.pc_encode = nfs3svc_encode_setaclres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_setaclargs),
+		.pc_argzero = sizeof(struct nfsd3_setaclargs),
 		.pc_ressize = sizeof(struct nfsd3_attrstat),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+pAT,
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index a41cca619338..923d9a80df92 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -150,7 +150,6 @@ nfsd3_proc_read(struct svc_rqst *rqstp)
 {
 	struct nfsd3_readargs *argp = rqstp->rq_argp;
 	struct nfsd3_readres *resp = rqstp->rq_resp;
-	u32 max_blocksize = svc_max_payload(rqstp);
 	unsigned int len;
 	int v;
 
@@ -159,7 +158,8 @@ nfsd3_proc_read(struct svc_rqst *rqstp)
 				(unsigned long) argp->count,
 				(unsigned long long) argp->offset);
 
-	argp->count = min_t(u32, argp->count, max_blocksize);
+	argp->count = min_t(u32, argp->count, svc_max_payload(rqstp));
+	argp->count = min_t(u32, argp->count, rqstp->rq_res.buflen);
 	if (argp->offset > (u64)OFFSET_MAX)
 		argp->offset = (u64)OFFSET_MAX;
 	if (argp->offset + argp->count > (u64)OFFSET_MAX)
@@ -563,25 +563,18 @@ static void nfsd3_init_dirlist_pages(struct svc_rqst *rqstp,
 {
 	struct xdr_buf *buf = &resp->dirlist;
 	struct xdr_stream *xdr = &resp->xdr;
-
-	count = clamp(count, (u32)(XDR_UNIT * 2), svc_max_payload(rqstp));
+	unsigned int sendbuf = min_t(unsigned int, rqstp->rq_res.buflen,
+				     svc_max_payload(rqstp));
 
 	memset(buf, 0, sizeof(*buf));
 
 	/* Reserve room for the NULL ptr & eof flag (-2 words) */
-	buf->buflen = count - XDR_UNIT * 2;
+	buf->buflen = clamp(count, (u32)(XDR_UNIT * 2), sendbuf);
+	buf->buflen -= XDR_UNIT * 2;
 	buf->pages = rqstp->rq_next_page;
 	rqstp->rq_next_page += (buf->buflen + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
-	/* This is xdr_init_encode(), but it assumes that
-	 * the head kvec has already been consumed. */
-	xdr_set_scratch_buffer(xdr, NULL, 0);
-	xdr->buf = buf;
-	xdr->page_ptr = buf->pages;
-	xdr->iov = NULL;
-	xdr->p = page_address(*buf->pages);
-	xdr->end = (void *)xdr->p + min_t(u32, buf->buflen, PAGE_SIZE);
-	xdr->rqst = NULL;
+	xdr_init_encode_pages(xdr, buf, buf->pages,  NULL);
 }
 
 /*
@@ -808,6 +801,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_decode = nfssvc_decode_voidarg,
 		.pc_encode = nfssvc_encode_voidres,
 		.pc_argsize = sizeof(struct nfsd_voidargs),
+		.pc_argzero = sizeof(struct nfsd_voidargs),
 		.pc_ressize = sizeof(struct nfsd_voidres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST,
@@ -819,6 +813,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_getattrres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
+		.pc_argzero = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd3_attrstatres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+AT,
@@ -830,6 +825,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_wccstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_sattrargs),
+		.pc_argzero = sizeof(struct nfsd3_sattrargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+WC,
@@ -841,6 +837,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_lookupres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
+		.pc_argzero = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_diropres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+FH+pAT+pAT,
@@ -852,6 +849,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_accessres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_accessargs),
+		.pc_argzero = sizeof(struct nfsd3_accessargs),
 		.pc_ressize = sizeof(struct nfsd3_accessres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+pAT+1,
@@ -863,6 +861,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_readlinkres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
+		.pc_argzero = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd3_readlinkres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+pAT+1+NFS3_MAXPATHLEN/4,
@@ -874,6 +873,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_readres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readargs),
+		.pc_argzero = sizeof(struct nfsd3_readargs),
 		.pc_ressize = sizeof(struct nfsd3_readres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+pAT+4+NFSSVC_MAXBLKSIZE/4,
@@ -885,6 +885,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_writeres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_writeargs),
+		.pc_argzero = sizeof(struct nfsd3_writeargs),
 		.pc_ressize = sizeof(struct nfsd3_writeres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+WC+4,
@@ -896,6 +897,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_createargs),
+		.pc_argzero = sizeof(struct nfsd3_createargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
@@ -907,6 +909,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mkdirargs),
+		.pc_argzero = sizeof(struct nfsd3_mkdirargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
@@ -918,6 +921,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_symlinkargs),
+		.pc_argzero = sizeof(struct nfsd3_symlinkargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
@@ -929,6 +933,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_createres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mknodargs),
+		.pc_argzero = sizeof(struct nfsd3_mknodargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
@@ -940,6 +945,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_wccstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
+		.pc_argzero = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+WC,
@@ -951,6 +957,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_wccstatres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
+		.pc_argzero = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+WC,
@@ -962,6 +969,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_renameres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_renameargs),
+		.pc_argzero = sizeof(struct nfsd3_renameargs),
 		.pc_ressize = sizeof(struct nfsd3_renameres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+WC+WC,
@@ -973,6 +981,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_linkres,
 		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_linkargs),
+		.pc_argzero = sizeof(struct nfsd3_linkargs),
 		.pc_ressize = sizeof(struct nfsd3_linkres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+pAT+WC,
@@ -984,6 +993,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_readdirres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirargs),
+		.pc_argzero = sizeof(struct nfsd3_readdirargs),
 		.pc_ressize = sizeof(struct nfsd3_readdirres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_name = "READDIR",
@@ -994,6 +1004,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_readdirres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirplusargs),
+		.pc_argzero = sizeof(struct nfsd3_readdirplusargs),
 		.pc_ressize = sizeof(struct nfsd3_readdirres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_name = "READDIRPLUS",
@@ -1003,6 +1014,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_decode = nfs3svc_decode_fhandleargs,
 		.pc_encode = nfs3svc_encode_fsstatres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
+		.pc_argzero = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_fsstatres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+pAT+2*6+1,
@@ -1013,6 +1025,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_decode = nfs3svc_decode_fhandleargs,
 		.pc_encode = nfs3svc_encode_fsinfores,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
+		.pc_argzero = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_fsinfores),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+pAT+12,
@@ -1023,6 +1036,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_decode = nfs3svc_decode_fhandleargs,
 		.pc_encode = nfs3svc_encode_pathconfres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
+		.pc_argzero = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_pathconfres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+pAT+6,
@@ -1034,6 +1048,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
 		.pc_encode = nfs3svc_encode_commitres,
 		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_commitargs),
+		.pc_argzero = sizeof(struct nfsd3_commitargs),
 		.pc_ressize = sizeof(struct nfsd3_commitres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+WC+2,
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 0293b8d65f10..3308dd671ef0 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -571,10 +571,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 		args->count = max_blocksize;
 		args->len = max_blocksize;
 	}
-	if (!xdr_stream_subsegment(xdr, &args->payload, args->count))
-		return false;
 
-	return true;
+	return xdr_stream_subsegment(xdr, &args->payload, args->count);
 }
 
 bool
@@ -616,8 +614,6 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 {
 	struct nfsd3_symlinkargs *args = rqstp->rq_argp;
 	struct kvec *head = rqstp->rq_arg.head;
-	struct kvec *tail = rqstp->rq_arg.tail;
-	size_t remaining;
 
 	if (!svcxdr_decode_diropargs3(xdr, &args->ffh, &args->fname, &args->flen))
 		return false;
@@ -626,16 +622,10 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	if (xdr_stream_decode_u32(xdr, &args->tlen) < 0)
 		return false;
 
-	/* request sanity */
-	remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len;
-	remaining -= xdr_stream_pos(xdr);
-	if (remaining < xdr_align_size(args->tlen))
-		return false;
-
-	args->first.iov_base = xdr->p;
+	/* symlink_data */
 	args->first.iov_len = head->iov_len - xdr_stream_pos(xdr);
-
-	return true;
+	args->first.iov_base = xdr_inline_decode(xdr, args->tlen);
+	return args->first.iov_base != NULL;
 }
 
 bool
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 4ce328209f61..f0e69edf5f0f 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1371,11 +1371,21 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
 	cb->cb_holds_slot = false;
 }
 
-void nfsd4_run_cb(struct nfsd4_callback *cb)
+/**
+ * nfsd4_run_cb - queue up a callback job to run
+ * @cb: callback to queue
+ *
+ * Kick off a callback to do its thing. Returns false if it was already
+ * on a queue, true otherwise.
+ */
+bool nfsd4_run_cb(struct nfsd4_callback *cb)
 {
 	struct nfs4_client *clp = cb->cb_clp;
+	bool queued;
 
 	nfsd41_cb_inflight_begin(clp);
-	if (!nfsd4_queue_cb(cb))
+	queued = nfsd4_queue_cb(cb);
+	if (!queued)
 		nfsd41_cb_inflight_end(clp);
+	return queued;
 }
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index f92161ce1f97..e70a1a2999b7 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -82,8 +82,8 @@ ent_init(struct cache_head *cnew, struct cache_head *citm)
 	new->id = itm->id;
 	new->type = itm->type;
 
-	strlcpy(new->name, itm->name, sizeof(new->name));
-	strlcpy(new->authname, itm->authname, sizeof(new->authname));
+	strscpy(new->name, itm->name, sizeof(new->name));
+	strscpy(new->authname, itm->authname, sizeof(new->authname));
 }
 
 static void
@@ -548,7 +548,7 @@ idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen
 		return nfserr_badowner;
 	memcpy(key.name, name, namelen);
 	key.name[namelen] = '\0';
-	strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
+	strscpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
 	ret = idmap_lookup(rqstp, nametoid_lookup, &key, nn->nametoid_cache, &item);
 	if (ret == -ENOENT)
 		return nfserr_badowner;
@@ -584,7 +584,7 @@ static __be32 idmap_id_to_name(struct xdr_stream *xdr,
 	int ret;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 
-	strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
+	strscpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
 	ret = idmap_lookup(rqstp, idtoname_lookup, &key, nn->idtoname_cache, &item);
 	if (ret == -ENOENT)
 		return encode_ascii_id(xdr, id);
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 2c05692a9abf..3564d1c6f610 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -658,7 +658,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
 	ktime_t now, cutoff;
 	const struct nfsd4_layout_ops *ops;
 
-
+	trace_nfsd_cb_layout_done(&ls->ls_stid.sc_stateid, task);
 	switch (task->tk_status) {
 	case 0:
 	case -NFS4ERR_DELAY:
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index a72ab97f77ef..8beb2bc4c328 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -141,7 +141,6 @@ fh_dup2(struct svc_fh *dst, struct svc_fh *src)
 static __be32
 do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open, int accmode)
 {
-	__be32 status;
 
 	if (open->op_truncate &&
 		!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
@@ -156,9 +155,7 @@ do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfs
 	if (open->op_share_deny & NFS4_SHARE_DENY_READ)
 		accmode |= NFSD_MAY_WRITE;
 
-	status = fh_verify(rqstp, current_fh, S_IFREG, accmode);
-
-	return status;
+	return fh_verify(rqstp, current_fh, S_IFREG, accmode);
 }
 
 static __be32 nfsd_check_obj_isreg(struct svc_fh *fh)
@@ -454,7 +451,6 @@ static __be32
 do_open_fhandle(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open)
 {
 	struct svc_fh *current_fh = &cstate->current_fh;
-	__be32 status;
 	int accmode = 0;
 
 	/* We don't know the target directory, and therefore can not
@@ -479,9 +475,7 @@ do_open_fhandle(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, str
 	if (open->op_claim_type == NFS4_OPEN_CLAIM_DELEG_CUR_FH)
 		accmode = NFSD_MAY_OWNER_OVERRIDE;
 
-	status = do_open_permission(rqstp, current_fh, open, accmode);
-
-	return status;
+	return do_open_permission(rqstp, current_fh, open, accmode);
 }
 
 static void
@@ -668,11 +662,9 @@ static __be32
 nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		union nfsd4_op_u *u)
 {
-	__be32 status;
-
 	fh_put(&cstate->current_fh);
-	status = exp_pseudoroot(rqstp, &cstate->current_fh);
-	return status;
+
+	return exp_pseudoroot(rqstp, &cstate->current_fh);
 }
 
 static __be32
@@ -1343,7 +1335,7 @@ try_again:
 		return 0;
 	}
 	if (work) {
-		strlcpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr) - 1);
+		strscpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr) - 1);
 		refcount_set(&work->nsui_refcnt, 2);
 		work->nsui_busy = true;
 		list_add_tail(&work->nsui_list, &nn->nfsd_ssc_mount_list);
@@ -1621,6 +1613,10 @@ static void nfsd4_cb_offload_release(struct nfsd4_callback *cb)
 static int nfsd4_cb_offload_done(struct nfsd4_callback *cb,
 				 struct rpc_task *task)
 {
+	struct nfsd4_cb_offload *cbo =
+		container_of(cb, struct nfsd4_cb_offload, co_cb);
+
+	trace_nfsd_cb_offload_done(&cbo->co_res.cb_stateid, task);
 	return 1;
 }
 
@@ -1768,7 +1764,13 @@ static int nfsd4_do_async_copy(void *data)
 		filp = nfs42_ssc_open(copy->ss_mnt, &copy->c_fh,
 				      &copy->stateid);
 		if (IS_ERR(filp)) {
-			nfserr = nfserr_offload_denied;
+			switch (PTR_ERR(filp)) {
+			case -EBADF:
+				nfserr = nfserr_wrong_type;
+				break;
+			default:
+				nfserr = nfserr_offload_denied;
+			}
 			nfsd4_interssc_disconnect(copy->ss_mnt);
 			goto do_callback;
 		}
@@ -1826,7 +1828,7 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		if (!nfs4_init_copy_state(nn, copy))
 			goto out_err;
 		refcount_set(&async_copy->refcount, 1);
-		memcpy(&copy->cp_res.cb_stateid, &copy->cp_stateid.stid,
+		memcpy(&copy->cp_res.cb_stateid, &copy->cp_stateid.cs_stid,
 			sizeof(copy->cp_res.cb_stateid));
 		dup_copy_fields(copy, async_copy);
 		async_copy->copy_task = kthread_create(nfsd4_do_async_copy,
@@ -1862,7 +1864,7 @@ find_async_copy(struct nfs4_client *clp, stateid_t *stateid)
 
 	spin_lock(&clp->async_lock);
 	list_for_each_entry(copy, &clp->async_copies, copies) {
-		if (memcmp(&copy->cp_stateid.stid, stateid, NFS4_STATEID_SIZE))
+		if (memcmp(&copy->cp_stateid.cs_stid, stateid, NFS4_STATEID_SIZE))
 			continue;
 		refcount_inc(&copy->refcount);
 		spin_unlock(&clp->async_lock);
@@ -1916,7 +1918,7 @@ nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	cps = nfs4_alloc_init_cpntf_state(nn, stid);
 	if (!cps)
 		goto out;
-	memcpy(&cn->cpn_cnr_stateid, &cps->cp_stateid.stid, sizeof(stateid_t));
+	memcpy(&cn->cpn_cnr_stateid, &cps->cp_stateid.cs_stid, sizeof(stateid_t));
 	memcpy(&cps->cp_p_stateid, &stid->sc_stateid, sizeof(stateid_t));
 	memcpy(&cps->cp_p_clid, &clp->cl_clientid, sizeof(clientid_t));
 
@@ -2633,9 +2635,6 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
 	status = nfserr_minor_vers_mismatch;
 	if (nfsd_minorversion(nn, args->minorversion, NFSD_TEST) <= 0)
 		goto out;
-	status = nfserr_resource;
-	if (args->opcnt > NFSD_MAX_OPS_PER_COMPOUND)
-		goto out;
 
 	status = nfs41_check_op_ordering(args);
 	if (status) {
@@ -2648,10 +2647,20 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
 
 	rqstp->rq_lease_breaker = (void **)&cstate->clp;
 
-	trace_nfsd_compound(rqstp, args->opcnt);
+	trace_nfsd_compound(rqstp, args->tag, args->taglen, args->client_opcnt);
 	while (!status && resp->opcnt < args->opcnt) {
 		op = &args->ops[resp->opcnt++];
 
+		if (unlikely(resp->opcnt == NFSD_MAX_OPS_PER_COMPOUND)) {
+			/* If there are still more operations to process,
+			 * stop here and report NFS4ERR_RESOURCE. */
+			if (cstate->minorversion == 0 &&
+			    args->client_opcnt > resp->opcnt) {
+				op->status = nfserr_resource;
+				goto encode_op;
+			}
+		}
+
 		/*
 		 * The XDR decode routines may have pre-set op->status;
 		 * for example, if there is a miscellaneous XDR error
@@ -2727,8 +2736,8 @@ encode_op:
 			status = op->status;
 		}
 
-		trace_nfsd_compound_status(args->opcnt, resp->opcnt, status,
-					   nfsd4_op_name(op->opnum));
+		trace_nfsd_compound_status(args->client_opcnt, resp->opcnt,
+					   status, nfsd4_op_name(op->opnum));
 
 		nfsd4_cstate_clear_replay(cstate);
 		nfsd4_increment_op_stats(op->opnum);
@@ -2762,28 +2771,49 @@ out:
 
 #define op_encode_channel_attrs_maxsz	(6 + 1 + 1)
 
-static inline u32 nfsd4_only_status_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+/*
+ * The _rsize() helpers are invoked by the NFSv4 COMPOUND decoder, which
+ * is called before sunrpc sets rq_res.buflen. Thus we have to compute
+ * the maximum payload size here, based on transport limits and the size
+ * of the remaining space in the rq_pages array.
+ */
+static u32 nfsd4_max_payload(const struct svc_rqst *rqstp)
+{
+	u32 buflen;
+
+	buflen = (rqstp->rq_page_end - rqstp->rq_next_page) * PAGE_SIZE;
+	buflen -= rqstp->rq_auth_slack;
+	buflen -= rqstp->rq_res.head[0].iov_len;
+	return min_t(u32, buflen, svc_max_payload(rqstp));
+}
+
+static u32 nfsd4_only_status_rsize(const struct svc_rqst *rqstp,
+				   const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_status_stateid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_status_stateid_rsize(const struct svc_rqst *rqstp,
+				      const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + op_encode_stateid_maxsz)* sizeof(__be32);
 }
 
-static inline u32 nfsd4_access_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_access_rsize(const struct svc_rqst *rqstp,
+			      const struct nfsd4_op *op)
 {
 	/* ac_supported, ac_resp_access */
 	return (op_encode_hdr_size + 2)* sizeof(__be32);
 }
 
-static inline u32 nfsd4_commit_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_commit_rsize(const struct svc_rqst *rqstp,
+			      const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + op_encode_verifier_maxsz) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_create_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_create_rsize(const struct svc_rqst *rqstp,
+			      const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + op_encode_change_info_maxsz
 		+ nfs4_fattr_bitmap_maxsz) * sizeof(__be32);
@@ -2794,17 +2824,17 @@ static inline u32 nfsd4_create_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op
  * the op prematurely if the estimate is too large.  We may turn off splice
  * reads unnecessarily.
  */
-static inline u32 nfsd4_getattr_rsize(struct svc_rqst *rqstp,
-				      struct nfsd4_op *op)
+static u32 nfsd4_getattr_rsize(const struct svc_rqst *rqstp,
+			       const struct nfsd4_op *op)
 {
-	u32 *bmap = op->u.getattr.ga_bmval;
+	const u32 *bmap = op->u.getattr.ga_bmval;
 	u32 bmap0 = bmap[0], bmap1 = bmap[1], bmap2 = bmap[2];
 	u32 ret = 0;
 
 	if (bmap0 & FATTR4_WORD0_ACL)
-		return svc_max_payload(rqstp);
+		return nfsd4_max_payload(rqstp);
 	if (bmap0 & FATTR4_WORD0_FS_LOCATIONS)
-		return svc_max_payload(rqstp);
+		return nfsd4_max_payload(rqstp);
 
 	if (bmap1 & FATTR4_WORD1_OWNER) {
 		ret += IDMAP_NAMESZ + 4;
@@ -2832,24 +2862,28 @@ static inline u32 nfsd4_getattr_rsize(struct svc_rqst *rqstp,
 	return ret;
 }
 
-static inline u32 nfsd4_getfh_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_getfh_rsize(const struct svc_rqst *rqstp,
+			     const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + 1) * sizeof(__be32) + NFS4_FHSIZE;
 }
 
-static inline u32 nfsd4_link_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_link_rsize(const struct svc_rqst *rqstp,
+			    const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + op_encode_change_info_maxsz)
 		* sizeof(__be32);
 }
 
-static inline u32 nfsd4_lock_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_lock_rsize(const struct svc_rqst *rqstp,
+			    const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + op_encode_lock_denied_maxsz)
 		* sizeof(__be32);
 }
 
-static inline u32 nfsd4_open_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_open_rsize(const struct svc_rqst *rqstp,
+			    const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + op_encode_stateid_maxsz
 		+ op_encode_change_info_maxsz + 1
@@ -2857,20 +2891,18 @@ static inline u32 nfsd4_open_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 		+ op_encode_delegation_maxsz) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_read_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_read_rsize(const struct svc_rqst *rqstp,
+			    const struct nfsd4_op *op)
 {
-	u32 maxcount = 0, rlen = 0;
-
-	maxcount = svc_max_payload(rqstp);
-	rlen = min(op->u.read.rd_length, maxcount);
+	u32 rlen = min(op->u.read.rd_length, nfsd4_max_payload(rqstp));
 
 	return (op_encode_hdr_size + 2 + XDR_QUADLEN(rlen)) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_read_plus_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_read_plus_rsize(const struct svc_rqst *rqstp,
+				 const struct nfsd4_op *op)
 {
-	u32 maxcount = svc_max_payload(rqstp);
-	u32 rlen = min(op->u.read.rd_length, maxcount);
+	u32 rlen = min(op->u.read.rd_length, nfsd4_max_payload(rqstp));
 	/*
 	 * If we detect that the file changed during hole encoding, then we
 	 * recover by encoding the remaining reply as data. This means we need
@@ -2881,70 +2913,77 @@ static inline u32 nfsd4_read_plus_rsize(struct svc_rqst *rqstp, struct nfsd4_op
 	return (op_encode_hdr_size + 2 + seg_len + XDR_QUADLEN(rlen)) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_readdir_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_readdir_rsize(const struct svc_rqst *rqstp,
+			       const struct nfsd4_op *op)
 {
-	u32 maxcount = 0, rlen = 0;
-
-	maxcount = svc_max_payload(rqstp);
-	rlen = min(op->u.readdir.rd_maxcount, maxcount);
+	u32 rlen = min(op->u.readdir.rd_maxcount, nfsd4_max_payload(rqstp));
 
 	return (op_encode_hdr_size + op_encode_verifier_maxsz +
 		XDR_QUADLEN(rlen)) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_readlink_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_readlink_rsize(const struct svc_rqst *rqstp,
+				const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + 1) * sizeof(__be32) + PAGE_SIZE;
 }
 
-static inline u32 nfsd4_remove_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_remove_rsize(const struct svc_rqst *rqstp,
+			      const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + op_encode_change_info_maxsz)
 		* sizeof(__be32);
 }
 
-static inline u32 nfsd4_rename_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_rename_rsize(const struct svc_rqst *rqstp,
+			      const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + op_encode_change_info_maxsz
 		+ op_encode_change_info_maxsz) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_sequence_rsize(struct svc_rqst *rqstp,
-				       struct nfsd4_op *op)
+static u32 nfsd4_sequence_rsize(const struct svc_rqst *rqstp,
+				const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size
 		+ XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_test_stateid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_test_stateid_rsize(const struct svc_rqst *rqstp,
+				    const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + 1 + op->u.test_stateid.ts_num_ids)
 		* sizeof(__be32);
 }
 
-static inline u32 nfsd4_setattr_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_setattr_rsize(const struct svc_rqst *rqstp,
+			       const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + nfs4_fattr_bitmap_maxsz) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_secinfo_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_secinfo_rsize(const struct svc_rqst *rqstp,
+			       const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + RPC_AUTH_MAXFLAVOR *
 		(4 + XDR_QUADLEN(GSS_OID_MAX_LEN))) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_setclientid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_setclientid_rsize(const struct svc_rqst *rqstp,
+				   const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + 2 + XDR_QUADLEN(NFS4_VERIFIER_SIZE)) *
 								sizeof(__be32);
 }
 
-static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_write_rsize(const struct svc_rqst *rqstp,
+			     const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + 2 + op_encode_verifier_maxsz) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_exchange_id_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_exchange_id_rsize(const struct svc_rqst *rqstp,
+				   const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + 2 + 1 + /* eir_clientid, eir_sequenceid */\
 		1 + 1 + /* eir_flags, spr_how */\
@@ -2958,14 +2997,16 @@ static inline u32 nfsd4_exchange_id_rsize(struct svc_rqst *rqstp, struct nfsd4_o
 		0 /* ignored eir_server_impl_id contents */) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_bind_conn_to_session_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_bind_conn_to_session_rsize(const struct svc_rqst *rqstp,
+					    const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + \
 		XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + /* bctsr_sessid */\
 		2 /* bctsr_dir, use_conn_in_rdma_mode */) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_create_session_rsize(const struct svc_rqst *rqstp,
+				      const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + \
 		XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + /* sessionid */\
@@ -2974,7 +3015,8 @@ static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd
 		op_encode_channel_attrs_maxsz) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_copy_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_copy_rsize(const struct svc_rqst *rqstp,
+			    const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size +
 		1 /* wr_callback */ +
@@ -2986,16 +3028,16 @@ static inline u32 nfsd4_copy_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 		1 /* cr_synchronous */) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_offload_status_rsize(struct svc_rqst *rqstp,
-					     struct nfsd4_op *op)
+static u32 nfsd4_offload_status_rsize(const struct svc_rqst *rqstp,
+				      const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size +
 		2 /* osr_count */ +
 		1 /* osr_complete<1> optional 0 for now */) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_copy_notify_rsize(struct svc_rqst *rqstp,
-					struct nfsd4_op *op)
+static u32 nfsd4_copy_notify_rsize(const struct svc_rqst *rqstp,
+				   const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size +
 		3 /* cnr_lease_time */ +
@@ -3010,12 +3052,10 @@ static inline u32 nfsd4_copy_notify_rsize(struct svc_rqst *rqstp,
 }
 
 #ifdef CONFIG_NFSD_PNFS
-static inline u32 nfsd4_getdeviceinfo_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_getdeviceinfo_rsize(const struct svc_rqst *rqstp,
+				     const struct nfsd4_op *op)
 {
-	u32 maxcount = 0, rlen = 0;
-
-	maxcount = svc_max_payload(rqstp);
-	rlen = min(op->u.getdeviceinfo.gd_maxcount, maxcount);
+	u32 rlen = min(op->u.getdeviceinfo.gd_maxcount, nfsd4_max_payload(rqstp));
 
 	return (op_encode_hdr_size +
 		1 /* gd_layout_type*/ +
@@ -3028,7 +3068,8 @@ static inline u32 nfsd4_getdeviceinfo_rsize(struct svc_rqst *rqstp, struct nfsd4
  * so we need to define an arbitrary upper bound here.
  */
 #define MAX_LAYOUT_SIZE		128
-static inline u32 nfsd4_layoutget_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_layoutget_rsize(const struct svc_rqst *rqstp,
+				 const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size +
 		1 /* logr_return_on_close */ +
@@ -3037,14 +3078,16 @@ static inline u32 nfsd4_layoutget_rsize(struct svc_rqst *rqstp, struct nfsd4_op
 		MAX_LAYOUT_SIZE) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_layoutcommit_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_layoutcommit_rsize(const struct svc_rqst *rqstp,
+				    const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size +
 		1 /* locr_newsize */ +
 		2 /* ns_size */) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_layoutreturn_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_layoutreturn_rsize(const struct svc_rqst *rqstp,
+				    const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size +
 		1 /* lrs_stateid */ +
@@ -3053,41 +3096,36 @@ static inline u32 nfsd4_layoutreturn_rsize(struct svc_rqst *rqstp, struct nfsd4_
 #endif /* CONFIG_NFSD_PNFS */
 
 
-static inline u32 nfsd4_seek_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+static u32 nfsd4_seek_rsize(const struct svc_rqst *rqstp,
+			    const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + 3) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_getxattr_rsize(struct svc_rqst *rqstp,
-				       struct nfsd4_op *op)
+static u32 nfsd4_getxattr_rsize(const struct svc_rqst *rqstp,
+				const struct nfsd4_op *op)
 {
-	u32 maxcount, rlen;
-
-	maxcount = svc_max_payload(rqstp);
-	rlen = min_t(u32, XATTR_SIZE_MAX, maxcount);
+	u32 rlen = min_t(u32, XATTR_SIZE_MAX, nfsd4_max_payload(rqstp));
 
 	return (op_encode_hdr_size + 1 + XDR_QUADLEN(rlen)) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_setxattr_rsize(struct svc_rqst *rqstp,
-				       struct nfsd4_op *op)
+static u32 nfsd4_setxattr_rsize(const struct svc_rqst *rqstp,
+				const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + op_encode_change_info_maxsz)
 		* sizeof(__be32);
 }
-static inline u32 nfsd4_listxattrs_rsize(struct svc_rqst *rqstp,
-					 struct nfsd4_op *op)
+static u32 nfsd4_listxattrs_rsize(const struct svc_rqst *rqstp,
+				  const struct nfsd4_op *op)
 {
-	u32 maxcount, rlen;
-
-	maxcount = svc_max_payload(rqstp);
-	rlen = min(op->u.listxattrs.lsxa_maxcount, maxcount);
+	u32 rlen = min(op->u.listxattrs.lsxa_maxcount, nfsd4_max_payload(rqstp));
 
 	return (op_encode_hdr_size + 4 + XDR_QUADLEN(rlen)) * sizeof(__be32);
 }
 
-static inline u32 nfsd4_removexattr_rsize(struct svc_rqst *rqstp,
-					  struct nfsd4_op *op)
+static u32 nfsd4_removexattr_rsize(const struct svc_rqst *rqstp,
+				   const struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + op_encode_change_info_maxsz)
 		* sizeof(__be32);
@@ -3576,6 +3614,7 @@ static const struct svc_procedure nfsd_procedures4[2] = {
 		.pc_decode = nfssvc_decode_voidarg,
 		.pc_encode = nfssvc_encode_voidres,
 		.pc_argsize = sizeof(struct nfsd_voidargs),
+		.pc_argzero = sizeof(struct nfsd_voidargs),
 		.pc_ressize = sizeof(struct nfsd_voidres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = 1,
@@ -3586,6 +3625,7 @@ static const struct svc_procedure nfsd_procedures4[2] = {
 		.pc_decode = nfs4svc_decode_compoundargs,
 		.pc_encode = nfs4svc_encode_compoundres,
 		.pc_argsize = sizeof(struct nfsd4_compoundargs),
+		.pc_argzero = offsetof(struct nfsd4_compoundargs, iops),
 		.pc_ressize = sizeof(struct nfsd4_compoundres),
 		.pc_release = nfsd4_release_compoundargs,
 		.pc_cachetype = RC_NOCACHE,
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index c634483d85d2..5d680045fa2c 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -807,16 +807,18 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg,
 			if (get_user(namelen, &ci->cc_name.cn_len))
 				return -EFAULT;
 			name.data = memdup_user(&ci->cc_name.cn_id, namelen);
-			if (IS_ERR_OR_NULL(name.data))
-				return -EFAULT;
+			if (IS_ERR(name.data))
+				return PTR_ERR(name.data);
 			name.len = namelen;
 			get_user(princhashlen, &ci->cc_princhash.cp_len);
 			if (princhashlen > 0) {
 				princhash.data = memdup_user(
 						&ci->cc_princhash.cp_data,
 						princhashlen);
-				if (IS_ERR_OR_NULL(princhash.data))
-					return -EFAULT;
+				if (IS_ERR(princhash.data)) {
+					kfree(name.data);
+					return PTR_ERR(princhash.data);
+				}
 				princhash.len = princhashlen;
 			} else
 				princhash.len = 0;
@@ -827,8 +829,8 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg,
 			if (get_user(namelen, &cnm->cn_len))
 				return -EFAULT;
 			name.data = memdup_user(&cnm->cn_id, namelen);
-			if (IS_ERR_OR_NULL(name.data))
-				return -EFAULT;
+			if (IS_ERR(name.data))
+				return PTR_ERR(name.data);
 			name.len = namelen;
 		}
 		if (name.len > 5 && memcmp(name.data, "hash:", 5) == 0) {
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c5d199d7e6b4..198d7abf34e4 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -160,6 +160,13 @@ static bool is_client_expired(struct nfs4_client *clp)
 	return clp->cl_time == 0;
 }
 
+static void nfsd4_dec_courtesy_client_count(struct nfsd_net *nn,
+					struct nfs4_client *clp)
+{
+	if (clp->cl_state != NFSD4_ACTIVE)
+		atomic_add_unless(&nn->nfsd_courtesy_clients, -1, 0);
+}
+
 static __be32 get_client_locked(struct nfs4_client *clp)
 {
 	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
@@ -169,6 +176,7 @@ static __be32 get_client_locked(struct nfs4_client *clp)
 	if (is_client_expired(clp))
 		return nfserr_expired;
 	atomic_inc(&clp->cl_rpc_users);
+	nfsd4_dec_courtesy_client_count(nn, clp);
 	clp->cl_state = NFSD4_ACTIVE;
 	return nfs_ok;
 }
@@ -190,6 +198,7 @@ renew_client_locked(struct nfs4_client *clp)
 
 	list_move_tail(&clp->cl_lru, &nn->client_lru);
 	clp->cl_time = ktime_get_boottime_seconds();
+	nfsd4_dec_courtesy_client_count(nn, clp);
 	clp->cl_state = NFSD4_ACTIVE;
 }
 
@@ -357,6 +366,8 @@ nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb)
 static int
 nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task)
 {
+	trace_nfsd_cb_notify_lock_done(&zero_stateid, task);
+
 	/*
 	 * Since this is just an optimization, we don't try very hard if it
 	 * turns out not to succeed. We'll requeue it on NFS4ERR_DELAY, and
@@ -963,19 +974,19 @@ out_free:
  * Create a unique stateid_t to represent each COPY.
  */
 static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid,
-			      unsigned char sc_type)
+			      unsigned char cs_type)
 {
 	int new_id;
 
-	stid->stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time;
-	stid->stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id;
-	stid->sc_type = sc_type;
+	stid->cs_stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time;
+	stid->cs_stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id;
+	stid->cs_type = cs_type;
 
 	idr_preload(GFP_KERNEL);
 	spin_lock(&nn->s2s_cp_lock);
 	new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, stid, 0, 0, GFP_NOWAIT);
-	stid->stid.si_opaque.so_id = new_id;
-	stid->stid.si_generation = 1;
+	stid->cs_stid.si_opaque.so_id = new_id;
+	stid->cs_stid.si_generation = 1;
 	spin_unlock(&nn->s2s_cp_lock);
 	idr_preload_end();
 	if (new_id < 0)
@@ -997,7 +1008,7 @@ struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn,
 	if (!cps)
 		return NULL;
 	cps->cpntf_time = ktime_get_boottime_seconds();
-	refcount_set(&cps->cp_stateid.sc_count, 1);
+	refcount_set(&cps->cp_stateid.cs_count, 1);
 	if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID))
 		goto out_free;
 	spin_lock(&nn->s2s_cp_lock);
@@ -1013,11 +1024,11 @@ void nfs4_free_copy_state(struct nfsd4_copy *copy)
 {
 	struct nfsd_net *nn;
 
-	WARN_ON_ONCE(copy->cp_stateid.sc_type != NFS4_COPY_STID);
+	WARN_ON_ONCE(copy->cp_stateid.cs_type != NFS4_COPY_STID);
 	nn = net_generic(copy->cp_clp->net, nfsd_net_id);
 	spin_lock(&nn->s2s_cp_lock);
 	idr_remove(&nn->s2s_cp_stateids,
-		   copy->cp_stateid.stid.si_opaque.so_id);
+		   copy->cp_stateid.cs_stid.si_opaque.so_id);
 	spin_unlock(&nn->s2s_cp_lock);
 }
 
@@ -1049,6 +1060,12 @@ static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp)
 
 static void nfs4_free_deleg(struct nfs4_stid *stid)
 {
+	struct nfs4_delegation *dp = delegstateid(stid);
+
+	WARN_ON_ONCE(!list_empty(&stid->sc_cp_list));
+	WARN_ON_ONCE(!list_empty(&dp->dl_perfile));
+	WARN_ON_ONCE(!list_empty(&dp->dl_perclnt));
+	WARN_ON_ONCE(!list_empty(&dp->dl_recall_lru));
 	kmem_cache_free(deleg_slab, stid);
 	atomic_long_dec(&num_delegations);
 }
@@ -1462,6 +1479,7 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid)
 	release_all_access(stp);
 	if (stp->st_stateowner)
 		nfs4_put_stateowner(stp->st_stateowner);
+	WARN_ON(!list_empty(&stid->sc_cp_list));
 	kmem_cache_free(stateid_slab, stid);
 }
 
@@ -2233,6 +2251,7 @@ __destroy_client(struct nfs4_client *clp)
 	if (clp->cl_cb_conn.cb_xprt)
 		svc_xprt_put(clp->cl_cb_conn.cb_xprt);
 	atomic_add_unless(&nn->nfs4_client_count, -1, 0);
+	nfsd4_dec_courtesy_client_count(nn, clp);
 	free_client(clp);
 	wake_up_all(&expiry_wq);
 }
@@ -2478,7 +2497,7 @@ static const char *cb_state2str(int state)
 
 static int client_info_show(struct seq_file *m, void *v)
 {
-	struct inode *inode = m->private;
+	struct inode *inode = file_inode(m->file);
 	struct nfs4_client *clp;
 	u64 clid;
 
@@ -2518,17 +2537,7 @@ static int client_info_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int client_info_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, client_info_show, inode);
-}
-
-static const struct file_operations client_info_fops = {
-	.open		= client_info_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(client_info);
 
 static void *states_start(struct seq_file *s, loff_t *pos)
 	__acquires(&clp->cl_lock)
@@ -4337,7 +4346,27 @@ out:
 	return -ENOMEM;
 }
 
-void nfsd4_init_leases_net(struct nfsd_net *nn)
+static unsigned long
+nfsd_courtesy_client_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+	int cnt;
+	struct nfsd_net *nn = container_of(shrink,
+			struct nfsd_net, nfsd_client_shrinker);
+
+	cnt = atomic_read(&nn->nfsd_courtesy_clients);
+	if (cnt > 0)
+		mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0);
+	return (unsigned long)cnt;
+}
+
+static unsigned long
+nfsd_courtesy_client_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+	return SHRINK_STOP;
+}
+
+int
+nfsd4_init_leases_net(struct nfsd_net *nn)
 {
 	struct sysinfo si;
 	u64 max_clients;
@@ -4356,6 +4385,18 @@ void nfsd4_init_leases_net(struct nfsd_net *nn)
 	max_clients = (u64)si.totalram * si.mem_unit / (1024 * 1024 * 1024);
 	max_clients *= NFS4_CLIENTS_PER_GB;
 	nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB);
+
+	atomic_set(&nn->nfsd_courtesy_clients, 0);
+	nn->nfsd_client_shrinker.scan_objects = nfsd_courtesy_client_scan;
+	nn->nfsd_client_shrinker.count_objects = nfsd_courtesy_client_count;
+	nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS;
+	return register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client");
+}
+
+void
+nfsd4_leases_net_shutdown(struct nfsd_net *nn)
+{
+	unregister_shrinker(&nn->nfsd_client_shrinker);
 }
 
 static void init_nfs4_replay(struct nfs4_replay *rp)
@@ -4715,6 +4756,35 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)
 	return ret;
 }
 
+static bool nfsd4_deleg_present(const struct inode *inode)
+{
+	struct file_lock_context *ctx = smp_load_acquire(&inode->i_flctx);
+
+	return ctx && !list_empty_careful(&ctx->flc_lease);
+}
+
+/**
+ * nfsd_wait_for_delegreturn - wait for delegations to be returned
+ * @rqstp: the RPC transaction being executed
+ * @inode: in-core inode of the file being waited for
+ *
+ * The timeout prevents deadlock if all nfsd threads happen to be
+ * tied up waiting for returning delegations.
+ *
+ * Return values:
+ *   %true: delegation was returned
+ *   %false: timed out waiting for delegreturn
+ */
+bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, struct inode *inode)
+{
+	long __maybe_unused timeo;
+
+	timeo = wait_var_event_timeout(inode, !nfsd4_deleg_present(inode),
+				       NFSD_DELEGRETURN_TIMEOUT);
+	trace_nfsd_delegret_wakeup(rqstp, inode, timeo);
+	return timeo > 0;
+}
+
 static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb)
 {
 	struct nfs4_delegation *dp = cb_to_delegation(cb);
@@ -4743,6 +4813,8 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb,
 {
 	struct nfs4_delegation *dp = cb_to_delegation(cb);
 
+	trace_nfsd_cb_recall_done(&dp->dl_stid.sc_stateid, task);
+
 	if (dp->dl_stid.sc_type == NFS4_CLOSED_DELEG_STID ||
 	    dp->dl_stid.sc_type == NFS4_REVOKED_DELEG_STID)
 	        return 1;
@@ -4788,18 +4860,17 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 	 * We're assuming the state code never drops its reference
 	 * without first removing the lease.  Since we're in this lease
 	 * callback (and since the lease code is serialized by the
-	 * i_lock) we know the server hasn't removed the lease yet, and
+	 * flc_lock) we know the server hasn't removed the lease yet, and
 	 * we know it's safe to take a reference.
 	 */
 	refcount_inc(&dp->dl_stid.sc_count);
-	nfsd4_run_cb(&dp->dl_recall);
+	WARN_ON_ONCE(!nfsd4_run_cb(&dp->dl_recall));
 }
 
-/* Called from break_lease() with i_lock held. */
+/* Called from break_lease() with flc_lock held. */
 static bool
 nfsd_break_deleg_cb(struct file_lock *fl)
 {
-	bool ret = false;
 	struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner;
 	struct nfs4_file *fp = dp->dl_stid.sc_file;
 	struct nfs4_client *clp = dp->dl_stid.sc_client;
@@ -4825,7 +4896,7 @@ nfsd_break_deleg_cb(struct file_lock *fl)
 	fp->fi_had_conflict = true;
 	nfsd_break_one_deleg(dp);
 	spin_unlock(&fp->fi_lock);
-	return ret;
+	return false;
 }
 
 /**
@@ -5878,8 +5949,11 @@ nfs4_get_client_reaplist(struct nfsd_net *nn, struct list_head *reaplist,
 			goto exp_client;
 		if (!state_expired(lt, clp->cl_time))
 			break;
-		if (!atomic_read(&clp->cl_rpc_users))
+		if (!atomic_read(&clp->cl_rpc_users)) {
+			if (clp->cl_state == NFSD4_ACTIVE)
+				atomic_inc(&nn->nfsd_courtesy_clients);
 			clp->cl_state = NFSD4_COURTESY;
+		}
 		if (!client_has_state(clp))
 			goto exp_client;
 		if (!nfs4_anylock_blockers(clp))
@@ -5894,10 +5968,49 @@ exp_client:
 	spin_unlock(&nn->client_lock);
 }
 
+static void
+nfs4_get_courtesy_client_reaplist(struct nfsd_net *nn,
+				struct list_head *reaplist)
+{
+	unsigned int maxreap = 0, reapcnt = 0;
+	struct list_head *pos, *next;
+	struct nfs4_client *clp;
+
+	maxreap = NFSD_CLIENT_MAX_TRIM_PER_RUN;
+	INIT_LIST_HEAD(reaplist);
+
+	spin_lock(&nn->client_lock);
+	list_for_each_safe(pos, next, &nn->client_lru) {
+		clp = list_entry(pos, struct nfs4_client, cl_lru);
+		if (clp->cl_state == NFSD4_ACTIVE)
+			break;
+		if (reapcnt >= maxreap)
+			break;
+		if (!mark_client_expired_locked(clp)) {
+			list_add(&clp->cl_lru, reaplist);
+			reapcnt++;
+		}
+	}
+	spin_unlock(&nn->client_lock);
+}
+
+static void
+nfs4_process_client_reaplist(struct list_head *reaplist)
+{
+	struct list_head *pos, *next;
+	struct nfs4_client *clp;
+
+	list_for_each_safe(pos, next, reaplist) {
+		clp = list_entry(pos, struct nfs4_client, cl_lru);
+		trace_nfsd_clid_purged(&clp->cl_clientid);
+		list_del_init(&clp->cl_lru);
+		expire_client(clp);
+	}
+}
+
 static time64_t
 nfs4_laundromat(struct nfsd_net *nn)
 {
-	struct nfs4_client *clp;
 	struct nfs4_openowner *oo;
 	struct nfs4_delegation *dp;
 	struct nfs4_ol_stateid *stp;
@@ -5920,18 +6033,14 @@ nfs4_laundromat(struct nfsd_net *nn)
 	spin_lock(&nn->s2s_cp_lock);
 	idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) {
 		cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid);
-		if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID &&
+		if (cps->cp_stateid.cs_type == NFS4_COPYNOTIFY_STID &&
 				state_expired(&lt, cps->cpntf_time))
 			_free_cpntf_state_locked(nn, cps);
 	}
 	spin_unlock(&nn->s2s_cp_lock);
 	nfs4_get_client_reaplist(nn, &reaplist, &lt);
-	list_for_each_safe(pos, next, &reaplist) {
-		clp = list_entry(pos, struct nfs4_client, cl_lru);
-		trace_nfsd_clid_purged(&clp->cl_clientid);
-		list_del_init(&clp->cl_lru);
-		expire_client(clp);
-	}
+	nfs4_process_client_reaplist(&reaplist);
+
 	spin_lock(&state_lock);
 	list_for_each_safe(pos, next, &nn->del_recall_lru) {
 		dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
@@ -6014,6 +6123,18 @@ laundromat_main(struct work_struct *laundry)
 	queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ);
 }
 
+static void
+courtesy_client_reaper(struct work_struct *reaper)
+{
+	struct list_head reaplist;
+	struct delayed_work *dwork = to_delayed_work(reaper);
+	struct nfsd_net *nn = container_of(dwork, struct nfsd_net,
+					nfsd_shrinker_work);
+
+	nfs4_get_courtesy_client_reaplist(nn, &reaplist);
+	nfs4_process_client_reaplist(&reaplist);
+}
+
 static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp)
 {
 	if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle))
@@ -6149,6 +6270,7 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		     struct nfs4_stid **s, struct nfsd_net *nn)
 {
 	__be32 status;
+	struct nfs4_stid *stid;
 	bool return_revoked = false;
 
 	/*
@@ -6171,15 +6293,16 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 	}
 	if (status)
 		return status;
-	*s = find_stateid_by_type(cstate->clp, stateid, typemask);
-	if (!*s)
+	stid = find_stateid_by_type(cstate->clp, stateid, typemask);
+	if (!stid)
 		return nfserr_bad_stateid;
-	if (((*s)->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) {
-		nfs4_put_stid(*s);
+	if ((stid->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) {
+		nfs4_put_stid(stid);
 		if (cstate->minorversion)
 			return nfserr_deleg_revoked;
 		return nfserr_bad_stateid;
 	}
+	*s = stid;
 	return nfs_ok;
 }
 
@@ -6244,12 +6367,12 @@ out:
 static void
 _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps)
 {
-	WARN_ON_ONCE(cps->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID);
-	if (!refcount_dec_and_test(&cps->cp_stateid.sc_count))
+	WARN_ON_ONCE(cps->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID);
+	if (!refcount_dec_and_test(&cps->cp_stateid.cs_count))
 		return;
 	list_del(&cps->cp_list);
 	idr_remove(&nn->s2s_cp_stateids,
-		   cps->cp_stateid.stid.si_opaque.so_id);
+		   cps->cp_stateid.cs_stid.si_opaque.so_id);
 	kfree(cps);
 }
 /*
@@ -6271,12 +6394,12 @@ __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st,
 	if (cps_t) {
 		state = container_of(cps_t, struct nfs4_cpntf_state,
 				     cp_stateid);
-		if (state->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID) {
+		if (state->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID) {
 			state = NULL;
 			goto unlock;
 		}
 		if (!clp)
-			refcount_inc(&state->cp_stateid.sc_count);
+			refcount_inc(&state->cp_stateid.cs_count);
 		else
 			_free_cpntf_state_locked(nn, state);
 	}
@@ -6684,6 +6807,7 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
 	struct nfs4_client *clp = s->st_stid.sc_client;
 	bool unhashed;
 	LIST_HEAD(reaplist);
+	struct nfs4_ol_stateid *stp;
 
 	spin_lock(&clp->cl_lock);
 	unhashed = unhash_open_stateid(s, &reaplist);
@@ -6692,6 +6816,8 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
 		if (unhashed)
 			put_ol_stateid_locked(s, &reaplist);
 		spin_unlock(&clp->cl_lock);
+		list_for_each_entry(stp, &reaplist, st_locks)
+			nfs4_free_cpntf_statelist(clp->net, &stp->st_stid);
 		free_ol_stateid_reaplist(&reaplist);
 	} else {
 		spin_unlock(&clp->cl_lock);
@@ -6775,6 +6901,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		goto put_stateid;
 
+	wake_up_var(d_inode(cstate->current_fh.fh_dentry));
 	destroy_delegation(dp);
 put_stateid:
 	nfs4_put_stid(&dp->dl_stid);
@@ -7830,6 +7957,7 @@ static int nfs4_state_create_net(struct net *net)
 	INIT_LIST_HEAD(&nn->blocked_locks_lru);
 
 	INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main);
+	INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, courtesy_client_reaper);
 	get_net(net);
 
 	return 0;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 1e9690a061ec..bcfeb1a922c0 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -42,6 +42,8 @@
 #include <linux/sunrpc/svcauth_gss.h>
 #include <linux/sunrpc/addr.h>
 #include <linux/xattr.h>
+#include <linux/vmalloc.h>
+
 #include <uapi/linux/xattr.h>
 
 #include "idmap.h"
@@ -791,6 +793,7 @@ nfsd4_decode_commit(struct nfsd4_compoundargs *argp, struct nfsd4_commit *commit
 		return nfserr_bad_xdr;
 	if (xdr_stream_decode_u32(argp->xdr, &commit->co_count) < 0)
 		return nfserr_bad_xdr;
+	memset(&commit->co_verf, 0, sizeof(commit->co_verf));
 	return nfs_ok;
 }
 
@@ -799,6 +802,7 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create
 {
 	__be32 *p, status;
 
+	memset(create, 0, sizeof(*create));
 	if (xdr_stream_decode_u32(argp->xdr, &create->cr_type) < 0)
 		return nfserr_bad_xdr;
 	switch (create->cr_type) {
@@ -848,6 +852,7 @@ nfsd4_decode_delegreturn(struct nfsd4_compoundargs *argp, struct nfsd4_delegretu
 static inline __be32
 nfsd4_decode_getattr(struct nfsd4_compoundargs *argp, struct nfsd4_getattr *getattr)
 {
+	memset(getattr, 0, sizeof(*getattr));
 	return nfsd4_decode_bitmap4(argp, getattr->ga_bmval,
 				    ARRAY_SIZE(getattr->ga_bmval));
 }
@@ -855,6 +860,7 @@ nfsd4_decode_getattr(struct nfsd4_compoundargs *argp, struct nfsd4_getattr *geta
 static __be32
 nfsd4_decode_link(struct nfsd4_compoundargs *argp, struct nfsd4_link *link)
 {
+	memset(link, 0, sizeof(*link));
 	return nfsd4_decode_component4(argp, &link->li_name, &link->li_namelen);
 }
 
@@ -903,6 +909,7 @@ nfsd4_decode_locker4(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock)
 static __be32
 nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock)
 {
+	memset(lock, 0, sizeof(*lock));
 	if (xdr_stream_decode_u32(argp->xdr, &lock->lk_type) < 0)
 		return nfserr_bad_xdr;
 	if ((lock->lk_type < NFS4_READ_LT) || (lock->lk_type > NFS4_WRITEW_LT))
@@ -919,6 +926,7 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock)
 static __be32
 nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt)
 {
+	memset(lockt, 0, sizeof(*lockt));
 	if (xdr_stream_decode_u32(argp->xdr, &lockt->lt_type) < 0)
 		return nfserr_bad_xdr;
 	if ((lockt->lt_type < NFS4_READ_LT) || (lockt->lt_type > NFS4_WRITEW_LT))
@@ -1140,11 +1148,8 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
 	__be32 status;
 	u32 dummy;
 
-	memset(open->op_bmval, 0, sizeof(open->op_bmval));
-	open->op_iattr.ia_valid = 0;
-	open->op_openowner = NULL;
+	memset(open, 0, sizeof(*open));
 
-	open->op_xdr_error = 0;
 	if (xdr_stream_decode_u32(argp->xdr, &open->op_seqid) < 0)
 		return nfserr_bad_xdr;
 	/* deleg_want is ignored */
@@ -1179,6 +1184,8 @@ nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_con
 	if (xdr_stream_decode_u32(argp->xdr, &open_conf->oc_seqid) < 0)
 		return nfserr_bad_xdr;
 
+	memset(&open_conf->oc_resp_stateid, 0,
+	       sizeof(open_conf->oc_resp_stateid));
 	return nfs_ok;
 }
 
@@ -1187,6 +1194,7 @@ nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_d
 {
 	__be32 status;
 
+	memset(open_down, 0, sizeof(*open_down));
 	status = nfsd4_decode_stateid4(argp, &open_down->od_stateid);
 	if (status)
 		return status;
@@ -1216,6 +1224,7 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh)
 	if (!putfh->pf_fhval)
 		return nfserr_jukebox;
 
+	putfh->no_verify = false;
 	return nfs_ok;
 }
 
@@ -1232,6 +1241,7 @@ nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read)
 {
 	__be32 status;
 
+	memset(read, 0, sizeof(*read));
 	status = nfsd4_decode_stateid4(argp, &read->rd_stateid);
 	if (status)
 		return status;
@@ -1248,6 +1258,7 @@ nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *read
 {
 	__be32 status;
 
+	memset(readdir, 0, sizeof(*readdir));
 	if (xdr_stream_decode_u64(argp->xdr, &readdir->rd_cookie) < 0)
 		return nfserr_bad_xdr;
 	status = nfsd4_decode_verifier4(argp, &readdir->rd_verf);
@@ -1267,6 +1278,7 @@ nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *read
 static __be32
 nfsd4_decode_remove(struct nfsd4_compoundargs *argp, struct nfsd4_remove *remove)
 {
+	memset(&remove->rm_cinfo, 0, sizeof(remove->rm_cinfo));
 	return nfsd4_decode_component4(argp, &remove->rm_name, &remove->rm_namelen);
 }
 
@@ -1275,6 +1287,7 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename
 {
 	__be32 status;
 
+	memset(rename, 0, sizeof(*rename));
 	status = nfsd4_decode_component4(argp, &rename->rn_sname, &rename->rn_snamelen);
 	if (status)
 		return status;
@@ -1291,6 +1304,7 @@ static __be32
 nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp,
 		     struct nfsd4_secinfo *secinfo)
 {
+	secinfo->si_exp = NULL;
 	return nfsd4_decode_component4(argp, &secinfo->si_name, &secinfo->si_namelen);
 }
 
@@ -1299,6 +1313,7 @@ nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *seta
 {
 	__be32 status;
 
+	memset(setattr, 0, sizeof(*setattr));
 	status = nfsd4_decode_stateid4(argp, &setattr->sa_stateid);
 	if (status)
 		return status;
@@ -1313,6 +1328,8 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient
 {
 	__be32 *p, status;
 
+	memset(setclientid, 0, sizeof(*setclientid));
+
 	if (argp->minorversion >= 1)
 		return nfserr_notsupp;
 
@@ -1369,6 +1386,8 @@ nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify
 {
 	__be32 *p, status;
 
+	memset(verify, 0, sizeof(*verify));
+
 	status = nfsd4_decode_bitmap4(argp, verify->ve_bmval,
 				      ARRAY_SIZE(verify->ve_bmval));
 	if (status)
@@ -1408,6 +1427,9 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write)
 	if (!xdr_stream_subsegment(argp->xdr, &write->wr_payload, write->wr_buflen))
 		return nfserr_bad_xdr;
 
+	write->wr_bytes_written = 0;
+	write->wr_how_written = 0;
+	memset(&write->wr_verifier, 0, sizeof(write->wr_verifier));
 	return nfs_ok;
 }
 
@@ -1432,6 +1454,7 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel
 
 static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, struct nfsd4_backchannel_ctl *bc)
 {
+	memset(bc, 0, sizeof(*bc));
 	if (xdr_stream_decode_u32(argp->xdr, &bc->bc_cb_program) < 0)
 		return nfserr_bad_xdr;
 	return nfsd4_decode_cb_sec(argp, &bc->bc_cb_sec);
@@ -1442,6 +1465,7 @@ static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp,
 	u32 use_conn_in_rdma_mode;
 	__be32 status;
 
+	memset(bcts, 0, sizeof(*bcts));
 	status = nfsd4_decode_sessionid4(argp, &bcts->sessionid);
 	if (status)
 		return status;
@@ -1583,6 +1607,7 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp,
 {
 	__be32 status;
 
+	memset(exid, 0, sizeof(*exid));
 	status = nfsd4_decode_verifier4(argp, &exid->verifier);
 	if (status)
 		return status;
@@ -1635,6 +1660,7 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
 {
 	__be32 status;
 
+	memset(sess, 0, sizeof(*sess));
 	status = nfsd4_decode_clientid4(argp, &sess->clientid);
 	if (status)
 		return status;
@@ -1650,11 +1676,7 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
 		return status;
 	if (xdr_stream_decode_u32(argp->xdr, &sess->callback_prog) < 0)
 		return nfserr_bad_xdr;
-	status = nfsd4_decode_cb_sec(argp, &sess->cb_sec);
-	if (status)
-		return status;
-
-	return nfs_ok;
+	return nfsd4_decode_cb_sec(argp, &sess->cb_sec);
 }
 
 static __be32
@@ -1678,6 +1700,7 @@ nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp,
 {
 	__be32 status;
 
+	memset(gdev, 0, sizeof(*gdev));
 	status = nfsd4_decode_deviceid4(argp, &gdev->gd_devid);
 	if (status)
 		return status;
@@ -1698,6 +1721,7 @@ nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp,
 {
 	__be32 *p, status;
 
+	memset(lcp, 0, sizeof(*lcp));
 	if (xdr_stream_decode_u64(argp->xdr, &lcp->lc_seg.offset) < 0)
 		return nfserr_bad_xdr;
 	if (xdr_stream_decode_u64(argp->xdr, &lcp->lc_seg.length) < 0)
@@ -1733,6 +1757,7 @@ nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp,
 {
 	__be32 status;
 
+	memset(lgp, 0, sizeof(*lgp));
 	if (xdr_stream_decode_u32(argp->xdr, &lgp->lg_signal) < 0)
 		return nfserr_bad_xdr;
 	if (xdr_stream_decode_u32(argp->xdr, &lgp->lg_layout_type) < 0)
@@ -1758,6 +1783,7 @@ static __be32
 nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp,
 		struct nfsd4_layoutreturn *lrp)
 {
+	memset(lrp, 0, sizeof(*lrp));
 	if (xdr_stream_decode_bool(argp->xdr, &lrp->lr_reclaim) < 0)
 		return nfserr_bad_xdr;
 	if (xdr_stream_decode_u32(argp->xdr, &lrp->lr_layout_type) < 0)
@@ -1773,6 +1799,8 @@ static __be32 nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp,
 {
 	if (xdr_stream_decode_u32(argp->xdr, &sin->sin_style) < 0)
 		return nfserr_bad_xdr;
+
+	sin->sin_exp = NULL;
 	return nfs_ok;
 }
 
@@ -1793,6 +1821,7 @@ nfsd4_decode_sequence(struct nfsd4_compoundargs *argp,
 	seq->maxslots = be32_to_cpup(p++);
 	seq->cachethis = be32_to_cpup(p);
 
+	seq->status_flags = 0;
 	return nfs_ok;
 }
 
@@ -1803,6 +1832,7 @@ nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_sta
 	__be32 status;
 	u32 i;
 
+	memset(test_stateid, 0, sizeof(*test_stateid));
 	if (xdr_stream_decode_u32(argp->xdr, &test_stateid->ts_num_ids) < 0)
 		return nfserr_bad_xdr;
 
@@ -1900,6 +1930,7 @@ nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy)
 	struct nl4_server *ns_dummy;
 	__be32 status;
 
+	memset(copy, 0, sizeof(*copy));
 	status = nfsd4_decode_stateid4(argp, &copy->cp_src_stateid);
 	if (status)
 		return status;
@@ -1955,6 +1986,7 @@ nfsd4_decode_copy_notify(struct nfsd4_compoundargs *argp,
 {
 	__be32 status;
 
+	memset(cn, 0, sizeof(*cn));
 	cn->cpn_src = svcxdr_tmpalloc(argp, sizeof(*cn->cpn_src));
 	if (cn->cpn_src == NULL)
 		return nfserr_jukebox;
@@ -1972,6 +2004,8 @@ static __be32
 nfsd4_decode_offload_status(struct nfsd4_compoundargs *argp,
 			    struct nfsd4_offload_status *os)
 {
+	os->count = 0;
+	os->status = 0;
 	return nfsd4_decode_stateid4(argp, &os->stateid);
 }
 
@@ -1988,6 +2022,8 @@ nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek)
 	if (xdr_stream_decode_u32(argp->xdr, &seek->seek_whence) < 0)
 		return nfserr_bad_xdr;
 
+	seek->seek_eof = 0;
+	seek->seek_pos = 0;
 	return nfs_ok;
 }
 
@@ -2123,6 +2159,7 @@ nfsd4_decode_getxattr(struct nfsd4_compoundargs *argp,
 	__be32 status;
 	u32 maxcount;
 
+	memset(getxattr, 0, sizeof(*getxattr));
 	status = nfsd4_decode_xattr_name(argp, &getxattr->getxa_name);
 	if (status)
 		return status;
@@ -2131,8 +2168,7 @@ nfsd4_decode_getxattr(struct nfsd4_compoundargs *argp,
 	maxcount = min_t(u32, XATTR_SIZE_MAX, maxcount);
 
 	getxattr->getxa_len = maxcount;
-
-	return status;
+	return nfs_ok;
 }
 
 static __be32
@@ -2142,6 +2178,8 @@ nfsd4_decode_setxattr(struct nfsd4_compoundargs *argp,
 	u32 flags, maxcount, size;
 	__be32 status;
 
+	memset(setxattr, 0, sizeof(*setxattr));
+
 	if (xdr_stream_decode_u32(argp->xdr, &flags) < 0)
 		return nfserr_bad_xdr;
 
@@ -2180,6 +2218,8 @@ nfsd4_decode_listxattrs(struct nfsd4_compoundargs *argp,
 {
 	u32 maxcount;
 
+	memset(listxattrs, 0, sizeof(*listxattrs));
+
 	if (xdr_stream_decode_u64(argp->xdr, &listxattrs->lsxa_cookie) < 0)
 		return nfserr_bad_xdr;
 
@@ -2207,6 +2247,7 @@ static __be32
 nfsd4_decode_removexattr(struct nfsd4_compoundargs *argp,
 			 struct nfsd4_removexattr *removexattr)
 {
+	memset(removexattr, 0, sizeof(*removexattr));
 	return nfsd4_decode_xattr_name(argp, &removexattr->rmxa_name);
 }
 
@@ -2357,22 +2398,15 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 
 	if (xdr_stream_decode_u32(argp->xdr, &argp->minorversion) < 0)
 		return false;
-	if (xdr_stream_decode_u32(argp->xdr, &argp->opcnt) < 0)
+	if (xdr_stream_decode_u32(argp->xdr, &argp->client_opcnt) < 0)
 		return false;
-
-	/*
-	 * NFS4ERR_RESOURCE is a more helpful error than GARBAGE_ARGS
-	 * here, so we return success at the xdr level so that
-	 * nfsd4_proc can handle this is an NFS-level error.
-	 */
-	if (argp->opcnt > NFSD_MAX_OPS_PER_COMPOUND)
-		return true;
+	argp->opcnt = min_t(u32, argp->client_opcnt,
+			    NFSD_MAX_OPS_PER_COMPOUND);
 
 	if (argp->opcnt > ARRAY_SIZE(argp->iops)) {
-		argp->ops = kzalloc(argp->opcnt * sizeof(*argp->ops), GFP_KERNEL);
+		argp->ops = vcalloc(argp->opcnt, sizeof(*argp->ops));
 		if (!argp->ops) {
 			argp->ops = argp->iops;
-			dprintk("nfsd: couldn't allocate room for COMPOUND\n");
 			return false;
 		}
 	}
@@ -2774,9 +2808,10 @@ static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *bmval2, u32
 }
 
 
-static int get_parent_attributes(struct svc_export *exp, struct kstat *stat)
+static int nfsd4_get_mounted_on_ino(struct svc_export *exp, u64 *pino)
 {
 	struct path path = exp->ex_path;
+	struct kstat stat;
 	int err;
 
 	path_get(&path);
@@ -2784,8 +2819,10 @@ static int get_parent_attributes(struct svc_export *exp, struct kstat *stat)
 		if (path.dentry != path.mnt->mnt_root)
 			break;
 	}
-	err = vfs_getattr(&path, stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
+	err = vfs_getattr(&path, &stat, STATX_INO, AT_STATX_SYNC_AS_STAT);
 	path_put(&path);
+	if (!err)
+		*pino = stat.ino;
 	return err;
 }
 
@@ -3282,22 +3319,21 @@ out_acl:
 		*p++ = cpu_to_be32(stat.btime.tv_nsec);
 	}
 	if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) {
-		struct kstat parent_stat;
 		u64 ino = stat.ino;
 
 		p = xdr_reserve_space(xdr, 8);
 		if (!p)
                 	goto out_resource;
 		/*
-		 * Get parent's attributes if not ignoring crossmount
-		 * and this is the root of a cross-mounted filesystem.
+		 * Get ino of mountpoint in parent filesystem, if not ignoring
+		 * crossmount and this is the root of a cross-mounted
+		 * filesystem.
 		 */
 		if (ignore_crossmnt == 0 &&
 		    dentry == exp->ex_path.mnt->mnt_root) {
-			err = get_parent_attributes(exp, &parent_stat);
+			err = nfsd4_get_mounted_on_ino(exp, &ino);
 			if (err)
 				goto out_nfserr;
-			ino = parent_stat.ino;
 		}
 		p = xdr_encode_hyper(p, ino);
 	}
@@ -3994,7 +4030,7 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 	}
 	if (resp->xdr->buf->page_len && splice_ok) {
 		WARN_ON_ONCE(1);
-		return nfserr_resource;
+		return nfserr_serverfault;
 	}
 	xdr_commit_encode(xdr);
 
@@ -5394,7 +5430,7 @@ void nfsd4_release_compoundargs(struct svc_rqst *rqstp)
 	struct nfsd4_compoundargs *args = rqstp->rq_argp;
 
 	if (args->ops != args->iops) {
-		kfree(args->ops);
+		vfree(args->ops);
 		args->ops = args->iops;
 	}
 	while (args->to_free) {
@@ -5423,12 +5459,8 @@ bool
 nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 {
 	struct nfsd4_compoundres *resp = rqstp->rq_resp;
-	struct xdr_buf *buf = xdr->buf;
 	__be32 *p;
 
-	WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len +
-				 buf->tail[0].iov_len);
-
 	/*
 	 * Send buffer space for the following items is reserved
 	 * at the top of nfsd4_proc_compound().
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 9b31e1103e7b..3e64a3d50a1c 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -604,9 +604,10 @@ nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data)
  * scraping this file for info should test the labels to ensure they're
  * getting the correct field.
  */
-static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v)
+int nfsd_reply_cache_stats_show(struct seq_file *m, void *v)
 {
-	struct nfsd_net *nn = m->private;
+	struct nfsd_net *nn = net_generic(file_inode(m->file)->i_sb->s_fs_info,
+					  nfsd_net_id);
 
 	seq_printf(m, "max entries:           %u\n", nn->max_drc_entries);
 	seq_printf(m, "num entries:           %u\n",
@@ -626,11 +627,3 @@ static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v)
 	seq_printf(m, "cachesize at longest:  %u\n", nn->longest_chain_cachesize);
 	return 0;
 }
-
-int nfsd_reply_cache_stats_open(struct inode *inode, struct file *file)
-{
-	struct nfsd_net *nn = net_generic(file_inode(file)->i_sb->s_fs_info,
-								nfsd_net_id);
-
-	return single_open(file, nfsd_reply_cache_stats_show, nn);
-}
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 917fa1892fd2..6a29bcfc9390 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -185,17 +185,7 @@ static int export_features_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int export_features_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, export_features_show, NULL);
-}
-
-static const struct file_operations export_features_operations = {
-	.open		= export_features_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(export_features);
 
 #if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE)
 static int supported_enctypes_show(struct seq_file *m, void *v)
@@ -204,17 +194,7 @@ static int supported_enctypes_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int supported_enctypes_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, supported_enctypes_show, NULL);
-}
-
-static const struct file_operations supported_enctypes_ops = {
-	.open		= supported_enctypes_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(supported_enctypes);
 #endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */
 
 static const struct file_operations pool_stats_operations = {
@@ -224,19 +204,9 @@ static const struct file_operations pool_stats_operations = {
 	.release	= nfsd_pool_stats_release,
 };
 
-static const struct file_operations reply_cache_stats_operations = {
-	.open		= nfsd_reply_cache_stats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(nfsd_reply_cache_stats);
 
-static const struct file_operations filecache_ops = {
-	.open		= nfsd_file_cache_stats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(nfsd_file_cache_stats);
 
 /*----------------------------------------------------------------------------*/
 /*
@@ -1365,7 +1335,7 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc)
 		/* Per-export io stats use same ops as exports file */
 		[NFSD_Export_Stats] = {"export_stats", &exports_nfsd_operations, S_IRUGO},
 		[NFSD_Export_features] = {"export_features",
-					&export_features_operations, S_IRUGO},
+					&export_features_fops, S_IRUGO},
 		[NFSD_FO_UnlockIP] = {"unlock_ip",
 					&transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_FO_UnlockFS] = {"unlock_filesystem",
@@ -1374,14 +1344,16 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc)
 		[NFSD_Threads] = {"threads", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Pool_Threads] = {"pool_threads", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Pool_Stats] = {"pool_stats", &pool_stats_operations, S_IRUGO},
-		[NFSD_Reply_Cache_Stats] = {"reply_cache_stats", &reply_cache_stats_operations, S_IRUGO},
+		[NFSD_Reply_Cache_Stats] = {"reply_cache_stats",
+					&nfsd_reply_cache_stats_fops, S_IRUGO},
 		[NFSD_Versions] = {"versions", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO},
 		[NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO},
 		[NFSD_MaxConnections] = {"max_connections", &transaction_ops, S_IWUSR|S_IRUGO},
-		[NFSD_Filecache] = {"filecache", &filecache_ops, S_IRUGO},
+		[NFSD_Filecache] = {"filecache", &nfsd_file_cache_stats_fops, S_IRUGO},
 #if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE)
-		[NFSD_SupportedEnctypes] = {"supported_krb5_enctypes", &supported_enctypes_ops, S_IRUGO},
+		[NFSD_SupportedEnctypes] = {"supported_krb5_enctypes",
+					&supported_enctypes_fops, S_IRUGO},
 #endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */
 #ifdef CONFIG_NFSD_V4
 		[NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR},
@@ -1481,11 +1453,12 @@ static __net_init int nfsd_init_net(struct net *net)
 		goto out_idmap_error;
 	nn->nfsd_versions = NULL;
 	nn->nfsd4_minorversions = NULL;
+	retval = nfsd4_init_leases_net(nn);
+	if (retval)
+		goto out_drc_error;
 	retval = nfsd_reply_cache_init(nn);
 	if (retval)
 		goto out_drc_error;
-	nfsd4_init_leases_net(nn);
-
 	get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key));
 	seqlock_init(&nn->writeverf_lock);
 
@@ -1507,6 +1480,7 @@ static __net_exit void nfsd_exit_net(struct net *net)
 	nfsd_idmap_shutdown(net);
 	nfsd_export_shutdown(net);
 	nfsd_netns_free_versions(net_generic(net, nfsd_net_id));
+	nfsd4_leases_net_shutdown(nn);
 }
 
 static struct pernet_operations nfsd_net_ops = {
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 57a468ed85c3..09726c5b9a31 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -164,6 +164,7 @@ char * nfs4_recoverydir(void);
 bool nfsd4_spo_must_allow(struct svc_rqst *rqstp);
 int nfsd4_create_laundry_wq(void);
 void nfsd4_destroy_laundry_wq(void);
+bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, struct inode *inode);
 #else
 static inline int nfsd4_init_slabs(void) { return 0; }
 static inline void nfsd4_free_slabs(void) { }
@@ -179,6 +180,11 @@ static inline bool nfsd4_spo_must_allow(struct svc_rqst *rqstp)
 }
 static inline int nfsd4_create_laundry_wq(void) { return 0; };
 static inline void nfsd4_destroy_laundry_wq(void) {};
+static inline bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp,
+					      struct inode *inode)
+{
+	return false;
+}
 #endif
 
 /*
@@ -343,6 +349,7 @@ void		nfsd_lockd_shutdown(void);
 #define	NFSD_COURTESY_CLIENT_TIMEOUT	(24 * 60 * 60)	/* seconds */
 #define	NFSD_CLIENT_MAX_TRIM_PER_RUN	128
 #define	NFS4_CLIENTS_PER_GB		1024
+#define NFSD_DELEGRETURN_TIMEOUT	(HZ / 34)	/* 30ms */
 
 /*
  * The following attributes are currently not supported by the NFSv4 server:
@@ -498,7 +505,8 @@ extern void unregister_cld_notifier(void);
 extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn);
 #endif
 
-extern void nfsd4_init_leases_net(struct nfsd_net *nn);
+extern int nfsd4_init_leases_net(struct nfsd_net *nn);
+extern void nfsd4_leases_net_shutdown(struct nfsd_net *nn);
 
 #else /* CONFIG_NFSD_V4 */
 static inline int nfsd4_is_junction(struct dentry *dentry)
@@ -506,7 +514,8 @@ static inline int nfsd4_is_junction(struct dentry *dentry)
 	return 0;
 }
 
-static inline void nfsd4_init_leases_net(struct nfsd_net *nn) {};
+static inline int nfsd4_init_leases_net(struct nfsd_net *nn) { return 0; };
+static inline void nfsd4_leases_net_shutdown(struct nfsd_net *nn) {};
 
 #define register_cld_notifier() 0
 #define unregister_cld_notifier() do { } while(0)
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index a5b71526cee0..d73434200df9 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -392,13 +392,7 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
 skip_pseudoflavor_check:
 	/* Finally, check access permissions. */
 	error = nfsd_permission(rqstp, exp, dentry, access);
-
-	if (error) {
-		dprintk("fh_verify: %pd2 permission failure, "
-			"acc=%x, error=%d\n",
-			dentry,
-			access, ntohl(error));
-	}
+	trace_nfsd_fh_verify_err(rqstp, fhp, type, access, error);
 out:
 	if (error == nfserr_stale)
 		nfsd_stats_fh_stale_inc(exp);
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 7381972f1677..82b3ddeacc33 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -185,6 +185,7 @@ nfsd_proc_read(struct svc_rqst *rqstp)
 		argp->count, argp->offset);
 
 	argp->count = min_t(u32, argp->count, NFSSVC_MAXBLKSIZE_V2);
+	argp->count = min_t(u32, argp->count, rqstp->rq_res.buflen);
 
 	v = 0;
 	len = argp->count;
@@ -390,9 +391,8 @@ nfsd_proc_create(struct svc_rqst *rqstp)
 	resp->status = nfs_ok;
 	if (!inode) {
 		/* File doesn't exist. Create it and set attrs */
-		resp->status = nfsd_create_locked(rqstp, dirfhp, argp->name,
-						  argp->len, &attrs, type, rdev,
-						  newfhp);
+		resp->status = nfsd_create_locked(rqstp, dirfhp, &attrs, type,
+						  rdev, newfhp);
 	} else if (type == S_IFREG) {
 		dprintk("nfsd:   existing %s, valid=%x, size=%ld\n",
 			argp->name, attr->ia_valid, (long) attr->ia_size);
@@ -567,24 +567,15 @@ static void nfsd_init_dirlist_pages(struct svc_rqst *rqstp,
 	struct xdr_buf *buf = &resp->dirlist;
 	struct xdr_stream *xdr = &resp->xdr;
 
-	count = clamp(count, (u32)(XDR_UNIT * 2), svc_max_payload(rqstp));
-
 	memset(buf, 0, sizeof(*buf));
 
 	/* Reserve room for the NULL ptr & eof flag (-2 words) */
-	buf->buflen = count - XDR_UNIT * 2;
+	buf->buflen = clamp(count, (u32)(XDR_UNIT * 2), (u32)PAGE_SIZE);
+	buf->buflen -= XDR_UNIT * 2;
 	buf->pages = rqstp->rq_next_page;
 	rqstp->rq_next_page++;
 
-	/* This is xdr_init_encode(), but it assumes that
-	 * the head kvec has already been consumed. */
-	xdr_set_scratch_buffer(xdr, NULL, 0);
-	xdr->buf = buf;
-	xdr->page_ptr = buf->pages;
-	xdr->iov = NULL;
-	xdr->p = page_address(*buf->pages);
-	xdr->end = (void *)xdr->p + min_t(u32, buf->buflen, PAGE_SIZE);
-	xdr->rqst = NULL;
+	xdr_init_encode_pages(xdr, buf, buf->pages,  NULL);
 }
 
 /*
@@ -646,6 +637,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_decode = nfssvc_decode_voidarg,
 		.pc_encode = nfssvc_encode_voidres,
 		.pc_argsize = sizeof(struct nfsd_voidargs),
+		.pc_argzero = sizeof(struct nfsd_voidargs),
 		.pc_ressize = sizeof(struct nfsd_voidres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = 0,
@@ -657,6 +649,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_encode = nfssvc_encode_attrstatres,
 		.pc_release = nfssvc_release_attrstat,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
+		.pc_argzero = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+AT,
@@ -668,6 +661,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_encode = nfssvc_encode_attrstatres,
 		.pc_release = nfssvc_release_attrstat,
 		.pc_argsize = sizeof(struct nfsd_sattrargs),
+		.pc_argzero = sizeof(struct nfsd_sattrargs),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+AT,
@@ -678,6 +672,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_decode = nfssvc_decode_voidarg,
 		.pc_encode = nfssvc_encode_voidres,
 		.pc_argsize = sizeof(struct nfsd_voidargs),
+		.pc_argzero = sizeof(struct nfsd_voidargs),
 		.pc_ressize = sizeof(struct nfsd_voidres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = 0,
@@ -689,6 +684,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_encode = nfssvc_encode_diropres,
 		.pc_release = nfssvc_release_diropres,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
+		.pc_argzero = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+FH+AT,
@@ -699,6 +695,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_decode = nfssvc_decode_fhandleargs,
 		.pc_encode = nfssvc_encode_readlinkres,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
+		.pc_argzero = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_readlinkres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+1+NFS_MAXPATHLEN/4,
@@ -710,6 +707,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_encode = nfssvc_encode_readres,
 		.pc_release = nfssvc_release_readres,
 		.pc_argsize = sizeof(struct nfsd_readargs),
+		.pc_argzero = sizeof(struct nfsd_readargs),
 		.pc_ressize = sizeof(struct nfsd_readres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4,
@@ -720,6 +718,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_decode = nfssvc_decode_voidarg,
 		.pc_encode = nfssvc_encode_voidres,
 		.pc_argsize = sizeof(struct nfsd_voidargs),
+		.pc_argzero = sizeof(struct nfsd_voidargs),
 		.pc_ressize = sizeof(struct nfsd_voidres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = 0,
@@ -731,6 +730,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_encode = nfssvc_encode_attrstatres,
 		.pc_release = nfssvc_release_attrstat,
 		.pc_argsize = sizeof(struct nfsd_writeargs),
+		.pc_argzero = sizeof(struct nfsd_writeargs),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+AT,
@@ -742,6 +742,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_encode = nfssvc_encode_diropres,
 		.pc_release = nfssvc_release_diropres,
 		.pc_argsize = sizeof(struct nfsd_createargs),
+		.pc_argzero = sizeof(struct nfsd_createargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+FH+AT,
@@ -752,6 +753,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_decode = nfssvc_decode_diropargs,
 		.pc_encode = nfssvc_encode_statres,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
+		.pc_argzero = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_stat),
 		.pc_cachetype = RC_REPLSTAT,
 		.pc_xdrressize = ST,
@@ -762,6 +764,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_decode = nfssvc_decode_renameargs,
 		.pc_encode = nfssvc_encode_statres,
 		.pc_argsize = sizeof(struct nfsd_renameargs),
+		.pc_argzero = sizeof(struct nfsd_renameargs),
 		.pc_ressize = sizeof(struct nfsd_stat),
 		.pc_cachetype = RC_REPLSTAT,
 		.pc_xdrressize = ST,
@@ -772,6 +775,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_decode = nfssvc_decode_linkargs,
 		.pc_encode = nfssvc_encode_statres,
 		.pc_argsize = sizeof(struct nfsd_linkargs),
+		.pc_argzero = sizeof(struct nfsd_linkargs),
 		.pc_ressize = sizeof(struct nfsd_stat),
 		.pc_cachetype = RC_REPLSTAT,
 		.pc_xdrressize = ST,
@@ -782,6 +786,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_decode = nfssvc_decode_symlinkargs,
 		.pc_encode = nfssvc_encode_statres,
 		.pc_argsize = sizeof(struct nfsd_symlinkargs),
+		.pc_argzero = sizeof(struct nfsd_symlinkargs),
 		.pc_ressize = sizeof(struct nfsd_stat),
 		.pc_cachetype = RC_REPLSTAT,
 		.pc_xdrressize = ST,
@@ -793,6 +798,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_encode = nfssvc_encode_diropres,
 		.pc_release = nfssvc_release_diropres,
 		.pc_argsize = sizeof(struct nfsd_createargs),
+		.pc_argzero = sizeof(struct nfsd_createargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+FH+AT,
@@ -803,6 +809,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_decode = nfssvc_decode_diropargs,
 		.pc_encode = nfssvc_encode_statres,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
+		.pc_argzero = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_stat),
 		.pc_cachetype = RC_REPLSTAT,
 		.pc_xdrressize = ST,
@@ -813,6 +820,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_decode = nfssvc_decode_readdirargs,
 		.pc_encode = nfssvc_encode_readdirres,
 		.pc_argsize = sizeof(struct nfsd_readdirargs),
+		.pc_argzero = sizeof(struct nfsd_readdirargs),
 		.pc_ressize = sizeof(struct nfsd_readdirres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_name = "READDIR",
@@ -822,6 +830,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
 		.pc_decode = nfssvc_decode_fhandleargs,
 		.pc_encode = nfssvc_encode_statfsres,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
+		.pc_argzero = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_statfsres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+5,
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 4bb5baa17040..bfbd9f672f59 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -799,7 +799,7 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
 	if (nrservs == 0 && nn->nfsd_serv == NULL)
 		goto out;
 
-	strlcpy(nn->nfsd_name, utsname()->nodename,
+	strscpy(nn->nfsd_name, utsname()->nodename,
 		sizeof(nn->nfsd_name));
 
 	error = nfsd_create_serv(net);
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index aba8520b4b8b..caf6355b18fa 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -338,10 +338,8 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 		return false;
 	if (args->len > NFSSVC_MAXBLKSIZE_V2)
 		return false;
-	if (!xdr_stream_subsegment(xdr, &args->payload, args->len))
-		return false;
 
-	return true;
+	return xdr_stream_subsegment(xdr, &args->payload, args->len);
 }
 
 bool
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index ae596dbf8667..e2daef3cc003 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -57,11 +57,11 @@ typedef struct {
 } stateid_t;
 
 typedef struct {
-	stateid_t		stid;
+	stateid_t		cs_stid;
 #define NFS4_COPY_STID 1
 #define NFS4_COPYNOTIFY_STID 2
-	unsigned char		sc_type;
-	refcount_t		sc_count;
+	unsigned char		cs_type;
+	refcount_t		cs_count;
 } copy_stateid_t;
 
 struct nfsd4_callback {
@@ -175,7 +175,7 @@ static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s)
 /* Maximum number of slots per session. 160 is useful for long haul TCP */
 #define NFSD_MAX_SLOTS_PER_SESSION     160
 /* Maximum number of operations per session compound */
-#define NFSD_MAX_OPS_PER_COMPOUND	16
+#define NFSD_MAX_OPS_PER_COMPOUND	50
 /* Maximum  session per slot cache size */
 #define NFSD_SLOT_CACHE_SIZE		2048
 /* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */
@@ -692,12 +692,11 @@ extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
 extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
 extern void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
 		const struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op);
-extern void nfsd4_run_cb(struct nfsd4_callback *cb);
+extern bool nfsd4_run_cb(struct nfsd4_callback *cb);
 extern int nfsd4_create_callback_queue(void);
 extern void nfsd4_destroy_callback_queue(void);
 extern void nfsd4_shutdown_callback(struct nfs4_client *);
 extern void nfsd4_shutdown_copy(struct nfs4_client *clp);
-extern void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp);
 extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name,
 				struct xdr_netobj princhash, struct nfsd_net *nn);
 extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn);
diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c
index a8c5a02a84f0..777e24e5da33 100644
--- a/fs/nfsd/stats.c
+++ b/fs/nfsd/stats.c
@@ -32,7 +32,7 @@ struct svc_stat		nfsd_svcstats = {
 	.program	= &nfsd_program,
 };
 
-static int nfsd_proc_show(struct seq_file *seq, void *v)
+static int nfsd_show(struct seq_file *seq, void *v)
 {
 	int i;
 
@@ -72,17 +72,7 @@ static int nfsd_proc_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int nfsd_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, nfsd_proc_show, NULL);
-}
-
-static const struct proc_ops nfsd_proc_ops = {
-	.proc_open	= nfsd_proc_open,
-	.proc_read	= seq_read,
-	.proc_lseek	= seq_lseek,
-	.proc_release	= single_release,
-};
+DEFINE_PROC_SHOW_ATTRIBUTE(nfsd);
 
 int nfsd_percpu_counters_init(struct percpu_counter counters[], int num)
 {
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 9ebd67d461f9..06a96e955bd0 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -84,19 +84,26 @@ DEFINE_NFSD_XDR_ERR_EVENT(cant_encode);
 		{ NFSD_MAY_64BIT_COOKIE,	"64BIT_COOKIE" })
 
 TRACE_EVENT(nfsd_compound,
-	TP_PROTO(const struct svc_rqst *rqst,
-		 u32 args_opcnt),
-	TP_ARGS(rqst, args_opcnt),
+	TP_PROTO(
+		const struct svc_rqst *rqst,
+		const char *tag,
+		u32 taglen,
+		u32 opcnt
+	),
+	TP_ARGS(rqst, tag, taglen, opcnt),
 	TP_STRUCT__entry(
 		__field(u32, xid)
-		__field(u32, args_opcnt)
+		__field(u32, opcnt)
+		__string_len(tag, tag, taglen)
 	),
 	TP_fast_assign(
 		__entry->xid = be32_to_cpu(rqst->rq_xid);
-		__entry->args_opcnt = args_opcnt;
+		__entry->opcnt = opcnt;
+		__assign_str_len(tag, tag, taglen);
 	),
-	TP_printk("xid=0x%08x opcnt=%u",
-		__entry->xid, __entry->args_opcnt)
+	TP_printk("xid=0x%08x opcnt=%u tag=%s",
+		__entry->xid, __entry->opcnt, __get_str(tag)
+	)
 )
 
 TRACE_EVENT(nfsd_compound_status,
@@ -195,7 +202,7 @@ TRACE_EVENT(nfsd_fh_verify,
 		__sockaddr(client, rqstp->rq_xprt->xpt_remotelen)
 		__field(u32, xid)
 		__field(u32, fh_hash)
-		__field(void *, inode)
+		__field(const void *, inode)
 		__field(unsigned long, type)
 		__field(unsigned long, access)
 	),
@@ -211,13 +218,55 @@ TRACE_EVENT(nfsd_fh_verify,
 		__entry->type = type;
 		__entry->access = access;
 	),
-	TP_printk("xid=0x%08x fh_hash=0x%08x inode=%p type=%s access=%s",
-		__entry->xid, __entry->fh_hash, __entry->inode,
+	TP_printk("xid=0x%08x fh_hash=0x%08x type=%s access=%s",
+		__entry->xid, __entry->fh_hash,
 		show_fs_file_type(__entry->type),
 		show_nfsd_may_flags(__entry->access)
 	)
 );
 
+TRACE_EVENT_CONDITION(nfsd_fh_verify_err,
+	TP_PROTO(
+		const struct svc_rqst *rqstp,
+		const struct svc_fh *fhp,
+		umode_t type,
+		int access,
+		__be32 error
+	),
+	TP_ARGS(rqstp, fhp, type, access, error),
+	TP_CONDITION(error),
+	TP_STRUCT__entry(
+		__field(unsigned int, netns_ino)
+		__sockaddr(server, rqstp->rq_xprt->xpt_remotelen)
+		__sockaddr(client, rqstp->rq_xprt->xpt_remotelen)
+		__field(u32, xid)
+		__field(u32, fh_hash)
+		__field(const void *, inode)
+		__field(unsigned long, type)
+		__field(unsigned long, access)
+		__field(int, error)
+	),
+	TP_fast_assign(
+		__entry->netns_ino = SVC_NET(rqstp)->ns.inum;
+		__assign_sockaddr(server, &rqstp->rq_xprt->xpt_local,
+		       rqstp->rq_xprt->xpt_locallen);
+		__assign_sockaddr(client, &rqstp->rq_xprt->xpt_remote,
+				  rqstp->rq_xprt->xpt_remotelen);
+		__entry->xid = be32_to_cpu(rqstp->rq_xid);
+		__entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle);
+		__entry->inode = d_inode(fhp->fh_dentry);
+		__entry->type = type;
+		__entry->access = access;
+		__entry->error = be32_to_cpu(error);
+	),
+	TP_printk("xid=0x%08x fh_hash=0x%08x type=%s access=%s error=%d",
+		__entry->xid, __entry->fh_hash,
+		show_fs_file_type(__entry->type),
+		show_nfsd_may_flags(__entry->access),
+		__entry->error
+	)
+);
+
 DECLARE_EVENT_CLASS(nfsd_fh_err_class,
 	TP_PROTO(struct svc_rqst *rqstp,
 		 struct svc_fh	*fhp,
@@ -489,6 +538,29 @@ DEFINE_NFSD_COPY_ERR_EVENT(clone_file_range_err);
 #include "filecache.h"
 #include "vfs.h"
 
+TRACE_EVENT(nfsd_delegret_wakeup,
+	TP_PROTO(
+		const struct svc_rqst *rqstp,
+		const struct inode *inode,
+		long timeo
+	),
+	TP_ARGS(rqstp, inode, timeo),
+	TP_STRUCT__entry(
+		__field(u32, xid)
+		__field(const void *, inode)
+		__field(long, timeo)
+	),
+	TP_fast_assign(
+		__entry->xid = be32_to_cpu(rqstp->rq_xid);
+		__entry->inode = inode;
+		__entry->timeo = timeo;
+	),
+	TP_printk("xid=0x%08x inode=%p%s",
+		  __entry->xid, __entry->inode,
+		  __entry->timeo == 0 ? " (timed out)" : ""
+	)
+);
+
 DECLARE_EVENT_CLASS(nfsd_stateid_class,
 	TP_PROTO(stateid_t *stp),
 	TP_ARGS(stp),
@@ -1399,6 +1471,45 @@ TRACE_EVENT(nfsd_cb_offload,
 		__entry->fh_hash, __entry->count, __entry->status)
 );
 
+DECLARE_EVENT_CLASS(nfsd_cb_done_class,
+	TP_PROTO(
+		const stateid_t *stp,
+		const struct rpc_task *task
+	),
+	TP_ARGS(stp, task),
+	TP_STRUCT__entry(
+		__field(u32, cl_boot)
+		__field(u32, cl_id)
+		__field(u32, si_id)
+		__field(u32, si_generation)
+		__field(int, status)
+	),
+	TP_fast_assign(
+		__entry->cl_boot = stp->si_opaque.so_clid.cl_boot;
+		__entry->cl_id = stp->si_opaque.so_clid.cl_id;
+		__entry->si_id = stp->si_opaque.so_id;
+		__entry->si_generation = stp->si_generation;
+		__entry->status = task->tk_status;
+	),
+	TP_printk("client %08x:%08x stateid %08x:%08x status=%d",
+		__entry->cl_boot, __entry->cl_id, __entry->si_id,
+		__entry->si_generation, __entry->status
+	)
+);
+
+#define DEFINE_NFSD_CB_DONE_EVENT(name)			\
+DEFINE_EVENT(nfsd_cb_done_class, name,			\
+	TP_PROTO(					\
+		const stateid_t *stp,			\
+		const struct rpc_task *task		\
+	),						\
+	TP_ARGS(stp, task))
+
+DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_recall_done);
+DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_notify_lock_done);
+DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_layout_done);
+DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_offload_done);
+
 #endif /* _NFSD_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 9f486b788ed0..83be89905cbf 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -300,6 +300,10 @@ commit_metadata(struct svc_fh *fhp)
 static void
 nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap)
 {
+	/* Ignore mode updates on symlinks */
+	if (S_ISLNK(inode->i_mode))
+		iap->ia_valid &= ~ATTR_MODE;
+
 	/* sanitize the mode change */
 	if (iap->ia_valid & ATTR_MODE) {
 		iap->ia_mode &= S_IALLUGO;
@@ -339,8 +343,61 @@ nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	return nfserrno(get_write_access(inode));
 }
 
-/*
- * Set various file attributes.  After this call fhp needs an fh_put.
+static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap)
+{
+	int host_err;
+
+	if (iap->ia_valid & ATTR_SIZE) {
+		/*
+		 * RFC5661, Section 18.30.4:
+		 *   Changing the size of a file with SETATTR indirectly
+		 *   changes the time_modify and change attributes.
+		 *
+		 * (and similar for the older RFCs)
+		 */
+		struct iattr size_attr = {
+			.ia_valid	= ATTR_SIZE | ATTR_CTIME | ATTR_MTIME,
+			.ia_size	= iap->ia_size,
+		};
+
+		if (iap->ia_size < 0)
+			return -EFBIG;
+
+		host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL);
+		if (host_err)
+			return host_err;
+		iap->ia_valid &= ~ATTR_SIZE;
+
+		/*
+		 * Avoid the additional setattr call below if the only other
+		 * attribute that the client sends is the mtime, as we update
+		 * it as part of the size change above.
+		 */
+		if ((iap->ia_valid & ~ATTR_MTIME) == 0)
+			return 0;
+	}
+
+	if (!iap->ia_valid)
+		return 0;
+
+	iap->ia_valid |= ATTR_CTIME;
+	return notify_change(&init_user_ns, dentry, iap, NULL);
+}
+
+/**
+ * nfsd_setattr - Set various file attributes.
+ * @rqstp: controlling RPC transaction
+ * @fhp: filehandle of target
+ * @attr: attributes to set
+ * @check_guard: set to 1 if guardtime is a valid timestamp
+ * @guardtime: do not act if ctime.tv_sec does not match this timestamp
+ *
+ * This call may adjust the contents of @attr (in particular, this
+ * call may change the bits in the na_iattr.ia_valid field).
+ *
+ * Returns nfs_ok on success, otherwise an NFS status code is
+ * returned. Caller must release @fhp by calling fh_put in either
+ * case.
  */
 __be32
 nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
@@ -356,6 +413,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	int		host_err;
 	bool		get_write_count;
 	bool		size_change = (iap->ia_valid & ATTR_SIZE);
+	int		retries;
 
 	if (iap->ia_valid & ATTR_SIZE) {
 		accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
@@ -391,13 +449,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	dentry = fhp->fh_dentry;
 	inode = d_inode(dentry);
 
-	/* Ignore any mode updates on symlinks */
-	if (S_ISLNK(inode->i_mode))
-		iap->ia_valid &= ~ATTR_MODE;
-
-	if (!iap->ia_valid)
-		return 0;
-
 	nfsd_sanitize_attrs(inode, iap);
 
 	if (check_guard && guardtime != inode->i_ctime.tv_sec)
@@ -417,41 +468,13 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	}
 
 	inode_lock(inode);
-	if (size_change) {
-		/*
-		 * RFC5661, Section 18.30.4:
-		 *   Changing the size of a file with SETATTR indirectly
-		 *   changes the time_modify and change attributes.
-		 *
-		 * (and similar for the older RFCs)
-		 */
-		struct iattr size_attr = {
-			.ia_valid	= ATTR_SIZE | ATTR_CTIME | ATTR_MTIME,
-			.ia_size	= iap->ia_size,
-		};
-
-		host_err = -EFBIG;
-		if (iap->ia_size < 0)
-			goto out_unlock;
-
-		host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL);
-		if (host_err)
-			goto out_unlock;
-		iap->ia_valid &= ~ATTR_SIZE;
-
-		/*
-		 * Avoid the additional setattr call below if the only other
-		 * attribute that the client sends is the mtime, as we update
-		 * it as part of the size change above.
-		 */
-		if ((iap->ia_valid & ~ATTR_MTIME) == 0)
-			goto out_unlock;
+	for (retries = 1;;) {
+		host_err = __nfsd_setattr(dentry, iap);
+		if (host_err != -EAGAIN || !retries--)
+			break;
+		if (!nfsd_wait_for_delegreturn(rqstp, inode))
+			break;
 	}
-
-	iap->ia_valid |= ATTR_CTIME;
-	host_err = notify_change(&init_user_ns, dentry, iap, NULL);
-
-out_unlock:
 	if (attr->na_seclabel && attr->na_seclabel->len)
 		attr->na_labelerr = security_inode_setsecctx(dentry,
 			attr->na_seclabel->data, attr->na_seclabel->len);
@@ -846,10 +869,14 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 		  struct splice_desc *sd)
 {
 	struct svc_rqst *rqstp = sd->u.data;
-
-	svc_rqst_replace_page(rqstp, buf->page);
-	if (rqstp->rq_res.page_len == 0)
-		rqstp->rq_res.page_base = buf->offset;
+	struct page *page = buf->page;	// may be a compound one
+	unsigned offset = buf->offset;
+
+	page += offset / PAGE_SIZE;
+	for (int i = sd->len; i > 0; i -= PAGE_SIZE)
+		svc_rqst_replace_page(rqstp, page++);
+	if (rqstp->rq_res.page_len == 0)	// first call
+		rqstp->rq_res.page_base = offset % PAGE_SIZE;
 	rqstp->rq_res.page_len += sd->len;
 	return sd->len;
 }
@@ -1252,7 +1279,7 @@ nfsd_check_ignore_resizing(struct iattr *iap)
 /* The parent directory should already be locked: */
 __be32
 nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
-		   char *fname, int flen, struct nfsd_attrs *attrs,
+		   struct nfsd_attrs *attrs,
 		   int type, dev_t rdev, struct svc_fh *resfhp)
 {
 	struct dentry	*dentry, *dchild;
@@ -1379,8 +1406,7 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (err)
 		goto out_unlock;
 	fh_fill_pre_attrs(fhp);
-	err = nfsd_create_locked(rqstp, fhp, fname, flen, attrs, type,
-				 rdev, resfhp);
+	err = nfsd_create_locked(rqstp, fhp, attrs, type, rdev, resfhp);
 	fh_fill_post_attrs(fhp);
 out_unlock:
 	inode_unlock(dentry->d_inode);
@@ -1670,7 +1696,15 @@ retry:
 			.new_dir	= tdir,
 			.new_dentry	= ndentry,
 		};
-		host_err = vfs_rename(&rd);
+		int retries;
+
+		for (retries = 1;;) {
+			host_err = vfs_rename(&rd);
+			if (host_err != -EAGAIN || !retries--)
+				break;
+			if (!nfsd_wait_for_delegreturn(rqstp, d_inode(odentry)))
+				break;
+		}
 		if (!host_err) {
 			host_err = commit_metadata(tfhp);
 			if (!host_err)
@@ -1754,9 +1788,18 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 
 	fh_fill_pre_attrs(fhp);
 	if (type != S_IFDIR) {
+		int retries;
+
 		if (rdentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK)
 			nfsd_close_cached_files(rdentry);
-		host_err = vfs_unlink(&init_user_ns, dirp, rdentry, NULL);
+
+		for (retries = 1;;) {
+			host_err = vfs_unlink(&init_user_ns, dirp, rdentry, NULL);
+			if (host_err != -EAGAIN || !retries--)
+				break;
+			if (!nfsd_wait_for_delegreturn(rqstp, rinode))
+				break;
+		}
 	} else {
 		host_err = vfs_rmdir(&init_user_ns, dirp, rdentry);
 	}
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index c95cd414b4bb..120521bc7b24 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -79,8 +79,8 @@ __be32		nfsd4_clone_file_range(struct svc_rqst *rqstp,
 				       u64 count, bool sync);
 #endif /* CONFIG_NFSD_V4 */
 __be32		nfsd_create_locked(struct svc_rqst *, struct svc_fh *,
-				char *name, int len, struct nfsd_attrs *attrs,
-				int type, dev_t rdev, struct svc_fh *res);
+				struct nfsd_attrs *attrs, int type, dev_t rdev,
+				struct svc_fh *res);
 __be32		nfsd_create(struct svc_rqst *, struct svc_fh *,
 				char *name, int len, struct nfsd_attrs *attrs,
 				int type, dev_t rdev, struct svc_fh *res);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 96267258e629..0eb00105d845 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -717,13 +717,13 @@ struct nfsd4_compoundargs {
 	struct svcxdr_tmpbuf		*to_free;
 	struct svc_rqst			*rqstp;
 
-	u32				taglen;
 	char *				tag;
+	u32				taglen;
 	u32				minorversion;
+	u32				client_opcnt;
 	u32				opcnt;
 	struct nfsd4_op			*ops;
 	struct nfsd4_op			iops[8];
-	int				cachetype;
 };
 
 struct nfsd4_compoundres {
@@ -732,8 +732,8 @@ struct nfsd4_compoundres {
 	struct svc_rqst *		rqstp;
 
 	__be32				*statusp;
-	u32				taglen;
 	char *				tag;
+	u32				taglen;
 	u32				opcnt;
 
 	struct nfsd4_compound_state	cstate;
@@ -888,7 +888,8 @@ struct nfsd4_operation {
 	u32 op_flags;
 	char *op_name;
 	/* Try to get response size before operation */
-	u32 (*op_rsize_bop)(struct svc_rqst *, struct nfsd4_op *);
+	u32 (*op_rsize_bop)(const struct svc_rqst *rqstp,
+			const struct nfsd4_op *op);
 	void (*op_get_currentstateid)(struct nfsd4_compound_state *,
 			union nfsd4_op_u *);
 	void (*op_set_currentstateid)(struct nfsd4_compound_state *,
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 5ae8de09b271..001f4e053c85 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -2092,7 +2092,8 @@ get_ctx_vol_failed:
 	// TODO: Initialize security.
 	/* Get the extended system files' directory inode. */
 	vol->extend_ino = ntfs_iget(sb, FILE_Extend);
-	if (IS_ERR(vol->extend_ino) || is_bad_inode(vol->extend_ino)) {
+	if (IS_ERR(vol->extend_ino) || is_bad_inode(vol->extend_ino) ||
+	    !S_ISDIR(vol->extend_ino->i_mode)) {
 		if (!IS_ERR(vol->extend_ino))
 			iput(vol->extend_ino);
 		ntfs_error(sb, "Failed to load $Extend.");
diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
index e8c00dda42ad..71f870d497ae 100644
--- a/fs/ntfs3/attrib.c
+++ b/fs/ntfs3/attrib.c
@@ -84,8 +84,8 @@ static inline bool attr_must_be_resident(struct ntfs_sb_info *sbi,
 /*
  * attr_load_runs - Load all runs stored in @attr.
  */
-int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni,
-		   struct runs_tree *run, const CLST *vcn)
+static int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni,
+			  struct runs_tree *run, const CLST *vcn)
 {
 	int err;
 	CLST svcn = le64_to_cpu(attr->nres.svcn);
@@ -140,7 +140,10 @@ failed:
 		}
 
 		if (lcn != SPARSE_LCN) {
-			mark_as_free_ex(sbi, lcn, clen, trim);
+			if (sbi) {
+				/* mark bitmap range [lcn + clen) as free and trim clusters. */
+				mark_as_free_ex(sbi, lcn, clen, trim);
+			}
 			dn += clen;
 		}
 
@@ -173,7 +176,6 @@ int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run,
 {
 	int err;
 	CLST flen, vcn0 = vcn, pre = pre_alloc ? *pre_alloc : 0;
-	struct wnd_bitmap *wnd = &sbi->used.bitmap;
 	size_t cnt = run->count;
 
 	for (;;) {
@@ -196,9 +198,7 @@ int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run,
 		/* Add new fragment into run storage. */
 		if (!run_add_entry(run, vcn, lcn, flen, opt == ALLOCATE_MFT)) {
 			/* Undo last 'ntfs_look_for_free_space' */
-			down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS);
-			wnd_set_free(wnd, lcn, flen);
-			up_write(&wnd->rw_lock);
+			mark_as_free_ex(sbi, lcn, len, false);
 			err = -ENOMEM;
 			goto out;
 		}
@@ -320,7 +320,7 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr,
 
 	err = ni_insert_nonresident(ni, attr_s->type, attr_name(attr_s),
 				    attr_s->name_len, run, 0, alen,
-				    attr_s->flags, &attr, NULL);
+				    attr_s->flags, &attr, NULL, NULL);
 	if (err)
 		goto out3;
 
@@ -419,40 +419,44 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type,
 	struct mft_inode *mi, *mi_b;
 	CLST alen, vcn, lcn, new_alen, old_alen, svcn, evcn;
 	CLST next_svcn, pre_alloc = -1, done = 0;
-	bool is_ext;
+	bool is_ext, is_bad = false;
 	u32 align;
 	struct MFT_REC *rec;
 
 again:
+	alen = 0;
 	le_b = NULL;
 	attr_b = ni_find_attr(ni, NULL, &le_b, type, name, name_len, NULL,
 			      &mi_b);
 	if (!attr_b) {
 		err = -ENOENT;
-		goto out;
+		goto bad_inode;
 	}
 
 	if (!attr_b->non_res) {
 		err = attr_set_size_res(ni, attr_b, le_b, mi_b, new_size, run,
 					&attr_b);
-		if (err || !attr_b->non_res)
-			goto out;
+		if (err)
+			return err;
+
+		/* Return if file is still resident. */
+		if (!attr_b->non_res)
+			goto ok1;
 
 		/* Layout of records may be changed, so do a full search. */
 		goto again;
 	}
 
 	is_ext = is_attr_ext(attr_b);
-
-again_1:
 	align = sbi->cluster_size;
-
 	if (is_ext)
 		align <<= attr_b->nres.c_unit;
 
 	old_valid = le64_to_cpu(attr_b->nres.valid_size);
 	old_size = le64_to_cpu(attr_b->nres.data_size);
 	old_alloc = le64_to_cpu(attr_b->nres.alloc_size);
+
+again_1:
 	old_alen = old_alloc >> cluster_bits;
 
 	new_alloc = (new_size + align - 1) & ~(u64)(align - 1);
@@ -475,24 +479,27 @@ again_1:
 		mi = mi_b;
 	} else if (!le_b) {
 		err = -EINVAL;
-		goto out;
+		goto bad_inode;
 	} else {
 		le = le_b;
 		attr = ni_find_attr(ni, attr_b, &le, type, name, name_len, &vcn,
 				    &mi);
 		if (!attr) {
 			err = -EINVAL;
-			goto out;
+			goto bad_inode;
 		}
 
 next_le_1:
 		svcn = le64_to_cpu(attr->nres.svcn);
 		evcn = le64_to_cpu(attr->nres.evcn);
 	}
-
+	/*
+	 * Here we have:
+	 * attr,mi,le - last attribute segment (containing 'vcn').
+	 * attr_b,mi_b,le_b - base (primary) attribute segment.
+	 */
 next_le:
 	rec = mi->mrec;
-
 	err = attr_load_runs(attr, ni, run, NULL);
 	if (err)
 		goto out;
@@ -507,6 +514,13 @@ next_le:
 			goto ok;
 		}
 
+		/*
+		 * Add clusters. In simple case we have to:
+		 *  - allocate space (vcn, lcn, len)
+		 *  - update packed run in 'mi'
+		 *  - update attr->nres.evcn
+		 *  - update attr_b->nres.data_size/attr_b->nres.alloc_size
+		 */
 		to_allocate = new_alen - old_alen;
 add_alloc_in_same_attr_seg:
 		lcn = 0;
@@ -520,9 +534,11 @@ add_alloc_in_same_attr_seg:
 			pre_alloc = 0;
 			if (type == ATTR_DATA && !name_len &&
 			    sbi->options->prealloc) {
-				CLST new_alen2 = bytes_to_cluster(
-					sbi, get_pre_allocated(new_size));
-				pre_alloc = new_alen2 - new_alen;
+				pre_alloc =
+					bytes_to_cluster(
+						sbi,
+						get_pre_allocated(new_size)) -
+					new_alen;
 			}
 
 			/* Get the last LCN to allocate from. */
@@ -580,7 +596,7 @@ add_alloc_in_same_attr_seg:
 pack_runs:
 		err = mi_pack_runs(mi, attr, run, vcn - svcn);
 		if (err)
-			goto out;
+			goto undo_1;
 
 		next_svcn = le64_to_cpu(attr->nres.evcn) + 1;
 		new_alloc_tmp = (u64)next_svcn << cluster_bits;
@@ -614,7 +630,7 @@ pack_runs:
 		if (type == ATTR_LIST) {
 			err = ni_expand_list(ni);
 			if (err)
-				goto out;
+				goto undo_2;
 			if (next_svcn < vcn)
 				goto pack_runs;
 
@@ -624,8 +640,9 @@ pack_runs:
 
 		if (!ni->attr_list.size) {
 			err = ni_create_attr_list(ni);
+			/* In case of error layout of records is not changed. */
 			if (err)
-				goto out;
+				goto undo_2;
 			/* Layout of records is changed. */
 		}
 
@@ -637,48 +654,57 @@ pack_runs:
 		/* Insert new attribute segment. */
 		err = ni_insert_nonresident(ni, type, name, name_len, run,
 					    next_svcn, vcn - next_svcn,
-					    attr_b->flags, &attr, &mi);
-		if (err)
-			goto out;
-
-		if (!is_mft)
-			run_truncate_head(run, evcn + 1);
-
-		svcn = le64_to_cpu(attr->nres.svcn);
-		evcn = le64_to_cpu(attr->nres.evcn);
+					    attr_b->flags, &attr, &mi, NULL);
 
-		le_b = NULL;
 		/*
 		 * Layout of records maybe changed.
 		 * Find base attribute to update.
 		 */
+		le_b = NULL;
 		attr_b = ni_find_attr(ni, NULL, &le_b, type, name, name_len,
 				      NULL, &mi_b);
 		if (!attr_b) {
-			err = -ENOENT;
-			goto out;
+			err = -EINVAL;
+			goto bad_inode;
 		}
 
-		attr_b->nres.alloc_size = cpu_to_le64((u64)vcn << cluster_bits);
-		attr_b->nres.data_size = attr_b->nres.alloc_size;
-		attr_b->nres.valid_size = attr_b->nres.alloc_size;
+		if (err) {
+			/* ni_insert_nonresident failed. */
+			attr = NULL;
+			goto undo_2;
+		}
+
+		if (!is_mft)
+			run_truncate_head(run, evcn + 1);
+
+		svcn = le64_to_cpu(attr->nres.svcn);
+		evcn = le64_to_cpu(attr->nres.evcn);
+
+		/*
+		 * Attribute is in consistency state.
+		 * Save this point to restore to if next steps fail.
+		 */
+		old_valid = old_size = old_alloc = (u64)vcn << cluster_bits;
+		attr_b->nres.valid_size = attr_b->nres.data_size =
+			attr_b->nres.alloc_size = cpu_to_le64(old_size);
 		mi_b->dirty = true;
 		goto again_1;
 	}
 
 	if (new_size != old_size ||
 	    (new_alloc != old_alloc && !keep_prealloc)) {
+		/*
+		 * Truncate clusters. In simple case we have to:
+		 *  - update packed run in 'mi'
+		 *  - update attr->nres.evcn
+		 *  - update attr_b->nres.data_size/attr_b->nres.alloc_size
+		 *  - mark and trim clusters as free (vcn, lcn, len)
+		 */
+		CLST dlen = 0;
+
 		vcn = max(svcn, new_alen);
 		new_alloc_tmp = (u64)vcn << cluster_bits;
 
-		alen = 0;
-		err = run_deallocate_ex(sbi, run, vcn, evcn - vcn + 1, &alen,
-					true);
-		if (err)
-			goto out;
-
-		run_truncate(run, vcn);
-
 		if (vcn > svcn) {
 			err = mi_pack_runs(mi, attr, run, vcn - svcn);
 			if (err)
@@ -697,7 +723,7 @@ pack_runs:
 
 			if (!al_remove_le(ni, le)) {
 				err = -EINVAL;
-				goto out;
+				goto bad_inode;
 			}
 
 			le = (struct ATTR_LIST_ENTRY *)((u8 *)le - le_sz);
@@ -723,12 +749,20 @@ pack_runs:
 				attr_b->nres.valid_size =
 					attr_b->nres.alloc_size;
 		}
+		mi_b->dirty = true;
 
-		if (is_ext)
+		err = run_deallocate_ex(sbi, run, vcn, evcn - vcn + 1, &dlen,
+					true);
+		if (err)
+			goto out;
+
+		if (is_ext) {
+			/* dlen - really deallocated clusters. */
 			le64_sub_cpu(&attr_b->nres.total_size,
-				     ((u64)alen << cluster_bits));
+				     ((u64)dlen << cluster_bits));
+		}
 
-		mi_b->dirty = true;
+		run_truncate(run, vcn);
 
 		if (new_alloc_tmp <= new_alloc)
 			goto ok;
@@ -747,7 +781,7 @@ pack_runs:
 		if (le->type != type || le->name_len != name_len ||
 		    memcmp(le_name(le), name, name_len * sizeof(short))) {
 			err = -EINVAL;
-			goto out;
+			goto bad_inode;
 		}
 
 		err = ni_load_mi(ni, le, &mi);
@@ -757,7 +791,7 @@ pack_runs:
 		attr = mi_find_attr(mi, NULL, type, name, name_len, &le->id);
 		if (!attr) {
 			err = -EINVAL;
-			goto out;
+			goto bad_inode;
 		}
 		goto next_le_1;
 	}
@@ -772,13 +806,13 @@ ok:
 		}
 	}
 
-out:
-	if (!err && attr_b && ret)
+ok1:
+	if (ret)
 		*ret = attr_b;
 
 	/* Update inode_set_bytes. */
-	if (!err && ((type == ATTR_DATA && !name_len) ||
-		     (type == ATTR_ALLOC && name == I30_NAME))) {
+	if (((type == ATTR_DATA && !name_len) ||
+	     (type == ATTR_ALLOC && name == I30_NAME))) {
 		bool dirty = false;
 
 		if (ni->vfs_inode.i_size != new_size) {
@@ -786,7 +820,7 @@ out:
 			dirty = true;
 		}
 
-		if (attr_b && attr_b->non_res) {
+		if (attr_b->non_res) {
 			new_alloc = le64_to_cpu(attr_b->nres.alloc_size);
 			if (inode_get_bytes(&ni->vfs_inode) != new_alloc) {
 				inode_set_bytes(&ni->vfs_inode, new_alloc);
@@ -800,6 +834,47 @@ out:
 		}
 	}
 
+	return 0;
+
+undo_2:
+	vcn -= alen;
+	attr_b->nres.data_size = cpu_to_le64(old_size);
+	attr_b->nres.valid_size = cpu_to_le64(old_valid);
+	attr_b->nres.alloc_size = cpu_to_le64(old_alloc);
+
+	/* Restore 'attr' and 'mi'. */
+	if (attr)
+		goto restore_run;
+
+	if (le64_to_cpu(attr_b->nres.svcn) <= svcn &&
+	    svcn <= le64_to_cpu(attr_b->nres.evcn)) {
+		attr = attr_b;
+		le = le_b;
+		mi = mi_b;
+	} else if (!le_b) {
+		err = -EINVAL;
+		goto bad_inode;
+	} else {
+		le = le_b;
+		attr = ni_find_attr(ni, attr_b, &le, type, name, name_len,
+				    &svcn, &mi);
+		if (!attr)
+			goto bad_inode;
+	}
+
+restore_run:
+	if (mi_pack_runs(mi, attr, run, evcn - svcn + 1))
+		is_bad = true;
+
+undo_1:
+	run_deallocate_ex(sbi, run, vcn, alen, NULL, false);
+
+	run_truncate(run, vcn);
+out:
+	if (is_bad) {
+bad_inode:
+		_ntfs_bad_inode(&ni->vfs_inode);
+	}
 	return err;
 }
 
@@ -855,7 +930,7 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 		goto out;
 	}
 
-	asize = le64_to_cpu(attr_b->nres.alloc_size) >> sbi->cluster_bits;
+	asize = le64_to_cpu(attr_b->nres.alloc_size) >> cluster_bits;
 	if (vcn >= asize) {
 		err = -EINVAL;
 		goto out;
@@ -1047,7 +1122,7 @@ ins_ext:
 	if (evcn1 > next_svcn) {
 		err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run,
 					    next_svcn, evcn1 - next_svcn,
-					    attr_b->flags, &attr, &mi);
+					    attr_b->flags, &attr, &mi, NULL);
 		if (err)
 			goto out;
 	}
@@ -1173,7 +1248,7 @@ int attr_load_runs_range(struct ntfs_inode *ni, enum ATTR_TYPE type,
 {
 	struct ntfs_sb_info *sbi = ni->mi.sbi;
 	u8 cluster_bits = sbi->cluster_bits;
-	CLST vcn = from >> cluster_bits;
+	CLST vcn;
 	CLST vcn_last = (to - 1) >> cluster_bits;
 	CLST lcn, clen;
 	int err;
@@ -1647,7 +1722,7 @@ ins_ext:
 	if (evcn1 > next_svcn) {
 		err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run,
 					    next_svcn, evcn1 - next_svcn,
-					    attr_b->flags, &attr, &mi);
+					    attr_b->flags, &attr, &mi, NULL);
 		if (err)
 			goto out;
 	}
@@ -1812,18 +1887,12 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 				err = ni_insert_nonresident(
 					ni, ATTR_DATA, NULL, 0, run, next_svcn,
 					evcn1 - eat - next_svcn, a_flags, &attr,
-					&mi);
+					&mi, &le);
 				if (err)
 					goto out;
 
 				/* Layout of records maybe changed. */
 				attr_b = NULL;
-				le = al_find_ex(ni, NULL, ATTR_DATA, NULL, 0,
-						&next_svcn);
-				if (!le) {
-					err = -EINVAL;
-					goto out;
-				}
 			}
 
 			/* Free all allocated memory. */
@@ -1918,7 +1987,7 @@ next_attr:
 out:
 	up_write(&ni->file.run_lock);
 	if (err)
-		make_bad_inode(&ni->vfs_inode);
+		_ntfs_bad_inode(&ni->vfs_inode);
 
 	return err;
 }
@@ -1936,9 +2005,11 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size)
 	struct ATTRIB *attr = NULL, *attr_b;
 	struct ATTR_LIST_ENTRY *le, *le_b;
 	struct mft_inode *mi, *mi_b;
-	CLST svcn, evcn1, vcn, len, end, alen, dealloc;
+	CLST svcn, evcn1, vcn, len, end, alen, hole, next_svcn;
 	u64 total_size, alloc_size;
 	u32 mask;
+	__le16 a_flags;
+	struct runs_tree run2;
 
 	if (!bytes)
 		return 0;
@@ -1990,6 +2061,9 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size)
 	}
 
 	down_write(&ni->file.run_lock);
+	run_init(&run2);
+	run_truncate(run, 0);
+
 	/*
 	 * Enumerate all attribute segments and punch hole where necessary.
 	 */
@@ -1997,10 +2071,11 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size)
 	vcn = vbo >> sbi->cluster_bits;
 	len = bytes >> sbi->cluster_bits;
 	end = vcn + len;
-	dealloc = 0;
+	hole = 0;
 
 	svcn = le64_to_cpu(attr_b->nres.svcn);
 	evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1;
+	a_flags = attr_b->flags;
 
 	if (svcn <= vcn && vcn < evcn1) {
 		attr = attr_b;
@@ -2008,14 +2083,14 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size)
 		mi = mi_b;
 	} else if (!le_b) {
 		err = -EINVAL;
-		goto out;
+		goto bad_inode;
 	} else {
 		le = le_b;
 		attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn,
 				    &mi);
 		if (!attr) {
 			err = -EINVAL;
-			goto out;
+			goto bad_inode;
 		}
 
 		svcn = le64_to_cpu(attr->nres.svcn);
@@ -2023,49 +2098,91 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size)
 	}
 
 	while (svcn < end) {
-		CLST vcn1, zero, dealloc2;
+		CLST vcn1, zero, hole2 = hole;
 
 		err = attr_load_runs(attr, ni, run, &svcn);
 		if (err)
-			goto out;
+			goto done;
 		vcn1 = max(vcn, svcn);
 		zero = min(end, evcn1) - vcn1;
 
-		dealloc2 = dealloc;
-		err = run_deallocate_ex(sbi, run, vcn1, zero, &dealloc, true);
+		/*
+		 * Check range [vcn1 + zero).
+		 * Calculate how many clusters there are.
+		 * Don't do any destructive actions.
+		 */
+		err = run_deallocate_ex(NULL, run, vcn1, zero, &hole2, false);
 		if (err)
-			goto out;
+			goto done;
 
-		if (dealloc2 == dealloc) {
-			/* Looks like the required range is already sparsed. */
-		} else {
-			if (!run_add_entry(run, vcn1, SPARSE_LCN, zero,
-					   false)) {
-				err = -ENOMEM;
-				goto out;
-			}
+		/* Check if required range is already hole. */
+		if (hole2 == hole)
+			goto next_attr;
+
+		/* Make a clone of run to undo. */
+		err = run_clone(run, &run2);
+		if (err)
+			goto done;
+
+		/* Make a hole range (sparse) [vcn1 + zero). */
+		if (!run_add_entry(run, vcn1, SPARSE_LCN, zero, false)) {
+			err = -ENOMEM;
+			goto done;
+		}
 
-			err = mi_pack_runs(mi, attr, run, evcn1 - svcn);
+		/* Update run in attribute segment. */
+		err = mi_pack_runs(mi, attr, run, evcn1 - svcn);
+		if (err)
+			goto done;
+		next_svcn = le64_to_cpu(attr->nres.evcn) + 1;
+		if (next_svcn < evcn1) {
+			/* Insert new attribute segment. */
+			err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run,
+						    next_svcn,
+						    evcn1 - next_svcn, a_flags,
+						    &attr, &mi, &le);
 			if (err)
-				goto out;
+				goto undo_punch;
+
+			/* Layout of records maybe changed. */
+			attr_b = NULL;
 		}
+
+		/* Real deallocate. Should not fail. */
+		run_deallocate_ex(sbi, &run2, vcn1, zero, &hole, true);
+
+next_attr:
 		/* Free all allocated memory. */
 		run_truncate(run, 0);
 
 		if (evcn1 >= alen)
 			break;
 
+		/* Get next attribute segment. */
 		attr = ni_enum_attr_ex(ni, attr, &le, &mi);
 		if (!attr) {
 			err = -EINVAL;
-			goto out;
+			goto bad_inode;
 		}
 
 		svcn = le64_to_cpu(attr->nres.svcn);
 		evcn1 = le64_to_cpu(attr->nres.evcn) + 1;
 	}
 
-	total_size -= (u64)dealloc << sbi->cluster_bits;
+done:
+	if (!hole)
+		goto out;
+
+	if (!attr_b) {
+		attr_b = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL,
+				      &mi_b);
+		if (!attr_b) {
+			err = -EINVAL;
+			goto bad_inode;
+		}
+	}
+
+	total_size -= (u64)hole << sbi->cluster_bits;
 	attr_b->nres.total_size = cpu_to_le64(total_size);
 	mi_b->dirty = true;
 
@@ -2075,9 +2192,263 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size)
 	mark_inode_dirty(&ni->vfs_inode);
 
 out:
+	run_close(&run2);
 	up_write(&ni->file.run_lock);
+	return err;
+
+bad_inode:
+	_ntfs_bad_inode(&ni->vfs_inode);
+	goto out;
+
+undo_punch:
+	/*
+	 * Restore packed runs.
+	 * 'mi_pack_runs' should not fail, cause we restore original.
+	 */
+	if (mi_pack_runs(mi, attr, &run2, evcn1 - svcn))
+		goto bad_inode;
+
+	goto done;
+}
+
+/*
+ * attr_insert_range - Insert range (hole) in file.
+ * Not for normal files.
+ */
+int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
+{
+	int err = 0;
+	struct runs_tree *run = &ni->file.run;
+	struct ntfs_sb_info *sbi = ni->mi.sbi;
+	struct ATTRIB *attr = NULL, *attr_b;
+	struct ATTR_LIST_ENTRY *le, *le_b;
+	struct mft_inode *mi, *mi_b;
+	CLST vcn, svcn, evcn1, len, next_svcn;
+	u64 data_size, alloc_size;
+	u32 mask;
+	__le16 a_flags;
+
+	if (!bytes)
+		return 0;
+
+	le_b = NULL;
+	attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b);
+	if (!attr_b)
+		return -ENOENT;
+
+	if (!is_attr_ext(attr_b)) {
+		/* It was checked above. See fallocate. */
+		return -EOPNOTSUPP;
+	}
+
+	if (!attr_b->non_res) {
+		data_size = le32_to_cpu(attr_b->res.data_size);
+		alloc_size = data_size;
+		mask = sbi->cluster_mask; /* cluster_size - 1 */
+	} else {
+		data_size = le64_to_cpu(attr_b->nres.data_size);
+		alloc_size = le64_to_cpu(attr_b->nres.alloc_size);
+		mask = (sbi->cluster_size << attr_b->nres.c_unit) - 1;
+	}
+
+	if (vbo > data_size) {
+		/* Insert range after the file size is not allowed. */
+		return -EINVAL;
+	}
+
+	if ((vbo & mask) || (bytes & mask)) {
+		/* Allow to insert only frame aligned ranges. */
+		return -EINVAL;
+	}
+
+	/*
+	 * valid_size <= data_size <= alloc_size
+	 * Check alloc_size for maximum possible.
+	 */
+	if (bytes > sbi->maxbytes_sparse - alloc_size)
+		return -EFBIG;
+
+	vcn = vbo >> sbi->cluster_bits;
+	len = bytes >> sbi->cluster_bits;
+
+	down_write(&ni->file.run_lock);
+
+	if (!attr_b->non_res) {
+		err = attr_set_size(ni, ATTR_DATA, NULL, 0, run,
+				    data_size + bytes, NULL, false, NULL);
+
+		le_b = NULL;
+		attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL,
+				      &mi_b);
+		if (!attr_b) {
+			err = -EINVAL;
+			goto bad_inode;
+		}
+
+		if (err)
+			goto out;
+
+		if (!attr_b->non_res) {
+			/* Still resident. */
+			char *data = Add2Ptr(attr_b, attr_b->res.data_off);
+
+			memmove(data + bytes, data, bytes);
+			memset(data, 0, bytes);
+			goto done;
+		}
+
+		/* Resident files becomes nonresident. */
+		data_size = le64_to_cpu(attr_b->nres.data_size);
+		alloc_size = le64_to_cpu(attr_b->nres.alloc_size);
+	}
+
+	/*
+	 * Enumerate all attribute segments and shift start vcn.
+	 */
+	a_flags = attr_b->flags;
+	svcn = le64_to_cpu(attr_b->nres.svcn);
+	evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1;
+
+	if (svcn <= vcn && vcn < evcn1) {
+		attr = attr_b;
+		le = le_b;
+		mi = mi_b;
+	} else if (!le_b) {
+		err = -EINVAL;
+		goto bad_inode;
+	} else {
+		le = le_b;
+		attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn,
+				    &mi);
+		if (!attr) {
+			err = -EINVAL;
+			goto bad_inode;
+		}
+
+		svcn = le64_to_cpu(attr->nres.svcn);
+		evcn1 = le64_to_cpu(attr->nres.evcn) + 1;
+	}
+
+	run_truncate(run, 0); /* clear cached values. */
+	err = attr_load_runs(attr, ni, run, NULL);
+	if (err)
+		goto out;
+
+	if (!run_insert_range(run, vcn, len)) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	/* Try to pack in current record as much as possible. */
+	err = mi_pack_runs(mi, attr, run, evcn1 + len - svcn);
 	if (err)
-		make_bad_inode(&ni->vfs_inode);
+		goto out;
+
+	next_svcn = le64_to_cpu(attr->nres.evcn) + 1;
+
+	while ((attr = ni_enum_attr_ex(ni, attr, &le, &mi)) &&
+	       attr->type == ATTR_DATA && !attr->name_len) {
+		le64_add_cpu(&attr->nres.svcn, len);
+		le64_add_cpu(&attr->nres.evcn, len);
+		if (le) {
+			le->vcn = attr->nres.svcn;
+			ni->attr_list.dirty = true;
+		}
+		mi->dirty = true;
+	}
+
+	if (next_svcn < evcn1 + len) {
+		err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run,
+					    next_svcn, evcn1 + len - next_svcn,
+					    a_flags, NULL, NULL, NULL);
+
+		le_b = NULL;
+		attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL,
+				      &mi_b);
+		if (!attr_b) {
+			err = -EINVAL;
+			goto bad_inode;
+		}
+
+		if (err) {
+			/* ni_insert_nonresident failed. Try to undo. */
+			goto undo_insert_range;
+		}
+	}
+
+	/*
+	 * Update primary attribute segment.
+	 */
+	if (vbo <= ni->i_valid)
+		ni->i_valid += bytes;
+
+	attr_b->nres.data_size = le64_to_cpu(data_size + bytes);
+	attr_b->nres.alloc_size = le64_to_cpu(alloc_size + bytes);
+
+	/* ni->valid may be not equal valid_size (temporary). */
+	if (ni->i_valid > data_size + bytes)
+		attr_b->nres.valid_size = attr_b->nres.data_size;
+	else
+		attr_b->nres.valid_size = cpu_to_le64(ni->i_valid);
+	mi_b->dirty = true;
+
+done:
+	ni->vfs_inode.i_size += bytes;
+	ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
+	mark_inode_dirty(&ni->vfs_inode);
+
+out:
+	run_truncate(run, 0); /* clear cached values. */
+
+	up_write(&ni->file.run_lock);
 
 	return err;
+
+bad_inode:
+	_ntfs_bad_inode(&ni->vfs_inode);
+	goto out;
+
+undo_insert_range:
+	svcn = le64_to_cpu(attr_b->nres.svcn);
+	evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1;
+
+	if (svcn <= vcn && vcn < evcn1) {
+		attr = attr_b;
+		le = le_b;
+		mi = mi_b;
+	} else if (!le_b) {
+		goto bad_inode;
+	} else {
+		le = le_b;
+		attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn,
+				    &mi);
+		if (!attr) {
+			goto bad_inode;
+		}
+
+		svcn = le64_to_cpu(attr->nres.svcn);
+		evcn1 = le64_to_cpu(attr->nres.evcn) + 1;
+	}
+
+	if (attr_load_runs(attr, ni, run, NULL))
+		goto bad_inode;
+
+	if (!run_collapse_range(run, vcn, len))
+		goto bad_inode;
+
+	if (mi_pack_runs(mi, attr, run, evcn1 + len - svcn))
+		goto bad_inode;
+
+	while ((attr = ni_enum_attr_ex(ni, attr, &le, &mi)) &&
+	       attr->type == ATTR_DATA && !attr->name_len) {
+		le64_sub_cpu(&attr->nres.svcn, len);
+		le64_sub_cpu(&attr->nres.evcn, len);
+		if (le) {
+			le->vcn = attr->nres.svcn;
+			ni->attr_list.dirty = true;
+		}
+		mi->dirty = true;
+	}
+
+	goto out;
 }
diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c
index aa184407520f..5d44ceac855b 100644
--- a/fs/ntfs3/bitmap.c
+++ b/fs/ntfs3/bitmap.c
@@ -51,11 +51,6 @@ void ntfs3_exit_bitmap(void)
 	kmem_cache_destroy(ntfs_enode_cachep);
 }
 
-static inline u32 wnd_bits(const struct wnd_bitmap *wnd, size_t i)
-{
-	return i + 1 == wnd->nwnd ? wnd->bits_last : wnd->sb->s_blocksize * 8;
-}
-
 /*
  * wnd_scan
  *
@@ -1333,9 +1328,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits)
 		if (!new_free)
 			return -ENOMEM;
 
-		if (new_free != wnd->free_bits)
-			memcpy(new_free, wnd->free_bits,
-			       wnd->nwnd * sizeof(short));
+		memcpy(new_free, wnd->free_bits, wnd->nwnd * sizeof(short));
 		memset(new_free + wnd->nwnd, 0,
 		       (new_wnd - wnd->nwnd) * sizeof(short));
 		kfree(wnd->free_bits);
@@ -1395,9 +1388,8 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits)
 
 void wnd_zone_set(struct wnd_bitmap *wnd, size_t lcn, size_t len)
 {
-	size_t zlen;
+	size_t zlen = wnd->zone_end - wnd->zone_bit;
 
-	zlen = wnd->zone_end - wnd->zone_bit;
 	if (zlen)
 		wnd_add_free_ext(wnd, wnd->zone_bit, zlen, false);
 
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 4a21745711fe..4f2ffc7ef296 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -530,21 +530,35 @@ static int ntfs_truncate(struct inode *inode, loff_t new_size)
 static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 {
 	struct inode *inode = file->f_mapping->host;
+	struct address_space *mapping = inode->i_mapping;
 	struct super_block *sb = inode->i_sb;
 	struct ntfs_sb_info *sbi = sb->s_fs_info;
 	struct ntfs_inode *ni = ntfs_i(inode);
 	loff_t end = vbo + len;
 	loff_t vbo_down = round_down(vbo, PAGE_SIZE);
-	loff_t i_size;
+	bool is_supported_holes = is_sparsed(ni) || is_compressed(ni);
+	loff_t i_size, new_size;
+	bool map_locked;
 	int err;
 
 	/* No support for dir. */
 	if (!S_ISREG(inode->i_mode))
 		return -EOPNOTSUPP;
 
-	/* Return error if mode is not supported. */
-	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
-		     FALLOC_FL_COLLAPSE_RANGE)) {
+	/*
+	 * vfs_fallocate checks all possible combinations of mode.
+	 * Do additional checks here before ntfs_set_state(dirty).
+	 */
+	if (mode & FALLOC_FL_PUNCH_HOLE) {
+		if (!is_supported_holes)
+			return -EOPNOTSUPP;
+	} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
+	} else if (mode & FALLOC_FL_INSERT_RANGE) {
+		if (!is_supported_holes)
+			return -EOPNOTSUPP;
+	} else if (mode &
+		   ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
+		     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)) {
 		ntfs_inode_warn(inode, "fallocate(0x%x) is not supported",
 				mode);
 		return -EOPNOTSUPP;
@@ -554,6 +568,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 
 	inode_lock(inode);
 	i_size = inode->i_size;
+	new_size = max(end, i_size);
+	map_locked = false;
 
 	if (WARN_ON(ni->ni_flags & NI_FLAG_COMPRESSED_MASK)) {
 		/* Should never be here, see ntfs_file_open. */
@@ -561,38 +577,27 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 		goto out;
 	}
 
+	if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE |
+		    FALLOC_FL_INSERT_RANGE)) {
+		inode_dio_wait(inode);
+		filemap_invalidate_lock(mapping);
+		map_locked = true;
+	}
+
 	if (mode & FALLOC_FL_PUNCH_HOLE) {
 		u32 frame_size;
 		loff_t mask, vbo_a, end_a, tmp;
 
-		if (!(mode & FALLOC_FL_KEEP_SIZE)) {
-			err = -EINVAL;
-			goto out;
-		}
-
-		err = filemap_write_and_wait_range(inode->i_mapping, vbo,
-						   end - 1);
+		err = filemap_write_and_wait_range(mapping, vbo, end - 1);
 		if (err)
 			goto out;
 
-		err = filemap_write_and_wait_range(inode->i_mapping, end,
-						   LLONG_MAX);
+		err = filemap_write_and_wait_range(mapping, end, LLONG_MAX);
 		if (err)
 			goto out;
 
-		inode_dio_wait(inode);
-
 		truncate_pagecache(inode, vbo_down);
 
-		if (!is_sparsed(ni) && !is_compressed(ni)) {
-			/*
-			 * Normal file, can't make hole.
-			 * TODO: Try to find way to save info about hole.
-			 */
-			err = -EOPNOTSUPP;
-			goto out;
-		}
-
 		ni_lock(ni);
 		err = attr_punch_hole(ni, vbo, len, &frame_size);
 		ni_unlock(ni);
@@ -624,17 +629,11 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 			ni_unlock(ni);
 		}
 	} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
-		if (mode & ~FALLOC_FL_COLLAPSE_RANGE) {
-			err = -EINVAL;
-			goto out;
-		}
-
 		/*
 		 * Write tail of the last page before removed range since
 		 * it will get removed from the page cache below.
 		 */
-		err = filemap_write_and_wait_range(inode->i_mapping, vbo_down,
-						   vbo);
+		err = filemap_write_and_wait_range(mapping, vbo_down, vbo);
 		if (err)
 			goto out;
 
@@ -642,34 +641,58 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 		 * Write data that will be shifted to preserve them
 		 * when discarding page cache below.
 		 */
-		err = filemap_write_and_wait_range(inode->i_mapping, end,
-						   LLONG_MAX);
+		err = filemap_write_and_wait_range(mapping, end, LLONG_MAX);
 		if (err)
 			goto out;
 
-		/* Wait for existing dio to complete. */
-		inode_dio_wait(inode);
-
 		truncate_pagecache(inode, vbo_down);
 
 		ni_lock(ni);
 		err = attr_collapse_range(ni, vbo, len);
 		ni_unlock(ni);
+	} else if (mode & FALLOC_FL_INSERT_RANGE) {
+		/* Check new size. */
+		err = inode_newsize_ok(inode, new_size);
+		if (err)
+			goto out;
+
+		/* Write out all dirty pages. */
+		err = filemap_write_and_wait_range(mapping, vbo_down,
+						   LLONG_MAX);
+		if (err)
+			goto out;
+		truncate_pagecache(inode, vbo_down);
+
+		ni_lock(ni);
+		err = attr_insert_range(ni, vbo, len);
+		ni_unlock(ni);
 	} else {
-		/*
-		 * Normal file: Allocate clusters, do not change 'valid' size.
-		 */
-		loff_t new_size = max(end, i_size);
+		/* Check new size. */
+
+		/* generic/213: expected -ENOSPC instead of -EFBIG. */
+		if (!is_supported_holes) {
+			loff_t to_alloc = new_size - inode_get_bytes(inode);
+
+			if (to_alloc > 0 &&
+			    (to_alloc >> sbi->cluster_bits) >
+				    wnd_zeroes(&sbi->used.bitmap)) {
+				err = -ENOSPC;
+				goto out;
+			}
+		}
 
 		err = inode_newsize_ok(inode, new_size);
 		if (err)
 			goto out;
 
+		/*
+		 * Allocate clusters, do not change 'valid' size.
+		 */
 		err = ntfs_set_size(inode, new_size);
 		if (err)
 			goto out;
 
-		if (is_sparsed(ni) || is_compressed(ni)) {
+		if (is_supported_holes) {
 			CLST vcn_v = ni->i_valid >> sbi->cluster_bits;
 			CLST vcn = vbo >> sbi->cluster_bits;
 			CLST cend = bytes_to_cluster(sbi, end);
@@ -717,8 +740,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 	}
 
 out:
-	if (err == -EFBIG)
-		err = -ENOSPC;
+	if (map_locked)
+		filemap_invalidate_unlock(mapping);
 
 	if (!err) {
 		inode->i_ctime = inode->i_mtime = current_time(inode);
@@ -989,7 +1012,6 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 		if (bytes > count)
 			bytes = count;
 
-		frame = pos >> frame_bits;
 		frame_vbo = pos & ~(frame_size - 1);
 		index = frame_vbo >> PAGE_SHIFT;
 
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index 18842998c8fa..381a38a06ec2 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -7,6 +7,7 @@
 
 #include <linux/fiemap.h>
 #include <linux/fs.h>
+#include <linux/minmax.h>
 #include <linux/vmalloc.h>
 
 #include "debug.h"
@@ -468,7 +469,7 @@ ni_ins_new_attr(struct ntfs_inode *ni, struct mft_inode *mi,
 				&ref, &le);
 		if (err) {
 			/* No memory or no space. */
-			return NULL;
+			return ERR_PTR(err);
 		}
 		le_added = true;
 
@@ -649,6 +650,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni)
 	struct mft_inode *mi;
 	u32 asize, free;
 	struct MFT_REF ref;
+	struct MFT_REC *mrec;
 	__le16 id;
 
 	if (!ni->attr_list.dirty)
@@ -692,11 +694,17 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni)
 		free -= asize;
 	}
 
+	/* Make a copy of primary record to restore if error. */
+	mrec = kmemdup(ni->mi.mrec, sbi->record_size, GFP_NOFS);
+	if (!mrec)
+		return 0; /* Not critical. */
+
 	/* It seems that attribute list can be removed from primary record. */
 	mi_remove_attr(NULL, &ni->mi, attr_list);
 
 	/*
-	 * Repeat the cycle above and move all attributes to primary record.
+	 * Repeat the cycle above and copy all attributes to primary record.
+	 * Do not remove original attributes from subrecords!
 	 * It should be success!
 	 */
 	le = NULL;
@@ -707,14 +715,14 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni)
 		mi = ni_find_mi(ni, ino_get(&le->ref));
 		if (!mi) {
 			/* Should never happened, 'cause already checked. */
-			goto bad;
+			goto out;
 		}
 
 		attr = mi_find_attr(mi, NULL, le->type, le_name(le),
 				    le->name_len, &le->id);
 		if (!attr) {
 			/* Should never happened, 'cause already checked. */
-			goto bad;
+			goto out;
 		}
 		asize = le32_to_cpu(attr->size);
 
@@ -724,18 +732,33 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni)
 					  le16_to_cpu(attr->name_off));
 		if (!attr_ins) {
 			/*
-			 * Internal error.
-			 * Either no space in primary record (already checked).
-			 * Either tried to insert another
-			 * non indexed attribute (logic error).
+			 * No space in primary record (already checked).
 			 */
-			goto bad;
+			goto out;
 		}
 
 		/* Copy all except id. */
 		id = attr_ins->id;
 		memcpy(attr_ins, attr, asize);
 		attr_ins->id = id;
+	}
+
+	/*
+	 * Repeat the cycle above and remove all attributes from subrecords.
+	 */
+	le = NULL;
+	while ((le = al_enumerate(ni, le))) {
+		if (!memcmp(&le->ref, &ref, sizeof(ref)))
+			continue;
+
+		mi = ni_find_mi(ni, ino_get(&le->ref));
+		if (!mi)
+			continue;
+
+		attr = mi_find_attr(mi, NULL, le->type, le_name(le),
+				    le->name_len, &le->id);
+		if (!attr)
+			continue;
 
 		/* Remove from original record. */
 		mi_remove_attr(NULL, mi, attr);
@@ -748,11 +771,13 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni)
 	ni->attr_list.le = NULL;
 	ni->attr_list.dirty = false;
 
+	kfree(mrec);
+	return 0;
+out:
+	/* Restore primary record. */
+	swap(mrec, ni->mi.mrec);
+	kfree(mrec);
 	return 0;
-bad:
-	ntfs_inode_err(&ni->vfs_inode, "Internal error");
-	make_bad_inode(&ni->vfs_inode);
-	return -EINVAL;
 }
 
 /*
@@ -986,6 +1011,8 @@ static int ni_ins_attr_ext(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le,
 				       name_off, svcn, ins_le);
 		if (!attr)
 			continue;
+		if (IS_ERR(attr))
+			return PTR_ERR(attr);
 
 		if (ins_attr)
 			*ins_attr = attr;
@@ -1007,8 +1034,15 @@ insert_ext:
 
 	attr = ni_ins_new_attr(ni, mi, le, type, name, name_len, asize,
 			       name_off, svcn, ins_le);
-	if (!attr)
+	if (!attr) {
+		err = -EINVAL;
 		goto out2;
+	}
+
+	if (IS_ERR(attr)) {
+		err = PTR_ERR(attr);
+		goto out2;
+	}
 
 	if (ins_attr)
 		*ins_attr = attr;
@@ -1020,10 +1054,9 @@ insert_ext:
 out2:
 	ni_remove_mi(ni, mi);
 	mi_put(mi);
-	err = -EINVAL;
 
 out1:
-	ntfs_mark_rec_free(sbi, rno);
+	ntfs_mark_rec_free(sbi, rno, is_mft);
 
 out:
 	return err;
@@ -1076,6 +1109,11 @@ static int ni_insert_attr(struct ntfs_inode *ni, enum ATTR_TYPE type,
 	if (asize <= free) {
 		attr = ni_ins_new_attr(ni, &ni->mi, NULL, type, name, name_len,
 				       asize, name_off, svcn, ins_le);
+		if (IS_ERR(attr)) {
+			err = PTR_ERR(attr);
+			goto out;
+		}
+
 		if (attr) {
 			if (ins_attr)
 				*ins_attr = attr;
@@ -1173,6 +1211,11 @@ static int ni_insert_attr(struct ntfs_inode *ni, enum ATTR_TYPE type,
 		goto out;
 	}
 
+	if (IS_ERR(attr)) {
+		err = PTR_ERR(attr);
+		goto out;
+	}
+
 	if (ins_attr)
 		*ins_attr = attr;
 	if (ins_mi)
@@ -1218,7 +1261,7 @@ static int ni_expand_mft_list(struct ntfs_inode *ni)
 		mft_min = mft_new;
 		mi_min = mi_new;
 	} else {
-		ntfs_mark_rec_free(sbi, mft_new);
+		ntfs_mark_rec_free(sbi, mft_new, true);
 		mft_new = 0;
 		ni_remove_mi(ni, mi_new);
 	}
@@ -1262,7 +1305,7 @@ static int ni_expand_mft_list(struct ntfs_inode *ni)
 	done = asize - run_size - SIZEOF_NONRESIDENT;
 	le32_sub_cpu(&ni->mi.mrec->used, done);
 
-	/* Estimate the size of second part: run_buf=NULL. */
+	/* Estimate packed size (run_buf=NULL). */
 	err = run_pack(run, svcn, evcn + 1 - svcn, NULL, sbi->record_size,
 		       &plen);
 	if (err < 0)
@@ -1288,10 +1331,16 @@ static int ni_expand_mft_list(struct ntfs_inode *ni)
 		goto out;
 	}
 
+	if (IS_ERR(attr)) {
+		err = PTR_ERR(attr);
+		goto out;
+	}
+
 	attr->non_res = 1;
 	attr->name_off = SIZEOF_NONRESIDENT_LE;
 	attr->flags = 0;
 
+	/* This function can't fail - cause already checked above. */
 	run_pack(run, svcn, evcn + 1 - svcn, Add2Ptr(attr, SIZEOF_NONRESIDENT),
 		 run_size, &plen);
 
@@ -1301,7 +1350,7 @@ static int ni_expand_mft_list(struct ntfs_inode *ni)
 
 out:
 	if (mft_new) {
-		ntfs_mark_rec_free(sbi, mft_new);
+		ntfs_mark_rec_free(sbi, mft_new, true);
 		ni_remove_mi(ni, mi_new);
 	}
 
@@ -1367,8 +1416,6 @@ int ni_expand_list(struct ntfs_inode *ni)
 
 	/* Split MFT data as much as possible. */
 	err = ni_expand_mft_list(ni);
-	if (err)
-		goto out;
 
 out:
 	return !err && !done ? -EOPNOTSUPP : err;
@@ -1381,7 +1428,7 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type,
 			  const __le16 *name, u8 name_len,
 			  const struct runs_tree *run, CLST svcn, CLST len,
 			  __le16 flags, struct ATTRIB **new_attr,
-			  struct mft_inode **mi)
+			  struct mft_inode **mi, struct ATTR_LIST_ENTRY **le)
 {
 	int err;
 	CLST plen;
@@ -1394,6 +1441,7 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type,
 	u32 run_size, asize;
 	struct ntfs_sb_info *sbi = ni->mi.sbi;
 
+	/* Estimate packed size (run_buf=NULL). */
 	err = run_pack(run, svcn, len, NULL, sbi->max_bytes_per_attr - run_off,
 		       &plen);
 	if (err < 0)
@@ -1414,7 +1462,7 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type,
 	}
 
 	err = ni_insert_attr(ni, type, name, name_len, asize, name_off, svcn,
-			     &attr, mi, NULL);
+			     &attr, mi, le);
 
 	if (err)
 		goto out;
@@ -1423,12 +1471,12 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type,
 	attr->name_off = cpu_to_le16(name_off);
 	attr->flags = flags;
 
+	/* This function can't fail - cause already checked above. */
 	run_pack(run, svcn, len, Add2Ptr(attr, run_off), run_size, &plen);
 
 	attr->nres.svcn = cpu_to_le64(svcn);
 	attr->nres.evcn = cpu_to_le64((u64)svcn + len - 1);
 
-	err = 0;
 	if (new_attr)
 		*new_attr = attr;
 
@@ -1560,7 +1608,7 @@ int ni_delete_all(struct ntfs_inode *ni)
 		mi->dirty = true;
 		mi_write(mi, 0);
 
-		ntfs_mark_rec_free(sbi, mi->rno);
+		ntfs_mark_rec_free(sbi, mi->rno, false);
 		ni_remove_mi(ni, mi);
 		mi_put(mi);
 		node = next;
@@ -1571,7 +1619,7 @@ int ni_delete_all(struct ntfs_inode *ni)
 	ni->mi.dirty = true;
 	err = mi_write(&ni->mi, 0);
 
-	ntfs_mark_rec_free(sbi, ni->mi.rno);
+	ntfs_mark_rec_free(sbi, ni->mi.rno, false);
 
 	return err;
 }
@@ -1589,7 +1637,8 @@ struct ATTR_FILE_NAME *ni_fname_name(struct ntfs_inode *ni,
 	struct ATTRIB *attr = NULL;
 	struct ATTR_FILE_NAME *fname;
 
-	*le = NULL;
+	if (le)
+		*le = NULL;
 
 	/* Enumerate all names. */
 next:
@@ -1605,7 +1654,7 @@ next:
 		goto next;
 
 	if (!uni)
-		goto next;
+		return fname;
 
 	if (uni->len != fname->name_len)
 		goto next;
@@ -2302,10 +2351,8 @@ remove_wof:
 
 out:
 	kfree(pages);
-	if (err) {
-		make_bad_inode(inode);
-		ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
-	}
+	if (err)
+		_ntfs_bad_inode(inode);
 
 	return err;
 }
@@ -2944,7 +2991,7 @@ bool ni_remove_name_undo(struct ntfs_inode *dir_ni, struct ntfs_inode *ni,
 }
 
 /*
- * ni_add_name - Add new name in MFT and in directory.
+ * ni_add_name - Add new name into MFT and into directory.
  */
 int ni_add_name(struct ntfs_inode *dir_ni, struct ntfs_inode *ni,
 		struct NTFS_DE *de)
@@ -2953,13 +3000,20 @@ int ni_add_name(struct ntfs_inode *dir_ni, struct ntfs_inode *ni,
 	struct ATTRIB *attr;
 	struct ATTR_LIST_ENTRY *le;
 	struct mft_inode *mi;
+	struct ATTR_FILE_NAME *fname;
 	struct ATTR_FILE_NAME *de_name = (struct ATTR_FILE_NAME *)(de + 1);
 	u16 de_key_size = le16_to_cpu(de->key_size);
 
 	mi_get_ref(&ni->mi, &de->ref);
 	mi_get_ref(&dir_ni->mi, &de_name->home);
 
-	/* Insert new name in MFT. */
+	/* Fill duplicate from any ATTR_NAME. */
+	fname = ni_fname_name(ni, NULL, NULL, NULL, NULL);
+	if (fname)
+		memcpy(&de_name->dup, &fname->dup, sizeof(fname->dup));
+	de_name->dup.fa = ni->std_fa;
+
+	/* Insert new name into MFT. */
 	err = ni_insert_resident(ni, de_key_size, ATTR_NAME, NULL, 0, &attr,
 				 &mi, &le);
 	if (err)
@@ -2967,7 +3021,7 @@ int ni_add_name(struct ntfs_inode *dir_ni, struct ntfs_inode *ni,
 
 	memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), de_name, de_key_size);
 
-	/* Insert new name in directory. */
+	/* Insert new name into directory. */
 	err = indx_insert_entry(&dir_ni->dir, dir_ni, de, ni->mi.sbi, NULL, 0);
 	if (err)
 		ni_remove_attr_le(ni, attr, mi, le);
@@ -2991,7 +3045,7 @@ int ni_rename(struct ntfs_inode *dir_ni, struct ntfs_inode *new_dir_ni,
 	 * 1) Add new name and remove old name.
 	 * 2) Remove old name and add new name.
 	 *
-	 * In most cases (not all!) adding new name in MFT and in directory can
+	 * In most cases (not all!) adding new name into MFT and into directory can
 	 * allocate additional cluster(s).
 	 * Second way may result to bad inode if we can't add new name
 	 * and then can't restore (add) old name.
@@ -3261,7 +3315,7 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint)
 			err = err2;
 
 		if (is_empty) {
-			ntfs_mark_rec_free(sbi, mi->rno);
+			ntfs_mark_rec_free(sbi, mi->rno, false);
 			rb_erase(node, &ni->mi_tree);
 			mi_put(mi);
 		}
diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c
index 49b7df616778..e7c494005122 100644
--- a/fs/ntfs3/fslog.c
+++ b/fs/ntfs3/fslog.c
@@ -3843,6 +3843,8 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 
 	memset(&rst_info2, 0, sizeof(struct restart_info));
 	err = log_read_rst(log, l_size, false, &rst_info2);
+	if (err)
+		goto out;
 
 	/* Determine which restart area to use. */
 	if (!rst_info2.restart || rst_info2.last_lsn <= rst_info.last_lsn)
@@ -5057,7 +5059,7 @@ undo_action_next:
 		goto add_allocated_vcns;
 
 	vcn = le64_to_cpu(lrh->target_vcn);
-	vcn &= ~(log->clst_per_page - 1);
+	vcn &= ~(u64)(log->clst_per_page - 1);
 
 add_allocated_vcns:
 	for (i = 0, vcn = le64_to_cpu(lrh->target_vcn),
diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index 1835e35199c2..4ed15f64b17f 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -703,12 +703,14 @@ out:
 
 /*
  * ntfs_mark_rec_free - Mark record as free.
+ * is_mft - true if we are changing MFT
  */
-void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno)
+void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno, bool is_mft)
 {
 	struct wnd_bitmap *wnd = &sbi->mft.bitmap;
 
-	down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_MFT);
+	if (!is_mft)
+		down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_MFT);
 	if (rno >= wnd->nbits)
 		goto out;
 
@@ -727,7 +729,8 @@ void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno)
 		sbi->mft.next_free = rno;
 
 out:
-	up_write(&wnd->rw_lock);
+	if (!is_mft)
+		up_write(&wnd->rw_lock);
 }
 
 /*
@@ -780,7 +783,7 @@ out:
  */
 int ntfs_refresh_zone(struct ntfs_sb_info *sbi)
 {
-	CLST zone_limit, zone_max, lcn, vcn, len;
+	CLST lcn, vcn, len;
 	size_t lcn_s, zlen;
 	struct wnd_bitmap *wnd = &sbi->used.bitmap;
 	struct ntfs_inode *ni = sbi->mft.ni;
@@ -789,16 +792,6 @@ int ntfs_refresh_zone(struct ntfs_sb_info *sbi)
 	if (wnd_zone_len(wnd))
 		return 0;
 
-	/*
-	 * Compute the MFT zone at two steps.
-	 * It would be nice if we are able to allocate 1/8 of
-	 * total clusters for MFT but not more then 512 MB.
-	 */
-	zone_limit = (512 * 1024 * 1024) >> sbi->cluster_bits;
-	zone_max = wnd->nbits >> 3;
-	if (zone_max > zone_limit)
-		zone_max = zone_limit;
-
 	vcn = bytes_to_cluster(sbi,
 			       (u64)sbi->mft.bitmap.nbits << sbi->record_bits);
 
@@ -812,13 +805,7 @@ int ntfs_refresh_zone(struct ntfs_sb_info *sbi)
 	lcn_s = lcn + 1;
 
 	/* Try to allocate clusters after last MFT run. */
-	zlen = wnd_find(wnd, zone_max, lcn_s, 0, &lcn_s);
-	if (!zlen) {
-		ntfs_notice(sbi->sb, "MftZone: unavailable");
-		return 0;
-	}
-
-	/* Truncate too large zone. */
+	zlen = wnd_find(wnd, sbi->zone_max, lcn_s, 0, &lcn_s);
 	wnd_zone_set(wnd, lcn_s, zlen);
 
 	return 0;
@@ -827,16 +814,21 @@ int ntfs_refresh_zone(struct ntfs_sb_info *sbi)
 /*
  * ntfs_update_mftmirr - Update $MFTMirr data.
  */
-int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait)
+void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait)
 {
 	int err;
 	struct super_block *sb = sbi->sb;
-	u32 blocksize = sb->s_blocksize;
+	u32 blocksize;
 	sector_t block1, block2;
 	u32 bytes;
 
+	if (!sb)
+		return;
+
+	blocksize = sb->s_blocksize;
+
 	if (!(sbi->flags & NTFS_FLAGS_MFTMIRR))
-		return 0;
+		return;
 
 	err = 0;
 	bytes = sbi->mft.recs_mirr << sbi->record_bits;
@@ -847,16 +839,13 @@ int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait)
 		struct buffer_head *bh1, *bh2;
 
 		bh1 = sb_bread(sb, block1++);
-		if (!bh1) {
-			err = -EIO;
-			goto out;
-		}
+		if (!bh1)
+			return;
 
 		bh2 = sb_getblk(sb, block2++);
 		if (!bh2) {
 			put_bh(bh1);
-			err = -EIO;
-			goto out;
+			return;
 		}
 
 		if (buffer_locked(bh2))
@@ -876,13 +865,24 @@ int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait)
 
 		put_bh(bh2);
 		if (err)
-			goto out;
+			return;
 	}
 
 	sbi->flags &= ~NTFS_FLAGS_MFTMIRR;
+}
 
-out:
-	return err;
+/*
+ * ntfs_bad_inode
+ *
+ * Marks inode as bad and marks fs as 'dirty'
+ */
+void ntfs_bad_inode(struct inode *inode, const char *hint)
+{
+	struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info;
+
+	ntfs_inode_err(inode, "%s", hint);
+	make_bad_inode(inode);
+	ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
 }
 
 /*
@@ -1395,7 +1395,7 @@ int ntfs_write_bh(struct ntfs_sb_info *sbi, struct NTFS_RECORD_HEADER *rhdr,
 		if (buffer_locked(bh))
 			__wait_on_buffer(bh);
 
-		lock_buffer(nb->bh[idx]);
+		lock_buffer(bh);
 
 		bh_data = bh->b_data + off;
 		end_data = Add2Ptr(bh_data, op);
@@ -2424,7 +2424,7 @@ static inline void ntfs_unmap_and_discard(struct ntfs_sb_info *sbi, CLST lcn,
 
 void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim)
 {
-	CLST end, i;
+	CLST end, i, zone_len, zlen;
 	struct wnd_bitmap *wnd = &sbi->used.bitmap;
 
 	down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS);
@@ -2459,6 +2459,28 @@ void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim)
 		ntfs_unmap_and_discard(sbi, lcn, len);
 	wnd_set_free(wnd, lcn, len);
 
+	/* append to MFT zone, if possible. */
+	zone_len = wnd_zone_len(wnd);
+	zlen = min(zone_len + len, sbi->zone_max);
+
+	if (zlen == zone_len) {
+		/* MFT zone already has maximum size. */
+	} else if (!zone_len) {
+		/* Create MFT zone only if 'zlen' is large enough. */
+		if (zlen == sbi->zone_max)
+			wnd_zone_set(wnd, lcn, zlen);
+	} else {
+		CLST zone_lcn = wnd_zone_bit(wnd);
+
+		if (lcn + len == zone_lcn) {
+			/* Append into head MFT zone. */
+			wnd_zone_set(wnd, lcn, zlen);
+		} else if (zone_lcn + zone_len == lcn) {
+			/* Append into tail MFT zone. */
+			wnd_zone_set(wnd, zone_lcn, zlen);
+		}
+	}
+
 out:
 	up_write(&wnd->rw_lock);
 }
diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c
index 6f81e3a49abf..440328147e7e 100644
--- a/fs/ntfs3/index.c
+++ b/fs/ntfs3/index.c
@@ -1042,19 +1042,16 @@ int indx_find(struct ntfs_index *indx, struct ntfs_inode *ni,
 {
 	int err;
 	struct NTFS_DE *e;
-	const struct INDEX_HDR *hdr;
 	struct indx_node *node;
 
 	if (!root)
 		root = indx_get_root(&ni->dir, ni, NULL, NULL);
 
 	if (!root) {
-		err = -EINVAL;
-		goto out;
+		/* Should not happen. */
+		return -EINVAL;
 	}
 
-	hdr = &root->ihdr;
-
 	/* Check cache. */
 	e = fnd->level ? fnd->de[fnd->level - 1] : fnd->root_de;
 	if (e && !de_is_last(e) &&
@@ -1068,39 +1065,35 @@ int indx_find(struct ntfs_index *indx, struct ntfs_inode *ni,
 	fnd_clear(fnd);
 
 	/* Lookup entry that is <= to the search value. */
-	e = hdr_find_e(indx, hdr, key, key_len, ctx, diff);
+	e = hdr_find_e(indx, &root->ihdr, key, key_len, ctx, diff);
 	if (!e)
 		return -EINVAL;
 
 	fnd->root_de = e;
-	err = 0;
 
 	for (;;) {
 		node = NULL;
-		if (*diff >= 0 || !de_has_vcn_ex(e)) {
-			*entry = e;
-			goto out;
-		}
+		if (*diff >= 0 || !de_has_vcn_ex(e))
+			break;
 
 		/* Read next level. */
 		err = indx_read(indx, ni, de_get_vbn(e), &node);
 		if (err)
-			goto out;
+			return err;
 
 		/* Lookup entry that is <= to the search value. */
 		e = hdr_find_e(indx, &node->index->ihdr, key, key_len, ctx,
 			       diff);
 		if (!e) {
-			err = -EINVAL;
 			put_indx_node(node);
-			goto out;
+			return -EINVAL;
 		}
 
 		fnd_push(fnd, node, e);
 	}
 
-out:
-	return err;
+	*entry = e;
+	return 0;
 }
 
 int indx_find_sort(struct ntfs_index *indx, struct ntfs_inode *ni,
@@ -1354,7 +1347,7 @@ static int indx_create_allocate(struct ntfs_index *indx, struct ntfs_inode *ni,
 		goto out;
 
 	err = ni_insert_nonresident(ni, ATTR_ALLOC, in->name, in->name_len,
-				    &run, 0, len, 0, &alloc, NULL);
+				    &run, 0, len, 0, &alloc, NULL, NULL);
 	if (err)
 		goto out1;
 
@@ -1685,8 +1678,8 @@ indx_insert_into_buffer(struct ntfs_index *indx, struct ntfs_inode *ni,
 {
 	int err;
 	const struct NTFS_DE *sp;
-	struct NTFS_DE *e, *de_t, *up_e = NULL;
-	struct indx_node *n2 = NULL;
+	struct NTFS_DE *e, *de_t, *up_e;
+	struct indx_node *n2;
 	struct indx_node *n1 = fnd->nodes[level];
 	struct INDEX_HDR *hdr1 = &n1->index->ihdr;
 	struct INDEX_HDR *hdr2;
@@ -1994,7 +1987,7 @@ static int indx_free_children(struct ntfs_index *indx, struct ntfs_inode *ni,
 			      const struct NTFS_DE *e, bool trim)
 {
 	int err;
-	struct indx_node *n;
+	struct indx_node *n = NULL;
 	struct INDEX_HDR *hdr;
 	CLST vbn = de_get_vbn(e);
 	size_t i;
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index 80104afeb2cd..26a76ebfe58f 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -430,6 +430,7 @@ end_enum:
 	} else if (fname && fname->home.low == cpu_to_le32(MFT_REC_EXTEND) &&
 		   fname->home.seq == cpu_to_le16(MFT_REC_EXTEND)) {
 		/* Records in $Extend are not a files or general directories. */
+		inode->i_op = &ntfs_file_inode_operations;
 	} else {
 		err = -EINVAL;
 		goto out;
@@ -500,7 +501,7 @@ struct inode *ntfs_iget5(struct super_block *sb, const struct MFT_REF *ref,
 		inode = ntfs_read_mft(inode, name, ref);
 	else if (ref->seq != ntfs_i(inode)->mi.mrec->seq) {
 		/* Inode overlaps? */
-		make_bad_inode(inode);
+		_ntfs_bad_inode(inode);
 	}
 
 	return inode;
@@ -1632,7 +1633,7 @@ out4:
 	ni->mi.dirty = false;
 	discard_new_inode(inode);
 out3:
-	ntfs_mark_rec_free(sbi, ino);
+	ntfs_mark_rec_free(sbi, ino, false);
 
 out2:
 	__putname(new_de);
@@ -1655,7 +1656,6 @@ int ntfs_link_inode(struct inode *inode, struct dentry *dentry)
 	struct ntfs_inode *ni = ntfs_i(inode);
 	struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info;
 	struct NTFS_DE *de;
-	struct ATTR_FILE_NAME *de_name;
 
 	/* Allocate PATH_MAX bytes. */
 	de = __getname();
@@ -1670,15 +1670,6 @@ int ntfs_link_inode(struct inode *inode, struct dentry *dentry)
 	if (err)
 		goto out;
 
-	de_name = (struct ATTR_FILE_NAME *)(de + 1);
-	/* Fill duplicate info. */
-	de_name->dup.cr_time = de_name->dup.m_time = de_name->dup.c_time =
-		de_name->dup.a_time = kernel2nt(&inode->i_ctime);
-	de_name->dup.alloc_size = de_name->dup.data_size =
-		cpu_to_le64(inode->i_size);
-	de_name->dup.fa = ni->std_fa;
-	de_name->dup.ea_size = de_name->dup.reparse = 0;
-
 	err = ni_add_name(ntfs_i(d_inode(dentry->d_parent)), ni, de);
 out:
 	__putname(de);
@@ -1731,9 +1722,7 @@ int ntfs_unlink_inode(struct inode *dir, const struct dentry *dentry)
 		if (inode->i_nlink)
 			mark_inode_dirty(inode);
 	} else if (!ni_remove_name_undo(dir_ni, ni, de, de2, undo_remove)) {
-		make_bad_inode(inode);
-		ntfs_inode_err(inode, "failed to undo unlink");
-		ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
+		_ntfs_bad_inode(inode);
 	} else {
 		if (ni_is_dirty(dir))
 			mark_inode_dirty(dir);
@@ -1938,8 +1927,6 @@ const struct inode_operations ntfs_link_inode_operations = {
 	.setattr	= ntfs3_setattr,
 	.listxattr	= ntfs_listxattr,
 	.permission	= ntfs_permission,
-	.get_acl	= ntfs_get_acl,
-	.set_acl	= ntfs_set_acl,
 };
 
 const struct address_space_operations ntfs_aops = {
diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c
index bc741213ad84..bc22cc321a74 100644
--- a/fs/ntfs3/namei.c
+++ b/fs/ntfs3/namei.c
@@ -208,7 +208,7 @@ static int ntfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
 }
 
 /*
- * ntfs_rmdir - inode_operations::rm_dir
+ * ntfs_rmdir - inode_operations::rmdir
  */
 static int ntfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
@@ -308,9 +308,7 @@ static int ntfs_rename(struct user_namespace *mnt_userns, struct inode *dir,
 	err = ni_rename(dir_ni, new_dir_ni, ni, de, new_de, &is_bad);
 	if (is_bad) {
 		/* Restore after failed rename failed too. */
-		make_bad_inode(inode);
-		ntfs_inode_err(inode, "failed to undo rename");
-		ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
+		_ntfs_bad_inode(inode);
 	} else if (!err) {
 		inode->i_ctime = dir->i_ctime = dir->i_mtime =
 			current_time(dir);
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 8dbdca03e1af..2c791222c4e2 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -220,6 +220,7 @@ struct ntfs_sb_info {
 
 	u32 flags; // See NTFS_FLAGS_XXX.
 
+	CLST zone_max; // Maximum MFT zone length in clusters
 	CLST bad_clusters; // The count of marked bad clusters.
 
 	u16 max_bytes_per_attr; // Maximum attribute size in record.
@@ -408,8 +409,6 @@ enum REPARSE_SIGN {
 };
 
 /* Functions from attrib.c */
-int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni,
-		   struct runs_tree *run, const CLST *vcn);
 int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run,
 			   CLST vcn, CLST lcn, CLST len, CLST *pre_alloc,
 			   enum ALLOCATE_OPT opt, CLST *alen, const size_t fr,
@@ -440,6 +439,7 @@ int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr,
 int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size,
 			u64 new_valid);
 int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes);
+int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes);
 int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size);
 
 /* Functions from attrlist.c */
@@ -528,7 +528,7 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type,
 			  const __le16 *name, u8 name_len,
 			  const struct runs_tree *run, CLST svcn, CLST len,
 			  __le16 flags, struct ATTRIB **new_attr,
-			  struct mft_inode **mi);
+			  struct mft_inode **mi, struct ATTR_LIST_ENTRY **le);
 int ni_insert_resident(struct ntfs_inode *ni, u32 data_size,
 		       enum ATTR_TYPE type, const __le16 *name, u8 name_len,
 		       struct ATTRIB **new_attr, struct mft_inode **mi,
@@ -589,10 +589,12 @@ int ntfs_look_for_free_space(struct ntfs_sb_info *sbi, CLST lcn, CLST len,
 			     enum ALLOCATE_OPT opt);
 int ntfs_look_free_mft(struct ntfs_sb_info *sbi, CLST *rno, bool mft,
 		       struct ntfs_inode *ni, struct mft_inode **mi);
-void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno);
+void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno, bool is_mft);
 int ntfs_clear_mft_tail(struct ntfs_sb_info *sbi, size_t from, size_t to);
 int ntfs_refresh_zone(struct ntfs_sb_info *sbi);
-int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait);
+void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait);
+void ntfs_bad_inode(struct inode *inode, const char *hint);
+#define _ntfs_bad_inode(i) ntfs_bad_inode(i, __func__)
 enum NTFS_DIRTY_FLAGS {
 	NTFS_DIRTY_CLEAR = 0,
 	NTFS_DIRTY_DIRTY = 1,
@@ -738,7 +740,6 @@ static inline struct ATTRIB *rec_find_attr_le(struct mft_inode *rec,
 int mi_write(struct mft_inode *mi, int wait);
 int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno,
 		  __le16 flags, bool is_mft);
-void mi_mark_free(struct mft_inode *mi);
 struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type,
 			      const __le16 *name, u8 name_len, u32 asize,
 			      u16 name_off);
@@ -780,10 +781,10 @@ bool run_lookup_entry(const struct runs_tree *run, CLST vcn, CLST *lcn,
 void run_truncate(struct runs_tree *run, CLST vcn);
 void run_truncate_head(struct runs_tree *run, CLST vcn);
 void run_truncate_around(struct runs_tree *run, CLST vcn);
-bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *Index);
 bool run_add_entry(struct runs_tree *run, CLST vcn, CLST lcn, CLST len,
 		   bool is_mft);
 bool run_collapse_range(struct runs_tree *run, CLST vcn, CLST len);
+bool run_insert_range(struct runs_tree *run, CLST vcn, CLST len);
 bool run_get_entry(const struct runs_tree *run, size_t index, CLST *vcn,
 		   CLST *lcn, CLST *len);
 bool run_is_mapped_full(const struct runs_tree *run, CLST svcn, CLST evcn);
@@ -802,6 +803,7 @@ int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino,
 #define run_unpack_ex run_unpack
 #endif
 int run_get_highest_vcn(CLST vcn, const u8 *run_buf, u64 *highest_vcn);
+int run_clone(const struct runs_tree *run, struct runs_tree *new_run);
 
 /* Globals from super.c */
 void *ntfs_set_shared(void *ptr, u32 bytes);
diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c
index 861e35791506..7d2fac5ee215 100644
--- a/fs/ntfs3/record.c
+++ b/fs/ntfs3/record.c
@@ -395,28 +395,6 @@ int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno,
 }
 
 /*
- * mi_mark_free - Mark record as unused and marks it as free in bitmap.
- */
-void mi_mark_free(struct mft_inode *mi)
-{
-	CLST rno = mi->rno;
-	struct ntfs_sb_info *sbi = mi->sbi;
-
-	if (rno >= MFT_REC_RESERVED && rno < MFT_REC_FREE) {
-		ntfs_clear_mft_tail(sbi, rno, rno + 1);
-		mi->dirty = false;
-		return;
-	}
-
-	if (mi->mrec) {
-		clear_rec_inuse(mi->mrec);
-		mi->dirty = true;
-		mi_write(mi, 0);
-	}
-	ntfs_mark_rec_free(sbi, rno);
-}
-
-/*
  * mi_insert_attr - Reserve space for new attribute.
  *
  * Return: Not full constructed attribute or NULL if not possible to create.
@@ -445,12 +423,11 @@ struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type,
 	attr = NULL;
 	while ((attr = mi_enum_attr(mi, attr))) {
 		diff = compare_attr(attr, type, name, name_len, upcase);
-		if (diff > 0)
-			break;
+
 		if (diff < 0)
 			continue;
 
-		if (!is_attr_indexed(attr))
+		if (!diff && !is_attr_indexed(attr))
 			return NULL;
 		break;
 	}
diff --git a/fs/ntfs3/run.c b/fs/ntfs3/run.c
index a8fec651f973..aaaa0d3d35a2 100644
--- a/fs/ntfs3/run.c
+++ b/fs/ntfs3/run.c
@@ -31,7 +31,7 @@ struct ntfs_run {
  * Case of entry missing from list 'index' will be set to
  * point to insertion position for the entry question.
  */
-bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *index)
+static bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *index)
 {
 	size_t min_idx, max_idx, mid_idx;
 	struct ntfs_run *r;
@@ -547,6 +547,48 @@ bool run_collapse_range(struct runs_tree *run, CLST vcn, CLST len)
 	return true;
 }
 
+/* run_insert_range
+ *
+ * Helper for attr_insert_range(),
+ * which is helper for fallocate(insert_range).
+ */
+bool run_insert_range(struct runs_tree *run, CLST vcn, CLST len)
+{
+	size_t index;
+	struct ntfs_run *r, *e;
+
+	if (WARN_ON(!run_lookup(run, vcn, &index)))
+		return false; /* Should never be here. */
+
+	e = run->runs + run->count;
+	r = run->runs + index;
+
+	if (vcn > r->vcn)
+		r += 1;
+
+	for (; r < e; r++)
+		r->vcn += len;
+
+	r = run->runs + index;
+
+	if (vcn > r->vcn) {
+		/* split fragment. */
+		CLST len1 = vcn - r->vcn;
+		CLST len2 = r->len - len1;
+		CLST lcn2 = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + len1);
+
+		r->len = len1;
+
+		if (!run_add_entry(run, vcn + len, lcn2, len2, false))
+			return false;
+	}
+
+	if (!run_add_entry(run, vcn, SPARSE_LCN, len, false))
+		return false;
+
+	return true;
+}
+
 /*
  * run_get_entry - Return index-th mapped region.
  */
@@ -778,26 +820,36 @@ int run_pack(const struct runs_tree *run, CLST svcn, CLST len, u8 *run_buf,
 	CLST next_vcn, vcn, lcn;
 	CLST prev_lcn = 0;
 	CLST evcn1 = svcn + len;
+	const struct ntfs_run *r, *r_end;
 	int packed_size = 0;
 	size_t i;
-	bool ok;
 	s64 dlcn;
 	int offset_size, size_size, tmp;
 
-	next_vcn = vcn = svcn;
-
 	*packed_vcns = 0;
 
 	if (!len)
 		goto out;
 
-	ok = run_lookup_entry(run, vcn, &lcn, &len, &i);
+	/* Check all required entries [svcn, encv1) available. */
+	if (!run_lookup(run, svcn, &i))
+		return -ENOENT;
+
+	r_end = run->runs + run->count;
+	r = run->runs + i;
 
-	if (!ok)
-		goto error;
+	for (next_vcn = r->vcn + r->len; next_vcn < evcn1;
+	     next_vcn = r->vcn + r->len) {
+		if (++r >= r_end || r->vcn != next_vcn)
+			return -ENOENT;
+	}
 
-	if (next_vcn != vcn)
-		goto error;
+	/* Repeat cycle above and pack runs. Assume no errors. */
+	r = run->runs + i;
+	len = svcn - r->vcn;
+	vcn = svcn;
+	lcn = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + len);
+	len = r->len - len;
 
 	for (;;) {
 		next_vcn = vcn + len;
@@ -846,12 +898,10 @@ int run_pack(const struct runs_tree *run, CLST svcn, CLST len, u8 *run_buf,
 		if (packed_size + 1 >= run_buf_size || next_vcn >= evcn1)
 			goto out;
 
-		ok = run_get_entry(run, ++i, &vcn, &lcn, &len);
-		if (!ok)
-			goto error;
-
-		if (next_vcn != vcn)
-			goto error;
+		r += 1;
+		vcn = r->vcn;
+		lcn = r->lcn;
+		len = r->len;
 	}
 
 out:
@@ -860,9 +910,6 @@ out:
 		run_buf[0] = 0;
 
 	return packed_size + 1;
-
-error:
-	return -EOPNOTSUPP;
 }
 
 /*
@@ -1109,3 +1156,28 @@ int run_get_highest_vcn(CLST vcn, const u8 *run_buf, u64 *highest_vcn)
 	*highest_vcn = vcn64 - 1;
 	return 0;
 }
+
+/*
+ * run_clone
+ *
+ * Make a copy of run
+ */
+int run_clone(const struct runs_tree *run, struct runs_tree *new_run)
+{
+	size_t bytes = run->count * sizeof(struct ntfs_run);
+
+	if (bytes > new_run->allocated) {
+		struct ntfs_run *new_ptr = kvmalloc(bytes, GFP_KERNEL);
+
+		if (!new_ptr)
+			return -ENOMEM;
+
+		kvfree(new_run->runs);
+		new_run->runs = new_ptr;
+		new_run->allocated = bytes;
+	}
+
+	memcpy(new_run->runs, run->runs, bytes);
+	new_run->count = run->count;
+	return 0;
+}
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 0c6de6287737..47012c9bf505 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -30,6 +30,7 @@
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
 #include <linux/log2.h>
+#include <linux/minmax.h>
 #include <linux/module.h>
 #include <linux/nls.h>
 #include <linux/seq_file.h>
@@ -390,7 +391,7 @@ static int ntfs_fs_reconfigure(struct fs_context *fc)
 		return -EINVAL;
 	}
 
-	memcpy(sbi->options, new_opts, sizeof(*new_opts));
+	swap(sbi->options, fc->fs_private);
 
 	return 0;
 }
@@ -870,6 +871,13 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
 	sb->s_maxbytes = 0xFFFFFFFFull << sbi->cluster_bits;
 #endif
 
+	/*
+	 * Compute the MFT zone at two steps.
+	 * It would be nice if we are able to allocate 1/8 of
+	 * total clusters for MFT but not more then 512 MB.
+	 */
+	sbi->zone_max = min_t(CLST, 0x20000000 >> sbi->cluster_bits, clusters >> 3);
+
 	err = 0;
 
 out:
@@ -900,6 +908,8 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	ref.high = 0;
 
 	sbi->sb = sb;
+	sbi->options = fc->fs_private;
+	fc->fs_private = NULL;
 	sb->s_flags |= SB_NODIRATIME;
 	sb->s_magic = 0x7366746e; // "ntfs"
 	sb->s_op = &ntfs_sops;
@@ -1262,8 +1272,6 @@ load_root:
 		goto put_inode_out;
 	}
 
-	fc->fs_private = NULL;
-
 	return 0;
 
 put_inode_out:
@@ -1378,7 +1386,7 @@ static const struct fs_context_operations ntfs_context_ops = {
 /*
  * ntfs_init_fs_context - Initialize spi and opts
  *
- * This will called when mount/remount. We will first initiliaze
+ * This will called when mount/remount. We will first initialize
  * options so that if remount we can use just that.
  */
 static int ntfs_init_fs_context(struct fs_context *fc)
@@ -1416,7 +1424,6 @@ static int ntfs_init_fs_context(struct fs_context *fc)
 	mutex_init(&sbi->compress.mtx_lzx);
 #endif
 
-	sbi->options = opts;
 	fc->s_fs_info = sbi;
 ok:
 	fc->fs_private = opts;
diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c
index 5e0e0280e70d..7de8718c68a9 100644
--- a/fs/ntfs3/xattr.c
+++ b/fs/ntfs3/xattr.c
@@ -118,7 +118,7 @@ static int ntfs_read_ea(struct ntfs_inode *ni, struct EA_FULL **ea,
 
 		run_init(&run);
 
-		err = attr_load_runs(attr_ea, ni, &run, NULL);
+		err = attr_load_runs_range(ni, ATTR_EA, NULL, 0, &run, 0, size);
 		if (!err)
 			err = ntfs_read_run_nb(sbi, &run, 0, ea_p, size, NULL);
 		run_close(&run);
@@ -444,6 +444,11 @@ update_ea:
 		/* Delete xattr, ATTR_EA */
 		ni_remove_attr_le(ni, attr, mi, le);
 	} else if (attr->non_res) {
+		err = attr_load_runs_range(ni, ATTR_EA, NULL, 0, &ea_run, 0,
+					   size);
+		if (err)
+			goto out;
+
 		err = ntfs_sb_write_run(sbi, &ea_run, 0, ea_all, size, 0);
 		if (err)
 			goto out;
@@ -478,8 +483,7 @@ out:
 }
 
 #ifdef CONFIG_NTFS3_FS_POSIX_ACL
-static struct posix_acl *ntfs_get_acl_ex(struct user_namespace *mnt_userns,
-					 struct inode *inode, int type,
+static struct posix_acl *ntfs_get_acl_ex(struct inode *inode, int type,
 					 int locked)
 {
 	struct ntfs_inode *ni = ntfs_i(inode);
@@ -514,7 +518,7 @@ static struct posix_acl *ntfs_get_acl_ex(struct user_namespace *mnt_userns,
 
 	/* Translate extended attribute to acl. */
 	if (err >= 0) {
-		acl = posix_acl_from_xattr(mnt_userns, buf, err);
+		acl = posix_acl_from_xattr(&init_user_ns, buf, err);
 	} else if (err == -ENODATA) {
 		acl = NULL;
 	} else {
@@ -537,8 +541,7 @@ struct posix_acl *ntfs_get_acl(struct inode *inode, int type, bool rcu)
 	if (rcu)
 		return ERR_PTR(-ECHILD);
 
-	/* TODO: init_user_ns? */
-	return ntfs_get_acl_ex(&init_user_ns, inode, type, 0);
+	return ntfs_get_acl_ex(inode, type, 0);
 }
 
 static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns,
@@ -547,28 +550,23 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns,
 {
 	const char *name;
 	size_t size, name_len;
-	void *value = NULL;
-	int err = 0;
+	void *value;
+	int err;
 	int flags;
+	umode_t mode;
 
 	if (S_ISLNK(inode->i_mode))
 		return -EOPNOTSUPP;
 
+	mode = inode->i_mode;
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		/* Do not change i_mode if we are in init_acl */
 		if (acl && !init_acl) {
-			umode_t mode;
-
 			err = posix_acl_update_mode(mnt_userns, inode, &mode,
 						    &acl);
 			if (err)
-				goto out;
-
-			if (inode->i_mode != mode) {
-				inode->i_mode = mode;
-				mark_inode_dirty(inode);
-			}
+				return err;
 		}
 		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		name_len = sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1;
@@ -595,7 +593,7 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns,
 		value = kmalloc(size, GFP_NOFS);
 		if (!value)
 			return -ENOMEM;
-		err = posix_acl_to_xattr(mnt_userns, acl, value, size);
+		err = posix_acl_to_xattr(&init_user_ns, acl, value, size);
 		if (err < 0)
 			goto out;
 		flags = 0;
@@ -604,8 +602,13 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns,
 	err = ntfs_set_ea(inode, name, name_len, value, size, flags, 0);
 	if (err == -ENODATA && !size)
 		err = 0; /* Removing non existed xattr. */
-	if (!err)
+	if (!err) {
 		set_cached_acl(inode, type, acl);
+		if (inode->i_mode != mode) {
+			inode->i_mode = mode;
+			mark_inode_dirty(inode);
+		}
+	}
 
 out:
 	kfree(value);
@@ -622,67 +625,6 @@ int ntfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 	return ntfs_set_acl_ex(mnt_userns, inode, acl, type, false);
 }
 
-static int ntfs_xattr_get_acl(struct user_namespace *mnt_userns,
-			      struct inode *inode, int type, void *buffer,
-			      size_t size)
-{
-	struct posix_acl *acl;
-	int err;
-
-	if (!(inode->i_sb->s_flags & SB_POSIXACL)) {
-		ntfs_inode_warn(inode, "add mount option \"acl\" to use acl");
-		return -EOPNOTSUPP;
-	}
-
-	acl = ntfs_get_acl(inode, type, false);
-	if (IS_ERR(acl))
-		return PTR_ERR(acl);
-
-	if (!acl)
-		return -ENODATA;
-
-	err = posix_acl_to_xattr(mnt_userns, acl, buffer, size);
-	posix_acl_release(acl);
-
-	return err;
-}
-
-static int ntfs_xattr_set_acl(struct user_namespace *mnt_userns,
-			      struct inode *inode, int type, const void *value,
-			      size_t size)
-{
-	struct posix_acl *acl;
-	int err;
-
-	if (!(inode->i_sb->s_flags & SB_POSIXACL)) {
-		ntfs_inode_warn(inode, "add mount option \"acl\" to use acl");
-		return -EOPNOTSUPP;
-	}
-
-	if (!inode_owner_or_capable(mnt_userns, inode))
-		return -EPERM;
-
-	if (!value) {
-		acl = NULL;
-	} else {
-		acl = posix_acl_from_xattr(mnt_userns, value, size);
-		if (IS_ERR(acl))
-			return PTR_ERR(acl);
-
-		if (acl) {
-			err = posix_acl_valid(mnt_userns, acl);
-			if (err)
-				goto release_and_out;
-		}
-	}
-
-	err = ntfs_set_acl(mnt_userns, inode, acl, type);
-
-release_and_out:
-	posix_acl_release(acl);
-	return err;
-}
-
 /*
  * ntfs_init_acl - Initialize the ACLs of a new inode.
  *
@@ -706,13 +648,13 @@ int ntfs_init_acl(struct user_namespace *mnt_userns, struct inode *inode,
 		inode->i_default_acl = NULL;
 	}
 
-	if (!acl)
-		inode->i_acl = NULL;
-	else {
+	if (acl) {
 		if (!err)
 			err = ntfs_set_acl_ex(mnt_userns, inode, acl,
 					      ACL_TYPE_ACCESS, true);
 		posix_acl_release(acl);
+	} else {
+		inode->i_acl = NULL;
 	}
 
 	return err;
@@ -849,23 +791,6 @@ static int ntfs_getxattr(const struct xattr_handler *handler, struct dentry *de,
 		goto out;
 	}
 
-#ifdef CONFIG_NTFS3_FS_POSIX_ACL
-	if ((name_len == sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1 &&
-	     !memcmp(name, XATTR_NAME_POSIX_ACL_ACCESS,
-		     sizeof(XATTR_NAME_POSIX_ACL_ACCESS))) ||
-	    (name_len == sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) - 1 &&
-	     !memcmp(name, XATTR_NAME_POSIX_ACL_DEFAULT,
-		     sizeof(XATTR_NAME_POSIX_ACL_DEFAULT)))) {
-		/* TODO: init_user_ns? */
-		err = ntfs_xattr_get_acl(
-			&init_user_ns, inode,
-			name_len == sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1
-				? ACL_TYPE_ACCESS
-				: ACL_TYPE_DEFAULT,
-			buffer, size);
-		goto out;
-	}
-#endif
 	/* Deal with NTFS extended attribute. */
 	err = ntfs_get_ea(inode, name, name_len, buffer, size, NULL);
 
@@ -978,22 +903,6 @@ set_new_fa:
 		goto out;
 	}
 
-#ifdef CONFIG_NTFS3_FS_POSIX_ACL
-	if ((name_len == sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1 &&
-	     !memcmp(name, XATTR_NAME_POSIX_ACL_ACCESS,
-		     sizeof(XATTR_NAME_POSIX_ACL_ACCESS))) ||
-	    (name_len == sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) - 1 &&
-	     !memcmp(name, XATTR_NAME_POSIX_ACL_DEFAULT,
-		     sizeof(XATTR_NAME_POSIX_ACL_DEFAULT)))) {
-		err = ntfs_xattr_set_acl(
-			mnt_userns, inode,
-			name_len == sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1
-				? ACL_TYPE_ACCESS
-				: ACL_TYPE_DEFAULT,
-			value, size);
-		goto out;
-	}
-#endif
 	/* Deal with NTFS extended attribute. */
 	err = ntfs_set_ea(inode, name, name_len, value, size, flags, 0);
 
@@ -1083,7 +992,7 @@ static bool ntfs_xattr_user_list(struct dentry *dentry)
 }
 
 // clang-format off
-static const struct xattr_handler ntfs_xattr_handler = {
+static const struct xattr_handler ntfs_other_xattr_handler = {
 	.prefix	= "",
 	.get	= ntfs_getxattr,
 	.set	= ntfs_setxattr,
@@ -1091,7 +1000,11 @@ static const struct xattr_handler ntfs_xattr_handler = {
 };
 
 const struct xattr_handler *ntfs_xattr_handlers[] = {
-	&ntfs_xattr_handler,
+#ifdef CONFIG_NTFS3_FS_POSIX_ACL
+	&posix_acl_access_xattr_handler,
+	&posix_acl_default_xattr_handler,
+#endif
+	&ntfs_other_xattr_handler,
 	NULL,
 };
 // clang-format on
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 801e60bab955..c28bc983a7b1 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -3403,10 +3403,12 @@ void ocfs2_dlm_shutdown(struct ocfs2_super *osb,
 	ocfs2_lock_res_free(&osb->osb_nfs_sync_lockres);
 	ocfs2_lock_res_free(&osb->osb_orphan_scan.os_lockres);
 
-	ocfs2_cluster_disconnect(osb->cconn, hangup_pending);
-	osb->cconn = NULL;
+	if (osb->cconn) {
+		ocfs2_cluster_disconnect(osb->cconn, hangup_pending);
+		osb->cconn = NULL;
 
-	ocfs2_dlm_shutdown_debug(osb);
+		ocfs2_dlm_shutdown_debug(osb);
+	}
 }
 
 static int ocfs2_drop_lock(struct ocfs2_super *osb,
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index a75e2b7d67f5..64e6ddcfe329 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -991,7 +991,7 @@ static int user_cluster_connect(struct ocfs2_cluster_connection *conn)
 	lc->oc_type = NO_CONTROLD;
 
 	rc = dlm_new_lockspace(conn->cc_name, conn->cc_cluster_name,
-			       DLM_LSFL_FS | DLM_LSFL_NEWEXCL, DLM_LVB_LEN,
+			       DLM_LSFL_NEWEXCL, DLM_LVB_LEN,
 			       &ocfs2_ls_ops, conn, &ops_rv, &fsdlm);
 	if (rc) {
 		if (rc == -EEXIST || rc == -EPROTO)
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 013a727bd7c8..e2cc9eec287c 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1914,8 +1914,7 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 	    !ocfs2_is_hard_readonly(osb))
 		hangup_needed = 1;
 
-	if (osb->cconn)
-		ocfs2_dlm_shutdown(osb, hangup_needed);
+	ocfs2_dlm_shutdown(osb, hangup_needed);
 
 	ocfs2_blockcheck_stats_debugfs_remove(&osb->osb_ecc_stats);
 	debugfs_remove_recursive(osb->osb_debug_root);
diff --git a/fs/open.c b/fs/open.c
index 8a813fa5ca56..cf7e5c350a54 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -716,6 +716,8 @@ int chown_common(const struct path *path, uid_t user, gid_t group)
 	fs_userns = i_user_ns(inode);
 
 retry_deleg:
+	newattrs.ia_vfsuid = INVALID_VFSUID;
+	newattrs.ia_vfsgid = INVALID_VFSGID;
 	newattrs.ia_valid =  ATTR_CTIME;
 	if ((user != (uid_t)-1) && !setattr_vfsuid(&newattrs, uid))
 		return -EINVAL;
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index b45fea69fff3..0fbcb590af84 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -460,9 +460,12 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
  * of the POSIX ACLs retrieved from the lower layer to this function to not
  * alter the POSIX ACLs for the underlying filesystem.
  */
-static void ovl_idmap_posix_acl(struct user_namespace *mnt_userns,
+static void ovl_idmap_posix_acl(struct inode *realinode,
+				struct user_namespace *mnt_userns,
 				struct posix_acl *acl)
 {
+	struct user_namespace *fs_userns = i_user_ns(realinode);
+
 	for (unsigned int i = 0; i < acl->a_count; i++) {
 		vfsuid_t vfsuid;
 		vfsgid_t vfsgid;
@@ -470,11 +473,11 @@ static void ovl_idmap_posix_acl(struct user_namespace *mnt_userns,
 		struct posix_acl_entry *e = &acl->a_entries[i];
 		switch (e->e_tag) {
 		case ACL_USER:
-			vfsuid = make_vfsuid(mnt_userns, &init_user_ns, e->e_uid);
+			vfsuid = make_vfsuid(mnt_userns, fs_userns, e->e_uid);
 			e->e_uid = vfsuid_into_kuid(vfsuid);
 			break;
 		case ACL_GROUP:
-			vfsgid = make_vfsgid(mnt_userns, &init_user_ns, e->e_gid);
+			vfsgid = make_vfsgid(mnt_userns, fs_userns, e->e_gid);
 			e->e_gid = vfsgid_into_kgid(vfsgid);
 			break;
 		}
@@ -536,7 +539,7 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu)
 	if (!clone)
 		clone = ERR_PTR(-ENOMEM);
 	else
-		ovl_idmap_posix_acl(mnt_user_ns(realpath.mnt), clone);
+		ovl_idmap_posix_acl(realinode, mnt_user_ns(realpath.mnt), clone);
 	/*
 	 * Since we're not in RCU path walk we always need to release the
 	 * original ACLs.
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 87759165d32b..ee93c825b06b 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -250,7 +250,7 @@ static inline int ovl_do_setxattr(struct ovl_fs *ofs, struct dentry *dentry,
 				  size_t size, int flags)
 {
 	int err = vfs_setxattr(ovl_upper_mnt_userns(ofs), dentry, name,
-			       (void *)value, size, flags);
+			       value, size, flags);
 
 	pr_debug("setxattr(%pd2, \"%s\", \"%*pE\", %zu, %d) = %i\n",
 		 dentry, name, min((int)size, 48), value, size, flags, err);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index ec746d447f1b..5da771b218d1 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1022,7 +1022,20 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
 
 	/* Check that everything is OK before copy-up */
 	if (value) {
-		acl = posix_acl_from_xattr(&init_user_ns, value, size);
+		/* The above comment can be understood in two ways:
+		 *
+		 * 1. We just want to check whether the basic POSIX ACL format
+		 *    is ok. For example, if the header is correct and the size
+		 *    is sane.
+		 * 2. We want to know whether the ACL_{GROUP,USER} entries can
+		 *    be mapped according to the underlying filesystem.
+		 *
+		 * Currently, we only check 1. If we wanted to check 2. we
+		 * would need to pass the mnt_userns and the fs_userns of the
+		 * underlying filesystem. But frankly, I think checking 1. is
+		 * enough to start the copy-up.
+		 */
+		acl = vfs_set_acl_prepare(&init_user_ns, &init_user_ns, value, size);
 		if (IS_ERR(acl))
 			return PTR_ERR(acl);
 	}
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 1d17d7b13dcd..b4f109875e79 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -361,6 +361,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode,
 		     const struct posix_acl *acl, int want)
 {
 	const struct posix_acl_entry *pa, *pe, *mask_obj;
+	struct user_namespace *fs_userns = i_user_ns(inode);
 	int found = 0;
 	vfsuid_t vfsuid;
 	vfsgid_t vfsgid;
@@ -376,7 +377,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode,
                                         goto check_perm;
                                 break;
                         case ACL_USER:
-				vfsuid = make_vfsuid(mnt_userns, &init_user_ns,
+				vfsuid = make_vfsuid(mnt_userns, fs_userns,
 						     pa->e_uid);
 				if (vfsuid_eq_kuid(vfsuid, current_fsuid()))
                                         goto mask;
@@ -390,7 +391,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode,
                                 }
 				break;
                         case ACL_GROUP:
-				vfsgid = make_vfsgid(mnt_userns, &init_user_ns,
+				vfsgid = make_vfsgid(mnt_userns, fs_userns,
 						     pa->e_gid);
 				if (vfsgid_in_group_p(vfsgid)) {
 					found = 1;
@@ -709,9 +710,9 @@ EXPORT_SYMBOL(posix_acl_update_mode);
 /*
  * Fix up the uids and gids in posix acl extended attributes in place.
  */
-static int posix_acl_fix_xattr_common(void *value, size_t size)
+static int posix_acl_fix_xattr_common(const void *value, size_t size)
 {
-	struct posix_acl_xattr_header *header = value;
+	const struct posix_acl_xattr_header *header = value;
 	int count;
 
 	if (!header)
@@ -719,13 +720,13 @@ static int posix_acl_fix_xattr_common(void *value, size_t size)
 	if (size < sizeof(struct posix_acl_xattr_header))
 		return -EINVAL;
 	if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION))
-		return -EINVAL;
+		return -EOPNOTSUPP;
 
 	count = posix_acl_xattr_count(size);
 	if (count < 0)
 		return -EINVAL;
 	if (count == 0)
-		return -EINVAL;
+		return 0;
 
 	return count;
 }
@@ -736,6 +737,7 @@ void posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns,
 {
 	struct posix_acl_xattr_header *header = value;
 	struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end;
+	struct user_namespace *fs_userns = i_user_ns(inode);
 	int count;
 	vfsuid_t vfsuid;
 	vfsgid_t vfsgid;
@@ -746,20 +748,20 @@ void posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns,
 		return;
 
 	count = posix_acl_fix_xattr_common(value, size);
-	if (count < 0)
+	if (count <= 0)
 		return;
 
 	for (end = entry + count; entry != end; entry++) {
 		switch (le16_to_cpu(entry->e_tag)) {
 		case ACL_USER:
 			uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id));
-			vfsuid = make_vfsuid(mnt_userns, &init_user_ns, uid);
+			vfsuid = make_vfsuid(mnt_userns, fs_userns, uid);
 			entry->e_id = cpu_to_le32(from_kuid(&init_user_ns,
 						vfsuid_into_kuid(vfsuid)));
 			break;
 		case ACL_GROUP:
 			gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id));
-			vfsgid = make_vfsgid(mnt_userns, &init_user_ns, gid);
+			vfsgid = make_vfsgid(mnt_userns, fs_userns, gid);
 			entry->e_id = cpu_to_le32(from_kgid(&init_user_ns,
 						vfsgid_into_kgid(vfsgid)));
 			break;
@@ -769,45 +771,6 @@ void posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns,
 	}
 }
 
-void posix_acl_setxattr_idmapped_mnt(struct user_namespace *mnt_userns,
-				     const struct inode *inode,
-				     void *value, size_t size)
-{
-	struct posix_acl_xattr_header *header = value;
-	struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end;
-	int count;
-	vfsuid_t vfsuid;
-	vfsgid_t vfsgid;
-	kuid_t uid;
-	kgid_t gid;
-
-	if (no_idmapping(mnt_userns, i_user_ns(inode)))
-		return;
-
-	count = posix_acl_fix_xattr_common(value, size);
-	if (count < 0)
-		return;
-
-	for (end = entry + count; entry != end; entry++) {
-		switch (le16_to_cpu(entry->e_tag)) {
-		case ACL_USER:
-			uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id));
-			vfsuid = VFSUIDT_INIT(uid);
-			uid = from_vfsuid(mnt_userns, &init_user_ns, vfsuid);
-			entry->e_id = cpu_to_le32(from_kuid(&init_user_ns, uid));
-			break;
-		case ACL_GROUP:
-			gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id));
-			vfsgid = VFSGIDT_INIT(gid);
-			gid = from_vfsgid(mnt_userns, &init_user_ns, vfsgid);
-			entry->e_id = cpu_to_le32(from_kgid(&init_user_ns, gid));
-			break;
-		default:
-			break;
-		}
-	}
-}
-
 static void posix_acl_fix_xattr_userns(
 	struct user_namespace *to, struct user_namespace *from,
 	void *value, size_t size)
@@ -819,7 +782,7 @@ static void posix_acl_fix_xattr_userns(
 	kgid_t gid;
 
 	count = posix_acl_fix_xattr_common(value, size);
-	if (count < 0)
+	if (count <= 0)
 		return;
 
 	for (end = entry + count; entry != end; entry++) {
@@ -854,12 +817,32 @@ void posix_acl_fix_xattr_to_user(void *value, size_t size)
 	posix_acl_fix_xattr_userns(user_ns, &init_user_ns, value, size);
 }
 
-/*
- * Convert from extended attribute to in-memory representation.
+/**
+ * make_posix_acl - convert POSIX ACLs from uapi to VFS format using the
+ *                  provided callbacks to map ACL_{GROUP,USER} entries into the
+ *                  appropriate format
+ * @mnt_userns: the mount's idmapping
+ * @fs_userns: the filesystem's idmapping
+ * @value: the uapi representation of POSIX ACLs
+ * @size: the size of @void
+ * @uid_cb: callback to use for mapping the uid stored in ACL_USER entries
+ * @gid_cb: callback to use for mapping the gid stored in ACL_GROUP entries
+ *
+ * The make_posix_acl() helper is an abstraction to translate from uapi format
+ * into the VFS format allowing the caller to specific callbacks to map
+ * ACL_{GROUP,USER} entries into the expected format. This is used in
+ * posix_acl_from_xattr() and vfs_set_acl_prepare() and avoids pointless code
+ * duplication.
+ *
+ * Return: Allocated struct posix_acl on success, NULL for a valid header but
+ *         without actual POSIX ACL entries, or ERR_PTR() encoded error code.
  */
-struct posix_acl *
-posix_acl_from_xattr(struct user_namespace *user_ns,
-		     const void *value, size_t size)
+static struct posix_acl *make_posix_acl(struct user_namespace *mnt_userns,
+	struct user_namespace *fs_userns, const void *value, size_t size,
+	kuid_t (*uid_cb)(struct user_namespace *, struct user_namespace *,
+			 const struct posix_acl_xattr_entry *),
+	kgid_t (*gid_cb)(struct user_namespace *, struct user_namespace *,
+			 const struct posix_acl_xattr_entry *))
 {
 	const struct posix_acl_xattr_header *header = value;
 	const struct posix_acl_xattr_entry *entry = (const void *)(header + 1), *end;
@@ -867,16 +850,9 @@ posix_acl_from_xattr(struct user_namespace *user_ns,
 	struct posix_acl *acl;
 	struct posix_acl_entry *acl_e;
 
-	if (!value)
-		return NULL;
-	if (size < sizeof(struct posix_acl_xattr_header))
-		 return ERR_PTR(-EINVAL);
-	if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION))
-		return ERR_PTR(-EOPNOTSUPP);
-
-	count = posix_acl_xattr_count(size);
+	count = posix_acl_fix_xattr_common(value, size);
 	if (count < 0)
-		return ERR_PTR(-EINVAL);
+		return ERR_PTR(count);
 	if (count == 0)
 		return NULL;
 	
@@ -897,16 +873,12 @@ posix_acl_from_xattr(struct user_namespace *user_ns,
 				break;
 
 			case ACL_USER:
-				acl_e->e_uid =
-					make_kuid(user_ns,
-						  le32_to_cpu(entry->e_id));
+				acl_e->e_uid = uid_cb(mnt_userns, fs_userns, entry);
 				if (!uid_valid(acl_e->e_uid))
 					goto fail;
 				break;
 			case ACL_GROUP:
-				acl_e->e_gid =
-					make_kgid(user_ns,
-						  le32_to_cpu(entry->e_id));
+				acl_e->e_gid = gid_cb(mnt_userns, fs_userns, entry);
 				if (!gid_valid(acl_e->e_gid))
 					goto fail;
 				break;
@@ -921,6 +893,181 @@ fail:
 	posix_acl_release(acl);
 	return ERR_PTR(-EINVAL);
 }
+
+/**
+ * vfs_set_acl_prepare_kuid - map ACL_USER uid according to mount- and
+ *                            filesystem idmapping
+ * @mnt_userns: the mount's idmapping
+ * @fs_userns: the filesystem's idmapping
+ * @e: a ACL_USER entry in POSIX ACL uapi format
+ *
+ * The uid stored as ACL_USER entry in @e is a kuid_t stored as a raw {g,u}id
+ * value. The vfs_set_acl_prepare_kuid() will recover the kuid_t through
+ * KUIDT_INIT() and then map it according to the idmapped mount. The resulting
+ * kuid_t is the value which the filesystem can map up into a raw backing store
+ * id in the filesystem's idmapping.
+ *
+ * This is used in vfs_set_acl_prepare() to generate the proper VFS
+ * representation of POSIX ACLs with ACL_USER entries during setxattr().
+ *
+ * Return: A kuid in @fs_userns for the uid stored in @e.
+ */
+static inline kuid_t
+vfs_set_acl_prepare_kuid(struct user_namespace *mnt_userns,
+			 struct user_namespace *fs_userns,
+			 const struct posix_acl_xattr_entry *e)
+{
+	kuid_t kuid = KUIDT_INIT(le32_to_cpu(e->e_id));
+	return from_vfsuid(mnt_userns, fs_userns, VFSUIDT_INIT(kuid));
+}
+
+/**
+ * vfs_set_acl_prepare_kgid - map ACL_GROUP gid according to mount- and
+ *                            filesystem idmapping
+ * @mnt_userns: the mount's idmapping
+ * @fs_userns: the filesystem's idmapping
+ * @e: a ACL_GROUP entry in POSIX ACL uapi format
+ *
+ * The gid stored as ACL_GROUP entry in @e is a kgid_t stored as a raw {g,u}id
+ * value. The vfs_set_acl_prepare_kgid() will recover the kgid_t through
+ * KGIDT_INIT() and then map it according to the idmapped mount. The resulting
+ * kgid_t is the value which the filesystem can map up into a raw backing store
+ * id in the filesystem's idmapping.
+ *
+ * This is used in vfs_set_acl_prepare() to generate the proper VFS
+ * representation of POSIX ACLs with ACL_GROUP entries during setxattr().
+ *
+ * Return: A kgid in @fs_userns for the gid stored in @e.
+ */
+static inline kgid_t
+vfs_set_acl_prepare_kgid(struct user_namespace *mnt_userns,
+			 struct user_namespace *fs_userns,
+			 const struct posix_acl_xattr_entry *e)
+{
+	kgid_t kgid = KGIDT_INIT(le32_to_cpu(e->e_id));
+	return from_vfsgid(mnt_userns, fs_userns, VFSGIDT_INIT(kgid));
+}
+
+/**
+ * vfs_set_acl_prepare - convert POSIX ACLs from uapi to VFS format taking
+ *                       mount and filesystem idmappings into account
+ * @mnt_userns: the mount's idmapping
+ * @fs_userns: the filesystem's idmapping
+ * @value: the uapi representation of POSIX ACLs
+ * @size: the size of @void
+ *
+ * When setting POSIX ACLs with ACL_{GROUP,USER} entries they need to be
+ * mapped according to the relevant mount- and filesystem idmapping. It is
+ * important that the ACL_{GROUP,USER} entries in struct posix_acl will be
+ * mapped into k{g,u}id_t that are supposed to be mapped up in the filesystem
+ * idmapping. This is crucial since the resulting struct posix_acl might be
+ * cached filesystem wide. The vfs_set_acl_prepare() function will take care to
+ * perform all necessary idmappings.
+ *
+ * Note, that since basically forever the {g,u}id values encoded as
+ * ACL_{GROUP,USER} entries in the uapi POSIX ACLs passed via @value contain
+ * values that have been mapped according to the caller's idmapping. In other
+ * words, POSIX ACLs passed in uapi format as @value during setxattr() contain
+ * {g,u}id values in their ACL_{GROUP,USER} entries that should actually have
+ * been stored as k{g,u}id_t.
+ *
+ * This means, vfs_set_acl_prepare() needs to first recover the k{g,u}id_t by
+ * calling K{G,U}IDT_INIT(). Afterwards they can be interpreted as vfs{g,u}id_t
+ * through from_vfs{g,u}id() to account for any idmapped mounts. The
+ * vfs_set_acl_prepare_k{g,u}id() helpers will take care to generate the
+ * correct k{g,u}id_t.
+ *
+ * The filesystem will then receive the POSIX ACLs ready to be cached
+ * filesystem wide and ready to be written to the backing store taking the
+ * filesystem's idmapping into account.
+ *
+ * Return: Allocated struct posix_acl on success, NULL for a valid header but
+ *         without actual POSIX ACL entries, or ERR_PTR() encoded error code.
+ */
+struct posix_acl *vfs_set_acl_prepare(struct user_namespace *mnt_userns,
+				      struct user_namespace *fs_userns,
+				      const void *value, size_t size)
+{
+	return make_posix_acl(mnt_userns, fs_userns, value, size,
+			      vfs_set_acl_prepare_kuid,
+			      vfs_set_acl_prepare_kgid);
+}
+EXPORT_SYMBOL(vfs_set_acl_prepare);
+
+/**
+ * posix_acl_from_xattr_kuid - map ACL_USER uid into filesystem idmapping
+ * @mnt_userns: unused
+ * @fs_userns: the filesystem's idmapping
+ * @e: a ACL_USER entry in POSIX ACL uapi format
+ *
+ * Map the uid stored as ACL_USER entry in @e into the filesystem's idmapping.
+ * This is used in posix_acl_from_xattr() to generate the proper VFS
+ * representation of POSIX ACLs with ACL_USER entries.
+ *
+ * Return: A kuid in @fs_userns for the uid stored in @e.
+ */
+static inline kuid_t
+posix_acl_from_xattr_kuid(struct user_namespace *mnt_userns,
+			  struct user_namespace *fs_userns,
+			  const struct posix_acl_xattr_entry *e)
+{
+	return make_kuid(fs_userns, le32_to_cpu(e->e_id));
+}
+
+/**
+ * posix_acl_from_xattr_kgid - map ACL_GROUP gid into filesystem idmapping
+ * @mnt_userns: unused
+ * @fs_userns: the filesystem's idmapping
+ * @e: a ACL_GROUP entry in POSIX ACL uapi format
+ *
+ * Map the gid stored as ACL_GROUP entry in @e into the filesystem's idmapping.
+ * This is used in posix_acl_from_xattr() to generate the proper VFS
+ * representation of POSIX ACLs with ACL_GROUP entries.
+ *
+ * Return: A kgid in @fs_userns for the gid stored in @e.
+ */
+static inline kgid_t
+posix_acl_from_xattr_kgid(struct user_namespace *mnt_userns,
+			  struct user_namespace *fs_userns,
+			  const struct posix_acl_xattr_entry *e)
+{
+	return make_kgid(fs_userns, le32_to_cpu(e->e_id));
+}
+
+/**
+ * posix_acl_from_xattr - convert POSIX ACLs from backing store to VFS format
+ * @fs_userns: the filesystem's idmapping
+ * @value: the uapi representation of POSIX ACLs
+ * @size: the size of @void
+ *
+ * Filesystems that store POSIX ACLs in the unaltered uapi format should use
+ * posix_acl_from_xattr() when reading them from the backing store and
+ * converting them into the struct posix_acl VFS format. The helper is
+ * specifically intended to be called from the ->get_acl() inode operation.
+ *
+ * The posix_acl_from_xattr() function will map the raw {g,u}id values stored
+ * in ACL_{GROUP,USER} entries into the filesystem idmapping in @fs_userns. The
+ * posix_acl_from_xattr_k{g,u}id() helpers will take care to generate the
+ * correct k{g,u}id_t. The returned struct posix_acl can be cached.
+ *
+ * Note that posix_acl_from_xattr() does not take idmapped mounts into account.
+ * If it did it calling is from the ->get_acl() inode operation would return
+ * POSIX ACLs mapped according to an idmapped mount which would mean that the
+ * value couldn't be cached for the filesystem. Idmapped mounts are taken into
+ * account on the fly during permission checking or right at the VFS -
+ * userspace boundary before reporting them to the user.
+ *
+ * Return: Allocated struct posix_acl on success, NULL for a valid header but
+ *         without actual POSIX ACL entries, or ERR_PTR() encoded error code.
+ */
+struct posix_acl *
+posix_acl_from_xattr(struct user_namespace *fs_userns,
+		     const void *value, size_t size)
+{
+	return make_posix_acl(&init_user_ns, fs_userns, value, size,
+			      posix_acl_from_xattr_kuid,
+			      posix_acl_from_xattr_kgid);
+}
 EXPORT_SYMBOL (posix_acl_from_xattr);
 
 /*
@@ -1024,7 +1171,17 @@ posix_acl_xattr_set(const struct xattr_handler *handler,
 	int ret;
 
 	if (value) {
-		acl = posix_acl_from_xattr(&init_user_ns, value, size);
+		/*
+		 * By the time we end up here the {g,u}ids stored in
+		 * ACL_{GROUP,USER} have already been mapped according to the
+		 * caller's idmapping. The vfs_set_acl_prepare() helper will
+		 * recover them and take idmapped mounts into account. The
+		 * filesystem will receive the POSIX ACLs in the correct
+		 * format ready to be cached or written to the backing store
+		 * taking the filesystem idmapping into account.
+		 */
+		acl = vfs_set_acl_prepare(mnt_userns, i_user_ns(inode),
+					  value, size);
 		if (IS_ERR(acl))
 			return PTR_ERR(acl);
 	}
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index a3398d0f1927..4e0023643f8b 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -527,10 +527,12 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 	struct vm_area_struct *vma = walk->vma;
 	bool locked = !!(vma->vm_flags & VM_LOCKED);
 	struct page *page = NULL;
-	bool migration = false;
+	bool migration = false, young = false, dirty = false;
 
 	if (pte_present(*pte)) {
 		page = vm_normal_page(vma, addr, *pte);
+		young = pte_young(*pte);
+		dirty = pte_dirty(*pte);
 	} else if (is_swap_pte(*pte)) {
 		swp_entry_t swpent = pte_to_swp_entry(*pte);
 
@@ -560,8 +562,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 	if (!page)
 		return;
 
-	smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte),
-		      locked, migration);
+	smaps_account(mss, page, false, young, dirty, locked, migration);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index b2fd3c20e7c2..0c034ea39954 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -28,14 +28,11 @@
 #include <linux/crypto.h>
 #include <linux/string.h>
 #include <linux/timer.h>
-#include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/jiffies.h>
 #include <linux/workqueue.h>
 
-#include <crypto/acompress.h>
-
 #include "internal.h"
 
 /*
@@ -93,8 +90,7 @@ module_param(compress, charp, 0444);
 MODULE_PARM_DESC(compress, "compression to use");
 
 /* Compression parameters */
-static struct crypto_acomp *tfm;
-static struct acomp_req *creq;
+static struct crypto_comp *tfm;
 
 struct pstore_zbackend {
 	int (*zbufsize)(size_t size);
@@ -272,21 +268,12 @@ static const struct pstore_zbackend zbackends[] = {
 static int pstore_compress(const void *in, void *out,
 			   unsigned int inlen, unsigned int outlen)
 {
-	struct scatterlist src, dst;
 	int ret;
 
 	if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS))
 		return -EINVAL;
 
-	sg_init_table(&src, 1);
-	sg_set_buf(&src, in, inlen);
-
-	sg_init_table(&dst, 1);
-	sg_set_buf(&dst, out, outlen);
-
-	acomp_request_set_params(creq, &src, &dst, inlen, outlen);
-
-	ret = crypto_acomp_compress(creq);
+	ret = crypto_comp_compress(tfm, in, inlen, out, &outlen);
 	if (ret) {
 		pr_err("crypto_comp_compress failed, ret = %d!\n", ret);
 		return ret;
@@ -297,7 +284,7 @@ static int pstore_compress(const void *in, void *out,
 
 static void allocate_buf_for_compression(void)
 {
-	struct crypto_acomp *acomp;
+	struct crypto_comp *ctx;
 	int size;
 	char *buf;
 
@@ -309,7 +296,7 @@ static void allocate_buf_for_compression(void)
 	if (!psinfo || tfm)
 		return;
 
-	if (!crypto_has_acomp(zbackend->name, 0, CRYPTO_ALG_ASYNC)) {
+	if (!crypto_has_comp(zbackend->name, 0, 0)) {
 		pr_err("Unknown compression: %s\n", zbackend->name);
 		return;
 	}
@@ -328,24 +315,16 @@ static void allocate_buf_for_compression(void)
 		return;
 	}
 
-	acomp = crypto_alloc_acomp(zbackend->name, 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR_OR_NULL(acomp)) {
+	ctx = crypto_alloc_comp(zbackend->name, 0, 0);
+	if (IS_ERR_OR_NULL(ctx)) {
 		kfree(buf);
 		pr_err("crypto_alloc_comp('%s') failed: %ld\n", zbackend->name,
-		       PTR_ERR(acomp));
-		return;
-	}
-
-	creq = acomp_request_alloc(acomp);
-	if (!creq) {
-		crypto_free_acomp(acomp);
-		kfree(buf);
-		pr_err("acomp_request_alloc('%s') failed\n", zbackend->name);
+		       PTR_ERR(ctx));
 		return;
 	}
 
 	/* A non-NULL big_oops_buf indicates compression is available. */
-	tfm = acomp;
+	tfm = ctx;
 	big_oops_buf_sz = size;
 	big_oops_buf = buf;
 
@@ -355,8 +334,7 @@ static void allocate_buf_for_compression(void)
 static void free_buf_for_compression(void)
 {
 	if (IS_ENABLED(CONFIG_PSTORE_COMPRESS) && tfm) {
-		acomp_request_free(creq);
-		crypto_free_acomp(tfm);
+		crypto_free_comp(tfm);
 		tfm = NULL;
 	}
 	kfree(big_oops_buf);
@@ -693,8 +671,6 @@ static void decompress_record(struct pstore_record *record)
 	int ret;
 	int unzipped_len;
 	char *unzipped, *workspace;
-	struct acomp_req *dreq;
-	struct scatterlist src, dst;
 
 	if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS) || !record->compressed)
 		return;
@@ -718,30 +694,16 @@ static void decompress_record(struct pstore_record *record)
 	if (!workspace)
 		return;
 
-	dreq = acomp_request_alloc(tfm);
-	if (!dreq) {
-		kfree(workspace);
-		return;
-	}
-
-	sg_init_table(&src, 1);
-	sg_set_buf(&src, record->buf, record->size);
-
-	sg_init_table(&dst, 1);
-	sg_set_buf(&dst, workspace, unzipped_len);
-
-	acomp_request_set_params(dreq, &src, &dst, record->size, unzipped_len);
-
 	/* After decompression "unzipped_len" is almost certainly smaller. */
-	ret = crypto_acomp_decompress(dreq);
+	ret = crypto_comp_decompress(tfm, record->buf, record->size,
+					  workspace, &unzipped_len);
 	if (ret) {
-		pr_err("crypto_acomp_decompress failed, ret = %d!\n", ret);
+		pr_err("crypto_comp_decompress failed, ret = %d!\n", ret);
 		kfree(workspace);
 		return;
 	}
 
 	/* Append ECC notice to decompressed buffer. */
-	unzipped_len = dreq->dlen;
 	memcpy(workspace + unzipped_len, record->buf + record->size,
 	       record->ecc_notice_size);
 
@@ -749,7 +711,6 @@ static void decompress_record(struct pstore_record *record)
 	unzipped = kmemdup(workspace, unzipped_len + record->ecc_notice_size,
 			   GFP_KERNEL);
 	kfree(workspace);
-	acomp_request_free(dreq);
 	if (!unzipped)
 		return;
 
diff --git a/fs/read_write.c b/fs/read_write.c
index 1a261dcf1778..328ce8cf9a85 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -496,14 +496,9 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t
 }
 
 /* caller is responsible for file_start_write/file_end_write */
-ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos)
+ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos)
 {
-	struct kvec iov = {
-		.iov_base	= (void *)buf,
-		.iov_len	= min_t(size_t, count, MAX_RW_COUNT),
-	};
 	struct kiocb kiocb;
-	struct iov_iter iter;
 	ssize_t ret;
 
 	if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE)))
@@ -519,8 +514,7 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t
 
 	init_sync_kiocb(&kiocb, file);
 	kiocb.ki_pos = pos ? *pos : 0;
-	iov_iter_kvec(&iter, WRITE, &iov, 1, iov.iov_len);
-	ret = file->f_op->write_iter(&kiocb, &iter);
+	ret = file->f_op->write_iter(&kiocb, from);
 	if (ret > 0) {
 		if (pos)
 			*pos = kiocb.ki_pos;
@@ -530,6 +524,18 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t
 	inc_syscw(current);
 	return ret;
 }
+
+/* caller is responsible for file_start_write/file_end_write */
+ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos)
+{
+	struct kvec iov = {
+		.iov_base	= (void *)buf,
+		.iov_len	= min_t(size_t, count, MAX_RW_COUNT),
+	};
+	struct iov_iter iter;
+	iov_iter_kvec(&iter, WRITE, &iov, 1, iov.iov_len);
+	return __kernel_write_iter(file, &iter, pos);
+}
 /*
  * This "EXPORT_SYMBOL_GPL()" is more of a "EXPORT_SYMBOL_DONTUSE()",
  * but autofs is one of the few internal kernel users that actually
diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index 98e64fec75b7..e56510964b22 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -593,7 +593,7 @@ static void squashfs_readahead(struct readahead_control *ractl)
 
 		res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor);
 
-		kfree(actor);
+		squashfs_page_actor_free(actor);
 
 		if (res == expected) {
 			int bytes;
diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c
index be4b12d31e0c..f1ccad519e28 100644
--- a/fs/squashfs/file_direct.c
+++ b/fs/squashfs/file_direct.c
@@ -74,7 +74,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize,
 	/* Decompress directly into the page cache buffers */
 	res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor);
 
-	kfree(actor);
+	squashfs_page_actor_free(actor);
 
 	if (res < 0)
 		goto mark_errored;
diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c
index b23b780d8f42..54b93bf4a25c 100644
--- a/fs/squashfs/page_actor.c
+++ b/fs/squashfs/page_actor.c
@@ -52,6 +52,7 @@ struct squashfs_page_actor *squashfs_page_actor_init(void **buffer,
 	actor->buffer = buffer;
 	actor->pages = pages;
 	actor->next_page = 0;
+	actor->tmp_buffer = NULL;
 	actor->squashfs_first_page = cache_first_page;
 	actor->squashfs_next_page = cache_next_page;
 	actor->squashfs_finish_page = cache_finish_page;
@@ -68,20 +69,9 @@ static void *handle_next_page(struct squashfs_page_actor *actor)
 
 	if ((actor->next_page == actor->pages) ||
 			(actor->next_index != actor->page[actor->next_page]->index)) {
-		if (actor->alloc_buffer) {
-			void *tmp_buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
-
-			if (tmp_buffer) {
-				actor->tmp_buffer = tmp_buffer;
-				actor->next_index++;
-				actor->returned_pages++;
-				return tmp_buffer;
-			}
-		}
-
 		actor->next_index++;
 		actor->returned_pages++;
-		return ERR_PTR(-ENOMEM);
+		return actor->alloc_buffer ? actor->tmp_buffer : ERR_PTR(-ENOMEM);
 	}
 
 	actor->next_index++;
@@ -96,11 +86,10 @@ static void *direct_first_page(struct squashfs_page_actor *actor)
 
 static void *direct_next_page(struct squashfs_page_actor *actor)
 {
-	if (actor->pageaddr)
+	if (actor->pageaddr) {
 		kunmap_local(actor->pageaddr);
-
-	kfree(actor->tmp_buffer);
-	actor->pageaddr = actor->tmp_buffer = NULL;
+		actor->pageaddr = NULL;
+	}
 
 	return handle_next_page(actor);
 }
@@ -109,8 +98,6 @@ static void direct_finish_page(struct squashfs_page_actor *actor)
 {
 	if (actor->pageaddr)
 		kunmap_local(actor->pageaddr);
-
-	kfree(actor->tmp_buffer);
 }
 
 struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_info *msblk,
@@ -121,6 +108,16 @@ struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_
 	if (actor == NULL)
 		return NULL;
 
+	if (msblk->decompressor->alloc_buffer) {
+		actor->tmp_buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
+
+		if (actor->tmp_buffer == NULL) {
+			kfree(actor);
+			return NULL;
+		}
+	} else
+		actor->tmp_buffer = NULL;
+
 	actor->length = length ? : pages * PAGE_SIZE;
 	actor->page = page;
 	actor->pages = pages;
@@ -128,7 +125,6 @@ struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_
 	actor->returned_pages = 0;
 	actor->next_index = page[0]->index & ~((1 << (msblk->block_log - PAGE_SHIFT)) - 1);
 	actor->pageaddr = NULL;
-	actor->tmp_buffer = NULL;
 	actor->alloc_buffer = msblk->decompressor->alloc_buffer;
 	actor->squashfs_first_page = direct_first_page;
 	actor->squashfs_next_page = direct_next_page;
diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h
index 24841d28bc0f..95ffbb543d91 100644
--- a/fs/squashfs/page_actor.h
+++ b/fs/squashfs/page_actor.h
@@ -29,6 +29,11 @@ extern struct squashfs_page_actor *squashfs_page_actor_init(void **buffer,
 extern struct squashfs_page_actor *squashfs_page_actor_init_special(
 				struct squashfs_sb_info *msblk,
 				struct page **page, int pages, int length);
+static inline void squashfs_page_actor_free(struct squashfs_page_actor *actor)
+{
+	kfree(actor->tmp_buffer);
+	kfree(actor);
+}
 static inline void *squashfs_first_page(struct squashfs_page_actor *actor)
 {
 	return actor->squashfs_first_page(actor);
diff --git a/fs/stat.c b/fs/stat.c
index 9ced8860e0f3..ef50573c72a2 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -5,6 +5,7 @@
  *  Copyright (C) 1991, 1992  Linus Torvalds
  */
 
+#include <linux/blkdev.h>
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/errno.h>
@@ -230,11 +231,22 @@ retry:
 		goto out;
 
 	error = vfs_getattr(&path, stat, request_mask, flags);
+
 	stat->mnt_id = real_mount(path.mnt)->mnt_id;
 	stat->result_mask |= STATX_MNT_ID;
+
 	if (path.mnt->mnt_root == path.dentry)
 		stat->attributes |= STATX_ATTR_MOUNT_ROOT;
 	stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT;
+
+	/* Handle STATX_DIOALIGN for block devices. */
+	if (request_mask & STATX_DIOALIGN) {
+		struct inode *inode = d_backing_inode(path.dentry);
+
+		if (S_ISBLK(inode->i_mode))
+			bdev_statx_dioalign(inode, stat);
+	}
+
 	path_put(&path);
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
@@ -611,6 +623,8 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer)
 	tmp.stx_dev_major = MAJOR(stat->dev);
 	tmp.stx_dev_minor = MINOR(stat->dev);
 	tmp.stx_mnt_id = stat->mnt_id;
+	tmp.stx_dio_mem_align = stat->dio_mem_align;
+	tmp.stx_dio_offset_align = stat->dio_offset_align;
 
 	return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
 }
diff --git a/fs/super.c b/fs/super.c
index 734ed584a946..6a82660e1adb 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -291,7 +291,6 @@ static void __put_super(struct super_block *s)
 		WARN_ON(s->s_inode_lru.node);
 		WARN_ON(!list_empty(&s->s_mounts));
 		security_sb_free(s);
-		fscrypt_sb_free(s);
 		put_user_ns(s->s_user_ns);
 		kfree(s->s_subtype);
 		call_rcu(&s->rcu, destroy_super_rcu);
@@ -480,6 +479,7 @@ void generic_shutdown_super(struct super_block *sb)
 		evict_inodes(sb);
 		/* only nonzero refcount inodes can have marks */
 		fsnotify_sb_delete(sb);
+		fscrypt_sb_delete(sb);
 		security_sb_delete(sb);
 
 		if (sb->s_dio_done_wq) {
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 81d26abf486f..da85b3979195 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -141,6 +141,8 @@ struct tracefs_mount_opts {
 	kuid_t uid;
 	kgid_t gid;
 	umode_t mode;
+	/* Opt_* bitfield. */
+	unsigned int opts;
 };
 
 enum {
@@ -241,6 +243,7 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
 	kgid_t gid;
 	char *p;
 
+	opts->opts = 0;
 	opts->mode = TRACEFS_DEFAULT_MODE;
 
 	while ((p = strsep(&data, ",")) != NULL) {
@@ -275,24 +278,36 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
 		 * but traditionally tracefs has ignored all mount options
 		 */
 		}
+
+		opts->opts |= BIT(token);
 	}
 
 	return 0;
 }
 
-static int tracefs_apply_options(struct super_block *sb)
+static int tracefs_apply_options(struct super_block *sb, bool remount)
 {
 	struct tracefs_fs_info *fsi = sb->s_fs_info;
 	struct inode *inode = d_inode(sb->s_root);
 	struct tracefs_mount_opts *opts = &fsi->mount_opts;
 
-	inode->i_mode &= ~S_IALLUGO;
-	inode->i_mode |= opts->mode;
+	/*
+	 * On remount, only reset mode/uid/gid if they were provided as mount
+	 * options.
+	 */
+
+	if (!remount || opts->opts & BIT(Opt_mode)) {
+		inode->i_mode &= ~S_IALLUGO;
+		inode->i_mode |= opts->mode;
+	}
 
-	inode->i_uid = opts->uid;
+	if (!remount || opts->opts & BIT(Opt_uid))
+		inode->i_uid = opts->uid;
 
-	/* Set all the group ids to the mount option */
-	set_gid(sb->s_root, opts->gid);
+	if (!remount || opts->opts & BIT(Opt_gid)) {
+		/* Set all the group ids to the mount option */
+		set_gid(sb->s_root, opts->gid);
+	}
 
 	return 0;
 }
@@ -307,7 +322,7 @@ static int tracefs_remount(struct super_block *sb, int *flags, char *data)
 	if (err)
 		goto fail;
 
-	tracefs_apply_options(sb);
+	tracefs_apply_options(sb, true);
 
 fail:
 	return err;
@@ -359,7 +374,7 @@ static int trace_fill_super(struct super_block *sb, void *data, int silent)
 
 	sb->s_op = &tracefs_super_operations;
 
-	tracefs_apply_options(sb);
+	tracefs_apply_options(sb, false);
 
 	return 0;
 
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 1c44bf75f916..0c1d33c4f74c 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -991,7 +991,7 @@ static int resolve_userfault_fork(struct userfaultfd_ctx *new,
 	int fd;
 
 	fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, new,
-			O_RDWR | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode);
+			O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode);
 	if (fd < 0)
 		return fd;
 
@@ -1601,6 +1601,10 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 			wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range);
 		}
 
+		/* Reset ptes for the whole vma range if wr-protected */
+		if (userfaultfd_wp(vma))
+			uffd_wp_range(mm, vma, start, vma_end - start, false);
+
 		new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
 		prev = vma_merge(mm, prev, start, vma_end, new_flags,
 				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
@@ -2090,7 +2094,7 @@ SYSCALL_DEFINE1(userfaultfd, int, flags)
 	mmgrab(ctx->mm);
 
 	fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, ctx,
-			O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL);
+			O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL);
 	if (fd < 0) {
 		mmdrop(ctx->mm);
 		kmem_cache_free(userfaultfd_ctx_cachep, ctx);
diff --git a/fs/verity/read_metadata.c b/fs/verity/read_metadata.c
index 6ee849dc7bc1..2aefc5565152 100644
--- a/fs/verity/read_metadata.c
+++ b/fs/verity/read_metadata.c
@@ -53,14 +53,14 @@ static int fsverity_read_merkle_tree(struct inode *inode,
 			break;
 		}
 
-		virt = kmap(page);
+		virt = kmap_local_page(page);
 		if (copy_to_user(buf, virt + offs_in_page, bytes_to_copy)) {
-			kunmap(page);
+			kunmap_local(virt);
 			put_page(page);
 			err = -EFAULT;
 			break;
 		}
-		kunmap(page);
+		kunmap_local(virt);
 		put_page(page);
 
 		retval += bytes_to_copy;
diff --git a/fs/verity/verify.c b/fs/verity/verify.c
index 14e2fb49cff5..bde8c9b7d25f 100644
--- a/fs/verity/verify.c
+++ b/fs/verity/verify.c
@@ -39,16 +39,6 @@ static void hash_at_level(const struct merkle_tree_params *params,
 		   (params->log_blocksize - params->log_arity);
 }
 
-/* Extract a hash from a hash page */
-static void extract_hash(struct page *hpage, unsigned int hoffset,
-			 unsigned int hsize, u8 *out)
-{
-	void *virt = kmap_atomic(hpage);
-
-	memcpy(out, virt + hoffset, hsize);
-	kunmap_atomic(virt);
-}
-
 static inline int cmp_hashes(const struct fsverity_info *vi,
 			     const u8 *want_hash, const u8 *real_hash,
 			     pgoff_t index, int level)
@@ -129,7 +119,7 @@ static bool verify_page(struct inode *inode, const struct fsverity_info *vi,
 		}
 
 		if (PageChecked(hpage)) {
-			extract_hash(hpage, hoffset, hsize, _want_hash);
+			memcpy_from_page(_want_hash, hpage, hoffset, hsize);
 			want_hash = _want_hash;
 			put_page(hpage);
 			pr_debug_ratelimited("Hash page already checked, want %s:%*phN\n",
@@ -158,7 +148,7 @@ descend:
 		if (err)
 			goto out;
 		SetPageChecked(hpage);
-		extract_hash(hpage, hoffset, hsize, _want_hash);
+		memcpy_from_page(_want_hash, hpage, hoffset, hsize);
 		want_hash = _want_hash;
 		put_page(hpage);
 		pr_debug("Verified hash page at level %d, now want %s:%*phN\n",
diff --git a/fs/xattr.c b/fs/xattr.c
index a1f4998bc6be..61107b6bbed2 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -290,7 +290,7 @@ static inline bool is_posix_acl_xattr(const char *name)
 
 int
 vfs_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
-	     const char *name, void *value, size_t size, int flags)
+	     const char *name, const void *value, size_t size, int flags)
 {
 	struct inode *inode = dentry->d_inode;
 	struct inode *delegated_inode = NULL;
@@ -298,16 +298,12 @@ vfs_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 	int error;
 
 	if (size && strcmp(name, XATTR_NAME_CAPS) == 0) {
-		error = cap_convert_nscap(mnt_userns, dentry,
-					  (const void **)&value, size);
+		error = cap_convert_nscap(mnt_userns, dentry, &value, size);
 		if (error < 0)
 			return error;
 		size = error;
 	}
 
-	if (size && is_posix_acl_xattr(name))
-		posix_acl_setxattr_idmapped_mnt(mnt_userns, inode, value, size);
-
 retry_deleg:
 	inode_lock(inode);
 	error = __vfs_setxattr_locked(mnt_userns, dentry, name, value, size,
@@ -587,9 +583,7 @@ int setxattr_copy(const char __user *name, struct xattr_ctx *ctx)
 static void setxattr_convert(struct user_namespace *mnt_userns,
 			     struct dentry *d, struct xattr_ctx *ctx)
 {
-	if (ctx->size &&
-		((strcmp(ctx->kname->name, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
-		(strcmp(ctx->kname->name, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)))
+	if (ctx->size && is_posix_acl_xattr(ctx->kname->name))
 		posix_acl_fix_xattr_from_user(ctx->kvalue, ctx->size);
 }
 
@@ -705,8 +699,7 @@ do_getxattr(struct user_namespace *mnt_userns, struct dentry *d,
 
 	error = vfs_getxattr(mnt_userns, d, kname, ctx->kvalue, ctx->size);
 	if (error > 0) {
-		if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
-		    (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
+		if (is_posix_acl_xattr(kname))
 			posix_acl_fix_xattr_to_user(ctx->kvalue, error);
 		if (ctx->size && copy_to_user(ctx->value, ctx->kvalue, error))
 			error = -EFAULT;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 45518b8c613c..f51c60d7e205 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -604,6 +604,16 @@ xfs_vn_getattr(
 		stat->blksize = BLKDEV_IOSIZE;
 		stat->rdev = inode->i_rdev;
 		break;
+	case S_IFREG:
+		if (request_mask & STATX_DIOALIGN) {
+			struct xfs_buftarg	*target = xfs_inode_buftarg(ip);
+			struct block_device	*bdev = target->bt_bdev;
+
+			stat->result_mask |= STATX_DIOALIGN;
+			stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
+			stat->dio_offset_align = bdev_logical_block_size(bdev);
+		}
+		fallthrough;
 	default:
 		stat->blksize = xfs_stat_blksize(ip);
 		stat->rdev = 0;
diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
index 69d9c83ea4b2..5b1f9a24ed59 100644
--- a/fs/xfs/xfs_notify_failure.c
+++ b/fs/xfs/xfs_notify_failure.c
@@ -175,13 +175,13 @@ xfs_dax_notify_failure(
 	u64			ddev_start;
 	u64			ddev_end;
 
-	if (!(mp->m_sb.sb_flags & SB_BORN)) {
+	if (!(mp->m_super->s_flags & SB_BORN)) {
 		xfs_warn(mp, "filesystem is not ready for notify_failure()!");
 		return -EIO;
 	}
 
 	if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) {
-		xfs_warn(mp,
+		xfs_debug(mp,
 			 "notify_failure() not supported on realtime device!");
 		return -EOPNOTSUPP;
 	}
@@ -194,7 +194,7 @@ xfs_dax_notify_failure(
 	}
 
 	if (!xfs_has_rmapbt(mp)) {
-		xfs_warn(mp, "notify_failure() needs rmapbt enabled!");
+		xfs_debug(mp, "notify_failure() needs rmapbt enabled!");
 		return -EOPNOTSUPP;
 	}
 
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index e7d27373ff71..c09d72986968 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -365,7 +365,6 @@ struct acpi_device {
 	int device_type;
 	acpi_handle handle;		/* no handle for fixed hardware */
 	struct fwnode_handle fwnode;
-	struct acpi_device *parent;
 	struct list_head wakeup_list;
 	struct list_head del_list;
 	struct acpi_device_status status;
@@ -458,6 +457,14 @@ static inline void *acpi_driver_data(struct acpi_device *d)
 #define to_acpi_device(d)	container_of(d, struct acpi_device, dev)
 #define to_acpi_driver(d)	container_of(d, struct acpi_driver, drv)
 
+static inline struct acpi_device *acpi_dev_parent(struct acpi_device *adev)
+{
+	if (adev->dev.parent)
+		return to_acpi_device(adev->dev.parent);
+
+	return NULL;
+}
+
 static inline void acpi_set_device_status(struct acpi_device *adev, u32 sta)
 {
 	*((u32 *)&adev->status) = sta;
@@ -512,7 +519,6 @@ extern int unregister_acpi_notifier(struct notifier_block *);
  * External Functions
  */
 
-struct acpi_device *acpi_fetch_acpi_dev(acpi_handle handle);
 acpi_status acpi_bus_get_status_handle(acpi_handle handle,
 				       unsigned long long *sta);
 int acpi_bus_get_status(struct acpi_device *device);
@@ -613,8 +619,7 @@ enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev);
 int acpi_iommu_fwspec_init(struct device *dev, u32 id,
 			   struct fwnode_handle *fwnode,
 			   const struct iommu_ops *ops);
-int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset,
-		       u64 *size);
+int acpi_dma_get_range(struct device *dev, const struct bus_dma_region **map);
 int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
 			   const u32 *input_id);
 static inline int acpi_dma_configure(struct device *dev,
@@ -733,10 +738,24 @@ static inline bool acpi_device_can_poweroff(struct acpi_device *adev)
 }
 
 bool acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2);
+int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer);
 
 void acpi_dev_clear_dependencies(struct acpi_device *supplier);
 bool acpi_dev_ready_for_enumeration(const struct acpi_device *device);
-struct acpi_device *acpi_dev_get_first_consumer_dev(struct acpi_device *supplier);
+struct acpi_device *acpi_dev_get_next_consumer_dev(struct acpi_device *supplier,
+						   struct acpi_device *start);
+
+/**
+ * for_each_acpi_consumer_dev - iterate over the consumer ACPI devices for a
+ *				given supplier
+ * @supplier: Pointer to the supplier's ACPI device
+ * @consumer: Pointer to &struct acpi_device to hold the consumer, initially NULL
+ */
+#define for_each_acpi_consumer_dev(supplier, consumer)			\
+	for (consumer = acpi_dev_get_next_consumer_dev(supplier, NULL);	\
+	     consumer;							\
+	     consumer = acpi_dev_get_next_consumer_dev(supplier, consumer))
+
 struct acpi_device *
 acpi_dev_get_next_match_dev(struct acpi_device *adev, const char *hid, const char *uid, s64 hrv);
 struct acpi_device *
@@ -767,9 +786,10 @@ static inline void acpi_dev_put(struct acpi_device *adev)
 		put_device(&adev->dev);
 }
 
-struct acpi_device *acpi_bus_get_acpi_device(acpi_handle handle);
+struct acpi_device *acpi_fetch_acpi_dev(acpi_handle handle);
+struct acpi_device *acpi_get_acpi_dev(acpi_handle handle);
 
-static inline void acpi_bus_put_acpi_device(struct acpi_device *adev)
+static inline void acpi_put_acpi_dev(struct acpi_device *adev)
 {
 	acpi_dev_put(adev);
 }
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index f73d357ecdf5..c5614444031f 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -140,6 +140,7 @@ extern int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs);
 extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls);
 extern int cppc_set_enable(int cpu, bool enable);
 extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps);
+extern bool cppc_perf_ctrs_in_pcc(void);
 extern bool acpi_cpc_valid(void);
 extern bool cppc_allow_fast_switch(void);
 extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data);
@@ -173,6 +174,10 @@ static inline int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps)
 {
 	return -ENOTSUPP;
 }
+static inline bool cppc_perf_ctrs_in_pcc(void)
+{
+	return false;
+}
 static inline bool acpi_cpc_valid(void)
 {
 	return false;
diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
index 3096f086b5a3..71ab4ba9c25d 100644
--- a/include/asm-generic/bitops/atomic.h
+++ b/include/asm-generic/bitops/atomic.h
@@ -39,9 +39,6 @@ arch_test_and_set_bit(unsigned int nr, volatile unsigned long *p)
 	unsigned long mask = BIT_MASK(nr);
 
 	p += BIT_WORD(nr);
-	if (READ_ONCE(*p) & mask)
-		return 1;
-
 	old = arch_atomic_long_fetch_or(mask, (atomic_long_t *)p);
 	return !!(old & mask);
 }
@@ -53,9 +50,6 @@ arch_test_and_clear_bit(unsigned int nr, volatile unsigned long *p)
 	unsigned long mask = BIT_MASK(nr);
 
 	p += BIT_WORD(nr);
-	if (!(READ_ONCE(*p) & mask))
-		return 0;
-
 	old = arch_atomic_long_fetch_andnot(mask, (atomic_long_t *)p);
 	return !!(old & mask);
 }
diff --git a/include/asm-generic/bitops/generic-non-atomic.h b/include/asm-generic/bitops/generic-non-atomic.h
index 3d5ebd24652b..564a8c675d85 100644
--- a/include/asm-generic/bitops/generic-non-atomic.h
+++ b/include/asm-generic/bitops/generic-non-atomic.h
@@ -4,6 +4,7 @@
 #define __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H
 
 #include <linux/bits.h>
+#include <asm/barrier.h>
 
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly
@@ -127,6 +128,18 @@ generic_test_bit(unsigned long nr, const volatile unsigned long *addr)
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * generic_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+generic_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * const_*() definitions provide good compile-time optimizations when
  * the passed arguments can be resolved at compile time.
@@ -137,6 +150,7 @@ generic_test_bit(unsigned long nr, const volatile unsigned long *addr)
 #define const___test_and_set_bit	generic___test_and_set_bit
 #define const___test_and_clear_bit	generic___test_and_clear_bit
 #define const___test_and_change_bit	generic___test_and_change_bit
+#define const_test_bit_acquire		generic_test_bit_acquire
 
 /**
  * const_test_bit - Determine whether a bit is set
diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h
index 988a3bbfba34..2b238b161a62 100644
--- a/include/asm-generic/bitops/instrumented-non-atomic.h
+++ b/include/asm-generic/bitops/instrumented-non-atomic.h
@@ -142,4 +142,16 @@ _test_bit(unsigned long nr, const volatile unsigned long *addr)
 	return arch_test_bit(nr, addr);
 }
 
+/**
+ * _test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_bit_acquire(nr, addr);
+}
+
 #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
diff --git a/include/asm-generic/bitops/non-atomic.h b/include/asm-generic/bitops/non-atomic.h
index 5c37ced343ae..71f8d54a5195 100644
--- a/include/asm-generic/bitops/non-atomic.h
+++ b/include/asm-generic/bitops/non-atomic.h
@@ -13,6 +13,7 @@
 #define arch___test_and_change_bit generic___test_and_change_bit
 
 #define arch_test_bit generic_test_bit
+#define arch_test_bit_acquire generic_test_bit_acquire
 
 #include <asm-generic/bitops/non-instrumented-non-atomic.h>
 
diff --git a/include/asm-generic/bitops/non-instrumented-non-atomic.h b/include/asm-generic/bitops/non-instrumented-non-atomic.h
index bdb9b1ffaee9..0ddc78dfc358 100644
--- a/include/asm-generic/bitops/non-instrumented-non-atomic.h
+++ b/include/asm-generic/bitops/non-instrumented-non-atomic.h
@@ -12,5 +12,6 @@
 #define ___test_and_change_bit	arch___test_and_change_bit
 
 #define _test_bit		arch_test_bit
+#define _test_bit_acquire	arch_test_bit_acquire
 
 #endif /* __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H */
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index ba1f860af38b..4050b191e1a9 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -220,22 +220,6 @@ extern __printf(1, 2) void __warn_printk(const char *fmt, ...);
 # define WARN_ON_SMP(x)			({0;})
 #endif
 
-/*
- * WARN_ON_FUNCTION_MISMATCH() warns if a value doesn't match a
- * function address, and can be useful for catching issues with
- * callback functions, for example.
- *
- * With CONFIG_CFI_CLANG, the warning is disabled because the
- * compiler replaces function addresses taken in C code with
- * local jump table addresses, which breaks cross-module function
- * address equality.
- */
-#if defined(CONFIG_CFI_CLANG) && defined(CONFIG_MODULES)
-# define WARN_ON_FUNCTION_MISMATCH(x, fn) ({ 0; })
-#else
-# define WARN_ON_FUNCTION_MISMATCH(x, fn) WARN_ON_ONCE((x) != (fn))
-#endif
-
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index d0f7bdd2fdf2..db13bb620f52 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -97,7 +97,7 @@ static inline bool memory_contains(void *begin, void *end, void *virt,
 /**
  * memory_intersects - checks if the region occupied by an object intersects
  *                     with another memory region
- * @begin: virtual address of the beginning of the memory regien
+ * @begin: virtual address of the beginning of the memory region
  * @end: virtual address of the end of the memory region
  * @virt: virtual address of the memory object
  * @size: size of the memory object
@@ -110,7 +110,10 @@ static inline bool memory_intersects(void *begin, void *end, void *virt,
 {
 	void *vend = virt + size;
 
-	return (virt >= begin && virt < end) || (vend >= begin && vend < end);
+	if (virt < end && vend > begin)
+		return true;
+
+	return false;
 }
 
 /**
diff --git a/include/asm-generic/softirq_stack.h b/include/asm-generic/softirq_stack.h
index d3e2d81656e0..2a67aed9ac52 100644
--- a/include/asm-generic/softirq_stack.h
+++ b/include/asm-generic/softirq_stack.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_GENERIC_SOFTIRQ_STACK_H
 #define __ASM_GENERIC_SOFTIRQ_STACK_H
 
-#if defined(CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK) && !defined(CONFIG_PREEMPT_RT)
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
 void do_softirq_own_stack(void);
 #else
 static inline void do_softirq_own_stack(void)
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 7515a465ec03..7501edfce11e 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -422,6 +422,22 @@
 #endif
 
 /*
+ * .kcfi_traps contains a list KCFI trap locations.
+ */
+#ifndef KCFI_TRAPS
+#ifdef CONFIG_ARCH_USES_CFI_TRAPS
+#define KCFI_TRAPS							\
+	__kcfi_traps : AT(ADDR(__kcfi_traps) - LOAD_OFFSET) {		\
+		__start___kcfi_traps = .;				\
+		KEEP(*(.kcfi_traps))					\
+		__stop___kcfi_traps = .;				\
+	}
+#else
+#define KCFI_TRAPS
+#endif
+#endif
+
+/*
  * Read only Data
  */
 #define RO_DATA(align)							\
@@ -529,6 +545,8 @@
 		__stop___modver = .;					\
 	}								\
 									\
+	KCFI_TRAPS							\
+									\
 	RO_EXCEPTION_TABLE						\
 	NOTES								\
 	BTF								\
@@ -538,21 +556,6 @@
 
 
 /*
- * .text..L.cfi.jumptable.* contain Control-Flow Integrity (CFI)
- * jump table entries.
- */
-#ifdef CONFIG_CFI_CLANG
-#define TEXT_CFI_JT							\
-		. = ALIGN(PMD_SIZE);					\
-		__cfi_jt_start = .;					\
-		*(.text..L.cfi.jumptable .text..L.cfi.jumptable.*)	\
-		. = ALIGN(PMD_SIZE);					\
-		__cfi_jt_end = .;
-#else
-#define TEXT_CFI_JT
-#endif
-
-/*
  * Non-instrumentable text section
  */
 #define NOINSTR_TEXT							\
@@ -579,7 +582,6 @@
 		*(.text..refcount)					\
 		*(.ref.text)						\
 		*(.text.asan.* .text.tsan.*)				\
-		TEXT_CFI_JT						\
 	MEM_KEEP(init.text*)						\
 	MEM_KEEP(exit.text*)						\
 
@@ -1008,8 +1010,7 @@
  * keep any .init_array.* sections.
  * https://bugs.llvm.org/show_bug.cgi?id=46478
  */
-#if defined(CONFIG_GCOV_KERNEL) || defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN) || \
-	defined(CONFIG_CFI_CLANG)
+#if defined(CONFIG_GCOV_KERNEL) || defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN)
 # ifdef CONFIG_CONSTRUCTORS
 #  define SANITIZER_DISCARDS						\
 	*(.eh_frame)
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index a1705d6b3fba..7df7876b2ad5 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -319,8 +319,8 @@ enum drm_panel_orientation {
  *             EDID's detailed monitor range
  */
 struct drm_monitor_range_info {
-	u8 min_vfreq;
-	u8 max_vfreq;
+	u16 min_vfreq;
+	u16 max_vfreq;
 };
 
 /**
diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h
index 2181977ae683..1ed61e2b30a4 100644
--- a/include/drm/drm_edid.h
+++ b/include/drm/drm_edid.h
@@ -92,6 +92,11 @@ struct detailed_data_string {
 	u8 str[13];
 } __attribute__((packed));
 
+#define DRM_EDID_RANGE_OFFSET_MIN_VFREQ (1 << 0) /* 1.4 */
+#define DRM_EDID_RANGE_OFFSET_MAX_VFREQ (1 << 1) /* 1.4 */
+#define DRM_EDID_RANGE_OFFSET_MIN_HFREQ (1 << 2) /* 1.4 */
+#define DRM_EDID_RANGE_OFFSET_MAX_HFREQ (1 << 3) /* 1.4 */
+
 #define DRM_EDID_DEFAULT_GTF_SUPPORT_FLAG   0x00
 #define DRM_EDID_RANGE_LIMITS_ONLY_FLAG     0x01
 #define DRM_EDID_SECONDARY_GTF_SUPPORT_FLAG 0x02
diff --git a/include/kunit/test.h b/include/kunit/test.h
index c958855681cc..840a2c375065 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -826,7 +826,7 @@ do {									       \
 
 #define KUNIT_EXPECT_LE_MSG(test, left, right, fmt, ...)		       \
 	KUNIT_BINARY_INT_ASSERTION(test,				       \
-				   KUNIT_ASSERTION,			       \
+				   KUNIT_EXPECTATION,			       \
 				   left, <=, right,			       \
 				   fmt,					       \
 				    ##__VA_ARGS__)
@@ -1116,7 +1116,7 @@ do {									       \
 
 #define KUNIT_ASSERT_LT_MSG(test, left, right, fmt, ...)		       \
 	KUNIT_BINARY_INT_ASSERTION(test,				       \
-				   KUNIT_EXPECTATION,			       \
+				   KUNIT_ASSERTION,			       \
 				   left, <, right,			       \
 				   fmt,					       \
 				    ##__VA_ARGS__)
@@ -1157,7 +1157,7 @@ do {									       \
 
 #define KUNIT_ASSERT_GT_MSG(test, left, right, fmt, ...)		       \
 	KUNIT_BINARY_INT_ASSERTION(test,				       \
-				   KUNIT_EXPECTATION,			       \
+				   KUNIT_ASSERTION,			       \
 				   left, >, right,			       \
 				   fmt,					       \
 				    ##__VA_ARGS__)
diff --git a/include/linux/a.out.h b/include/linux/a.out.h
deleted file mode 100644
index 600cf45645c6..000000000000
--- a/include/linux/a.out.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __A_OUT_GNU_H__
-#define __A_OUT_GNU_H__
-
-#include <uapi/linux/a.out.h>
-
-#ifndef __ASSEMBLY__
-#ifdef linux
-#include <asm/page.h>
-#if defined(__i386__) || defined(__mc68000__)
-#else
-#ifndef SEGMENT_SIZE
-#define SEGMENT_SIZE	PAGE_SIZE
-#endif
-#endif
-#endif
-#endif /*__ASSEMBLY__ */
-#endif /* __A_OUT_GNU_H__ */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 6f64b2f3dc54..2f9193b8dfc1 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -279,14 +279,17 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) { }
 
 void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa);
 
+#if defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH)
+void acpi_arch_dma_setup(struct device *dev);
+#else
+static inline void acpi_arch_dma_setup(struct device *dev) { }
+#endif
+
 #ifdef CONFIG_ARM64
 void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa);
-void acpi_arch_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size);
 #else
 static inline void
 acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { }
-static inline void
-acpi_arch_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size) { }
 #endif
 
 int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma);
@@ -506,6 +509,7 @@ int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list,
 			   void *preproc_data);
 int acpi_dev_get_dma_resources(struct acpi_device *adev,
 			       struct list_head *list);
+int acpi_dev_get_memory_resources(struct acpi_device *adev, struct list_head *list);
 int acpi_dev_filter_resource_type(struct acpi_resource *ares,
 				  unsigned long types);
 
@@ -798,6 +802,11 @@ acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *u
 	return false;
 }
 
+static inline int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer)
+{
+	return -ENODEV;
+}
+
 static inline struct acpi_device *
 acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv)
 {
@@ -977,8 +986,7 @@ static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev)
 	return DEV_DMA_NOT_SUPPORTED;
 }
 
-static inline int acpi_dma_get_range(struct device *dev, u64 *dma_addr,
-				     u64 *offset, u64 *size)
+static inline int acpi_dma_get_range(struct device *dev, const struct bus_dma_region **map)
 {
 	return -ENODEV;
 }
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index e94cdf235f1d..5001e14c5c06 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -67,6 +67,7 @@ struct amba_device {
 	struct clk		*pclk;
 	struct device_dma_parameters dma_parms;
 	unsigned int		periphid;
+	struct mutex		periphid_lock;
 	unsigned int		cid;
 	struct amba_cs_uci_id	uci;
 	unsigned int		irq[AMBA_NR_IRQS];
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 3dc20c4f394c..8d51f69f9f5e 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -43,9 +43,6 @@ struct linux_binprm {
 		 * original userspace.
 		 */
 		point_of_no_return:1;
-#ifdef __alpha__
-	unsigned int taso:1;
-#endif
 	struct file *executable; /* Executable to pass to the interpreter */
 	struct file *interpreter;
 	struct file *file;
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index cf9bf65039f2..3b89c64bcfd8 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -59,6 +59,7 @@ extern unsigned long __sw_hweight64(__u64 w);
 #define __test_and_clear_bit(nr, addr)	bitop(___test_and_clear_bit, nr, addr)
 #define __test_and_change_bit(nr, addr)	bitop(___test_and_change_bit, nr, addr)
 #define test_bit(nr, addr)		bitop(_test_bit, nr, addr)
+#define test_bit_acquire(nr, addr)	bitop(_test_bit_acquire, nr, addr)
 
 /*
  * Include this here because some architectures need generic_ffs/fls in
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index effee1dc715a..92294a5fb083 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -857,7 +857,6 @@ void blk_mq_kick_requeue_list(struct request_queue *q);
 void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
 void blk_mq_complete_request(struct request *rq);
 bool blk_mq_complete_request_remote(struct request *rq);
-bool blk_mq_queue_stopped(struct request_queue *q);
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
 void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
 void blk_mq_stop_hw_queues(struct request_queue *q);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 84b13fdd34a7..8038c5fbde40 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1498,6 +1498,7 @@ int sync_blockdev(struct block_device *bdev);
 int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend);
 int sync_blockdev_nowait(struct block_device *bdev);
 void sync_bdevs(bool wait);
+void bdev_statx_dioalign(struct inode *inode, struct kstat *stat);
 void printk_all_partitions(void);
 #else
 static inline void invalidate_bdev(struct block_device *bdev)
@@ -1514,6 +1515,9 @@ static inline int sync_blockdev_nowait(struct block_device *bdev)
 static inline void sync_bdevs(bool wait)
 {
 }
+static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
+{
+}
 static inline void printk_all_partitions(void)
 {
 }
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index def8b8d30ccc..df518c429667 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -138,6 +138,17 @@ BUFFER_FNS(Defer_Completion, defer_completion)
 static __always_inline void set_buffer_uptodate(struct buffer_head *bh)
 {
 	/*
+	 * If somebody else already set this uptodate, they will
+	 * have done the memory barrier, and a reader will thus
+	 * see *some* valid buffer state.
+	 *
+	 * Any other serialization (with IO errors or whatever that
+	 * might clear the bit) has to come from other state (eg BH_Lock).
+	 */
+	if (test_bit(BH_Uptodate, &bh->b_state))
+		return;
+
+	/*
 	 * make it consistent with folio_mark_uptodate
 	 * pairs with smp_load_acquire in buffer_uptodate
 	 */
@@ -156,7 +167,7 @@ static __always_inline int buffer_uptodate(const struct buffer_head *bh)
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
diff --git a/include/linux/cfi.h b/include/linux/cfi.h
index c6dfc1ed0626..5e134f4ce8b7 100644
--- a/include/linux/cfi.h
+++ b/include/linux/cfi.h
@@ -2,49 +2,38 @@
 /*
  * Clang Control Flow Integrity (CFI) support.
  *
- * Copyright (C) 2021 Google LLC
+ * Copyright (C) 2022 Google LLC
  */
 #ifndef _LINUX_CFI_H
 #define _LINUX_CFI_H
 
-#ifdef CONFIG_CFI_CLANG
-typedef void (*cfi_check_fn)(uint64_t id, void *ptr, void *diag);
-
-/* Compiler-generated function in each module, and the kernel */
-extern void __cfi_check(uint64_t id, void *ptr, void *diag);
-
-/*
- * Force the compiler to generate a CFI jump table entry for a function
- * and store the jump table address to __cfi_jt_<function>.
- */
-#define __CFI_ADDRESSABLE(fn, __attr) \
-	const void *__cfi_jt_ ## fn __visible __attr = (void *)&fn
-
-#ifdef CONFIG_CFI_CLANG_SHADOW
-
-extern void cfi_module_add(struct module *mod, unsigned long base_addr);
-extern void cfi_module_remove(struct module *mod, unsigned long base_addr);
-
-#else
+#include <linux/bug.h>
+#include <linux/module.h>
 
-static inline void cfi_module_add(struct module *mod, unsigned long base_addr) {}
-static inline void cfi_module_remove(struct module *mod, unsigned long base_addr) {}
-
-#endif /* CONFIG_CFI_CLANG_SHADOW */
-
-#else /* !CONFIG_CFI_CLANG */
-
-#ifdef CONFIG_X86_KERNEL_IBT
-
-#define __CFI_ADDRESSABLE(fn, __attr) \
-	const void *__cfi_jt_ ## fn __visible __attr = (void *)&fn
+#ifdef CONFIG_CFI_CLANG
+enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr,
+				      unsigned long *target, u32 type);
 
-#endif /* CONFIG_X86_KERNEL_IBT */
+static inline enum bug_trap_type report_cfi_failure_noaddr(struct pt_regs *regs,
+							   unsigned long addr)
+{
+	return report_cfi_failure(regs, addr, NULL, 0);
+}
 
+#ifdef CONFIG_ARCH_USES_CFI_TRAPS
+bool is_cfi_trap(unsigned long addr);
+#endif
 #endif /* CONFIG_CFI_CLANG */
 
-#ifndef __CFI_ADDRESSABLE
-#define __CFI_ADDRESSABLE(fn, __attr)
-#endif
+#ifdef CONFIG_MODULES
+#ifdef CONFIG_ARCH_USES_CFI_TRAPS
+void module_cfi_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
+			 struct module *mod);
+#else
+static inline void module_cfi_finalize(const Elf_Ehdr *hdr,
+				       const Elf_Shdr *sechdrs,
+				       struct module *mod) {}
+#endif /* CONFIG_ARCH_USES_CFI_TRAPS */
+#endif /* CONFIG_MODULES */
 
 #endif /* _LINUX_CFI_H */
diff --git a/include/linux/cfi_types.h b/include/linux/cfi_types.h
new file mode 100644
index 000000000000..6b8713675765
--- /dev/null
+++ b/include/linux/cfi_types.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Clang Control Flow Integrity (CFI) type definitions.
+ */
+#ifndef _LINUX_CFI_TYPES_H
+#define _LINUX_CFI_TYPES_H
+
+#ifdef __ASSEMBLY__
+#include <linux/linkage.h>
+
+#ifdef CONFIG_CFI_CLANG
+/*
+ * Use the __kcfi_typeid_<function> type identifier symbol to
+ * annotate indirectly called assembly functions. The compiler emits
+ * these symbols for all address-taken function declarations in C
+ * code.
+ */
+#ifndef __CFI_TYPE
+#define __CFI_TYPE(name)				\
+	.4byte __kcfi_typeid_##name
+#endif
+
+#define SYM_TYPED_ENTRY(name, linkage, align...)	\
+	linkage(name) ASM_NL				\
+	align ASM_NL					\
+	__CFI_TYPE(name) ASM_NL				\
+	name:
+
+#define SYM_TYPED_START(name, linkage, align...)	\
+	SYM_TYPED_ENTRY(name, linkage, align)
+
+#else /* CONFIG_CFI_CLANG */
+
+#define SYM_TYPED_START(name, linkage, align...)	\
+	SYM_START(name, linkage, align)
+
+#endif /* CONFIG_CFI_CLANG */
+
+#ifndef SYM_TYPED_FUNC_START
+#define SYM_TYPED_FUNC_START(name) 			\
+	SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* _LINUX_CFI_TYPES_H */
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index ed53bfe7c46c..ac5d0515680e 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -734,11 +734,6 @@ static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
 	return NULL;
 }
 
-static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
-{
-	return NULL;
-}
-
 static inline bool cgroup_psi_enabled(void)
 {
 	return false;
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index c84fec767445..42e55579d649 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -66,17 +66,9 @@
 # define __noscs	__attribute__((__no_sanitize__("shadow-call-stack")))
 #endif
 
-#define __nocfi		__attribute__((__no_sanitize__("cfi")))
-#define __cficanonical	__attribute__((__cfi_canonical_jump_table__))
-
-#if defined(CONFIG_CFI_CLANG)
-/*
- * With CONFIG_CFI_CLANG, the compiler replaces function address
- * references with the address of the function's CFI jump table
- * entry. The function_nocfi macro always returns the address of the
- * actual function instead.
- */
-#define function_nocfi(x)	__builtin_function_start(x)
+#if __has_feature(kcfi)
+/* Disable CFI checking inside a function. */
+#define __nocfi		__attribute__((__no_sanitize__("kcfi")))
 #endif
 
 /*
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 01ce94b58b42..973a1bfd7ef5 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -203,16 +203,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 	__v;								\
 })
 
-/*
- * With CONFIG_CFI_CLANG, the compiler replaces function addresses in
- * instrumented C code with jump table addresses. Architectures that
- * support CFI can define this macro to return the actual function address
- * when needed.
- */
-#ifndef function_nocfi
-#define function_nocfi(x) (x)
-#endif
-
 #endif /* __KERNEL__ */
 
 /*
@@ -221,9 +211,11 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
  * otherwise, or eliminated entirely due to lack of references that are
  * visible to the compiler.
  */
-#define __ADDRESSABLE(sym) \
-	static void * __section(".discard.addressable") __used \
+#define ___ADDRESSABLE(sym, __attrs) \
+	static void * __used __attrs \
 		__UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)&sym;
+#define __ADDRESSABLE(sym) \
+	___ADDRESSABLE(sym, __section(".discard.addressable"))
 
 /**
  * offset_to_ptr - convert a relative memory offset to an absolute pointer
@@ -240,6 +232,12 @@ static inline void *offset_to_ptr(const int *off)
 #define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
 
 /*
+ * Whether 'type' is a signed type or an unsigned type. Supports scalar types,
+ * bool and also pointer types.
+ */
+#define is_signed_type(type) (((type)(-1)) < (__force type)1)
+
+/*
  * This is needed in functions which generate the stack canary, see
  * arch/x86/kernel/smpboot.c::start_secondary() for an example.
  */
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 4f2a819fd60a..d9d98e8a9a3b 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -4,8 +4,12 @@
 
 #ifndef __ASSEMBLY__
 
+/*
+ * Skipped when running bindgen due to a libclang issue;
+ * see https://github.com/rust-lang/rust-bindgen/issues/2244.
+ */
 #if defined(CONFIG_DEBUG_INFO_BTF) && defined(CONFIG_PAHOLE_HAS_BTF_TAG) && \
-	__has_attribute(btf_type_tag)
+	__has_attribute(btf_type_tag) && !defined(__BINDGEN__)
 # define BTF_TYPE_TAG(value) __attribute__((btf_type_tag(#value)))
 #else
 # define BTF_TYPE_TAG(value) /* nothing */
@@ -265,10 +269,6 @@ struct ftrace_likely_data {
 # define __nocfi
 #endif
 
-#ifndef __cficanonical
-# define __cficanonical
-#endif
-
 /*
  * Any place that could be marked with the "alloc_size" attribute is also
  * a place to be marked with the "malloc" attribute. Do this as part of the
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 0d435d0edbcb..e8ad12b5b9d2 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -202,12 +202,13 @@ static inline unsigned int cpumask_local_spread(unsigned int i, int node)
 	return 0;
 }
 
-static inline int cpumask_any_and_distribute(const struct cpumask *src1p,
-					     const struct cpumask *src2p) {
+static inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
+						      const struct cpumask *src2p)
+{
 	return cpumask_first_and(src1p, src2p);
 }
 
-static inline int cpumask_any_distribute(const struct cpumask *srcp)
+static inline unsigned int cpumask_any_distribute(const struct cpumask *srcp)
 {
 	return cpumask_first(srcp);
 }
@@ -261,7 +262,26 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
 		(cpu) = cpumask_next_zero((cpu), (mask)),	\
 		(cpu) < nr_cpu_ids;)
 
+#if NR_CPUS == 1
+static inline
+unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
+{
+	cpumask_check(start);
+	if (n != -1)
+		cpumask_check(n);
+
+	/*
+	 * Return the first available CPU when wrapping, or when starting before cpu0,
+	 * since there is only one valid option.
+	 */
+	if (wrap && n >= 0)
+		return nr_cpumask_bits;
+
+	return cpumask_first(mask);
+}
+#else
 unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap);
+#endif
 
 /**
  * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location
@@ -1107,9 +1127,10 @@ cpumap_print_list_to_buf(char *buf, const struct cpumask *mask,
  * cover a worst-case of every other cpu being on one of two nodes for a
  * very large NR_CPUS.
  *
- *  Use PAGE_SIZE as a minimum for smaller configurations.
+ *  Use PAGE_SIZE as a minimum for smaller configurations while avoiding
+ *  unsigned comparison to -1.
  */
-#define CPUMAP_FILE_MAX_BYTES  ((((NR_CPUS * 9)/32 - 1) > PAGE_SIZE) \
+#define CPUMAP_FILE_MAX_BYTES  (((NR_CPUS * 9)/32 > PAGE_SIZE) \
 					? (NR_CPUS * 9)/32 - 1 : PAGE_SIZE)
 #define CPULIST_FILE_MAX_BYTES  (((NR_CPUS * 7)/2 > PAGE_SIZE) ? (NR_CPUS * 7)/2 : PAGE_SIZE)
 
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index c869f1e73d75..f60674692d36 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -91,6 +91,8 @@ struct dentry *debugfs_create_automount(const char *name,
 void debugfs_remove(struct dentry *dentry);
 #define debugfs_remove_recursive debugfs_remove
 
+void debugfs_lookup_and_remove(const char *name, struct dentry *parent);
+
 const struct file_operations *debugfs_real_fops(const struct file *filp);
 
 int debugfs_file_get(struct dentry *dentry);
@@ -225,6 +227,10 @@ static inline void debugfs_remove(struct dentry *dentry)
 static inline void debugfs_remove_recursive(struct dentry *dentry)
 { }
 
+static inline void debugfs_lookup_and_remove(const char *name,
+					     struct dentry *parent)
+{ }
+
 const struct file_operations *debugfs_real_fops(const struct file *filp);
 
 static inline int debugfs_file_get(struct dentry *dentry)
diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h
index 7acaabde5396..2114d65b862f 100644
--- a/include/linux/device/driver.h
+++ b/include/linux/device/driver.h
@@ -242,6 +242,7 @@ driver_find_device_by_acpi_dev(struct device_driver *drv, const void *adev)
 
 extern int driver_deferred_probe_timeout;
 void driver_deferred_probe_add(struct device *dev);
+int driver_deferred_probe_check_state(struct device *dev);
 void driver_init(void);
 
 /**
diff --git a/include/linux/dlm.h b/include/linux/dlm.h
index ff951e9f6f20..c6bc2b5ee7e6 100644
--- a/include/linux/dlm.h
+++ b/include/linux/dlm.h
@@ -56,9 +56,6 @@ struct dlm_lockspace_ops {
  * DLM_LSFL_TIMEWARN
  *   The dlm should emit netlink messages if locks have been waiting
  *   for a configurable amount of time.  (Unused.)
- * DLM_LSFL_FS
- *   The lockspace user is in the kernel (i.e. filesystem).  Enables
- *   direct bast/cast callbacks.
  * DLM_LSFL_NEWEXCL
  *   dlm_new_lockspace() should return -EEXIST if the lockspace exists.
  *
@@ -134,7 +131,7 @@ int dlm_lock(dlm_lockspace_t *lockspace,
 	     int mode,
 	     struct dlm_lksb *lksb,
 	     uint32_t flags,
-	     void *name,
+	     const void *name,
 	     unsigned int namelen,
 	     uint32_t parent_lkid,
 	     void (*lockast) (void *astarg),
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 25a30906289d..0ee20b764000 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -139,7 +139,6 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
 bool dma_can_mmap(struct device *dev);
-int dma_supported(struct device *dev, u64 mask);
 bool dma_pci_p2pdma_supported(struct device *dev);
 int dma_set_mask(struct device *dev, u64 mask);
 int dma_set_coherent_mask(struct device *dev, u64 mask);
@@ -248,10 +247,6 @@ static inline bool dma_can_mmap(struct device *dev)
 {
 	return false;
 }
-static inline int dma_supported(struct device *dev, u64 mask)
-{
-	return 0;
-}
 static inline bool dma_pci_p2pdma_supported(struct device *dev)
 {
 	return false;
diff --git a/include/linux/edac.h b/include/linux/edac.h
index e730b3468719..fa4bda2a70f6 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -231,21 +231,21 @@ enum mem_type {
 #define MEM_FLAG_DDR		BIT(MEM_DDR)
 #define MEM_FLAG_RDDR		BIT(MEM_RDDR)
 #define MEM_FLAG_RMBS		BIT(MEM_RMBS)
-#define MEM_FLAG_DDR2           BIT(MEM_DDR2)
-#define MEM_FLAG_FB_DDR2        BIT(MEM_FB_DDR2)
-#define MEM_FLAG_RDDR2          BIT(MEM_RDDR2)
-#define MEM_FLAG_XDR            BIT(MEM_XDR)
-#define MEM_FLAG_DDR3           BIT(MEM_DDR3)
-#define MEM_FLAG_RDDR3          BIT(MEM_RDDR3)
-#define MEM_FLAG_LPDDR3         BIT(MEM_LPDDR3)
-#define MEM_FLAG_DDR4           BIT(MEM_DDR4)
-#define MEM_FLAG_RDDR4          BIT(MEM_RDDR4)
-#define MEM_FLAG_LRDDR4         BIT(MEM_LRDDR4)
-#define MEM_FLAG_LPDDR4         BIT(MEM_LPDDR4)
-#define MEM_FLAG_DDR5           BIT(MEM_DDR5)
-#define MEM_FLAG_RDDR5          BIT(MEM_RDDR5)
-#define MEM_FLAG_LRDDR5         BIT(MEM_LRDDR5)
-#define MEM_FLAG_NVDIMM         BIT(MEM_NVDIMM)
+#define MEM_FLAG_DDR2		BIT(MEM_DDR2)
+#define MEM_FLAG_FB_DDR2	BIT(MEM_FB_DDR2)
+#define MEM_FLAG_RDDR2		BIT(MEM_RDDR2)
+#define MEM_FLAG_XDR		BIT(MEM_XDR)
+#define MEM_FLAG_DDR3		BIT(MEM_DDR3)
+#define MEM_FLAG_RDDR3		BIT(MEM_RDDR3)
+#define MEM_FLAG_LPDDR3		BIT(MEM_LPDDR3)
+#define MEM_FLAG_DDR4		BIT(MEM_DDR4)
+#define MEM_FLAG_RDDR4		BIT(MEM_RDDR4)
+#define MEM_FLAG_LRDDR4		BIT(MEM_LRDDR4)
+#define MEM_FLAG_LPDDR4		BIT(MEM_LPDDR4)
+#define MEM_FLAG_DDR5		BIT(MEM_DDR5)
+#define MEM_FLAG_RDDR5		BIT(MEM_RDDR5)
+#define MEM_FLAG_LRDDR5		BIT(MEM_LRDDR5)
+#define MEM_FLAG_NVDIMM		BIT(MEM_NVDIMM)
 #define MEM_FLAG_WIO2		BIT(MEM_WIO2)
 #define MEM_FLAG_HBM2		BIT(MEM_HBM2)
 
diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index 3b401fa0f374..b62c90cfafaf 100644
--- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h
@@ -2,7 +2,9 @@
 #ifndef _LINUX_FORTIFY_STRING_H_
 #define _LINUX_FORTIFY_STRING_H_
 
+#include <linux/bug.h>
 #include <linux/const.h>
+#include <linux/limits.h>
 
 #define __FORTIFY_INLINE extern __always_inline __gnu_inline __overloadable
 #define __RENAME(x) __asm__(#x)
@@ -17,9 +19,10 @@ void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning("
 #define __compiletime_strlen(p)					\
 ({								\
 	unsigned char *__p = (unsigned char *)(p);		\
-	size_t __ret = (size_t)-1;				\
-	size_t __p_size = __builtin_object_size(p, 1);		\
-	if (__p_size != (size_t)-1) {				\
+	size_t __ret = SIZE_MAX;				\
+	size_t __p_size = __member_size(p);			\
+	if (__p_size != SIZE_MAX &&				\
+	    __builtin_constant_p(*__p)) {			\
 		size_t __p_len = __p_size - 1;			\
 		if (__builtin_constant_p(__p[__p_len]) &&	\
 		    __p[__p_len] == '\0')			\
@@ -69,20 +72,59 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size)
 	__underlying_memcpy(dst, src, bytes)
 
 /*
- * Clang's use of __builtin_object_size() within inlines needs hinting via
- * __pass_object_size(). The preference is to only ever use type 1 (member
+ * Clang's use of __builtin_*object_size() within inlines needs hinting via
+ * __pass_*object_size(). The preference is to only ever use type 1 (member
  * size, rather than struct size), but there remain some stragglers using
  * type 0 that will be converted in the future.
  */
-#define POS	__pass_object_size(1)
-#define POS0	__pass_object_size(0)
+#define POS			__pass_object_size(1)
+#define POS0			__pass_object_size(0)
+#define __struct_size(p)	__builtin_object_size(p, 0)
+#define __member_size(p)	__builtin_object_size(p, 1)
 
+#define __compiletime_lessthan(bounds, length)	(	\
+	__builtin_constant_p((bounds) < (length)) &&	\
+	(bounds) < (length)				\
+)
+
+/**
+ * strncpy - Copy a string to memory with non-guaranteed NUL padding
+ *
+ * @p: pointer to destination of copy
+ * @q: pointer to NUL-terminated source string to copy
+ * @size: bytes to write at @p
+ *
+ * If strlen(@q) >= @size, the copy of @q will stop after @size bytes,
+ * and @p will NOT be NUL-terminated
+ *
+ * If strlen(@q) < @size, following the copy of @q, trailing NUL bytes
+ * will be written to @p until @size total bytes have been written.
+ *
+ * Do not use this function. While FORTIFY_SOURCE tries to avoid
+ * over-reads of @q, it cannot defend against writing unterminated
+ * results to @p. Using strncpy() remains ambiguous and fragile.
+ * Instead, please choose an alternative, so that the expectation
+ * of @p's contents is unambiguous:
+ *
+ * +--------------------+-----------------+------------+
+ * | @p needs to be:    | padded to @size | not padded |
+ * +====================+=================+============+
+ * |     NUL-terminated | strscpy_pad()   | strscpy()  |
+ * +--------------------+-----------------+------------+
+ * | not NUL-terminated | strtomem_pad()  | strtomem() |
+ * +--------------------+-----------------+------------+
+ *
+ * Note strscpy*()'s differing return values for detecting truncation,
+ * and strtomem*()'s expectation that the destination is marked with
+ * __nonstring when it is a character array.
+ *
+ */
 __FORTIFY_INLINE __diagnose_as(__builtin_strncpy, 1, 2, 3)
 char *strncpy(char * const POS p, const char *q, __kernel_size_t size)
 {
-	size_t p_size = __builtin_object_size(p, 1);
+	size_t p_size = __member_size(p);
 
-	if (__builtin_constant_p(size) && p_size < size)
+	if (__compiletime_lessthan(p_size, size))
 		__write_overflow();
 	if (p_size < size)
 		fortify_panic(__func__);
@@ -92,9 +134,9 @@ char *strncpy(char * const POS p, const char *q, __kernel_size_t size)
 __FORTIFY_INLINE __diagnose_as(__builtin_strcat, 1, 2)
 char *strcat(char * const POS p, const char *q)
 {
-	size_t p_size = __builtin_object_size(p, 1);
+	size_t p_size = __member_size(p);
 
-	if (p_size == (size_t)-1)
+	if (p_size == SIZE_MAX)
 		return __underlying_strcat(p, q);
 	if (strlcat(p, q, p_size) >= p_size)
 		fortify_panic(__func__);
@@ -104,12 +146,12 @@ char *strcat(char * const POS p, const char *q)
 extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen);
 __FORTIFY_INLINE __kernel_size_t strnlen(const char * const POS p, __kernel_size_t maxlen)
 {
-	size_t p_size = __builtin_object_size(p, 1);
+	size_t p_size = __member_size(p);
 	size_t p_len = __compiletime_strlen(p);
 	size_t ret;
 
 	/* We can take compile-time actions when maxlen is const. */
-	if (__builtin_constant_p(maxlen) && p_len != (size_t)-1) {
+	if (__builtin_constant_p(maxlen) && p_len != SIZE_MAX) {
 		/* If p is const, we can use its compile-time-known len. */
 		if (maxlen >= p_size)
 			return p_len;
@@ -134,10 +176,10 @@ __FORTIFY_INLINE __diagnose_as(__builtin_strlen, 1)
 __kernel_size_t __fortify_strlen(const char * const POS p)
 {
 	__kernel_size_t ret;
-	size_t p_size = __builtin_object_size(p, 1);
+	size_t p_size = __member_size(p);
 
 	/* Give up if we don't know how large p is. */
-	if (p_size == (size_t)-1)
+	if (p_size == SIZE_MAX)
 		return __underlying_strlen(p);
 	ret = strnlen(p, p_size);
 	if (p_size <= ret)
@@ -149,12 +191,12 @@ __kernel_size_t __fortify_strlen(const char * const POS p)
 extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy);
 __FORTIFY_INLINE size_t strlcpy(char * const POS p, const char * const POS q, size_t size)
 {
-	size_t p_size = __builtin_object_size(p, 1);
-	size_t q_size = __builtin_object_size(q, 1);
+	size_t p_size = __member_size(p);
+	size_t q_size = __member_size(q);
 	size_t q_len;	/* Full count of source string length. */
 	size_t len;	/* Count of characters going into destination. */
 
-	if (p_size == (size_t)-1 && q_size == (size_t)-1)
+	if (p_size == SIZE_MAX && q_size == SIZE_MAX)
 		return __real_strlcpy(p, q, size);
 	q_len = strlen(q);
 	len = (q_len >= size) ? size - 1 : q_len;
@@ -178,18 +220,18 @@ __FORTIFY_INLINE ssize_t strscpy(char * const POS p, const char * const POS q, s
 {
 	size_t len;
 	/* Use string size rather than possible enclosing struct size. */
-	size_t p_size = __builtin_object_size(p, 1);
-	size_t q_size = __builtin_object_size(q, 1);
+	size_t p_size = __member_size(p);
+	size_t q_size = __member_size(q);
 
 	/* If we cannot get size of p and q default to call strscpy. */
-	if (p_size == (size_t) -1 && q_size == (size_t) -1)
+	if (p_size == SIZE_MAX && q_size == SIZE_MAX)
 		return __real_strscpy(p, q, size);
 
 	/*
 	 * If size can be known at compile time and is greater than
 	 * p_size, generate a compile time write overflow error.
 	 */
-	if (__builtin_constant_p(size) && size > p_size)
+	if (__compiletime_lessthan(p_size, size))
 		__write_overflow();
 
 	/*
@@ -224,10 +266,10 @@ __FORTIFY_INLINE __diagnose_as(__builtin_strncat, 1, 2, 3)
 char *strncat(char * const POS p, const char * const POS q, __kernel_size_t count)
 {
 	size_t p_len, copy_len;
-	size_t p_size = __builtin_object_size(p, 1);
-	size_t q_size = __builtin_object_size(q, 1);
+	size_t p_size = __member_size(p);
+	size_t q_size = __member_size(q);
 
-	if (p_size == (size_t)-1 && q_size == (size_t)-1)
+	if (p_size == SIZE_MAX && q_size == SIZE_MAX)
 		return __underlying_strncat(p, q, count);
 	p_len = strlen(p);
 	copy_len = strnlen(q, count);
@@ -246,15 +288,16 @@ __FORTIFY_INLINE void fortify_memset_chk(__kernel_size_t size,
 		/*
 		 * Length argument is a constant expression, so we
 		 * can perform compile-time bounds checking where
-		 * buffer sizes are known.
+		 * buffer sizes are also known at compile time.
 		 */
 
 		/* Error when size is larger than enclosing struct. */
-		if (p_size > p_size_field && p_size < size)
+		if (__compiletime_lessthan(p_size_field, p_size) &&
+		    __compiletime_lessthan(p_size, size))
 			__write_overflow();
 
 		/* Warn when write size is larger than dest field. */
-		if (p_size_field < size)
+		if (__compiletime_lessthan(p_size_field, size))
 			__write_overflow_field(p_size_field, size);
 	}
 	/*
@@ -268,10 +311,10 @@ __FORTIFY_INLINE void fortify_memset_chk(__kernel_size_t size,
 	/*
 	 * Always stop accesses beyond the struct that contains the
 	 * field, when the buffer's remaining size is known.
-	 * (The -1 test is to optimize away checks where the buffer
+	 * (The SIZE_MAX test is to optimize away checks where the buffer
 	 * lengths are unknown.)
 	 */
-	if (p_size != (size_t)(-1) && p_size < size)
+	if (p_size != SIZE_MAX && p_size < size)
 		fortify_panic("memset");
 }
 
@@ -282,11 +325,11 @@ __FORTIFY_INLINE void fortify_memset_chk(__kernel_size_t size,
 })
 
 /*
- * __builtin_object_size() must be captured here to avoid evaluating argument
- * side-effects further into the macro layers.
+ * __struct_size() vs __member_size() must be captured here to avoid
+ * evaluating argument side-effects further into the macro layers.
  */
 #define memset(p, c, s) __fortify_memset_chk(p, c, s,			\
-		__builtin_object_size(p, 0), __builtin_object_size(p, 1))
+		__struct_size(p), __member_size(p))
 
 /*
  * To make sure the compiler can enforce protection against buffer overflows,
@@ -319,7 +362,7 @@ __FORTIFY_INLINE void fortify_memset_chk(__kernel_size_t size,
  * V = vulnerable to run-time overflow (will need refactoring to solve)
  *
  */
-__FORTIFY_INLINE void fortify_memcpy_chk(__kernel_size_t size,
+__FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
 					 const size_t p_size,
 					 const size_t q_size,
 					 const size_t p_size_field,
@@ -330,25 +373,28 @@ __FORTIFY_INLINE void fortify_memcpy_chk(__kernel_size_t size,
 		/*
 		 * Length argument is a constant expression, so we
 		 * can perform compile-time bounds checking where
-		 * buffer sizes are known.
+		 * buffer sizes are also known at compile time.
 		 */
 
 		/* Error when size is larger than enclosing struct. */
-		if (p_size > p_size_field && p_size < size)
+		if (__compiletime_lessthan(p_size_field, p_size) &&
+		    __compiletime_lessthan(p_size, size))
 			__write_overflow();
-		if (q_size > q_size_field && q_size < size)
+		if (__compiletime_lessthan(q_size_field, q_size) &&
+		    __compiletime_lessthan(q_size, size))
 			__read_overflow2();
 
 		/* Warn when write size argument larger than dest field. */
-		if (p_size_field < size)
+		if (__compiletime_lessthan(p_size_field, size))
 			__write_overflow_field(p_size_field, size);
 		/*
 		 * Warn for source field over-read when building with W=1
 		 * or when an over-write happened, so both can be fixed at
 		 * the same time.
 		 */
-		if ((IS_ENABLED(KBUILD_EXTRA_WARN1) || p_size_field < size) &&
-		    q_size_field < size)
+		if ((IS_ENABLED(KBUILD_EXTRA_WARN1) ||
+		     __compiletime_lessthan(p_size_field, size)) &&
+		    __compiletime_lessthan(q_size_field, size))
 			__read_overflow2_field(q_size_field, size);
 	}
 	/*
@@ -362,41 +408,104 @@ __FORTIFY_INLINE void fortify_memcpy_chk(__kernel_size_t size,
 	/*
 	 * Always stop accesses beyond the struct that contains the
 	 * field, when the buffer's remaining size is known.
-	 * (The -1 test is to optimize away checks where the buffer
+	 * (The SIZE_MAX test is to optimize away checks where the buffer
 	 * lengths are unknown.)
 	 */
-	if ((p_size != (size_t)(-1) && p_size < size) ||
-	    (q_size != (size_t)(-1) && q_size < size))
+	if ((p_size != SIZE_MAX && p_size < size) ||
+	    (q_size != SIZE_MAX && q_size < size))
 		fortify_panic(func);
+
+	/*
+	 * Warn when writing beyond destination field size.
+	 *
+	 * We must ignore p_size_field == 0 for existing 0-element
+	 * fake flexible arrays, until they are all converted to
+	 * proper flexible arrays.
+	 *
+	 * The implementation of __builtin_*object_size() behaves
+	 * like sizeof() when not directly referencing a flexible
+	 * array member, which means there will be many bounds checks
+	 * that will appear at run-time, without a way for them to be
+	 * detected at compile-time (as can be done when the destination
+	 * is specifically the flexible array member).
+	 * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101832
+	 */
+	if (p_size_field != 0 && p_size_field != SIZE_MAX &&
+	    p_size != p_size_field && p_size_field < size)
+		return true;
+
+	return false;
 }
 
 #define __fortify_memcpy_chk(p, q, size, p_size, q_size,		\
 			     p_size_field, q_size_field, op) ({		\
 	size_t __fortify_size = (size_t)(size);				\
-	fortify_memcpy_chk(__fortify_size, p_size, q_size,		\
-			   p_size_field, q_size_field, #op);		\
+	WARN_ONCE(fortify_memcpy_chk(__fortify_size, p_size, q_size,	\
+				     p_size_field, q_size_field, #op),	\
+		  #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \
+		  __fortify_size,					\
+		  "field \"" #p "\" at " __FILE__ ":" __stringify(__LINE__), \
+		  p_size_field);					\
 	__underlying_##op(p, q, __fortify_size);			\
 })
 
 /*
- * __builtin_object_size() must be captured here to avoid evaluating argument
- * side-effects further into the macro layers.
+ * Notes about compile-time buffer size detection:
+ *
+ * With these types...
+ *
+ *	struct middle {
+ *		u16 a;
+ *		u8 middle_buf[16];
+ *		int b;
+ *	};
+ *	struct end {
+ *		u16 a;
+ *		u8 end_buf[16];
+ *	};
+ *	struct flex {
+ *		int a;
+ *		u8 flex_buf[];
+ *	};
+ *
+ *	void func(TYPE *ptr) { ... }
+ *
+ * Cases where destination size cannot be currently detected:
+ * - the size of ptr's object (seemingly by design, gcc & clang fail):
+ *	__builtin_object_size(ptr, 1) == SIZE_MAX
+ * - the size of flexible arrays in ptr's obj (by design, dynamic size):
+ *	__builtin_object_size(ptr->flex_buf, 1) == SIZE_MAX
+ * - the size of ANY array at the end of ptr's obj (gcc and clang bug):
+ *	__builtin_object_size(ptr->end_buf, 1) == SIZE_MAX
+ *	https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101836
+ *
+ * Cases where destination size is currently detected:
+ * - the size of non-array members within ptr's object:
+ *	__builtin_object_size(ptr->a, 1) == 2
+ * - the size of non-flexible-array in the middle of ptr's obj:
+ *	__builtin_object_size(ptr->middle_buf, 1) == 16
+ *
+ */
+
+/*
+ * __struct_size() vs __member_size() must be captured here to avoid
+ * evaluating argument side-effects further into the macro layers.
  */
 #define memcpy(p, q, s)  __fortify_memcpy_chk(p, q, s,			\
-		__builtin_object_size(p, 0), __builtin_object_size(q, 0), \
-		__builtin_object_size(p, 1), __builtin_object_size(q, 1), \
+		__struct_size(p), __struct_size(q),			\
+		__member_size(p), __member_size(q),			\
 		memcpy)
 #define memmove(p, q, s)  __fortify_memcpy_chk(p, q, s,			\
-		__builtin_object_size(p, 0), __builtin_object_size(q, 0), \
-		__builtin_object_size(p, 1), __builtin_object_size(q, 1), \
+		__struct_size(p), __struct_size(q),			\
+		__member_size(p), __member_size(q),			\
 		memmove)
 
 extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan);
 __FORTIFY_INLINE void *memscan(void * const POS0 p, int c, __kernel_size_t size)
 {
-	size_t p_size = __builtin_object_size(p, 0);
+	size_t p_size = __struct_size(p);
 
-	if (__builtin_constant_p(size) && p_size < size)
+	if (__compiletime_lessthan(p_size, size))
 		__read_overflow();
 	if (p_size < size)
 		fortify_panic(__func__);
@@ -406,13 +515,13 @@ __FORTIFY_INLINE void *memscan(void * const POS0 p, int c, __kernel_size_t size)
 __FORTIFY_INLINE __diagnose_as(__builtin_memcmp, 1, 2, 3)
 int memcmp(const void * const POS0 p, const void * const POS0 q, __kernel_size_t size)
 {
-	size_t p_size = __builtin_object_size(p, 0);
-	size_t q_size = __builtin_object_size(q, 0);
+	size_t p_size = __struct_size(p);
+	size_t q_size = __struct_size(q);
 
 	if (__builtin_constant_p(size)) {
-		if (p_size < size)
+		if (__compiletime_lessthan(p_size, size))
 			__read_overflow();
-		if (q_size < size)
+		if (__compiletime_lessthan(q_size, size))
 			__read_overflow2();
 	}
 	if (p_size < size || q_size < size)
@@ -423,9 +532,9 @@ int memcmp(const void * const POS0 p, const void * const POS0 q, __kernel_size_t
 __FORTIFY_INLINE __diagnose_as(__builtin_memchr, 1, 2, 3)
 void *memchr(const void * const POS0 p, int c, __kernel_size_t size)
 {
-	size_t p_size = __builtin_object_size(p, 0);
+	size_t p_size = __struct_size(p);
 
-	if (__builtin_constant_p(size) && p_size < size)
+	if (__compiletime_lessthan(p_size, size))
 		__read_overflow();
 	if (p_size < size)
 		fortify_panic(__func__);
@@ -435,9 +544,9 @@ void *memchr(const void * const POS0 p, int c, __kernel_size_t size)
 void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv);
 __FORTIFY_INLINE void *memchr_inv(const void * const POS0 p, int c, size_t size)
 {
-	size_t p_size = __builtin_object_size(p, 0);
+	size_t p_size = __struct_size(p);
 
-	if (__builtin_constant_p(size) && p_size < size)
+	if (__compiletime_lessthan(p_size, size))
 		__read_overflow();
 	if (p_size < size)
 		fortify_panic(__func__);
@@ -447,9 +556,9 @@ __FORTIFY_INLINE void *memchr_inv(const void * const POS0 p, int c, size_t size)
 extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup);
 __FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp)
 {
-	size_t p_size = __builtin_object_size(p, 0);
+	size_t p_size = __struct_size(p);
 
-	if (__builtin_constant_p(size) && p_size < size)
+	if (__compiletime_lessthan(p_size, size))
 		__read_overflow();
 	if (p_size < size)
 		fortify_panic(__func__);
@@ -460,16 +569,18 @@ __FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp
 __FORTIFY_INLINE __diagnose_as(__builtin_strcpy, 1, 2)
 char *strcpy(char * const POS p, const char * const POS q)
 {
-	size_t p_size = __builtin_object_size(p, 1);
-	size_t q_size = __builtin_object_size(q, 1);
+	size_t p_size = __member_size(p);
+	size_t q_size = __member_size(q);
 	size_t size;
 
 	/* If neither buffer size is known, immediately give up. */
-	if (p_size == (size_t)-1 && q_size == (size_t)-1)
+	if (__builtin_constant_p(p_size) &&
+	    __builtin_constant_p(q_size) &&
+	    p_size == SIZE_MAX && q_size == SIZE_MAX)
 		return __underlying_strcpy(p, q);
 	size = strlen(q) + 1;
 	/* Compile-time check for const size overflow. */
-	if (__builtin_constant_p(size) && p_size < size)
+	if (__compiletime_lessthan(p_size, size))
 		__write_overflow();
 	/* Run-time check for dynamic size overflow. */
 	if (p_size < size)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9eced4cc286e..0830486f47ef 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1472,7 +1472,7 @@ struct super_block {
 	const struct xattr_handler **s_xattr;
 #ifdef CONFIG_FS_ENCRYPTION
 	const struct fscrypt_operations	*s_cop;
-	struct key		*s_master_keys; /* master crypto keys in use */
+	struct fscrypt_keyring	*s_master_keys; /* master crypto keys in use */
 #endif
 #ifdef CONFIG_FS_VERITY
 	const struct fsverity_operations *s_vop;
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index 720874e6ee94..36e5dd84cf59 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -258,7 +258,7 @@ struct fscache_cookie *fscache_acquire_cookie(struct fscache_volume *volume,
 
 /**
  * fscache_use_cookie - Request usage of cookie attached to an object
- * @object: Object description
+ * @cookie: The cookie representing the cache object
  * @will_modify: If cache is expected to be modified locally
  *
  * Request usage of the cookie attached to an object.  The caller should tell
@@ -274,7 +274,7 @@ static inline void fscache_use_cookie(struct fscache_cookie *cookie,
 
 /**
  * fscache_unuse_cookie - Cease usage of cookie attached to an object
- * @object: Object description
+ * @cookie: The cookie representing the cache object
  * @aux_data: Updated auxiliary data (or NULL)
  * @object_size: Revised size of the object (or NULL)
  *
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 7d2f1e0f23b1..cad78b569c7e 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -161,24 +161,21 @@ struct fscrypt_operations {
 				      int *ino_bits_ret, int *lblk_bits_ret);
 
 	/*
-	 * Return the number of block devices to which the filesystem may write
-	 * encrypted file contents.
+	 * Return an array of pointers to the block devices to which the
+	 * filesystem may write encrypted file contents, NULL if the filesystem
+	 * only has a single such block device, or an ERR_PTR() on error.
+	 *
+	 * On successful non-NULL return, *num_devs is set to the number of
+	 * devices in the returned array.  The caller must free the returned
+	 * array using kfree().
 	 *
 	 * If the filesystem can use multiple block devices (other than block
 	 * devices that aren't used for encrypted file contents, such as
 	 * external journal devices), and wants to support inline encryption,
 	 * then it must implement this function.  Otherwise it's not needed.
 	 */
-	int (*get_num_devices)(struct super_block *sb);
-
-	/*
-	 * If ->get_num_devices() returns a value greater than 1, then this
-	 * function is called to get the array of request_queues that the
-	 * filesystem is using -- one per block device.  (There may be duplicate
-	 * entries in this array, as block devices can share a request_queue.)
-	 */
-	void (*get_devices)(struct super_block *sb,
-			    struct request_queue **devs);
+	struct block_device **(*get_devices)(struct super_block *sb,
+					     unsigned int *num_devs);
 };
 
 static inline struct fscrypt_info *fscrypt_get_info(const struct inode *inode)
@@ -295,8 +292,6 @@ int fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param,
 				    struct fscrypt_dummy_policy *dummy_policy);
 bool fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1,
 				  const struct fscrypt_dummy_policy *p2);
-int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg,
-				struct fscrypt_dummy_policy *dummy_policy);
 void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep,
 					struct super_block *sb);
 static inline bool
@@ -312,7 +307,7 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy)
 }
 
 /* keyring.c */
-void fscrypt_sb_free(struct super_block *sb);
+void fscrypt_sb_delete(struct super_block *sb);
 int fscrypt_ioctl_add_key(struct file *filp, void __user *arg);
 int fscrypt_add_test_dummy_key(struct super_block *sb,
 			       const struct fscrypt_dummy_policy *dummy_policy);
@@ -353,7 +348,7 @@ u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name);
 int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags);
 
 /* bio.c */
-void fscrypt_decrypt_bio(struct bio *bio);
+bool fscrypt_decrypt_bio(struct bio *bio);
 int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
 			  sector_t pblk, unsigned int len);
 
@@ -526,7 +521,7 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy)
 }
 
 /* keyring.c */
-static inline void fscrypt_sb_free(struct super_block *sb)
+static inline void fscrypt_sb_delete(struct super_block *sb)
 {
 }
 
@@ -646,8 +641,9 @@ static inline int fscrypt_d_revalidate(struct dentry *dentry,
 }
 
 /* bio.c */
-static inline void fscrypt_decrypt_bio(struct bio *bio)
+static inline bool fscrypt_decrypt_bio(struct bio *bio)
 {
+	return true;
 }
 
 static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
@@ -768,7 +764,7 @@ bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode,
 bool fscrypt_mergeable_bio_bh(struct bio *bio,
 			      const struct buffer_head *next_bh);
 
-bool fscrypt_dio_supported(struct kiocb *iocb, struct iov_iter *iter);
+bool fscrypt_dio_supported(struct inode *inode);
 
 u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, u64 nr_blocks);
 
@@ -801,11 +797,8 @@ static inline bool fscrypt_mergeable_bio_bh(struct bio *bio,
 	return true;
 }
 
-static inline bool fscrypt_dio_supported(struct kiocb *iocb,
-					 struct iov_iter *iter)
+static inline bool fscrypt_dio_supported(struct inode *inode)
 {
-	const struct inode *inode = file_inode(iocb->ki_filp);
-
 	return !fscrypt_needs_contents_encryption(inode);
 }
 
diff --git a/include/linux/hp_sdc.h b/include/linux/hp_sdc.h
index 6f1dee7e67e0..9be8704e2d38 100644
--- a/include/linux/hp_sdc.h
+++ b/include/linux/hp_sdc.h
@@ -180,7 +180,7 @@ switch (val) {						\
 
 #define HP_SDC_CMD_SET_IM	0x40    /* 010xxxxx == set irq mask */
 
-/* The documents provided do not explicitly state that all registers betweem 
+/* The documents provided do not explicitly state that all registers between
  * 0x01 and 0x1f inclusive can be read by sending their register index as a 
  * command, but this is implied and appears to be the case.
  */
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 55e6f4ad0ca6..b6e6d5b40774 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -310,9 +310,11 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2)
 struct ieee80211_hdr {
 	__le16 frame_control;
 	__le16 duration_id;
-	u8 addr1[ETH_ALEN];
-	u8 addr2[ETH_ALEN];
-	u8 addr3[ETH_ALEN];
+	struct_group(addrs,
+		u8 addr1[ETH_ALEN];
+		u8 addr2[ETH_ALEN];
+		u8 addr3[ETH_ALEN];
+	);
 	__le16 seq_ctrl;
 	u8 addr4[ETH_ALEN];
 } __packed __aligned(2);
diff --git a/include/linux/init.h b/include/linux/init.h
index baf0b29a7010..a0a90cd73ebe 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -47,7 +47,7 @@
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(".init.text") __cold  __latent_entropy __noinitretpoline __nocfi
+#define __init		__section(".init.text") __cold  __latent_entropy __noinitretpoline
 #define __initdata	__section(".init.data")
 #define __initconst	__section(".init.rodata")
 #define __exitdata	__section(".exit.data")
@@ -220,8 +220,8 @@ extern bool initcall_debug;
 	__initcall_name(initstub, __iid, id)
 
 #define __define_initcall_stub(__stub, fn)			\
-	int __init __cficanonical __stub(void);			\
-	int __init __cficanonical __stub(void)			\
+	int __init __stub(void);				\
+	int __init __stub(void)					\
 	{ 							\
 		return fn();					\
 	}							\
diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h
index ad39636e0c3f..649faac31ddb 100644
--- a/include/linux/kallsyms.h
+++ b/include/linux/kallsyms.h
@@ -15,7 +15,7 @@
 
 #include <asm/sections.h>
 
-#define KSYM_NAME_LEN 128
+#define KSYM_NAME_LEN 512
 #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s %s]") + \
 			(KSYM_NAME_LEN - 1) + \
 			2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + \
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1c480b1821e1..f4519d3689e1 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -656,12 +656,12 @@ struct kvm_irq_routing_table {
 };
 #endif
 
-#ifndef KVM_PRIVATE_MEM_SLOTS
-#define KVM_PRIVATE_MEM_SLOTS 0
+#ifndef KVM_INTERNAL_MEM_SLOTS
+#define KVM_INTERNAL_MEM_SLOTS 0
 #endif
 
 #define KVM_MEM_SLOTS_NUM SHRT_MAX
-#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_PRIVATE_MEM_SLOTS)
+#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS)
 
 #ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
 static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
@@ -765,10 +765,10 @@ struct kvm {
 
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 	struct mmu_notifier mmu_notifier;
-	unsigned long mmu_notifier_seq;
-	long mmu_notifier_count;
-	unsigned long mmu_notifier_range_start;
-	unsigned long mmu_notifier_range_end;
+	unsigned long mmu_invalidate_seq;
+	long mmu_invalidate_in_progress;
+	unsigned long mmu_invalidate_range_start;
+	unsigned long mmu_invalidate_range_end;
 #endif
 	struct list_head devices;
 	u64 manual_dirty_log_protect;
@@ -1357,10 +1357,10 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc);
 void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
 #endif
 
-void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
-				   unsigned long end);
-void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start,
-				   unsigned long end);
+void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
+			      unsigned long end);
+void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
+			    unsigned long end);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -1907,42 +1907,44 @@ extern const struct kvm_stats_header kvm_vcpu_stats_header;
 extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
 
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
-static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
+static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 {
-	if (unlikely(kvm->mmu_notifier_count))
+	if (unlikely(kvm->mmu_invalidate_in_progress))
 		return 1;
 	/*
-	 * Ensure the read of mmu_notifier_count happens before the read
-	 * of mmu_notifier_seq.  This interacts with the smp_wmb() in
-	 * mmu_notifier_invalidate_range_end to make sure that the caller
-	 * either sees the old (non-zero) value of mmu_notifier_count or
-	 * the new (incremented) value of mmu_notifier_seq.
-	 * PowerPC Book3s HV KVM calls this under a per-page lock
-	 * rather than under kvm->mmu_lock, for scalability, so
-	 * can't rely on kvm->mmu_lock to keep things ordered.
+	 * Ensure the read of mmu_invalidate_in_progress happens before
+	 * the read of mmu_invalidate_seq.  This interacts with the
+	 * smp_wmb() in mmu_notifier_invalidate_range_end to make sure
+	 * that the caller either sees the old (non-zero) value of
+	 * mmu_invalidate_in_progress or the new (incremented) value of
+	 * mmu_invalidate_seq.
+	 *
+	 * PowerPC Book3s HV KVM calls this under a per-page lock rather
+	 * than under kvm->mmu_lock, for scalability, so can't rely on
+	 * kvm->mmu_lock to keep things ordered.
 	 */
 	smp_rmb();
-	if (kvm->mmu_notifier_seq != mmu_seq)
+	if (kvm->mmu_invalidate_seq != mmu_seq)
 		return 1;
 	return 0;
 }
 
-static inline int mmu_notifier_retry_hva(struct kvm *kvm,
-					 unsigned long mmu_seq,
-					 unsigned long hva)
+static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
+					   unsigned long mmu_seq,
+					   unsigned long hva)
 {
 	lockdep_assert_held(&kvm->mmu_lock);
 	/*
-	 * If mmu_notifier_count is non-zero, then the range maintained by
-	 * kvm_mmu_notifier_invalidate_range_start contains all addresses that
-	 * might be being invalidated. Note that it may include some false
+	 * If mmu_invalidate_in_progress is non-zero, then the range maintained
+	 * by kvm_mmu_notifier_invalidate_range_start contains all addresses
+	 * that might be being invalidated. Note that it may include some false
 	 * positives, due to shortcuts when handing concurrent invalidations.
 	 */
-	if (unlikely(kvm->mmu_notifier_count) &&
-	    hva >= kvm->mmu_notifier_range_start &&
-	    hva < kvm->mmu_notifier_range_end)
+	if (unlikely(kvm->mmu_invalidate_in_progress) &&
+	    hva >= kvm->mmu_invalidate_range_start &&
+	    hva < kvm->mmu_invalidate_range_end)
 		return 1;
-	if (kvm->mmu_notifier_seq != mmu_seq)
+	if (kvm->mmu_invalidate_seq != mmu_seq)
 		return 1;
 	return 0;
 }
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 0269ff114f5a..20765d1c5f80 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1136,8 +1136,8 @@ extern int ata_scsi_slave_config(struct scsi_device *sdev);
 extern void ata_scsi_slave_destroy(struct scsi_device *sdev);
 extern int ata_scsi_change_queue_depth(struct scsi_device *sdev,
 				       int queue_depth);
-extern int __ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev,
-				    int queue_depth);
+extern int ata_change_queue_depth(struct ata_port *ap, struct ata_device *dev,
+				  struct scsi_device *sdev, int queue_depth);
 extern struct ata_device *ata_dev_pair(struct ata_device *adev);
 extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev);
 extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap);
@@ -1382,7 +1382,8 @@ extern const struct attribute_group *ata_common_sdev_groups[];
 	.proc_name		= drv_name,			\
 	.slave_destroy		= ata_scsi_slave_destroy,	\
 	.bios_param		= ata_std_bios_param,		\
-	.unlock_native_capacity	= ata_scsi_unlock_native_capacity
+	.unlock_native_capacity	= ata_scsi_unlock_native_capacity,\
+	.max_sectors		= ATA_MAX_SECTORS_LBA48
 
 #define ATA_SUBBASE_SHT(drv_name)				\
 	__ATA_BASE_SHT(drv_name),				\
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 806448173033..f8715ddbfcf4 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -224,6 +224,7 @@ LSM_HOOK(int, -ENOSYS, task_prctl, int option, unsigned long arg2,
 	 unsigned long arg3, unsigned long arg4, unsigned long arg5)
 LSM_HOOK(void, LSM_RET_VOID, task_to_inode, struct task_struct *p,
 	 struct inode *inode)
+LSM_HOOK(int, 0, userns_create, const struct cred *cred)
 LSM_HOOK(int, 0, ipc_permission, struct kern_ipc_perm *ipcp, short flag)
 LSM_HOOK(void, LSM_RET_VOID, ipc_getsecid, struct kern_ipc_perm *ipcp,
 	 u32 *secid)
@@ -407,4 +408,5 @@ LSM_HOOK(int, 0, perf_event_write, struct perf_event *event)
 #ifdef CONFIG_IO_URING
 LSM_HOOK(int, 0, uring_override_creds, const struct cred *new)
 LSM_HOOK(int, 0, uring_sqpoll, void)
+LSM_HOOK(int, 0, uring_cmd, struct io_uring_cmd *ioucmd)
 #endif /* CONFIG_IO_URING */
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 84a0d7e02176..4ec80b96c22e 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -806,6 +806,10 @@
  *	security attributes, e.g. for /proc/pid inodes.
  *	@p contains the task_struct for the task.
  *	@inode contains the inode structure for the inode.
+ * @userns_create:
+ *	Check permission prior to creating a new user namespace.
+ *	@cred points to prepared creds.
+ *	Return 0 if successful, otherwise < 0 error code.
  *
  * Security hooks for Netlink messaging.
  *
@@ -1582,6 +1586,9 @@
  *      Check whether the current task is allowed to spawn a io_uring polling
  *      thread (IORING_SETUP_SQPOLL).
  *
+ * @uring_cmd:
+ *      Check whether the file_operations uring_cmd is allowed to run.
+ *
  */
 union security_list_options {
 	#define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 4d31ce55b1c0..567f12323f55 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -987,19 +987,30 @@ static inline void mod_memcg_page_state(struct page *page,
 
 static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
 {
-	return READ_ONCE(memcg->vmstats.state[idx]);
+	long x = READ_ONCE(memcg->vmstats.state[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 					      enum node_stat_item idx)
 {
 	struct mem_cgroup_per_node *pn;
+	long x;
 
 	if (mem_cgroup_disabled())
 		return node_page_state(lruvec_pgdat(lruvec), idx);
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	return READ_ONCE(pn->lruvec_stats.state[idx]);
+	x = READ_ONCE(pn->lruvec_stats.state[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
@@ -1777,42 +1788,6 @@ static inline void count_objcg_event(struct obj_cgroup *objcg,
 	rcu_read_unlock();
 }
 
-/**
- * get_mem_cgroup_from_obj - get a memcg associated with passed kernel object.
- * @p: pointer to object from which memcg should be extracted. It can be NULL.
- *
- * Retrieves the memory group into which the memory of the pointed kernel
- * object is accounted. If memcg is found, its reference is taken.
- * If a passed kernel object is uncharged, or if proper memcg cannot be found,
- * as well as if mem_cgroup is disabled, NULL is returned.
- *
- * Return: valid memcg pointer with taken reference or NULL.
- */
-static inline struct mem_cgroup *get_mem_cgroup_from_obj(void *p)
-{
-	struct mem_cgroup *memcg;
-
-	rcu_read_lock();
-	do {
-		memcg = mem_cgroup_from_obj(p);
-	} while (memcg && !css_tryget(&memcg->css));
-	rcu_read_unlock();
-	return memcg;
-}
-
-/**
- * mem_cgroup_or_root - always returns a pointer to a valid memory cgroup.
- * @memcg: pointer to a valid memory cgroup or NULL.
- *
- * If passed argument is not NULL, returns it without any additional checks
- * and changes. Otherwise, root_mem_cgroup is returned.
- *
- * NOTE: root_mem_cgroup can be NULL during early boot.
- */
-static inline struct mem_cgroup *mem_cgroup_or_root(struct mem_cgroup *memcg)
-{
-	return memcg ? memcg : root_mem_cgroup;
-}
 #else
 static inline bool mem_cgroup_kmem_disabled(void)
 {
@@ -1869,15 +1844,6 @@ static inline void count_objcg_event(struct obj_cgroup *objcg,
 {
 }
 
-static inline struct mem_cgroup *get_mem_cgroup_from_obj(void *p)
-{
-	return NULL;
-}
-
-static inline struct mem_cgroup *mem_cgroup_or_root(struct mem_cgroup *memcg)
-{
-	return NULL;
-}
 #endif /* CONFIG_MEMCG_KMEM */
 
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 19010491a603..c3b4cc84877b 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -139,6 +139,11 @@ struct dev_pagemap {
 	};
 };
 
+static inline bool pgmap_has_memory_failure(struct dev_pagemap *pgmap)
+{
+	return pgmap->ops && pgmap->ops->memory_failure;
+}
+
 static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap)
 {
 	if (pgmap->flags & PGMAP_ALTMAP_VALID)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 96b16fbe1aa4..c32de987fa71 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -779,6 +779,7 @@ struct mlx5_core_dev {
 	enum mlx5_device_state	state;
 	/* sync interface state */
 	struct mutex		intf_state_mutex;
+	struct lock_class_key	lock_key;
 	unsigned long		intf_state;
 	struct mlx5_priv	priv;
 	struct mlx5_profile	profile;
@@ -1279,16 +1280,17 @@ enum {
 	MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32,
 };
 
-static inline bool mlx5_is_roce_init_enabled(struct mlx5_core_dev *dev)
+bool mlx5_is_roce_on(struct mlx5_core_dev *dev);
+
+static inline bool mlx5_get_roce_state(struct mlx5_core_dev *dev)
 {
-	struct devlink *devlink = priv_to_devlink(dev);
-	union devlink_param_value val;
-	int err;
-
-	err = devlink_param_driverinit_value_get(devlink,
-						 DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
-						 &val);
-	return err ? MLX5_CAP_GEN(dev, roce) : val.vbool;
+	if (MLX5_CAP_GEN(dev, roce_rw_supported))
+		return MLX5_CAP_GEN(dev, roce);
+
+	/* If RoCE cap is read-only in FW, get RoCE state from devlink
+	 * in order to support RoCE enable/disable feature
+	 */
+	return mlx5_is_roce_on(dev);
 }
 
 #endif /* MLX5_DRIVER_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3bedc449c14d..21f8b27bd9fd 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1544,9 +1544,16 @@ static inline bool is_longterm_pinnable_page(struct page *page)
 	if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
 		return false;
 #endif
-	return !(is_device_coherent_page(page) ||
-		 is_zone_movable_page(page) ||
-		 is_zero_pfn(page_to_pfn(page)));
+	/* The zero page may always be pinned */
+	if (is_zero_pfn(page_to_pfn(page)))
+		return true;
+
+	/* Coherent device memory must always allow eviction. */
+	if (is_device_coherent_page(page))
+		return false;
+
+	/* Otherwise, non-movable zone pages can be pinned. */
+	return !is_zone_movable_page(page);
 }
 #else
 static inline bool is_longterm_pinnable_page(struct page *page)
@@ -2885,7 +2892,6 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 #define FOLL_MIGRATION	0x400	/* wait for page to replace migration entry */
 #define FOLL_TRIED	0x800	/* a retry, previous pass started an IO */
 #define FOLL_REMOTE	0x2000	/* we are working on non-current tsk/mm */
-#define FOLL_COW	0x4000	/* internal GUP flag */
 #define FOLL_ANON	0x8000	/* don't do file mappings */
 #define FOLL_LONGTERM	0x10000	/* mapping lifetime is indefinite: see below */
 #define FOLL_SPLIT_PMD	0x20000	/* split huge pmd before returning */
diff --git a/include/linux/module.h b/include/linux/module.h
index 518296ea7f73..ec61fb53979a 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -27,7 +27,6 @@
 #include <linux/tracepoint-defs.h>
 #include <linux/srcu.h>
 #include <linux/static_call_types.h>
-#include <linux/cfi.h>
 
 #include <linux/percpu.h>
 #include <asm/module.h>
@@ -132,7 +131,7 @@ extern void cleanup_module(void);
 	{ return initfn; }					\
 	int init_module(void) __copy(initfn)			\
 		__attribute__((alias(#initfn)));		\
-	__CFI_ADDRESSABLE(init_module, __initdata);
+	___ADDRESSABLE(init_module, __initdata);
 
 /* This is only required if you want to be unloadable. */
 #define module_exit(exitfn)					\
@@ -140,7 +139,7 @@ extern void cleanup_module(void);
 	{ return exitfn; }					\
 	void cleanup_module(void) __copy(exitfn)		\
 		__attribute__((alias(#exitfn)));		\
-	__CFI_ADDRESSABLE(cleanup_module, __exitdata);
+	___ADDRESSABLE(cleanup_module, __exitdata);
 
 #endif
 
@@ -387,8 +386,9 @@ struct module {
 	const s32 *crcs;
 	unsigned int num_syms;
 
-#ifdef CONFIG_CFI_CLANG
-	cfi_check_fn cfi_check;
+#ifdef CONFIG_ARCH_USES_CFI_TRAPS
+	s32 *kcfi_traps;
+	s32 *kcfi_traps_end;
 #endif
 
 	/* Kernel parameters. */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1a3cb93c3dcc..05d6f3facd5a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -640,9 +640,23 @@ extern int sysctl_devconf_inherit_init_net;
  */
 static inline bool net_has_fallback_tunnels(const struct net *net)
 {
-	return !IS_ENABLED(CONFIG_SYSCTL) ||
-	       !sysctl_fb_tunnels_only_for_init_net ||
-	       (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1);
+#if IS_ENABLED(CONFIG_SYSCTL)
+	int fb_tunnels_only_for_init_net = READ_ONCE(sysctl_fb_tunnels_only_for_init_net);
+
+	return !fb_tunnels_only_for_init_net ||
+		(net_eq(net, &init_net) && fb_tunnels_only_for_init_net == 1);
+#else
+	return true;
+#endif
+}
+
+static inline int net_inherit_devconf(void)
+{
+#if IS_ENABLED(CONFIG_SYSCTL)
+	return READ_ONCE(sysctl_devconf_inherit_init_net);
+#else
+	return 0;
+#endif
 }
 
 static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h
index a13296d6c7ce..fd533552a062 100644
--- a/include/linux/netfilter_bridge/ebtables.h
+++ b/include/linux/netfilter_bridge/ebtables.h
@@ -94,10 +94,6 @@ struct ebt_table {
 	struct ebt_replace_kernel *table;
 	unsigned int valid_hooks;
 	rwlock_t lock;
-	/* e.g. could be the table explicitly only allows certain
-	 * matches, targets, ... 0 == let it in */
-	int (*check)(const struct ebt_table_info *info,
-	   unsigned int valid_hooks);
 	/* the data used by the kernel */
 	struct ebt_table_info *private;
 	struct nf_hook_ops *ops;
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index b32ed68e7dc4..7931fa472561 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -83,7 +83,6 @@ struct nfs_open_context {
 	fmode_t mode;
 
 	unsigned long flags;
-#define NFS_CONTEXT_RESEND_WRITES	(1)
 #define NFS_CONTEXT_BAD			(2)
 #define NFS_CONTEXT_UNLOCK	(3)
 #define NFS_CONTEXT_FILE_OPEN		(4)
@@ -182,6 +181,7 @@ struct nfs_inode {
 		/* Regular file */
 		struct {
 			atomic_long_t	nrequests;
+			atomic_long_t	redirtied_pages;
 			struct nfs_mds_commit_info commit_info;
 			struct mutex	commit_mutex;
 		};
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 1d7992a02e36..1a803e4335d3 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -101,8 +101,9 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
 }
 
 static inline int of_dma_configure_id(struct device *dev,
-				   struct device_node *np,
-				   bool force_dma)
+				      struct device_node *np,
+				      bool force_dma,
+				      const u32 *id)
 {
 	return 0;
 }
diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index f1221d11f8e5..19dfdd74835e 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -30,7 +30,6 @@
  * https://mail-index.netbsd.org/tech-misc/2007/02/05/0000.html -
  * credit to Christian Biere.
  */
-#define is_signed_type(type)       (((type)(-1)) < (type)1)
 #define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type)))
 #define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T)))
 #define type_min(T) ((T)((T)-type_max(T)-(T)1))
@@ -52,40 +51,50 @@ static inline bool __must_check __must_check_overflow(bool overflow)
 	return unlikely(overflow);
 }
 
-/*
- * For simplicity and code hygiene, the fallback code below insists on
- * a, b and *d having the same type (similar to the min() and max()
- * macros), whereas gcc's type-generic overflow checkers accept
- * different types. Hence we don't just make check_add_overflow an
- * alias for __builtin_add_overflow, but add type checks similar to
- * below.
+/** check_add_overflow() - Calculate addition with overflow checking
+ *
+ * @a: first addend
+ * @b: second addend
+ * @d: pointer to store sum
+ *
+ * Returns 0 on success.
+ *
+ * *@d holds the results of the attempted addition, but is not considered
+ * "safe for use" on a non-zero return value, which indicates that the
+ * sum has overflowed or been truncated.
  */
-#define check_add_overflow(a, b, d) __must_check_overflow(({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	__builtin_add_overflow(__a, __b, __d);	\
-}))
+#define check_add_overflow(a, b, d)	\
+	__must_check_overflow(__builtin_add_overflow(a, b, d))
 
-#define check_sub_overflow(a, b, d) __must_check_overflow(({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	__builtin_sub_overflow(__a, __b, __d);	\
-}))
+/** check_sub_overflow() - Calculate subtraction with overflow checking
+ *
+ * @a: minuend; value to subtract from
+ * @b: subtrahend; value to subtract from @a
+ * @d: pointer to store difference
+ *
+ * Returns 0 on success.
+ *
+ * *@d holds the results of the attempted subtraction, but is not considered
+ * "safe for use" on a non-zero return value, which indicates that the
+ * difference has underflowed or been truncated.
+ */
+#define check_sub_overflow(a, b, d)	\
+	__must_check_overflow(__builtin_sub_overflow(a, b, d))
 
-#define check_mul_overflow(a, b, d) __must_check_overflow(({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	__builtin_mul_overflow(__a, __b, __d);	\
-}))
+/** check_mul_overflow() - Calculate multiplication with overflow checking
+ *
+ * @a: first factor
+ * @b: second factor
+ * @d: pointer to store product
+ *
+ * Returns 0 on success.
+ *
+ * *@d holds the results of the attempted multiplication, but is not
+ * considered "safe for use" on a non-zero return value, which indicates
+ * that the product has overflowed or been truncated.
+ */
+#define check_mul_overflow(a, b, d)	\
+	__must_check_overflow(__builtin_mul_overflow(a, b, d))
 
 /** check_shl_overflow() - Calculate a left-shifted value and check overflow
  *
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 060af91bafcd..5da0846aa3c1 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2019,8 +2019,8 @@ enum pci_fixup_pass {
 #ifdef CONFIG_LTO_CLANG
 #define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class,	\
 				  class_shift, hook, stub)		\
-	void __cficanonical stub(struct pci_dev *dev);			\
-	void __cficanonical stub(struct pci_dev *dev)			\
+	void stub(struct pci_dev *dev);					\
+	void stub(struct pci_dev *dev)					\
 	{ 								\
 		hook(dev); 						\
 	}								\
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 6feade66efdb..b362d90eb9b0 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -75,6 +75,9 @@
 #define PCI_CLASS_COMMUNICATION_MODEM	0x0703
 #define PCI_CLASS_COMMUNICATION_OTHER	0x0780
 
+/* Interface for SERIAL/MODEM */
+#define PCI_SERIAL_16550_COMPATIBLE	0x02
+
 #define PCI_BASE_CLASS_SYSTEM		0x08
 #define PCI_CLASS_SYSTEM_PIC		0x0800
 #define PCI_CLASS_SYSTEM_PIC_IOAPIC	0x080010
@@ -2079,6 +2082,9 @@
 #define PCI_DEVICE_ID_ICE_1712		0x1712
 #define PCI_DEVICE_ID_VT1724		0x1724
 
+#define PCI_VENDOR_ID_MICROSOFT		0x1414
+#define PCI_DEVICE_ID_HYPERV_VIDEO	0x5353
+
 #define PCI_VENDOR_ID_OXSEMI		0x1415
 #define PCI_DEVICE_ID_OXSEMI_12PCI840	0x8403
 #define PCI_DEVICE_ID_OXSEMI_PCIe840		0xC000
diff --git a/include/linux/platform_data/tps68470.h b/include/linux/platform_data/tps68470.h
index 126d082c3f2e..e605a2cab07f 100644
--- a/include/linux/platform_data/tps68470.h
+++ b/include/linux/platform_data/tps68470.h
@@ -27,9 +27,14 @@ struct tps68470_regulator_platform_data {
 	const struct regulator_init_data *reg_init_data[TPS68470_NUM_REGULATORS];
 };
 
-struct tps68470_clk_platform_data {
+struct tps68470_clk_consumer {
 	const char *consumer_dev_name;
 	const char *consumer_con_id;
 };
 
+struct tps68470_clk_platform_data {
+	unsigned int n_consumers;
+	struct tps68470_clk_consumer consumers[];
+};
+
 #endif
diff --git a/include/linux/platform_data/x86/pmc_atom.h b/include/linux/platform_data/x86/pmc_atom.h
index 3edfb6d4e67a..dd81f510e4cf 100644
--- a/include/linux/platform_data/x86/pmc_atom.h
+++ b/include/linux/platform_data/x86/pmc_atom.h
@@ -7,6 +7,8 @@
 #ifndef PMC_ATOM_H
 #define PMC_ATOM_H
 
+#include <linux/bits.h>
+
 /* ValleyView Power Control Unit PCI Device ID */
 #define	PCI_DEVICE_ID_VLV_PMC	0x0F1C
 /* CherryTrail Power Control Unit PCI Device ID */
@@ -139,9 +141,9 @@
 #define	ACPI_MMIO_REG_LEN	0x100
 
 #define	PM1_CNT			0x4
-#define	SLEEP_TYPE_MASK		0xFFFFECFF
+#define	SLEEP_TYPE_MASK		GENMASK(12, 10)
 #define	SLEEP_TYPE_S5		0x1C00
-#define	SLEEP_ENABLE		0x2000
+#define	SLEEP_ENABLE		BIT(13)
 
 extern int pmc_atom_read(int offset, u32 *value);
 
diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h
index b6bd3eac2bcc..8163dd48c430 100644
--- a/include/linux/posix_acl_xattr.h
+++ b/include/linux/posix_acl_xattr.h
@@ -38,9 +38,6 @@ void posix_acl_fix_xattr_to_user(void *value, size_t size);
 void posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns,
 				     const struct inode *inode,
 				     void *value, size_t size);
-void posix_acl_setxattr_idmapped_mnt(struct user_namespace *mnt_userns,
-				     const struct inode *inode,
-				     void *value, size_t size);
 #else
 static inline void posix_acl_fix_xattr_from_user(void *value, size_t size)
 {
@@ -54,18 +51,15 @@ posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns,
 				size_t size)
 {
 }
-static inline void
-posix_acl_setxattr_idmapped_mnt(struct user_namespace *mnt_userns,
-				const struct inode *inode, void *value,
-				size_t size)
-{
-}
 #endif
 
 struct posix_acl *posix_acl_from_xattr(struct user_namespace *user_ns, 
 				       const void *value, size_t size);
 int posix_acl_to_xattr(struct user_namespace *user_ns,
 		       const struct posix_acl *acl, void *buffer, size_t size);
+struct posix_acl *vfs_set_acl_prepare(struct user_namespace *mnt_userns,
+				      struct user_namespace *fs_userns,
+				      const void *value, size_t size);
 
 extern const struct xattr_handler posix_acl_access_xattr_handler;
 extern const struct xattr_handler posix_acl_default_xattr_handler;
diff --git a/include/linux/psi.h b/include/linux/psi.h
index 89784763d19e..dd74411ac21d 100644
--- a/include/linux/psi.h
+++ b/include/linux/psi.h
@@ -27,7 +27,7 @@ void psi_memstall_leave(unsigned long *flags);
 
 int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res);
 struct psi_trigger *psi_trigger_create(struct psi_group *group,
-			char *buf, size_t nbytes, enum psi_res res);
+			char *buf, enum psi_res res);
 void psi_trigger_destroy(struct psi_trigger *t);
 
 __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index f527f27e6438..08605ce7379d 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -42,7 +42,31 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func);
 void rcu_barrier_tasks(void);
 void rcu_barrier_tasks_rude(void);
 void synchronize_rcu(void);
+
+struct rcu_gp_oldstate;
 unsigned long get_completed_synchronize_rcu(void);
+void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp);
+
+// Maximum number of unsigned long values corresponding to
+// not-yet-completed RCU grace periods.
+#define NUM_ACTIVE_RCU_POLL_OLDSTATE 2
+
+/**
+ * same_state_synchronize_rcu - Are two old-state values identical?
+ * @oldstate1: First old-state value.
+ * @oldstate2: Second old-state value.
+ *
+ * The two old-state values must have been obtained from either
+ * get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or
+ * get_completed_synchronize_rcu().  Returns @true if the two values are
+ * identical and @false otherwise.  This allows structures whose lifetimes
+ * are tracked by old-state values to push these values to a list header,
+ * allowing those structures to be slightly smaller.
+ */
+static inline bool same_state_synchronize_rcu(unsigned long oldstate1, unsigned long oldstate2)
+{
+	return oldstate1 == oldstate2;
+}
 
 #ifdef CONFIG_PREEMPT_RCU
 
@@ -496,13 +520,21 @@ do {									      \
  * against NULL.  Although rcu_access_pointer() may also be used in cases
  * where update-side locks prevent the value of the pointer from changing,
  * you should instead use rcu_dereference_protected() for this use case.
+ * Within an RCU read-side critical section, there is little reason to
+ * use rcu_access_pointer().
+ *
+ * It is usually best to test the rcu_access_pointer() return value
+ * directly in order to avoid accidental dereferences being introduced
+ * by later inattentive changes.  In other words, assigning the
+ * rcu_access_pointer() return value to a local variable results in an
+ * accident waiting to happen.
  *
  * It is also permissible to use rcu_access_pointer() when read-side
- * access to the pointer was removed at least one grace period ago, as
- * is the case in the context of the RCU callback that is freeing up
- * the data, or after a synchronize_rcu() returns.  This can be useful
- * when tearing down multi-linked structures after a grace period
- * has elapsed.
+ * access to the pointer was removed at least one grace period ago, as is
+ * the case in the context of the RCU callback that is freeing up the data,
+ * or after a synchronize_rcu() returns.  This can be useful when tearing
+ * down multi-linked structures after a grace period has elapsed.  However,
+ * rcu_dereference_protected() is normally preferred for this use case.
  */
 #define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu)
 
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 62815c0a2dce..768196a5f39d 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -14,25 +14,75 @@
 
 #include <asm/param.h> /* for HZ */
 
+struct rcu_gp_oldstate {
+	unsigned long rgos_norm;
+};
+
+// Maximum number of rcu_gp_oldstate values corresponding to
+// not-yet-completed RCU grace periods.
+#define NUM_ACTIVE_RCU_POLL_FULL_OLDSTATE 2
+
+/*
+ * Are the two oldstate values the same?  See the Tree RCU version for
+ * docbook header.
+ */
+static inline bool same_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp1,
+						   struct rcu_gp_oldstate *rgosp2)
+{
+	return rgosp1->rgos_norm == rgosp2->rgos_norm;
+}
+
 unsigned long get_state_synchronize_rcu(void);
+
+static inline void get_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
+{
+	rgosp->rgos_norm = get_state_synchronize_rcu();
+}
+
 unsigned long start_poll_synchronize_rcu(void);
+
+static inline void start_poll_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
+{
+	rgosp->rgos_norm = start_poll_synchronize_rcu();
+}
+
 bool poll_state_synchronize_rcu(unsigned long oldstate);
 
+static inline bool poll_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
+{
+	return poll_state_synchronize_rcu(rgosp->rgos_norm);
+}
+
 static inline void cond_synchronize_rcu(unsigned long oldstate)
 {
 	might_sleep();
 }
 
+static inline void cond_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
+{
+	cond_synchronize_rcu(rgosp->rgos_norm);
+}
+
 static inline unsigned long start_poll_synchronize_rcu_expedited(void)
 {
 	return start_poll_synchronize_rcu();
 }
 
+static inline void start_poll_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp)
+{
+	rgosp->rgos_norm = start_poll_synchronize_rcu_expedited();
+}
+
 static inline void cond_synchronize_rcu_expedited(unsigned long oldstate)
 {
 	cond_synchronize_rcu(oldstate);
 }
 
+static inline void cond_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp)
+{
+	cond_synchronize_rcu_expedited(rgosp->rgos_norm);
+}
+
 extern void rcu_barrier(void);
 
 static inline void synchronize_rcu_expedited(void)
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 47eaa4cb0df7..5efb51486e8a 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -40,12 +40,52 @@ bool rcu_eqs_special_set(int cpu);
 void rcu_momentary_dyntick_idle(void);
 void kfree_rcu_scheduler_running(void);
 bool rcu_gp_might_be_stalled(void);
+
+struct rcu_gp_oldstate {
+	unsigned long rgos_norm;
+	unsigned long rgos_exp;
+};
+
+// Maximum number of rcu_gp_oldstate values corresponding to
+// not-yet-completed RCU grace periods.
+#define NUM_ACTIVE_RCU_POLL_FULL_OLDSTATE 4
+
+/**
+ * same_state_synchronize_rcu_full - Are two old-state values identical?
+ * @rgosp1: First old-state value.
+ * @rgosp2: Second old-state value.
+ *
+ * The two old-state values must have been obtained from either
+ * get_state_synchronize_rcu_full(), start_poll_synchronize_rcu_full(),
+ * or get_completed_synchronize_rcu_full().  Returns @true if the two
+ * values are identical and @false otherwise.  This allows structures
+ * whose lifetimes are tracked by old-state values to push these values
+ * to a list header, allowing those structures to be slightly smaller.
+ *
+ * Note that equality is judged on a bitwise basis, so that an
+ * @rcu_gp_oldstate structure with an already-completed state in one field
+ * will compare not-equal to a structure with an already-completed state
+ * in the other field.  After all, the @rcu_gp_oldstate structure is opaque
+ * so how did such a situation come to pass in the first place?
+ */
+static inline bool same_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp1,
+						   struct rcu_gp_oldstate *rgosp2)
+{
+	return rgosp1->rgos_norm == rgosp2->rgos_norm && rgosp1->rgos_exp == rgosp2->rgos_exp;
+}
+
 unsigned long start_poll_synchronize_rcu_expedited(void);
+void start_poll_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp);
 void cond_synchronize_rcu_expedited(unsigned long oldstate);
+void cond_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp);
 unsigned long get_state_synchronize_rcu(void);
+void get_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp);
 unsigned long start_poll_synchronize_rcu(void);
+void start_poll_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp);
 bool poll_state_synchronize_rcu(unsigned long oldstate);
+bool poll_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp);
 void cond_synchronize_rcu(unsigned long oldstate);
+void cond_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp);
 
 bool rcu_is_idle_cpu(int cpu);
 
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 21deb5212bbd..0cf5b20c6ddf 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -15,6 +15,9 @@ int proc_resctrl_show(struct seq_file *m,
 
 #endif
 
+/* max value for struct rdt_domain's mbps_val */
+#define MBA_MAX_MBPS   U32_MAX
+
 /**
  * enum resctrl_conf_type - The type of configuration.
  * @CDP_NONE:	No prioritisation, both code and data are controlled or monitored.
@@ -29,6 +32,16 @@ enum resctrl_conf_type {
 
 #define CDP_NUM_TYPES	(CDP_DATA + 1)
 
+/*
+ * Event IDs, the values match those used to program IA32_QM_EVTSEL before
+ * reading IA32_QM_CTR on RDT systems.
+ */
+enum resctrl_event_id {
+	QOS_L3_OCCUP_EVENT_ID		= 0x01,
+	QOS_L3_MBM_TOTAL_EVENT_ID	= 0x02,
+	QOS_L3_MBM_LOCAL_EVENT_ID	= 0x03,
+};
+
 /**
  * struct resctrl_staged_config - parsed configuration to be applied
  * @new_ctrl:		new ctrl value to be loaded
@@ -53,6 +66,9 @@ struct resctrl_staged_config {
  * @cqm_work_cpu:	worker CPU for CQM h/w counters
  * @plr:		pseudo-locked region (if any) associated with domain
  * @staged_config:	parsed configuration to be applied
+ * @mbps_val:		When mba_sc is enabled, this holds the array of user
+ *			specified control values for mba_sc in MBps, indexed
+ *			by closid
  */
 struct rdt_domain {
 	struct list_head		list;
@@ -67,6 +83,7 @@ struct rdt_domain {
 	int				cqm_work_cpu;
 	struct pseudo_lock_region	*plr;
 	struct resctrl_staged_config	staged_config[CDP_NUM_TYPES];
+	u32				*mbps_val;
 };
 
 /**
@@ -130,8 +147,6 @@ struct resctrl_schema;
 /**
  * struct rdt_resource - attributes of a resctrl resource
  * @rid:		The index of the resource
- * @alloc_enabled:	Is allocation enabled on this machine
- * @mon_enabled:	Is monitoring enabled for this feature
  * @alloc_capable:	Is allocation available on this machine
  * @mon_capable:	Is monitor feature available on this machine
  * @num_rmid:		Number of RMIDs available
@@ -150,8 +165,6 @@ struct resctrl_schema;
  */
 struct rdt_resource {
 	int			rid;
-	bool			alloc_enabled;
-	bool			mon_enabled;
 	bool			alloc_capable;
 	bool			mon_capable;
 	int			num_rmid;
@@ -194,7 +207,50 @@ struct resctrl_schema {
 /* The number of closid supported by this resource regardless of CDP */
 u32 resctrl_arch_get_num_closid(struct rdt_resource *r);
 int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
+
+/*
+ * Update the ctrl_val and apply this config right now.
+ * Must be called on one of the domain's CPUs.
+ */
+int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
+			    u32 closid, enum resctrl_conf_type t, u32 cfg_val);
+
 u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
 			    u32 closid, enum resctrl_conf_type type);
+int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d);
+void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d);
+
+/**
+ * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
+ *			      for this resource and domain.
+ * @r:			resource that the counter should be read from.
+ * @d:			domain that the counter should be read from.
+ * @rmid:		rmid of the counter to read.
+ * @eventid:		eventid to read, e.g. L3 occupancy.
+ * @val:		result of the counter read in bytes.
+ *
+ * Call from process context on a CPU that belongs to domain @d.
+ *
+ * Return:
+ * 0 on success, or -EIO, -EINVAL etc on error.
+ */
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+			   u32 rmid, enum resctrl_event_id eventid, u64 *val);
+
+/**
+ * resctrl_arch_reset_rmid() - Reset any private state associated with rmid
+ *			       and eventid.
+ * @r:		The domain's resource.
+ * @d:		The rmid's domain.
+ * @rmid:	The rmid whose counter values should be reset.
+ * @eventid:	The eventid whose counter values should be reset.
+ *
+ * This can be called from any CPU.
+ */
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
+			     u32 rmid, enum resctrl_event_id eventid);
+
+extern unsigned int resctrl_rmid_realloc_threshold;
+extern unsigned int resctrl_rmid_realloc_limit;
 
 #endif /* _RESCTRL_H */
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index bf80adca980b..b89b4b86951f 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -41,12 +41,15 @@ struct anon_vma {
 	atomic_t refcount;
 
 	/*
-	 * Count of child anon_vmas and VMAs which points to this anon_vma.
+	 * Count of child anon_vmas. Equals to the count of all anon_vmas that
+	 * have ->parent pointing to this one, including itself.
 	 *
 	 * This counter is used for making decision about reusing anon_vma
 	 * instead of forking new one. See comments in function anon_vma_clone.
 	 */
-	unsigned degree;
+	unsigned long num_children;
+	/* Count of VMAs whose ->anon_vma pointer points to this object. */
+	unsigned long num_active_vmas;
 
 	struct anon_vma *parent;	/* Parent of this anon_vma */
 
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index a193884ecf2b..4f765bc788ff 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -84,7 +84,7 @@ struct scmi_protocol_handle;
 struct scmi_clk_proto_ops {
 	int (*count_get)(const struct scmi_protocol_handle *ph);
 
-	const struct scmi_clock_info *(*info_get)
+	const struct scmi_clock_info __must_check *(*info_get)
 		(const struct scmi_protocol_handle *ph, u32 clk_id);
 	int (*rate_get)(const struct scmi_protocol_handle *ph, u32 clk_id,
 			u64 *rate);
@@ -466,7 +466,7 @@ enum scmi_sensor_class {
  */
 struct scmi_sensor_proto_ops {
 	int (*count_get)(const struct scmi_protocol_handle *ph);
-	const struct scmi_sensor_info *(*info_get)
+	const struct scmi_sensor_info __must_check *(*info_get)
 		(const struct scmi_protocol_handle *ph, u32 sensor_id);
 	int (*trip_point_config)(const struct scmi_protocol_handle *ph,
 				 u32 sensor_id, u8 trip_id, u64 trip_value);
diff --git a/include/linux/security.h b/include/linux/security.h
index 1bc362cb413f..3480f61e1b2d 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -437,6 +437,7 @@ int security_task_kill(struct task_struct *p, struct kernel_siginfo *info,
 int security_task_prctl(int option, unsigned long arg2, unsigned long arg3,
 			unsigned long arg4, unsigned long arg5);
 void security_task_to_inode(struct task_struct *p, struct inode *inode);
+int security_create_user_ns(const struct cred *cred);
 int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag);
 void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid);
 int security_msg_msg_alloc(struct msg_msg *msg);
@@ -1194,6 +1195,11 @@ static inline int security_task_prctl(int option, unsigned long arg2,
 static inline void security_task_to_inode(struct task_struct *p, struct inode *inode)
 { }
 
+static inline int security_create_user_ns(const struct cred *cred)
+{
+	return 0;
+}
+
 static inline int security_ipc_permission(struct kern_ipc_perm *ipcp,
 					  short flag)
 {
@@ -2060,6 +2066,7 @@ static inline int security_perf_event_write(struct perf_event *event)
 #ifdef CONFIG_SECURITY
 extern int security_uring_override_creds(const struct cred *new);
 extern int security_uring_sqpoll(void);
+extern int security_uring_cmd(struct io_uring_cmd *ioucmd);
 #else
 static inline int security_uring_override_creds(const struct cred *new)
 {
@@ -2069,6 +2076,10 @@ static inline int security_uring_sqpoll(void)
 {
 	return 0;
 }
+static inline int security_uring_cmd(struct io_uring_cmd *ioucmd)
+{
+	return 0;
+}
 #endif /* CONFIG_SECURITY */
 #endif /* CONFIG_IO_URING */
 
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index aef3145f2032..1eaea9fe44d8 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -141,6 +141,14 @@ struct gpio_desc;
  *	Locking: none.
  *	Interrupts: caller dependent.
  *
+ * @start_rx: ``void ()(struct uart_port *port)``
+ *
+ *	Start receiving characters.
+ *
+ *	Locking: @port->lock taken.
+ *	Interrupts: locally disabled.
+ *	This call must not sleep
+ *
  * @stop_rx: ``void ()(struct uart_port *port)``
  *
  *	Stop receiving characters; the @port is in the process of being closed.
@@ -616,6 +624,23 @@ struct uart_state {
 /* number of characters left in xmit buffer before we ask for more */
 #define WAKEUP_CHARS		256
 
+/**
+ * uart_xmit_advance - Advance xmit buffer and account Tx'ed chars
+ * @up: uart_port structure describing the port
+ * @chars: number of characters sent
+ *
+ * This function advances the tail of circular xmit buffer by the number of
+ * @chars transmitted and handles accounting of transmitted bytes (into
+ * @up's icount.tx).
+ */
+static inline void uart_xmit_advance(struct uart_port *up, unsigned int chars)
+{
+	struct circ_buf *xmit = &up->state->xmit;
+
+	xmit->tail = (xmit->tail + chars) & (UART_XMIT_SIZE - 1);
+	up->icount.tx += chars;
+}
+
 struct module;
 struct tty_driver;
 
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 1b6c4013f691..ff0b990de83d 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -29,15 +29,10 @@ struct shmem_inode_info {
 	struct inode		vfs_inode;
 };
 
-#define SHMEM_FL_USER_VISIBLE FS_FL_USER_VISIBLE
-#define SHMEM_FL_USER_MODIFIABLE FS_FL_USER_MODIFIABLE
-#define SHMEM_FL_INHERITED FS_FL_USER_MODIFIABLE
-
-/* Flags that are appropriate for regular files (all but dir-specific ones). */
-#define SHMEM_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
-
-/* Flags that are appropriate for non-directories/regular files. */
-#define SHMEM_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL)
+#define SHMEM_FL_USER_VISIBLE		FS_FL_USER_VISIBLE
+#define SHMEM_FL_USER_MODIFIABLE \
+	(FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL)
+#define SHMEM_FL_INHERITED		(FS_NODUMP_FL | FS_NOATIME_FL)
 
 struct shmem_sb_info {
 	unsigned long max_blocks;   /* How many blocks are allowed */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ca8afa382bf2..18e163a3460d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2444,6 +2444,27 @@ static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
 	skb_shinfo(skb)->nr_frags = i + 1;
 }
 
+/**
+ * skb_fill_page_desc_noacc - initialise a paged fragment in an skb
+ * @skb: buffer containing fragment to be initialised
+ * @i: paged fragment index to initialise
+ * @page: the page to use for this fragment
+ * @off: the offset to the data with @page
+ * @size: the length of the data
+ *
+ * Variant of skb_fill_page_desc() which does not deal with
+ * pfmemalloc, if page is not owned by us.
+ */
+static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i,
+					    struct page *page, int off,
+					    int size)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+	__skb_fill_page_desc_noacc(shinfo, i, page, off, size);
+	shinfo->nr_frags = i + 1;
+}
+
 void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
 		     int size, unsigned int truesize);
 
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index e6c73d5ff1a8..f089ee1ead58 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -469,6 +469,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch
  *	SPI_TRANS_FAIL_NO_START.
  * @queue_empty: signal green light for opportunistically skipping the queue
  *	for spi_sync transfers.
+ * @must_async: disable all fast paths in the core
  *
  * Each SPI controller can communicate with one or more @spi_device
  * children.  These make a small bus, sharing MOSI, MISO and SCK signals
@@ -690,6 +691,7 @@ struct spi_controller {
 
 	/* Flag for enabling opportunistic skipping of the queue in spi_sync */
 	bool			queue_empty;
+	bool			must_async;
 };
 
 static inline void *spi_controller_get_devdata(struct spi_controller *ctlr)
diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h
index 6cfaa0a9a9b9..5aa5e0faf6a1 100644
--- a/include/linux/srcutiny.h
+++ b/include/linux/srcutiny.h
@@ -15,10 +15,10 @@
 
 struct srcu_struct {
 	short srcu_lock_nesting[2];	/* srcu_read_lock() nesting depth. */
-	unsigned short srcu_idx;	/* Current reader array element in bit 0x2. */
-	unsigned short srcu_idx_max;	/* Furthest future srcu_idx request. */
 	u8 srcu_gp_running;		/* GP workqueue running? */
 	u8 srcu_gp_waiting;		/* GP waiting for readers? */
+	unsigned long srcu_idx;		/* Current reader array element in bit 0x2. */
+	unsigned long srcu_idx_max;	/* Furthest future srcu_idx request. */
 	struct swait_queue_head srcu_wq;
 					/* Last srcu_read_unlock() wakes GP. */
 	struct rcu_head *srcu_cb_head;	/* Pending callbacks: Head. */
@@ -82,10 +82,12 @@ static inline void srcu_torture_stats_print(struct srcu_struct *ssp,
 	int idx;
 
 	idx = ((data_race(READ_ONCE(ssp->srcu_idx)) + 1) & 0x2) >> 1;
-	pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n",
+	pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd) gp: %lu->%lu\n",
 		 tt, tf, idx,
 		 data_race(READ_ONCE(ssp->srcu_lock_nesting[!idx])),
-		 data_race(READ_ONCE(ssp->srcu_lock_nesting[idx])));
+		 data_race(READ_ONCE(ssp->srcu_lock_nesting[idx])),
+		 data_race(READ_ONCE(ssp->srcu_idx)),
+		 data_race(READ_ONCE(ssp->srcu_idx_max)));
 }
 
 #endif
diff --git a/include/linux/stat.h b/include/linux/stat.h
index 7df06931f25d..ff277ced50e9 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -50,6 +50,8 @@ struct kstat {
 	struct timespec64 btime;			/* File creation time */
 	u64		blocks;
 	u64		mnt_id;
+	u32		dio_mem_align;
+	u32		dio_offset_align;
 };
 
 #endif
diff --git a/include/linux/string.h b/include/linux/string.h
index 61ec7e4f6311..cf7607b32102 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -261,6 +261,49 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count,
 		    int pad);
 
 /**
+ * strtomem_pad - Copy NUL-terminated string to non-NUL-terminated buffer
+ *
+ * @dest: Pointer of destination character array (marked as __nonstring)
+ * @src: Pointer to NUL-terminated string
+ * @pad: Padding character to fill any remaining bytes of @dest after copy
+ *
+ * This is a replacement for strncpy() uses where the destination is not
+ * a NUL-terminated string, but with bounds checking on the source size, and
+ * an explicit padding character. If padding is not required, use strtomem().
+ *
+ * Note that the size of @dest is not an argument, as the length of @dest
+ * must be discoverable by the compiler.
+ */
+#define strtomem_pad(dest, src, pad)	do {				\
+	const size_t _dest_len = __builtin_object_size(dest, 1);	\
+									\
+	BUILD_BUG_ON(!__builtin_constant_p(_dest_len) ||		\
+		     _dest_len == (size_t)-1);				\
+	memcpy_and_pad(dest, _dest_len, src, strnlen(src, _dest_len), pad); \
+} while (0)
+
+/**
+ * strtomem - Copy NUL-terminated string to non-NUL-terminated buffer
+ *
+ * @dest: Pointer of destination character array (marked as __nonstring)
+ * @src: Pointer to NUL-terminated string
+ *
+ * This is a replacement for strncpy() uses where the destination is not
+ * a NUL-terminated string, but with bounds checking on the source size, and
+ * without trailing padding. If padding is required, use strtomem_pad().
+ *
+ * Note that the size of @dest is not an argument, as the length of @dest
+ * must be discoverable by the compiler.
+ */
+#define strtomem(dest, src)	do {					\
+	const size_t _dest_len = __builtin_object_size(dest, 1);	\
+									\
+	BUILD_BUG_ON(!__builtin_constant_p(_dest_len) ||		\
+		     _dest_len == (size_t)-1);				\
+	memcpy(dest, src, min(_dest_len, strnlen(src, _dest_len)));	\
+} while (0)
+
+/**
  * memset_after - Set a value after a struct member to the end of a struct
  *
  * @obj: Address of target struct instance
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index daecb009c05b..88de45491376 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -472,6 +472,7 @@ struct svc_procedure {
 	/* XDR free result: */
 	void			(*pc_release)(struct svc_rqst *);
 	unsigned int		pc_argsize;	/* argument struct size */
+	unsigned int		pc_argzero;	/* how much of argument to clear */
 	unsigned int		pc_ressize;	/* result struct size */
 	unsigned int		pc_cachetype;	/* cache info (NFS) */
 	unsigned int		pc_xdrressize;	/* maximum size of XDR reply */
@@ -544,16 +545,27 @@ static inline void svc_reserve_auth(struct svc_rqst *rqstp, int space)
 }
 
 /**
- * svcxdr_init_decode - Prepare an xdr_stream for svc Call decoding
+ * svcxdr_init_decode - Prepare an xdr_stream for Call decoding
  * @rqstp: controlling server RPC transaction context
  *
+ * This function currently assumes the RPC header in rq_arg has
+ * already been decoded. Upon return, xdr->p points to the
+ * location of the upper layer header.
  */
 static inline void svcxdr_init_decode(struct svc_rqst *rqstp)
 {
 	struct xdr_stream *xdr = &rqstp->rq_arg_stream;
-	struct kvec *argv = rqstp->rq_arg.head;
+	struct xdr_buf *buf = &rqstp->rq_arg;
+	struct kvec *argv = buf->head;
 
-	xdr_init_decode(xdr, &rqstp->rq_arg, argv->iov_base, NULL);
+	/*
+	 * svc_getnl() and friends do not keep the xdr_buf's ::len
+	 * field up to date. Refresh that field before initializing
+	 * the argument decoding stream.
+	 */
+	buf->len = buf->head->iov_len + buf->page_len + buf->tail->iov_len;
+
+	xdr_init_decode(xdr, buf, argv->iov_base, NULL);
 	xdr_set_scratch_page(xdr, rqstp->rq_scratch_page);
 }
 
@@ -576,7 +588,7 @@ static inline void svcxdr_init_encode(struct svc_rqst *rqstp)
 	xdr->end = resv->iov_base + PAGE_SIZE - rqstp->rq_auth_slack;
 	buf->len = resv->iov_len;
 	xdr->page_ptr = buf->pages - 1;
-	buf->buflen = PAGE_SIZE * (1 + rqstp->rq_page_end - buf->pages);
+	buf->buflen = PAGE_SIZE * (rqstp->rq_page_end - buf->pages);
 	buf->buflen -= rqstp->rq_auth_slack;
 	xdr->rqst = NULL;
 }
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 69175029abbb..f84e2a1358e1 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -240,6 +240,8 @@ typedef int	(*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 
 extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf,
 			    __be32 *p, struct rpc_rqst *rqst);
+extern void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
+			   struct page **pages, struct rpc_rqst *rqst);
 extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
 extern int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec,
 		size_t nbytes);
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 70f2921e2e70..23a253df7f6b 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -75,7 +75,7 @@ extern struct suspend_stats suspend_stats;
 
 static inline void dpm_save_failed_dev(const char *name)
 {
-	strlcpy(suspend_stats.failed_devs[suspend_stats.last_failed_dev],
+	strscpy(suspend_stats.failed_devs[suspend_stats.last_failed_dev],
 		name,
 		sizeof(suspend_stats.failed_devs[0]));
 	suspend_stats.last_failed_dev++;
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 1386c713885d..6f1ec4fb7ef8 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -17,8 +17,6 @@
 #include <linux/workqueue.h>
 #include <uapi/linux/thermal.h>
 
-#define THERMAL_MAX_TRIPS	12
-
 /* invalid cooling state */
 #define THERMAL_CSTATE_INVALID -1UL
 
@@ -296,82 +294,53 @@ struct thermal_zone_params {
 	int offset;
 };
 
-/**
- * struct thermal_zone_of_device_ops - callbacks for handling DT based zones
- *
- * Mandatory:
- * @get_temp: a pointer to a function that reads the sensor temperature.
- *
- * Optional:
- * @get_trend: a pointer to a function that reads the sensor temperature trend.
- * @set_trips: a pointer to a function that sets a temperature window. When
- *	       this window is left the driver must inform the thermal core via
- *	       thermal_zone_device_update.
- * @set_emul_temp: a pointer to a function that sets sensor emulated
- *		   temperature.
- * @set_trip_temp: a pointer to a function that sets the trip temperature on
- *		   hardware.
- * @change_mode: a pointer to a function that notifies the thermal zone
- *		   mode change.
- */
-struct thermal_zone_of_device_ops {
-	int (*get_temp)(void *, int *);
-	int (*get_trend)(void *, int, enum thermal_trend *);
-	int (*set_trips)(void *, int, int);
-	int (*set_emul_temp)(void *, int);
-	int (*set_trip_temp)(void *, int, int);
-	int (*change_mode) (void *, enum thermal_device_mode);
-};
-
 /* Function declarations */
 #ifdef CONFIG_THERMAL_OF
+struct thermal_zone_device *thermal_of_zone_register(struct device_node *sensor, int id, void *data,
+						     const struct thermal_zone_device_ops *ops);
+
+struct thermal_zone_device *devm_thermal_of_zone_register(struct device *dev, int id, void *data,
+							  const struct thermal_zone_device_ops *ops);
+
+void thermal_of_zone_unregister(struct thermal_zone_device *tz);
+
+void devm_thermal_of_zone_unregister(struct device *dev, struct thermal_zone_device *tz);
+
+void thermal_of_zone_unregister(struct thermal_zone_device *tz);
+
 int thermal_zone_of_get_sensor_id(struct device_node *tz_np,
 				  struct device_node *sensor_np,
 				  u32 *id);
-struct thermal_zone_device *
-thermal_zone_of_sensor_register(struct device *dev, int id, void *data,
-				const struct thermal_zone_of_device_ops *ops);
-void thermal_zone_of_sensor_unregister(struct device *dev,
-				       struct thermal_zone_device *tz);
-struct thermal_zone_device *devm_thermal_zone_of_sensor_register(
-		struct device *dev, int id, void *data,
-		const struct thermal_zone_of_device_ops *ops);
-void devm_thermal_zone_of_sensor_unregister(struct device *dev,
-					    struct thermal_zone_device *tz);
 #else
-
-static inline int thermal_zone_of_get_sensor_id(struct device_node *tz_np,
-					 struct device_node *sensor_np,
-					 u32 *id)
-{
-	return -ENOENT;
-}
-static inline struct thermal_zone_device *
-thermal_zone_of_sensor_register(struct device *dev, int id, void *data,
-				const struct thermal_zone_of_device_ops *ops)
+static inline
+struct thermal_zone_device *thermal_of_zone_register(struct device_node *sensor, int id, void *data,
+						     const struct thermal_zone_device_ops *ops)
 {
-	return ERR_PTR(-ENODEV);
+	return ERR_PTR(-ENOTSUPP);
 }
 
 static inline
-void thermal_zone_of_sensor_unregister(struct device *dev,
-				       struct thermal_zone_device *tz)
+struct thermal_zone_device *devm_thermal_of_zone_register(struct device *dev, int id, void *data,
+							  const struct thermal_zone_device_ops *ops)
 {
+	return ERR_PTR(-ENOTSUPP);
 }
 
-static inline struct thermal_zone_device *devm_thermal_zone_of_sensor_register(
-		struct device *dev, int id, void *data,
-		const struct thermal_zone_of_device_ops *ops)
+static inline void thermal_of_zone_unregister(struct thermal_zone_device *tz)
 {
-	return ERR_PTR(-ENODEV);
 }
 
-static inline
-void devm_thermal_zone_of_sensor_unregister(struct device *dev,
-					    struct thermal_zone_device *tz)
+static inline void devm_thermal_of_zone_unregister(struct device *dev,
+						   struct thermal_zone_device *tz)
 {
 }
 
+static inline int thermal_zone_of_get_sensor_id(struct device_node *tz_np,
+						struct device_node *sensor_np,
+						u32 *id)
+{
+	return -ENOENT;
+}
 #endif
 
 #ifdef CONFIG_THERMAL
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index b18759a673c6..8401dec93c15 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -814,8 +814,6 @@ extern int trace_add_event_call(struct trace_event_call *call);
 extern int trace_remove_event_call(struct trace_event_call *call);
 extern int trace_event_get_offsets(struct trace_event_call *call);
 
-#define is_signed_type(type)	(((type)(-1)) < (type)1)
-
 int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set);
 int trace_set_clr_event(const char *system, const char *event, int set);
 int trace_array_set_clr_event(struct trace_array *tr, const char *system,
diff --git a/include/linux/udp.h b/include/linux/udp.h
index 254a2654400f..e96da4157d04 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -70,6 +70,7 @@ struct udp_sock {
 	 * For encapsulation sockets.
 	 */
 	int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
+	void (*encap_err_rcv)(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset);
 	int (*encap_err_lookup)(struct sock *sk, struct sk_buff *skb);
 	void (*encap_destroy)(struct sock *sk);
 
diff --git a/include/linux/usb.h b/include/linux/usb.h
index f7a9914fc97f..9ff1ad4dfad1 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -575,6 +575,7 @@ struct usb3_lpm_parameters {
  * @devaddr: device address, XHCI: assigned by HW, others: same as devnum
  * @can_submit: URBs may be submitted
  * @persist_enabled:  USB_PERSIST enabled for this device
+ * @reset_in_progress: the device is being reset
  * @have_langid: whether string_langid is valid
  * @authorized: policy has said we can use it;
  *	(user space) policy determines if we authorize this device to be
@@ -662,6 +663,7 @@ struct usb_device {
 
 	unsigned can_submit:1;
 	unsigned persist_enabled:1;
+	unsigned reset_in_progress:1;
 	unsigned have_langid:1;
 	unsigned authorized:1;
 	unsigned authenticated:1;
diff --git a/include/linux/usb/typec_dp.h b/include/linux/usb/typec_dp.h
index cfb916cccd31..8d09c2f0a9b8 100644
--- a/include/linux/usb/typec_dp.h
+++ b/include/linux/usb/typec_dp.h
@@ -73,6 +73,11 @@ enum {
 #define DP_CAP_USB			BIT(7)
 #define DP_CAP_DFP_D_PIN_ASSIGN(_cap_)	(((_cap_) & GENMASK(15, 8)) >> 8)
 #define DP_CAP_UFP_D_PIN_ASSIGN(_cap_)	(((_cap_) & GENMASK(23, 16)) >> 16)
+/* Get pin assignment taking plug & receptacle into consideration */
+#define DP_CAP_PIN_ASSIGN_UFP_D(_cap_) ((_cap_ & DP_CAP_RECEPTACLE) ? \
+			DP_CAP_UFP_D_PIN_ASSIGN(_cap_) : DP_CAP_DFP_D_PIN_ASSIGN(_cap_))
+#define DP_CAP_PIN_ASSIGN_DFP_D(_cap_) ((_cap_ & DP_CAP_RECEPTACLE) ? \
+			DP_CAP_DFP_D_PIN_ASSIGN(_cap_) : DP_CAP_UFP_D_PIN_ASSIGN(_cap_))
 
 /* DisplayPort Status Update VDO bits */
 #define DP_STATUS_CONNECTION(_status_)	((_status_) & 3)
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 732b522bacb7..e1b8a915e9e9 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -73,6 +73,8 @@ extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start,
 extern int mwriteprotect_range(struct mm_struct *dst_mm,
 			       unsigned long start, unsigned long len,
 			       bool enable_wp, atomic_t *mmap_changing);
+extern void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma,
+			  unsigned long start, unsigned long len, bool enable_wp);
 
 /* mm helpers */
 static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index a3f73bb6733e..dcab9c7e8784 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -11,7 +11,7 @@
 #include <linux/gfp.h>
 
 /**
- * virtqueue - a queue to register buffers for sending or receiving.
+ * struct virtqueue - a queue to register buffers for sending or receiving.
  * @list: the chain of virtqueues for this device
  * @callback: the function to call when buffers are consumed (can be NULL).
  * @name: the name of this virtqueue (mainly for debugging)
@@ -97,7 +97,7 @@ int virtqueue_resize(struct virtqueue *vq, u32 num,
 		     void (*recycle)(struct virtqueue *vq, void *buf));
 
 /**
- * virtio_device - representation of a device using virtio
+ * struct virtio_device - representation of a device using virtio
  * @index: unique position on the virtio bus
  * @failed: saved value for VIRTIO_CONFIG_S_FAILED bit (for restore)
  * @config_enabled: configuration change reporting enabled
@@ -156,7 +156,7 @@ size_t virtio_max_dma_size(struct virtio_device *vdev);
 	list_for_each_entry(vq, &vdev->vqs, list)
 
 /**
- * virtio_driver - operations for a virtio I/O driver
+ * struct virtio_driver - operations for a virtio I/O driver
  * @driver: underlying device driver (populate name and owner).
  * @id_table: the ids serviced by this driver.
  * @feature_table: an array of feature numbers supported by this driver.
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 6adff09f7170..4b517649cfe8 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -55,7 +55,6 @@ struct virtio_shm_region {
  *		include a NULL entry for vqs that do not need a callback
  *	names: array of virtqueue names (mainly for debugging)
  *		include a NULL entry for vqs unused by driver
- *	sizes: array of virtqueue sizes
  *	Returns 0 on success or error status
  * @del_vqs: free virtqueues found by find_vqs().
  * @synchronize_cbs: synchronize with the virtqueue callbacks (optional)
@@ -104,9 +103,7 @@ struct virtio_config_ops {
 	void (*reset)(struct virtio_device *vdev);
 	int (*find_vqs)(struct virtio_device *, unsigned nvqs,
 			struct virtqueue *vqs[], vq_callback_t *callbacks[],
-			const char * const names[],
-			u32 sizes[],
-			const bool *ctx,
+			const char * const names[], const bool *ctx,
 			struct irq_affinity *desc);
 	void (*del_vqs)(struct virtio_device *);
 	void (*synchronize_cbs)(struct virtio_device *);
@@ -215,7 +212,7 @@ struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev,
 	const char *names[] = { n };
 	struct virtqueue *vq;
 	int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names, NULL,
-					 NULL, NULL);
+					 NULL);
 	if (err < 0)
 		return ERR_PTR(err);
 	return vq;
@@ -227,8 +224,7 @@ int virtio_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 			const char * const names[],
 			struct irq_affinity *desc)
 {
-	return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL,
-				      NULL, desc);
+	return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL, desc);
 }
 
 static inline
@@ -237,25 +233,13 @@ int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs,
 			const char * const names[], const bool *ctx,
 			struct irq_affinity *desc)
 {
-	return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL,
-				      ctx, desc);
-}
-
-static inline
-int virtio_find_vqs_ctx_size(struct virtio_device *vdev, u32 nvqs,
-			     struct virtqueue *vqs[],
-			     vq_callback_t *callbacks[],
-			     const char * const names[],
-			     u32 sizes[],
-			     const bool *ctx, struct irq_affinity *desc)
-{
-	return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, sizes,
-				      ctx, desc);
+	return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, ctx,
+				      desc);
 }
 
 /**
  * virtio_synchronize_cbs - synchronize with virtqueue callbacks
- * @vdev: the device
+ * @dev: the virtio device
  */
 static inline
 void virtio_synchronize_cbs(struct virtio_device *dev)
@@ -274,7 +258,7 @@ void virtio_synchronize_cbs(struct virtio_device *dev)
 
 /**
  * virtio_device_ready - enable vq use in probe function
- * @vdev: the device
+ * @dev: the virtio device
  *
  * Driver must call this to use vqs in the probe function.
  *
@@ -322,7 +306,7 @@ const char *virtio_bus_name(struct virtio_device *vdev)
 /**
  * virtqueue_set_affinity - setting affinity for a virtqueue
  * @vq: the virtqueue
- * @cpu: the cpu no.
+ * @cpu_mask: the cpu mask
  *
  * Pay attention the function are best-effort: the affinity hint may not be set
  * due to config support, irq type and sharing.
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 404024486fa5..f3fc36cd2276 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -20,12 +20,19 @@
 #define HIGHMEM_ZONE(xx)
 #endif
 
-#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL, HIGHMEM_ZONE(xx) xx##_MOVABLE
+#ifdef CONFIG_ZONE_DEVICE
+#define DEVICE_ZONE(xx) xx##_DEVICE,
+#else
+#define DEVICE_ZONE(xx)
+#endif
+
+#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL, \
+	HIGHMEM_ZONE(xx) xx##_MOVABLE, DEVICE_ZONE(xx)
 
 enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
-		FOR_ALL_ZONES(PGALLOC),
-		FOR_ALL_ZONES(ALLOCSTALL),
-		FOR_ALL_ZONES(PGSCAN_SKIP),
+		FOR_ALL_ZONES(PGALLOC)
+		FOR_ALL_ZONES(ALLOCSTALL)
+		FOR_ALL_ZONES(PGSCAN_SKIP)
 		PGFREE, PGACTIVATE, PGDEACTIVATE, PGLAZYFREE,
 		PGFAULT, PGMAJFAULT,
 		PGLAZYFREED,
diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h
index 7dec36aecbd9..7725b7579b78 100644
--- a/include/linux/wait_bit.h
+++ b/include/linux/wait_bit.h
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index 979a9d3e5bfb..4c379d23ec6e 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -61,7 +61,7 @@ int __vfs_setxattr_locked(struct user_namespace *, struct dentry *,
 			  const char *, const void *, size_t, int,
 			  struct inode **);
 int vfs_setxattr(struct user_namespace *, struct dentry *, const char *,
-		 void *, size_t, int);
+		 const void *, size_t, int);
 int __vfs_removexattr(struct user_namespace *, struct dentry *, const char *);
 int __vfs_removexattr_locked(struct user_namespace *, struct dentry *,
 			     const char *, struct inode **);
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index cee5f83c0f11..b69ca695935c 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -66,8 +66,6 @@ int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t,
 void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64);
 bool rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *);
 u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *);
-bool rxrpc_kernel_get_reply_time(struct socket *, struct rxrpc_call *,
-				 ktime_t *);
 bool rxrpc_kernel_call_is_complete(struct rxrpc_call *);
 void rxrpc_kernel_set_max_life(struct socket *, struct rxrpc_call *,
 			       unsigned long);
diff --git a/include/net/bluetooth/hci_sock.h b/include/net/bluetooth/hci_sock.h
index 0520e21ab698..9949870f7d78 100644
--- a/include/net/bluetooth/hci_sock.h
+++ b/include/net/bluetooth/hci_sock.h
@@ -124,8 +124,6 @@ struct hci_dev_info {
 	__u16 acl_pkts;
 	__u16 sco_mtu;
 	__u16 sco_pkts;
-	__u16 iso_mtu;
-	__u16 iso_pkts;
 
 	struct hci_dev_stats stat;
 };
diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h
index 184105d68294..a016f275cb01 100644
--- a/include/net/bond_3ad.h
+++ b/include/net/bond_3ad.h
@@ -15,8 +15,6 @@
 #define PKT_TYPE_LACPDU         cpu_to_be16(ETH_P_SLOW)
 #define AD_TIMER_INTERVAL       100 /*msec*/
 
-#define MULTICAST_LACPDU_ADDR    {0x01, 0x80, 0xC2, 0x00, 0x00, 0x02}
-
 #define AD_LACP_SLOW 0
 #define AD_LACP_FAST 1
 
@@ -290,7 +288,7 @@ static inline const char *bond_3ad_churn_desc(churn_state_t state)
 }
 
 /* ========== AD Exported functions to the main bonding code ========== */
-void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution);
+void bond_3ad_initialize(struct bonding *bond);
 void bond_3ad_bind_slave(struct slave *slave);
 void bond_3ad_unbind_slave(struct slave *slave);
 void bond_3ad_state_machine_handler(struct work_struct *);
diff --git a/include/net/bonding.h b/include/net/bonding.h
index afd606df149a..e999f851738b 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -786,6 +786,9 @@ extern struct rtnl_link_ops bond_link_ops;
 /* exported from bond_sysfs_slave.c */
 extern const struct sysfs_ops slave_sysfs_ops;
 
+/* exported from bond_3ad.c */
+extern const u8 lacpdu_mcast_addr[];
+
 static inline netdev_tx_t bond_tx_drop(struct net_device *dev, struct sk_buff *skb)
 {
 	dev_core_stats_tx_dropped_inc(dev);
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index c4898fcbf923..f90f0021f5f2 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -33,7 +33,7 @@ extern unsigned int sysctl_net_busy_poll __read_mostly;
 
 static inline bool net_busy_loop_on(void)
 {
-	return sysctl_net_busy_poll;
+	return READ_ONCE(sysctl_net_busy_poll);
 }
 
 static inline bool sk_can_busy_loop(const struct sock *sk)
diff --git a/include/net/dropreason.h b/include/net/dropreason.h
index fae9b40e54fa..c1cbcdbaf149 100644
--- a/include/net/dropreason.h
+++ b/include/net/dropreason.h
@@ -3,6 +3,73 @@
 #ifndef _LINUX_DROPREASON_H
 #define _LINUX_DROPREASON_H
 
+#define DEFINE_DROP_REASON(FN, FNe)	\
+	FN(NOT_SPECIFIED)		\
+	FN(NO_SOCKET)			\
+	FN(PKT_TOO_SMALL)		\
+	FN(TCP_CSUM)			\
+	FN(SOCKET_FILTER)		\
+	FN(UDP_CSUM)			\
+	FN(NETFILTER_DROP)		\
+	FN(OTHERHOST)			\
+	FN(IP_CSUM)			\
+	FN(IP_INHDR)			\
+	FN(IP_RPFILTER)			\
+	FN(UNICAST_IN_L2_MULTICAST)	\
+	FN(XFRM_POLICY)			\
+	FN(IP_NOPROTO)			\
+	FN(SOCKET_RCVBUFF)		\
+	FN(PROTO_MEM)			\
+	FN(TCP_MD5NOTFOUND)		\
+	FN(TCP_MD5UNEXPECTED)		\
+	FN(TCP_MD5FAILURE)		\
+	FN(SOCKET_BACKLOG)		\
+	FN(TCP_FLAGS)			\
+	FN(TCP_ZEROWINDOW)		\
+	FN(TCP_OLD_DATA)		\
+	FN(TCP_OVERWINDOW)		\
+	FN(TCP_OFOMERGE)		\
+	FN(TCP_RFC7323_PAWS)		\
+	FN(TCP_INVALID_SEQUENCE)	\
+	FN(TCP_RESET)			\
+	FN(TCP_INVALID_SYN)		\
+	FN(TCP_CLOSE)			\
+	FN(TCP_FASTOPEN)		\
+	FN(TCP_OLD_ACK)			\
+	FN(TCP_TOO_OLD_ACK)		\
+	FN(TCP_ACK_UNSENT_DATA)		\
+	FN(TCP_OFO_QUEUE_PRUNE)		\
+	FN(TCP_OFO_DROP)		\
+	FN(IP_OUTNOROUTES)		\
+	FN(BPF_CGROUP_EGRESS)		\
+	FN(IPV6DISABLED)		\
+	FN(NEIGH_CREATEFAIL)		\
+	FN(NEIGH_FAILED)		\
+	FN(NEIGH_QUEUEFULL)		\
+	FN(NEIGH_DEAD)			\
+	FN(TC_EGRESS)			\
+	FN(QDISC_DROP)			\
+	FN(CPU_BACKLOG)			\
+	FN(XDP)				\
+	FN(TC_INGRESS)			\
+	FN(UNHANDLED_PROTO)		\
+	FN(SKB_CSUM)			\
+	FN(SKB_GSO_SEG)			\
+	FN(SKB_UCOPY_FAULT)		\
+	FN(DEV_HDR)			\
+	FN(DEV_READY)			\
+	FN(FULL_RING)			\
+	FN(NOMEM)			\
+	FN(HDR_TRUNC)			\
+	FN(TAP_FILTER)			\
+	FN(TAP_TXFILTER)		\
+	FN(ICMP_CSUM)			\
+	FN(INVALID_PROTO)		\
+	FN(IP_INADDRERRORS)		\
+	FN(IP_INNOROUTES)		\
+	FN(PKT_TOO_BIG)			\
+	FNe(MAX)
+
 /**
  * enum skb_drop_reason - the reasons of skb drops
  *
diff --git a/include/net/gro.h b/include/net/gro.h
index 867656b0739c..24003dea8fa4 100644
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -439,7 +439,7 @@ static inline void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb,
 {
 	list_add_tail(&skb->list, &napi->rx_list);
 	napi->rx_count += segs;
-	if (napi->rx_count >= gro_normal_batch)
+	if (napi->rx_count >= READ_ONCE(gro_normal_batch))
 		gro_normal_list(napi);
 }
 
diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h
index d0d188c3294b..a8994f307fc3 100644
--- a/include/net/ieee802154_netdev.h
+++ b/include/net/ieee802154_netdev.h
@@ -15,6 +15,22 @@
 #ifndef IEEE802154_NETDEVICE_H
 #define IEEE802154_NETDEVICE_H
 
+#define IEEE802154_REQUIRED_SIZE(struct_type, member) \
+	(offsetof(typeof(struct_type), member) + \
+	sizeof(((typeof(struct_type) *)(NULL))->member))
+
+#define IEEE802154_ADDR_OFFSET \
+	offsetof(typeof(struct sockaddr_ieee802154), addr)
+
+#define IEEE802154_MIN_NAMELEN (IEEE802154_ADDR_OFFSET + \
+	IEEE802154_REQUIRED_SIZE(struct ieee802154_addr_sa, addr_type))
+
+#define IEEE802154_NAMELEN_SHORT (IEEE802154_ADDR_OFFSET + \
+	IEEE802154_REQUIRED_SIZE(struct ieee802154_addr_sa, short_addr))
+
+#define IEEE802154_NAMELEN_LONG (IEEE802154_ADDR_OFFSET + \
+	IEEE802154_REQUIRED_SIZE(struct ieee802154_addr_sa, hwaddr))
+
 #include <net/af_ieee802154.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
@@ -165,6 +181,27 @@ static inline void ieee802154_devaddr_to_raw(void *raw, __le64 addr)
 	memcpy(raw, &temp, IEEE802154_ADDR_LEN);
 }
 
+static inline int
+ieee802154_sockaddr_check_size(struct sockaddr_ieee802154 *daddr, int len)
+{
+	struct ieee802154_addr_sa *sa;
+
+	sa = &daddr->addr;
+	if (len < IEEE802154_MIN_NAMELEN)
+		return -EINVAL;
+	switch (sa->addr_type) {
+	case IEEE802154_ADDR_SHORT:
+		if (len < IEEE802154_NAMELEN_SHORT)
+			return -EINVAL;
+		break;
+	case IEEE802154_ADDR_LONG:
+		if (len < IEEE802154_NAMELEN_LONG)
+			return -EINVAL;
+		break;
+	}
+	return 0;
+}
+
 static inline void ieee802154_addr_from_sa(struct ieee802154_addr *a,
 					   const struct ieee802154_addr_sa *sa)
 {
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 63fac94f9ace..ced80e2f8b58 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -246,7 +246,8 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4,
 				       __be32 daddr, __be32 saddr,
 				       __be32 key, __u8 tos,
 				       struct net *net, int oif,
-				       __u32 mark, __u32 tun_inner_hash)
+				       __u32 mark, __u32 tun_inner_hash,
+				       __u8 flow_flags)
 {
 	memset(fl4, 0, sizeof(*fl4));
 
@@ -263,6 +264,7 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4,
 	fl4->fl4_gre_key = key;
 	fl4->flowi4_mark = mark;
 	fl4->flowi4_multipath_hash = tun_inner_hash;
+	fl4->flowi4_flags = flow_flags;
 }
 
 int ip_tunnel_init(struct net_device *dev);
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 9f0bab0589d9..3827a6b395fd 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -83,6 +83,7 @@ struct neigh_parms {
 	struct rcu_head rcu_head;
 
 	int	reachable_time;
+	int	qlen;
 	int	data[NEIGH_VAR_DATA_MAX];
 	DECLARE_BITMAP(data_state, NEIGH_VAR_DATA_MAX);
 };
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index a32be8aa7ed2..6a2019aaa464 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -53,8 +53,6 @@ struct nf_conntrack_net {
 	/* only used when new connection is allocated: */
 	atomic_t count;
 	unsigned int expect_count;
-	u8 sysctl_auto_assign_helper;
-	bool auto_assign_helper_warned;
 
 	/* only used from work queues, configuration plane, and so on: */
 	unsigned int users4;
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index d5326c44b453..cd982f4a0f50 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -270,6 +270,7 @@ void flow_offload_refresh(struct nf_flowtable *flow_table,
 
 struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table,
 						     struct flow_offload_tuple *tuple);
+void nf_flow_table_gc_run(struct nf_flowtable *flow_table);
 void nf_flow_table_gc_cleanup(struct nf_flowtable *flowtable,
 			      struct net_device *dev);
 void nf_flow_table_cleanup(struct net_device *dev);
@@ -306,6 +307,8 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable,
 			   struct flow_offload *flow);
 
 void nf_flow_table_offload_flush(struct nf_flowtable *flowtable);
+void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable);
+
 int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
 				struct net_device *dev,
 				enum flow_block_command cmd);
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 99aae36c04b9..cdb7db9b0e25 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1652,6 +1652,7 @@ struct nftables_pernet {
 	struct list_head	module_list;
 	struct list_head	notify_list;
 	struct mutex		commit_mutex;
+	u64			table_handle;
 	unsigned int		base_seq;
 	u8			validate_state;
 };
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 0677cd3de034..e1290c159184 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -95,13 +95,12 @@ struct nf_ip_net {
 
 struct netns_ct {
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
-	bool ctnetlink_has_listener;
+	u8 ctnetlink_has_listener;
 	bool ecache_dwork_pending;
 #endif
 	u8			sysctl_log_invalid; /* Log invalid packets */
 	u8			sysctl_events;
 	u8			sysctl_acct;
-	u8			sysctl_auto_assign_helper;
 	u8			sysctl_tstamp;
 	u8			sysctl_checksum;
 
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index c7320ef356d9..6320a76cefdc 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -179,6 +179,8 @@ struct netns_ipv4 {
 	unsigned int sysctl_tcp_fastopen_blackhole_timeout;
 	atomic_t tfo_active_disable_times;
 	unsigned long tfo_active_disable_stamp;
+	u32 tcp_challenge_timestamp;
+	u32 tcp_challenge_count;
 
 	int sysctl_udp_wmem_min;
 	int sysctl_udp_rmem_min;
diff --git a/include/net/sock.h b/include/net/sock.h
index 05a1bbdf5805..d08cfe190a78 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -578,6 +578,31 @@ static inline bool sk_user_data_is_nocopy(const struct sock *sk)
 #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))
 
 /**
+ * __locked_read_sk_user_data_with_flags - return the pointer
+ * only if argument flags all has been set in sk_user_data. Otherwise
+ * return NULL
+ *
+ * @sk: socket
+ * @flags: flag bits
+ *
+ * The caller must be holding sk->sk_callback_lock.
+ */
+static inline void *
+__locked_read_sk_user_data_with_flags(const struct sock *sk,
+				      uintptr_t flags)
+{
+	uintptr_t sk_user_data =
+		(uintptr_t)rcu_dereference_check(__sk_user_data(sk),
+						 lockdep_is_held(&sk->sk_callback_lock));
+
+	WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK);
+
+	if ((sk_user_data & flags) == flags)
+		return (void *)(sk_user_data & SK_USER_DATA_PTRMASK);
+	return NULL;
+}
+
+/**
  * __rcu_dereference_sk_user_data_with_flags - return the pointer
  * only if argument flags all has been set in sk_user_data. Otherwise
  * return NULL
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index afc7ce713657..72394f441dad 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -67,6 +67,9 @@ static inline int udp_sock_create(struct net *net,
 typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
 typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk,
 					     struct sk_buff *skb);
+typedef void (*udp_tunnel_encap_err_rcv_t)(struct sock *sk,
+					   struct sk_buff *skb,
+					   unsigned int udp_offset);
 typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
 typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk,
 						    struct list_head *head,
@@ -80,6 +83,7 @@ struct udp_tunnel_sock_cfg {
 	__u8  encap_type;
 	udp_tunnel_encap_rcv_t encap_rcv;
 	udp_tunnel_encap_err_lookup_t encap_err_lookup;
+	udp_tunnel_encap_err_rcv_t encap_err_rcv;
 	udp_tunnel_encap_destroy_t encap_destroy;
 	udp_tunnel_gro_receive_t gro_receive;
 	udp_tunnel_gro_complete_t gro_complete;
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 3113471ca375..2493bd65351a 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -309,8 +309,6 @@ struct scsi_target {
 	struct list_head	devices;
 	struct device		dev;
 	struct kref		reap_ref; /* last put renders target invisible */
-	atomic_t		sdev_count;
-	wait_queue_head_t	sdev_wq;
 	unsigned int		channel;
 	unsigned int		id; /* target id ... replace
 				     * scsi_device.id eventually */
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index aa7b7496c93a..9b0a028bf053 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -557,6 +557,8 @@ struct Scsi_Host {
 	struct scsi_host_template *hostt;
 	struct scsi_transport_template *transportt;
 
+	struct kref		tagset_refcnt;
+	struct completion	tagset_freed;
 	/* Area to keep a shared tag map */
 	struct blk_mq_tag_set	tag_set;
 
@@ -690,9 +692,6 @@ struct Scsi_Host {
 	/* ldm bits */
 	struct device		shost_gendev, shost_dev;
 
-	atomic_t		target_count;
-	wait_queue_head_t	targets_wq;
-
 	/*
 	 * Points to the transport data (if any) which is allocated
 	 * separately
diff --git a/include/soc/at91/sama7-ddr.h b/include/soc/at91/sama7-ddr.h
index 9e17247474fa..6ce3bd22f6c6 100644
--- a/include/soc/at91/sama7-ddr.h
+++ b/include/soc/at91/sama7-ddr.h
@@ -38,6 +38,14 @@
 #define		DDR3PHY_DSGCR_ODTPDD_ODT0	(1 << 20)	/* ODT[0] Power Down Driver */
 
 #define DDR3PHY_ZQ0SR0				(0x188)		/* ZQ status register 0 */
+#define DDR3PHY_ZQ0SR0_PDO_OFF			(0)		/* Pull-down output impedance select offset */
+#define DDR3PHY_ZQ0SR0_PUO_OFF			(5)		/* Pull-up output impedance select offset */
+#define DDR3PHY_ZQ0SR0_PDODT_OFF		(10)		/* Pull-down on-die termination impedance select offset */
+#define DDR3PHY_ZQ0SRO_PUODT_OFF		(15)		/* Pull-up on-die termination impedance select offset */
+
+#define	DDR3PHY_DX0DLLCR			(0x1CC)		/* DDR3PHY DATX8 DLL Control Register */
+#define	DDR3PHY_DX1DLLCR			(0x20C)		/* DDR3PHY DATX8 DLL Control Register */
+#define		DDR3PHY_DXDLLCR_DLLDIS		(1 << 31)	/* DLL Disable */
 
 /* UDDRC */
 #define UDDRC_STAT				(0x04)		/* UDDRC Operating Mode Status Register */
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index ac151ecc7f19..2edea901bbd5 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -105,11 +105,6 @@
 #define REG_RESERVED_ADDR		0xffffffff
 #define REG_RESERVED(reg)		REG(reg, REG_RESERVED_ADDR)
 
-#define for_each_stat(ocelot, stat)				\
-	for ((stat) = (ocelot)->stats_layout;			\
-	     ((stat)->name[0] != '\0');				\
-	     (stat)++)
-
 enum ocelot_target {
 	ANA = 1,
 	QS,
@@ -335,13 +330,38 @@ enum ocelot_reg {
 	SYS_COUNT_RX_64,
 	SYS_COUNT_RX_65_127,
 	SYS_COUNT_RX_128_255,
-	SYS_COUNT_RX_256_1023,
+	SYS_COUNT_RX_256_511,
+	SYS_COUNT_RX_512_1023,
 	SYS_COUNT_RX_1024_1526,
 	SYS_COUNT_RX_1527_MAX,
 	SYS_COUNT_RX_PAUSE,
 	SYS_COUNT_RX_CONTROL,
 	SYS_COUNT_RX_LONGS,
 	SYS_COUNT_RX_CLASSIFIED_DROPS,
+	SYS_COUNT_RX_RED_PRIO_0,
+	SYS_COUNT_RX_RED_PRIO_1,
+	SYS_COUNT_RX_RED_PRIO_2,
+	SYS_COUNT_RX_RED_PRIO_3,
+	SYS_COUNT_RX_RED_PRIO_4,
+	SYS_COUNT_RX_RED_PRIO_5,
+	SYS_COUNT_RX_RED_PRIO_6,
+	SYS_COUNT_RX_RED_PRIO_7,
+	SYS_COUNT_RX_YELLOW_PRIO_0,
+	SYS_COUNT_RX_YELLOW_PRIO_1,
+	SYS_COUNT_RX_YELLOW_PRIO_2,
+	SYS_COUNT_RX_YELLOW_PRIO_3,
+	SYS_COUNT_RX_YELLOW_PRIO_4,
+	SYS_COUNT_RX_YELLOW_PRIO_5,
+	SYS_COUNT_RX_YELLOW_PRIO_6,
+	SYS_COUNT_RX_YELLOW_PRIO_7,
+	SYS_COUNT_RX_GREEN_PRIO_0,
+	SYS_COUNT_RX_GREEN_PRIO_1,
+	SYS_COUNT_RX_GREEN_PRIO_2,
+	SYS_COUNT_RX_GREEN_PRIO_3,
+	SYS_COUNT_RX_GREEN_PRIO_4,
+	SYS_COUNT_RX_GREEN_PRIO_5,
+	SYS_COUNT_RX_GREEN_PRIO_6,
+	SYS_COUNT_RX_GREEN_PRIO_7,
 	SYS_COUNT_TX_OCTETS,
 	SYS_COUNT_TX_UNICAST,
 	SYS_COUNT_TX_MULTICAST,
@@ -351,11 +371,46 @@ enum ocelot_reg {
 	SYS_COUNT_TX_PAUSE,
 	SYS_COUNT_TX_64,
 	SYS_COUNT_TX_65_127,
-	SYS_COUNT_TX_128_511,
+	SYS_COUNT_TX_128_255,
+	SYS_COUNT_TX_256_511,
 	SYS_COUNT_TX_512_1023,
 	SYS_COUNT_TX_1024_1526,
 	SYS_COUNT_TX_1527_MAX,
+	SYS_COUNT_TX_YELLOW_PRIO_0,
+	SYS_COUNT_TX_YELLOW_PRIO_1,
+	SYS_COUNT_TX_YELLOW_PRIO_2,
+	SYS_COUNT_TX_YELLOW_PRIO_3,
+	SYS_COUNT_TX_YELLOW_PRIO_4,
+	SYS_COUNT_TX_YELLOW_PRIO_5,
+	SYS_COUNT_TX_YELLOW_PRIO_6,
+	SYS_COUNT_TX_YELLOW_PRIO_7,
+	SYS_COUNT_TX_GREEN_PRIO_0,
+	SYS_COUNT_TX_GREEN_PRIO_1,
+	SYS_COUNT_TX_GREEN_PRIO_2,
+	SYS_COUNT_TX_GREEN_PRIO_3,
+	SYS_COUNT_TX_GREEN_PRIO_4,
+	SYS_COUNT_TX_GREEN_PRIO_5,
+	SYS_COUNT_TX_GREEN_PRIO_6,
+	SYS_COUNT_TX_GREEN_PRIO_7,
 	SYS_COUNT_TX_AGING,
+	SYS_COUNT_DROP_LOCAL,
+	SYS_COUNT_DROP_TAIL,
+	SYS_COUNT_DROP_YELLOW_PRIO_0,
+	SYS_COUNT_DROP_YELLOW_PRIO_1,
+	SYS_COUNT_DROP_YELLOW_PRIO_2,
+	SYS_COUNT_DROP_YELLOW_PRIO_3,
+	SYS_COUNT_DROP_YELLOW_PRIO_4,
+	SYS_COUNT_DROP_YELLOW_PRIO_5,
+	SYS_COUNT_DROP_YELLOW_PRIO_6,
+	SYS_COUNT_DROP_YELLOW_PRIO_7,
+	SYS_COUNT_DROP_GREEN_PRIO_0,
+	SYS_COUNT_DROP_GREEN_PRIO_1,
+	SYS_COUNT_DROP_GREEN_PRIO_2,
+	SYS_COUNT_DROP_GREEN_PRIO_3,
+	SYS_COUNT_DROP_GREEN_PRIO_4,
+	SYS_COUNT_DROP_GREEN_PRIO_5,
+	SYS_COUNT_DROP_GREEN_PRIO_6,
+	SYS_COUNT_DROP_GREEN_PRIO_7,
 	SYS_RESET_CFG,
 	SYS_SR_ETYPE_CFG,
 	SYS_VLAN_ETYPE_CFG,
@@ -538,16 +593,111 @@ enum ocelot_ptp_pins {
 	TOD_ACC_PIN
 };
 
+enum ocelot_stat {
+	OCELOT_STAT_RX_OCTETS,
+	OCELOT_STAT_RX_UNICAST,
+	OCELOT_STAT_RX_MULTICAST,
+	OCELOT_STAT_RX_BROADCAST,
+	OCELOT_STAT_RX_SHORTS,
+	OCELOT_STAT_RX_FRAGMENTS,
+	OCELOT_STAT_RX_JABBERS,
+	OCELOT_STAT_RX_CRC_ALIGN_ERRS,
+	OCELOT_STAT_RX_SYM_ERRS,
+	OCELOT_STAT_RX_64,
+	OCELOT_STAT_RX_65_127,
+	OCELOT_STAT_RX_128_255,
+	OCELOT_STAT_RX_256_511,
+	OCELOT_STAT_RX_512_1023,
+	OCELOT_STAT_RX_1024_1526,
+	OCELOT_STAT_RX_1527_MAX,
+	OCELOT_STAT_RX_PAUSE,
+	OCELOT_STAT_RX_CONTROL,
+	OCELOT_STAT_RX_LONGS,
+	OCELOT_STAT_RX_CLASSIFIED_DROPS,
+	OCELOT_STAT_RX_RED_PRIO_0,
+	OCELOT_STAT_RX_RED_PRIO_1,
+	OCELOT_STAT_RX_RED_PRIO_2,
+	OCELOT_STAT_RX_RED_PRIO_3,
+	OCELOT_STAT_RX_RED_PRIO_4,
+	OCELOT_STAT_RX_RED_PRIO_5,
+	OCELOT_STAT_RX_RED_PRIO_6,
+	OCELOT_STAT_RX_RED_PRIO_7,
+	OCELOT_STAT_RX_YELLOW_PRIO_0,
+	OCELOT_STAT_RX_YELLOW_PRIO_1,
+	OCELOT_STAT_RX_YELLOW_PRIO_2,
+	OCELOT_STAT_RX_YELLOW_PRIO_3,
+	OCELOT_STAT_RX_YELLOW_PRIO_4,
+	OCELOT_STAT_RX_YELLOW_PRIO_5,
+	OCELOT_STAT_RX_YELLOW_PRIO_6,
+	OCELOT_STAT_RX_YELLOW_PRIO_7,
+	OCELOT_STAT_RX_GREEN_PRIO_0,
+	OCELOT_STAT_RX_GREEN_PRIO_1,
+	OCELOT_STAT_RX_GREEN_PRIO_2,
+	OCELOT_STAT_RX_GREEN_PRIO_3,
+	OCELOT_STAT_RX_GREEN_PRIO_4,
+	OCELOT_STAT_RX_GREEN_PRIO_5,
+	OCELOT_STAT_RX_GREEN_PRIO_6,
+	OCELOT_STAT_RX_GREEN_PRIO_7,
+	OCELOT_STAT_TX_OCTETS,
+	OCELOT_STAT_TX_UNICAST,
+	OCELOT_STAT_TX_MULTICAST,
+	OCELOT_STAT_TX_BROADCAST,
+	OCELOT_STAT_TX_COLLISION,
+	OCELOT_STAT_TX_DROPS,
+	OCELOT_STAT_TX_PAUSE,
+	OCELOT_STAT_TX_64,
+	OCELOT_STAT_TX_65_127,
+	OCELOT_STAT_TX_128_255,
+	OCELOT_STAT_TX_256_511,
+	OCELOT_STAT_TX_512_1023,
+	OCELOT_STAT_TX_1024_1526,
+	OCELOT_STAT_TX_1527_MAX,
+	OCELOT_STAT_TX_YELLOW_PRIO_0,
+	OCELOT_STAT_TX_YELLOW_PRIO_1,
+	OCELOT_STAT_TX_YELLOW_PRIO_2,
+	OCELOT_STAT_TX_YELLOW_PRIO_3,
+	OCELOT_STAT_TX_YELLOW_PRIO_4,
+	OCELOT_STAT_TX_YELLOW_PRIO_5,
+	OCELOT_STAT_TX_YELLOW_PRIO_6,
+	OCELOT_STAT_TX_YELLOW_PRIO_7,
+	OCELOT_STAT_TX_GREEN_PRIO_0,
+	OCELOT_STAT_TX_GREEN_PRIO_1,
+	OCELOT_STAT_TX_GREEN_PRIO_2,
+	OCELOT_STAT_TX_GREEN_PRIO_3,
+	OCELOT_STAT_TX_GREEN_PRIO_4,
+	OCELOT_STAT_TX_GREEN_PRIO_5,
+	OCELOT_STAT_TX_GREEN_PRIO_6,
+	OCELOT_STAT_TX_GREEN_PRIO_7,
+	OCELOT_STAT_TX_AGED,
+	OCELOT_STAT_DROP_LOCAL,
+	OCELOT_STAT_DROP_TAIL,
+	OCELOT_STAT_DROP_YELLOW_PRIO_0,
+	OCELOT_STAT_DROP_YELLOW_PRIO_1,
+	OCELOT_STAT_DROP_YELLOW_PRIO_2,
+	OCELOT_STAT_DROP_YELLOW_PRIO_3,
+	OCELOT_STAT_DROP_YELLOW_PRIO_4,
+	OCELOT_STAT_DROP_YELLOW_PRIO_5,
+	OCELOT_STAT_DROP_YELLOW_PRIO_6,
+	OCELOT_STAT_DROP_YELLOW_PRIO_7,
+	OCELOT_STAT_DROP_GREEN_PRIO_0,
+	OCELOT_STAT_DROP_GREEN_PRIO_1,
+	OCELOT_STAT_DROP_GREEN_PRIO_2,
+	OCELOT_STAT_DROP_GREEN_PRIO_3,
+	OCELOT_STAT_DROP_GREEN_PRIO_4,
+	OCELOT_STAT_DROP_GREEN_PRIO_5,
+	OCELOT_STAT_DROP_GREEN_PRIO_6,
+	OCELOT_STAT_DROP_GREEN_PRIO_7,
+	OCELOT_NUM_STATS,
+};
+
 struct ocelot_stat_layout {
-	u32 offset;
+	u32 reg;
 	char name[ETH_GSTRING_LEN];
 };
 
-#define OCELOT_STAT_END { .name = "" }
-
 struct ocelot_stats_region {
 	struct list_head node;
-	u32 offset;
+	u32 base;
 	int count;
 	u32 *buf;
 };
@@ -707,7 +857,6 @@ struct ocelot {
 	const u32 *const		*map;
 	const struct ocelot_stat_layout	*stats_layout;
 	struct list_head		stats_regions;
-	unsigned int			num_stats;
 
 	u32				pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM];
 	int				packet_buffer_size;
@@ -750,7 +899,7 @@ struct ocelot {
 	struct ocelot_psfp_list		psfp;
 
 	/* Workqueue to check statistics for overflow with its lock */
-	struct mutex			stats_lock;
+	spinlock_t			stats_lock;
 	u64				*stats;
 	struct delayed_work		stats_work;
 	struct workqueue_struct		*stats_queue;
@@ -786,8 +935,8 @@ struct ocelot_policer {
 	u32 burst; /* bytes */
 };
 
-#define ocelot_bulk_read_rix(ocelot, reg, ri, buf, count) \
-	__ocelot_bulk_read_ix(ocelot, reg, reg##_RSZ * (ri), buf, count)
+#define ocelot_bulk_read(ocelot, reg, buf, count) \
+	__ocelot_bulk_read_ix(ocelot, reg, 0, buf, count)
 
 #define ocelot_read_ix(ocelot, reg, gi, ri) \
 	__ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
diff --git a/include/trace/events/dlm.h b/include/trace/events/dlm.h
index bad21222130e..da0eaae98fa3 100644
--- a/include/trace/events/dlm.h
+++ b/include/trace/events/dlm.h
@@ -49,7 +49,7 @@
 /* note: we begin tracing dlm_lock_start() only if ls and lkb are found */
 TRACE_EVENT(dlm_lock_start,
 
-	TP_PROTO(struct dlm_ls *ls, struct dlm_lkb *lkb, void *name,
+	TP_PROTO(struct dlm_ls *ls, struct dlm_lkb *lkb, const void *name,
 		 unsigned int namelen, int mode, __u32 flags),
 
 	TP_ARGS(ls, lkb, name, namelen, mode, flags),
@@ -91,10 +91,11 @@ TRACE_EVENT(dlm_lock_start,
 
 TRACE_EVENT(dlm_lock_end,
 
-	TP_PROTO(struct dlm_ls *ls, struct dlm_lkb *lkb, void *name,
-		 unsigned int namelen, int mode, __u32 flags, int error),
+	TP_PROTO(struct dlm_ls *ls, struct dlm_lkb *lkb, const void *name,
+		 unsigned int namelen, int mode, __u32 flags, int error,
+		 bool kernel_lock),
 
-	TP_ARGS(ls, lkb, name, namelen, mode, flags, error),
+	TP_ARGS(ls, lkb, name, namelen, mode, flags, error, kernel_lock),
 
 	TP_STRUCT__entry(
 		__field(__u32, ls_id)
@@ -113,6 +114,7 @@ TRACE_EVENT(dlm_lock_end,
 		__entry->lkb_id = lkb->lkb_id;
 		__entry->mode = mode;
 		__entry->flags = flags;
+		__entry->error = error;
 
 		r = lkb->lkb_resource;
 		if (r)
@@ -122,14 +124,14 @@ TRACE_EVENT(dlm_lock_end,
 			memcpy(__get_dynamic_array(res_name), name,
 			       __get_dynamic_array_len(res_name));
 
-		/* return value will be zeroed in those cases by dlm_lock()
-		 * we do it here again to not introduce more overhead if
-		 * trace isn't running and error reflects the return value.
-		 */
-		if (error == -EAGAIN || error == -EDEADLK)
-			__entry->error = 0;
-		else
-			__entry->error = error;
+		if (kernel_lock) {
+			/* return value will be zeroed in those cases by dlm_lock()
+			 * we do it here again to not introduce more overhead if
+			 * trace isn't running and error reflects the return value.
+			 */
+			if (error == -EAGAIN || error == -EDEADLK)
+				__entry->error = 0;
+		}
 
 	),
 
diff --git a/include/trace/events/erofs.h b/include/trace/events/erofs.h
index 57de057bd503..4f4c44ea3a65 100644
--- a/include/trace/events/erofs.h
+++ b/include/trace/events/erofs.h
@@ -53,15 +53,14 @@ TRACE_EVENT(erofs_lookup,
 );
 
 TRACE_EVENT(erofs_fill_inode,
-	TP_PROTO(struct inode *inode, int isdir),
-	TP_ARGS(inode, isdir),
+	TP_PROTO(struct inode *inode),
+	TP_ARGS(inode),
 
 	TP_STRUCT__entry(
 		__field(dev_t,		dev	)
 		__field(erofs_nid_t,	nid	)
 		__field(erofs_blk_t,	blkaddr )
 		__field(unsigned int,	ofs	)
-		__field(int,		isdir	)
 	),
 
 	TP_fast_assign(
@@ -69,13 +68,11 @@ TRACE_EVENT(erofs_fill_inode,
 		__entry->nid		= EROFS_I(inode)->nid;
 		__entry->blkaddr	= erofs_blknr(iloc(EROFS_I_SB(inode), __entry->nid));
 		__entry->ofs		= erofs_blkoff(iloc(EROFS_I_SB(inode), __entry->nid));
-		__entry->isdir		= isdir;
 	),
 
-	TP_printk("dev = (%d,%d), nid = %llu, blkaddr %u ofs %u, isdir %d",
+	TP_printk("dev = (%d,%d), nid = %llu, blkaddr %u ofs %u",
 		  show_dev_nid(__entry),
-		  __entry->blkaddr, __entry->ofs,
-		  __entry->isdir)
+		  __entry->blkaddr, __entry->ofs)
 );
 
 TRACE_EVENT(erofs_readpage,
diff --git a/include/trace/events/scmi.h b/include/trace/events/scmi.h
index 65016a767b7a..f160d68f961d 100644
--- a/include/trace/events/scmi.h
+++ b/include/trace/events/scmi.h
@@ -27,9 +27,9 @@ TRACE_EVENT(scmi_fc_call,
 		__entry->val2 = val2;
 	),
 
-	TP_printk("[0x%02X]:[0x%02X]:[%08X]:%u:%u",
-		  __entry->protocol_id, __entry->msg_id,
-		  __entry->res_id, __entry->val1, __entry->val2)
+	TP_printk("pt=%02X msg_id=%02X res_id:%u vals=%u:%u",
+		__entry->protocol_id, __entry->msg_id,
+		__entry->res_id, __entry->val1, __entry->val2)
 );
 
 TRACE_EVENT(scmi_xfer_begin,
@@ -53,9 +53,9 @@ TRACE_EVENT(scmi_xfer_begin,
 		__entry->poll = poll;
 	),
 
-	TP_printk("transfer_id=%d msg_id=%u protocol_id=%u seq=%u poll=%u",
-		__entry->transfer_id, __entry->msg_id, __entry->protocol_id,
-		__entry->seq, __entry->poll)
+	TP_printk("pt=%02X msg_id=%02X seq=%04X transfer_id=%X poll=%u",
+		__entry->protocol_id, __entry->msg_id, __entry->seq,
+		__entry->transfer_id, __entry->poll)
 );
 
 TRACE_EVENT(scmi_xfer_response_wait,
@@ -81,9 +81,9 @@ TRACE_EVENT(scmi_xfer_response_wait,
 		__entry->poll = poll;
 	),
 
-	TP_printk("transfer_id=%d msg_id=%u protocol_id=%u seq=%u tmo_ms=%u poll=%u",
-		__entry->transfer_id, __entry->msg_id, __entry->protocol_id,
-		__entry->seq, __entry->timeout, __entry->poll)
+	TP_printk("pt=%02X msg_id=%02X seq=%04X transfer_id=%X tmo_ms=%u poll=%u",
+		__entry->protocol_id, __entry->msg_id, __entry->seq,
+		__entry->transfer_id, __entry->timeout, __entry->poll)
 );
 
 TRACE_EVENT(scmi_xfer_end,
@@ -107,9 +107,9 @@ TRACE_EVENT(scmi_xfer_end,
 		__entry->status = status;
 	),
 
-	TP_printk("transfer_id=%d msg_id=%u protocol_id=%u seq=%u status=%d",
-		__entry->transfer_id, __entry->msg_id, __entry->protocol_id,
-		__entry->seq, __entry->status)
+	TP_printk("pt=%02X msg_id=%02X seq=%04X transfer_id=%X s=%d",
+		__entry->protocol_id, __entry->msg_id, __entry->seq,
+		__entry->transfer_id, __entry->status)
 );
 
 TRACE_EVENT(scmi_rx_done,
@@ -133,9 +133,9 @@ TRACE_EVENT(scmi_rx_done,
 		__entry->msg_type = msg_type;
 	),
 
-	TP_printk("transfer_id=%d msg_id=%u protocol_id=%u seq=%u msg_type=%u",
-		__entry->transfer_id, __entry->msg_id, __entry->protocol_id,
-		__entry->seq, __entry->msg_type)
+	TP_printk("pt=%02X msg_id=%02X seq=%04X transfer_id=%X msg_type=%u",
+		__entry->protocol_id, __entry->msg_id, __entry->seq,
+		__entry->transfer_id, __entry->msg_type)
 );
 
 TRACE_EVENT(scmi_msg_dump,
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 45264e4bb254..50a974f7dfb4 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -9,6 +9,15 @@
 #include <linux/netdevice.h>
 #include <linux/tracepoint.h>
 
+#undef FN
+#define FN(reason)	TRACE_DEFINE_ENUM(SKB_DROP_REASON_##reason);
+DEFINE_DROP_REASON(FN, FN)
+
+#undef FN
+#undef FNe
+#define FN(reason)	{ SKB_DROP_REASON_##reason, #reason },
+#define FNe(reason)	{ SKB_DROP_REASON_##reason, #reason }
+
 /*
  * Tracepoint for free an sk_buff:
  */
@@ -35,9 +44,13 @@ TRACE_EVENT(kfree_skb,
 
 	TP_printk("skbaddr=%p protocol=%u location=%p reason: %s",
 		  __entry->skbaddr, __entry->protocol, __entry->location,
-		  drop_reasons[__entry->reason])
+		  __print_symbolic(__entry->reason,
+				   DEFINE_DROP_REASON(FN, FNe)))
 );
 
+#undef FN
+#undef FNe
+
 TRACE_EVENT(consume_skb,
 
 	TP_PROTO(struct sk_buff *skb),
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7bf9ba1329be..59a217ca2dfd 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -79,7 +79,7 @@ struct bpf_insn {
 /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
 struct bpf_lpm_trie_key {
 	__u32	prefixlen;	/* up to 32 for AF_INET, 128 for AF_INET6 */
-	__u8	data[];	/* Arbitrary size */
+	__u8	data[0];	/* Arbitrary size */
 };
 
 struct bpf_cgroup_storage_key {
diff --git a/include/uapi/linux/dlm.h b/include/uapi/linux/dlm.h
index 0d2eca287567..1923f4f3b05e 100644
--- a/include/uapi/linux/dlm.h
+++ b/include/uapi/linux/dlm.h
@@ -69,7 +69,6 @@ struct dlm_lksb {
 /* dlm_new_lockspace() flags */
 
 #define DLM_LSFL_TIMEWARN	0x00000002
-#define DLM_LSFL_FS     	0x00000004
 #define DLM_LSFL_NEWEXCL     	0x00000008
 
 
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 2ec07de1d73b..b6d7b868f290 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -67,6 +67,8 @@
 #define IFF_TAP		0x0002
 #define IFF_NAPI	0x0010
 #define IFF_NAPI_FRAGS	0x0020
+/* Used in TUNSETIFF to bring up tun/tap without carrier */
+#define IFF_NO_CARRIER	0x0040
 #define IFF_NO_PI	0x1000
 /* This flag has no real effect */
 #define IFF_ONE_QUEUE	0x2000
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 1463cfecb56b..6b83177fd41d 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -12,6 +12,10 @@
 #include <linux/types.h>
 #include <linux/time_types.h>
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 /*
  * IO submission data structure (Submission Queue Entry)
  */
@@ -67,8 +71,8 @@ struct io_uring_sqe {
 		__s32	splice_fd_in;
 		__u32	file_index;
 		struct {
-			__u16	notification_idx;
 			__u16	addr_len;
+			__u16	__pad3[1];
 		};
 	};
 	union {
@@ -174,8 +178,7 @@ enum io_uring_op {
 	IORING_OP_FALLOCATE,
 	IORING_OP_OPENAT,
 	IORING_OP_CLOSE,
-	IORING_OP_RSRC_UPDATE,
-	IORING_OP_FILES_UPDATE = IORING_OP_RSRC_UPDATE,
+	IORING_OP_FILES_UPDATE,
 	IORING_OP_STATX,
 	IORING_OP_READ,
 	IORING_OP_WRITE,
@@ -202,7 +205,7 @@ enum io_uring_op {
 	IORING_OP_GETXATTR,
 	IORING_OP_SOCKET,
 	IORING_OP_URING_CMD,
-	IORING_OP_SENDZC_NOTIF,
+	IORING_OP_SEND_ZC,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -224,7 +227,6 @@ enum io_uring_op {
 #define IORING_TIMEOUT_ETIME_SUCCESS	(1U << 5)
 #define IORING_TIMEOUT_CLOCK_MASK	(IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME)
 #define IORING_TIMEOUT_UPDATE_MASK	(IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE)
-
 /*
  * sqe->splice_flags
  * extends splice(2) flags
@@ -277,29 +279,16 @@ enum io_uring_op {
  *
  * IORING_RECVSEND_FIXED_BUF	Use registered buffers, the index is stored in
  *				the buf_index field.
- *
- * IORING_RECVSEND_NOTIF_FLUSH	Flush a notification after a successful
- *				successful. Only for zerocopy sends.
  */
 #define IORING_RECVSEND_POLL_FIRST	(1U << 0)
 #define IORING_RECV_MULTISHOT		(1U << 1)
 #define IORING_RECVSEND_FIXED_BUF	(1U << 2)
-#define IORING_RECVSEND_NOTIF_FLUSH	(1U << 3)
 
 /*
  * accept flags stored in sqe->ioprio
  */
 #define IORING_ACCEPT_MULTISHOT	(1U << 0)
 
-
-/*
- * IORING_OP_RSRC_UPDATE flags
- */
-enum {
-	IORING_RSRC_UPDATE_FILES,
-	IORING_RSRC_UPDATE_NOTIF,
-};
-
 /*
  * IORING_OP_MSG_RING command types, stored in sqe->addr
  */
@@ -337,10 +326,13 @@ struct io_uring_cqe {
  * IORING_CQE_F_BUFFER	If set, the upper 16 bits are the buffer ID
  * IORING_CQE_F_MORE	If set, parent SQE will generate more CQE entries
  * IORING_CQE_F_SOCK_NONEMPTY	If set, more data to read after socket recv
+ * IORING_CQE_F_NOTIF	Set for notification CQEs. Can be used to distinct
+ * 			them from sends.
  */
 #define IORING_CQE_F_BUFFER		(1U << 0)
 #define IORING_CQE_F_MORE		(1U << 1)
 #define IORING_CQE_F_SOCK_NONEMPTY	(1U << 2)
+#define IORING_CQE_F_NOTIF		(1U << 3)
 
 enum {
 	IORING_CQE_BUFFER_SHIFT		= 16,
@@ -481,10 +473,6 @@ enum {
 	/* register a range of fixed file slots for automatic slot allocation */
 	IORING_REGISTER_FILE_ALLOC_RANGE	= 25,
 
-	/* zerocopy notification API */
-	IORING_REGISTER_NOTIFIERS		= 26,
-	IORING_UNREGISTER_NOTIFIERS		= 27,
-
 	/* this goes last */
 	IORING_REGISTER_LAST
 };
@@ -661,4 +649,8 @@ struct io_uring_recvmsg_out {
 	__u32 flags;
 };
 
+#ifdef __cplusplus
+}
+#endif
+
 #endif
diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h
index 1500a0f58041..7cab2c65d3d7 100644
--- a/include/uapi/linux/stat.h
+++ b/include/uapi/linux/stat.h
@@ -124,7 +124,8 @@ struct statx {
 	__u32	stx_dev_minor;
 	/* 0x90 */
 	__u64	stx_mnt_id;
-	__u64	__spare2;
+	__u32	stx_dio_mem_align;	/* Memory buffer alignment for direct I/O */
+	__u32	stx_dio_offset_align;	/* File offset alignment for direct I/O */
 	/* 0xa0 */
 	__u64	__spare3[12];	/* Spare space for future expansion */
 	/* 0x100 */
@@ -152,6 +153,7 @@ struct statx {
 #define STATX_BASIC_STATS	0x000007ffU	/* The stuff in the normal stat struct */
 #define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
 #define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
+#define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 29ced55514d4..6cb842ea8979 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -56,7 +56,7 @@
 #define VIRTIO_NET_F_MQ	22	/* Device supports Receive Flow
 					 * Steering */
 #define VIRTIO_NET_F_CTRL_MAC_ADDR 23	/* Set MAC address */
-#define VIRTIO_NET_F_NOTF_COAL	53	/* Guest can handle notifications coalescing */
+#define VIRTIO_NET_F_NOTF_COAL	53	/* Device supports notifications coalescing */
 #define VIRTIO_NET_F_HASH_REPORT  57	/* Supports hash report */
 #define VIRTIO_NET_F_RSS	  60	/* Supports RSS RX steering */
 #define VIRTIO_NET_F_RSC_EXT	  61	/* extended coalescing info */
@@ -364,24 +364,24 @@ struct virtio_net_hash_config {
  */
 #define VIRTIO_NET_CTRL_NOTF_COAL		6
 /*
- * Set the tx-usecs/tx-max-packets patameters.
- * tx-usecs - Maximum number of usecs to delay a TX notification.
- * tx-max-packets - Maximum number of packets to send before a TX notification.
+ * Set the tx-usecs/tx-max-packets parameters.
  */
 struct virtio_net_ctrl_coal_tx {
+	/* Maximum number of packets to send before a TX notification */
 	__le32 tx_max_packets;
+	/* Maximum number of usecs to delay a TX notification */
 	__le32 tx_usecs;
 };
 
 #define VIRTIO_NET_CTRL_NOTF_COAL_TX_SET		0
 
 /*
- * Set the rx-usecs/rx-max-packets patameters.
- * rx-usecs - Maximum number of usecs to delay a RX notification.
- * rx-max-frames - Maximum number of packets to receive before a RX notification.
+ * Set the rx-usecs/rx-max-packets parameters.
  */
 struct virtio_net_ctrl_coal_rx {
+	/* Maximum number of packets to receive before a RX notification */
 	__le32 rx_max_packets;
+	/* Maximum number of usecs to delay a RX notification */
 	__le32 rx_usecs;
 };
 
diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h
index 476d3e5c0fe7..f8c20d3de8da 100644
--- a/include/uapi/linux/virtio_ring.h
+++ b/include/uapi/linux/virtio_ring.h
@@ -93,15 +93,21 @@
 #define VRING_USED_ALIGN_SIZE 4
 #define VRING_DESC_ALIGN_SIZE 16
 
-/* Virtio ring descriptors: 16 bytes.  These can chain together via "next". */
+/**
+ * struct vring_desc - Virtio ring descriptors,
+ * 16 bytes long. These can chain together via @next.
+ *
+ * @addr: buffer address (guest-physical)
+ * @len: buffer length
+ * @flags: descriptor flags
+ * @next: index of the next descriptor in the chain,
+ *        if the VRING_DESC_F_NEXT flag is set. We chain unused
+ *        descriptors via this, too.
+ */
 struct vring_desc {
-	/* Address (guest-physical). */
 	__virtio64 addr;
-	/* Length. */
 	__virtio32 len;
-	/* The flags as indicated above. */
 	__virtio16 flags;
-	/* We chain unused descriptors via this, too */
 	__virtio16 next;
 };
 
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index b1f3e6a8f11a..4f84ea7ee14c 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -296,7 +296,7 @@ enum xfrm_attr_type_t {
 	XFRMA_ETIMER_THRESH,
 	XFRMA_SRCADDR,		/* xfrm_address_t */
 	XFRMA_COADDR,		/* xfrm_address_t */
-	XFRMA_LASTUSED,		/* unsigned long  */
+	XFRMA_LASTUSED,		/* __u64 */
 	XFRMA_POLICY_TYPE,	/* struct xfrm_userpolicy_type */
 	XFRMA_MIGRATE,
 	XFRMA_ALG_AEAD,		/* struct xfrm_algo_aead */
diff --git a/include/ufs/ufshci.h b/include/ufs/ufshci.h
index f81aa95ffbc4..f525566a0864 100644
--- a/include/ufs/ufshci.h
+++ b/include/ufs/ufshci.h
@@ -135,11 +135,7 @@ static inline u32 ufshci_version(u32 major, u32 minor)
 
 #define UFSHCD_UIC_MASK		(UIC_COMMAND_COMPL | UFSHCD_UIC_PWR_MASK)
 
-#define UFSHCD_ERROR_MASK	(UIC_ERROR |\
-				DEVICE_FATAL_ERROR |\
-				CONTROLLER_FATAL_ERROR |\
-				SYSTEM_BUS_FATAL_ERROR |\
-				CRYPTO_ENGINE_FATAL_ERROR)
+#define UFSHCD_ERROR_MASK	(UIC_ERROR | INT_FATAL_ERRORS)
 
 #define INT_FATAL_ERRORS	(DEVICE_FATAL_ERROR |\
 				CONTROLLER_FATAL_ERROR |\
diff --git a/init/Kconfig b/init/Kconfig
index 80fe60fa77fb..a078cb026523 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -60,6 +60,17 @@ config LLD_VERSION
 	default $(ld-version) if LD_IS_LLD
 	default 0
 
+config RUST_IS_AVAILABLE
+	def_bool $(success,$(srctree)/scripts/rust_is_available.sh)
+	help
+	  This shows whether a suitable Rust toolchain is available (found).
+
+	  Please see Documentation/rust/quick-start.rst for instructions on how
+	  to satify the build requirements of Rust support.
+
+	  In particular, the Makefile target 'rustavailable' is useful to check
+	  why the Rust toolchain is not being detected.
+
 config CC_CAN_LINK
 	bool
 	default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m64-flag)) if 64BIT
@@ -70,11 +81,7 @@ config CC_CAN_LINK_STATIC
 	default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m64-flag) -static) if 64BIT
 	default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m32-flag) -static)
 
-config CC_HAS_ASM_GOTO
-	def_bool $(success,$(srctree)/scripts/gcc-goto.sh $(CC))
-
 config CC_HAS_ASM_GOTO_OUTPUT
-	depends on CC_HAS_ASM_GOTO
 	def_bool $(success,echo 'int foo(int x) { asm goto ("": "=r"(x) ::: bar); return x; bar: return 0; }' | $(CC) -x c - -c -o /dev/null)
 
 config CC_HAS_ASM_GOTO_TIED_OUTPUT
@@ -151,7 +158,8 @@ config WERROR
 	default COMPILE_TEST
 	help
 	  A kernel build should not cause any compiler warnings, and this
-	  enables the '-Werror' flag to enforce that rule by default.
+	  enables the '-Werror' (for C) and '-Dwarnings' (for Rust) flags
+	  to enforce that rule by default.
 
 	  However, if you have a new (or very old) compiler with odd and
 	  unusual warnings, or you have some architecture with problems,
@@ -1903,6 +1911,38 @@ config PROFILING
 	  Say Y here to enable the extended profiling support mechanisms used
 	  by profilers.
 
+config RUST
+	bool "Rust support"
+	depends on HAVE_RUST
+	depends on RUST_IS_AVAILABLE
+	depends on !MODVERSIONS
+	depends on !GCC_PLUGINS
+	depends on !RANDSTRUCT
+	depends on !DEBUG_INFO_BTF
+	select CONSTRUCTORS
+	help
+	  Enables Rust support in the kernel.
+
+	  This allows other Rust-related options, like drivers written in Rust,
+	  to be selected.
+
+	  It is also required to be able to load external kernel modules
+	  written in Rust.
+
+	  See Documentation/rust/ for more information.
+
+	  If unsure, say N.
+
+config RUSTC_VERSION_TEXT
+	string
+	depends on RUST
+	default $(shell,command -v $(RUSTC) >/dev/null 2>&1 && $(RUSTC) --version || echo n)
+
+config BINDGEN_VERSION_TEXT
+	string
+	depends on RUST
+	default $(shell,command -v $(BINDGEN) >/dev/null 2>&1 && $(BINDGEN) --version || echo n)
+
 #
 # Place an empty function call at each tracepoint site. Can be
 # dynamically changed for a probe function.
diff --git a/init/main.c b/init/main.c
index 91642a4e69be..1fe7942f5d4a 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1446,13 +1446,25 @@ static noinline void __init kernel_init_freeable(void);
 
 #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_STRICT_MODULE_RWX)
 bool rodata_enabled __ro_after_init = true;
+
+#ifndef arch_parse_debug_rodata
+static inline bool arch_parse_debug_rodata(char *str) { return false; }
+#endif
+
 static int __init set_debug_rodata(char *str)
 {
-	if (strtobool(str, &rodata_enabled))
+	if (arch_parse_debug_rodata(str))
+		return 0;
+
+	if (str && !strcmp(str, "on"))
+		rodata_enabled = true;
+	else if (str && !strcmp(str, "off"))
+		rodata_enabled = false;
+	else
 		pr_warn("Invalid option string for rodata: '%s'\n", str);
-	return 1;
+	return 0;
 }
-__setup("rodata=", set_debug_rodata);
+early_param("rodata", set_debug_rodata);
 #endif
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
diff --git a/io_uring/cancel.c b/io_uring/cancel.c
index e4e1dc0325f0..5fc5d3e80fcb 100644
--- a/io_uring/cancel.c
+++ b/io_uring/cancel.c
@@ -218,7 +218,7 @@ static int __io_sync_cancel(struct io_uring_task *tctx,
 	    (cd->flags & IORING_ASYNC_CANCEL_FD_FIXED)) {
 		unsigned long file_ptr;
 
-		if (unlikely(fd > ctx->nr_user_files))
+		if (unlikely(fd >= ctx->nr_user_files))
 			return -EBADF;
 		fd = array_index_nospec(fd, ctx->nr_user_files);
 		file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr;
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index ebfdb2212ec2..242d896c00f3 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1450,9 +1450,10 @@ int io_req_prep_async(struct io_kiocb *req)
 		return 0;
 	if (WARN_ON_ONCE(req_has_async_data(req)))
 		return -EFAULT;
-	if (io_alloc_async_data(req))
-		return -EAGAIN;
-
+	if (!io_op_defs[req->opcode].manual_alloc) {
+		if (io_alloc_async_data(req))
+			return -EAGAIN;
+	}
 	return def->prep_async(req);
 }
 
@@ -1727,6 +1728,7 @@ static void io_queue_async(struct io_kiocb *req, int ret)
 
 	switch (io_arm_poll_handler(req, 0)) {
 	case IO_APOLL_READY:
+		io_kbuf_recycle(req, 0);
 		io_req_task_queue(req);
 		break;
 	case IO_APOLL_ABORTED:
@@ -2639,7 +2641,6 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 		io_unregister_personality(ctx, index);
 	if (ctx->rings)
 		io_poll_remove_all(ctx, NULL, true);
-	io_notif_unregister(ctx);
 	mutex_unlock(&ctx->uring_lock);
 
 	/* failed during ring init, it couldn't have issued any requests */
@@ -2647,6 +2648,9 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 		io_kill_timeouts(ctx, NULL, true);
 		/* if we failed setting up the ctx, we might not have any rings */
 		io_iopoll_try_reap_events(ctx);
+		/* drop cached put refs after potentially doing completions */
+		if (current->io_uring)
+			io_uring_drop_tctx_refs(current);
 	}
 
 	INIT_WORK(&ctx->exit_work, io_ring_exit_work);
@@ -3353,6 +3357,10 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
 		goto err;
 	}
 
+	if (ctx->flags & IORING_SETUP_SINGLE_ISSUER
+	    && !(ctx->flags & IORING_SETUP_R_DISABLED))
+		ctx->submitter_task = get_task_struct(current);
+
 	file = io_uring_get_file(ctx);
 	if (IS_ERR(file)) {
 		ret = PTR_ERR(file);
@@ -3544,6 +3552,9 @@ static int io_register_enable_rings(struct io_ring_ctx *ctx)
 	if (!(ctx->flags & IORING_SETUP_R_DISABLED))
 		return -EBADFD;
 
+	if (ctx->flags & IORING_SETUP_SINGLE_ISSUER && !ctx->submitter_task)
+		ctx->submitter_task = get_task_struct(current);
+
 	if (ctx->restrictions.registered)
 		ctx->restricted = 1;
 
@@ -3838,15 +3849,6 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_register_file_alloc_range(ctx, arg);
 		break;
-	case IORING_REGISTER_NOTIFIERS:
-		ret = io_notif_register(ctx, arg, nr_args);
-		break;
-	case IORING_UNREGISTER_NOTIFIERS:
-		ret = -EINVAL;
-		if (arg || nr_args)
-			break;
-		ret = io_notif_unregister(ctx);
-		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -3932,8 +3934,8 @@ static int __init io_uring_init(void)
 	BUILD_BUG_SQE_ELEM(42, __u16,  personality);
 	BUILD_BUG_SQE_ELEM(44, __s32,  splice_fd_in);
 	BUILD_BUG_SQE_ELEM(44, __u32,  file_index);
-	BUILD_BUG_SQE_ELEM(44, __u16,  notification_idx);
-	BUILD_BUG_SQE_ELEM(46, __u16,  addr_len);
+	BUILD_BUG_SQE_ELEM(44, __u16,  addr_len);
+	BUILD_BUG_SQE_ELEM(46, __u16,  __pad3[0]);
 	BUILD_BUG_SQE_ELEM(48, __u64,  addr3);
 	BUILD_BUG_SQE_ELEM_SIZE(48, 0, cmd);
 	BUILD_BUG_SQE_ELEM(56, __u64,  __pad2);
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index d6af208d109f..746fbf31a703 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -91,9 +91,13 @@ static inline void io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
 	 * buffer data. However if that buffer is recycled the original request
 	 * data stored in addr is lost. Therefore forbid recycling for now.
 	 */
-	if (req->opcode == IORING_OP_READV)
+	if (req->opcode == IORING_OP_READV) {
+		if ((req->flags & REQ_F_BUFFER_RING) && req->buf_list) {
+			req->buf_list->head++;
+			req->buf_list = NULL;
+		}
 		return;
-
+	}
 	if (req->flags & REQ_F_BUFFER_SELECTED)
 		io_kbuf_recycle_legacy(req, issue_flags);
 	if (req->flags & REQ_F_BUFFER_RING)
diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c
index 976c4ba68ee7..4a7e5d030c78 100644
--- a/io_uring/msg_ring.c
+++ b/io_uring/msg_ring.c
@@ -165,7 +165,8 @@ done:
 		req_set_fail(req);
 	io_req_set_res(req, ret, 0);
 	/* put file to avoid an attempt to IOPOLL the req */
-	io_put_file(req->file);
+	if (!(req->flags & REQ_F_FIXED_FILE))
+		io_put_file(req->file);
 	req->file = NULL;
 	return IOU_OK;
 }
diff --git a/io_uring/net.c b/io_uring/net.c
index 6d71748e2c5a..60e392f7f2dc 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -65,12 +65,12 @@ struct io_sendzc {
 	struct file			*file;
 	void __user			*buf;
 	size_t				len;
-	u16				slot_idx;
 	unsigned			msg_flags;
 	unsigned			flags;
 	unsigned			addr_len;
 	void __user			*addr;
 	size_t				done_io;
+	struct io_kiocb 		*notif;
 };
 
 #define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED)
@@ -116,7 +116,7 @@ static void io_netmsg_recycle(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_async_msghdr *hdr = req->async_data;
 
-	if (!hdr || issue_flags & IO_URING_F_UNLOCKED)
+	if (!req_has_async_data(req) || issue_flags & IO_URING_F_UNLOCKED)
 		return;
 
 	/* Let normal cleanup path reap it if we fail adding to the cache */
@@ -152,9 +152,9 @@ static int io_setup_async_msg(struct io_kiocb *req,
 			      struct io_async_msghdr *kmsg,
 			      unsigned int issue_flags)
 {
-	struct io_async_msghdr *async_msg = req->async_data;
+	struct io_async_msghdr *async_msg;
 
-	if (async_msg)
+	if (req_has_async_data(req))
 		return -EAGAIN;
 	async_msg = io_recvmsg_alloc_async(req, issue_flags);
 	if (!async_msg) {
@@ -182,6 +182,37 @@ static int io_sendmsg_copy_hdr(struct io_kiocb *req,
 					&iomsg->free_iov);
 }
 
+int io_sendzc_prep_async(struct io_kiocb *req)
+{
+	struct io_sendzc *zc = io_kiocb_to_cmd(req, struct io_sendzc);
+	struct io_async_msghdr *io;
+	int ret;
+
+	if (!zc->addr || req_has_async_data(req))
+		return 0;
+	if (io_alloc_async_data(req))
+		return -ENOMEM;
+
+	io = req->async_data;
+	ret = move_addr_to_kernel(zc->addr, zc->addr_len, &io->addr);
+	return ret;
+}
+
+static int io_setup_async_addr(struct io_kiocb *req,
+			      struct sockaddr_storage *addr,
+			      unsigned int issue_flags)
+{
+	struct io_async_msghdr *io;
+
+	if (!addr || req_has_async_data(req))
+		return -EAGAIN;
+	if (io_alloc_async_data(req))
+		return -ENOMEM;
+	io = req->async_data;
+	memcpy(&io->addr, addr, sizeof(io->addr));
+	return -EAGAIN;
+}
+
 int io_sendmsg_prep_async(struct io_kiocb *req)
 {
 	int ret;
@@ -848,18 +879,39 @@ out_free:
 	return ret;
 }
 
+void io_sendzc_cleanup(struct io_kiocb *req)
+{
+	struct io_sendzc *zc = io_kiocb_to_cmd(req, struct io_sendzc);
+
+	zc->notif->flags |= REQ_F_CQE_SKIP;
+	io_notif_flush(zc->notif);
+	zc->notif = NULL;
+}
+
 int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_sendzc *zc = io_kiocb_to_cmd(req, struct io_sendzc);
 	struct io_ring_ctx *ctx = req->ctx;
+	struct io_kiocb *notif;
 
-	if (READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3))
+	if (READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3) ||
+	    READ_ONCE(sqe->__pad3[0]))
+		return -EINVAL;
+	/* we don't support IOSQE_CQE_SKIP_SUCCESS just yet */
+	if (req->flags & REQ_F_CQE_SKIP)
 		return -EINVAL;
 
 	zc->flags = READ_ONCE(sqe->ioprio);
 	if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST |
-			  IORING_RECVSEND_FIXED_BUF | IORING_RECVSEND_NOTIF_FLUSH))
+			  IORING_RECVSEND_FIXED_BUF))
 		return -EINVAL;
+	notif = zc->notif = io_alloc_notif(ctx);
+	if (!notif)
+		return -ENOMEM;
+	notif->cqe.user_data = req->cqe.user_data;
+	notif->cqe.res = 0;
+	notif->cqe.flags = IORING_CQE_F_NOTIF;
+	req->flags |= REQ_F_NEED_CLEANUP;
 	if (zc->flags & IORING_RECVSEND_FIXED_BUF) {
 		unsigned idx = READ_ONCE(sqe->buf_index);
 
@@ -867,13 +919,12 @@ int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 			return -EFAULT;
 		idx = array_index_nospec(idx, ctx->nr_user_bufs);
 		req->imu = READ_ONCE(ctx->user_bufs[idx]);
-		io_req_set_rsrc_node(req, ctx, 0);
+		io_req_set_rsrc_node(notif, ctx, 0);
 	}
 
 	zc->buf = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	zc->len = READ_ONCE(sqe->len);
 	zc->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
-	zc->slot_idx = READ_ONCE(sqe->notification_idx);
 	if (zc->msg_flags & MSG_DONTWAIT)
 		req->flags |= REQ_F_NOWAIT;
 
@@ -925,7 +976,7 @@ static int io_sg_from_iter(struct sock *sk, struct sk_buff *skb,
 	shinfo->nr_frags = frag;
 	from->bvec += bi.bi_idx;
 	from->nr_segs -= bi.bi_idx;
-	from->count = bi.bi_size;
+	from->count -= copied;
 	from->iov_offset = bi.bi_bvec_done;
 
 	skb->data_len += copied;
@@ -944,62 +995,57 @@ static int io_sg_from_iter(struct sock *sk, struct sk_buff *skb,
 
 int io_sendzc(struct io_kiocb *req, unsigned int issue_flags)
 {
-	struct sockaddr_storage address;
-	struct io_ring_ctx *ctx = req->ctx;
+	struct sockaddr_storage __address, *addr = NULL;
 	struct io_sendzc *zc = io_kiocb_to_cmd(req, struct io_sendzc);
-	struct io_notif_slot *notif_slot;
-	struct io_kiocb *notif;
 	struct msghdr msg;
 	struct iovec iov;
 	struct socket *sock;
-	unsigned msg_flags;
+	unsigned msg_flags, cflags;
 	int ret, min_ret = 0;
 
-	if (!(req->flags & REQ_F_POLLED) &&
-	    (zc->flags & IORING_RECVSEND_POLL_FIRST))
-		return -EAGAIN;
-
-	if (issue_flags & IO_URING_F_UNLOCKED)
-		return -EAGAIN;
 	sock = sock_from_file(req->file);
 	if (unlikely(!sock))
 		return -ENOTSOCK;
 
-	notif_slot = io_get_notif_slot(ctx, zc->slot_idx);
-	if (!notif_slot)
-		return -EINVAL;
-	notif = io_get_notif(ctx, notif_slot);
-	if (!notif)
-		return -ENOMEM;
-
 	msg.msg_name = NULL;
 	msg.msg_control = NULL;
 	msg.msg_controllen = 0;
 	msg.msg_namelen = 0;
 
+	if (zc->addr) {
+		if (req_has_async_data(req)) {
+			struct io_async_msghdr *io = req->async_data;
+
+			msg.msg_name = addr = &io->addr;
+		} else {
+			ret = move_addr_to_kernel(zc->addr, zc->addr_len, &__address);
+			if (unlikely(ret < 0))
+				return ret;
+			msg.msg_name = (struct sockaddr *)&__address;
+			addr = &__address;
+		}
+		msg.msg_namelen = zc->addr_len;
+	}
+
+	if (!(req->flags & REQ_F_POLLED) &&
+	    (zc->flags & IORING_RECVSEND_POLL_FIRST))
+		return io_setup_async_addr(req, addr, issue_flags);
+
 	if (zc->flags & IORING_RECVSEND_FIXED_BUF) {
 		ret = io_import_fixed(WRITE, &msg.msg_iter, req->imu,
 					(u64)(uintptr_t)zc->buf, zc->len);
 		if (unlikely(ret))
-				return ret;
+			return ret;
 	} else {
 		ret = import_single_range(WRITE, zc->buf, zc->len, &iov,
 					  &msg.msg_iter);
 		if (unlikely(ret))
 			return ret;
-		ret = io_notif_account_mem(notif, zc->len);
+		ret = io_notif_account_mem(zc->notif, zc->len);
 		if (unlikely(ret))
 			return ret;
 	}
 
-	if (zc->addr) {
-		ret = move_addr_to_kernel(zc->addr, zc->addr_len, &address);
-		if (unlikely(ret < 0))
-			return ret;
-		msg.msg_name = (struct sockaddr *)&address;
-		msg.msg_namelen = zc->addr_len;
-	}
-
 	msg_flags = zc->msg_flags | MSG_ZEROCOPY;
 	if (issue_flags & IO_URING_F_NONBLOCK)
 		msg_flags |= MSG_DONTWAIT;
@@ -1007,31 +1053,37 @@ int io_sendzc(struct io_kiocb *req, unsigned int issue_flags)
 		min_ret = iov_iter_count(&msg.msg_iter);
 
 	msg.msg_flags = msg_flags;
-	msg.msg_ubuf = &io_notif_to_data(notif)->uarg;
+	msg.msg_ubuf = &io_notif_to_data(zc->notif)->uarg;
 	msg.sg_from_iter = io_sg_from_iter;
 	ret = sock_sendmsg(sock, &msg);
 
 	if (unlikely(ret < min_ret)) {
 		if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
-			return -EAGAIN;
+			return io_setup_async_addr(req, addr, issue_flags);
+
 		if (ret > 0 && io_net_retry(sock, msg.msg_flags)) {
 			zc->len -= ret;
 			zc->buf += ret;
 			zc->done_io += ret;
 			req->flags |= REQ_F_PARTIAL_IO;
-			return -EAGAIN;
+			return io_setup_async_addr(req, addr, issue_flags);
 		}
+		if (ret < 0 && !zc->done_io)
+			zc->notif->flags |= REQ_F_CQE_SKIP;
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
-	} else if (zc->flags & IORING_RECVSEND_NOTIF_FLUSH) {
-		io_notif_slot_flush_submit(notif_slot, 0);
+		req_set_fail(req);
 	}
 
 	if (ret >= 0)
 		ret += zc->done_io;
 	else if (zc->done_io)
 		ret = zc->done_io;
-	io_req_set_res(req, ret, 0);
+
+	io_notif_flush(zc->notif);
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+	cflags = ret >= 0 ? IORING_CQE_F_MORE : 0;
+	io_req_set_res(req, ret, cflags);
 	return IOU_OK;
 }
 
diff --git a/io_uring/net.h b/io_uring/net.h
index 7c438d39c089..d744a0a874e7 100644
--- a/io_uring/net.h
+++ b/io_uring/net.h
@@ -31,6 +31,7 @@ struct io_async_connect {
 int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 int io_shutdown(struct io_kiocb *req, unsigned int issue_flags);
 
+int io_sendzc_prep_async(struct io_kiocb *req);
 int io_sendmsg_prep_async(struct io_kiocb *req);
 void io_sendmsg_recvmsg_cleanup(struct io_kiocb *req);
 int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
@@ -54,6 +55,7 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags);
 
 int io_sendzc(struct io_kiocb *req, unsigned int issue_flags);
 int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+void io_sendzc_cleanup(struct io_kiocb *req);
 
 void io_netmsg_cache_free(struct io_cache_entry *entry);
 #else
diff --git a/io_uring/notif.c b/io_uring/notif.c
index 977736e82c1a..e37c6569d82e 100644
--- a/io_uring/notif.c
+++ b/io_uring/notif.c
@@ -21,14 +21,6 @@ static void __io_notif_complete_tw(struct io_kiocb *notif, bool *locked)
 	io_req_task_complete(notif, locked);
 }
 
-static inline void io_notif_complete(struct io_kiocb *notif)
-	__must_hold(&notif->ctx->uring_lock)
-{
-	bool locked = true;
-
-	__io_notif_complete_tw(notif, &locked);
-}
-
 static void io_uring_tx_zerocopy_callback(struct sk_buff *skb,
 					  struct ubuf_info *uarg,
 					  bool success)
@@ -42,8 +34,7 @@ static void io_uring_tx_zerocopy_callback(struct sk_buff *skb,
 	}
 }
 
-struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx,
-				struct io_notif_slot *slot)
+struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx)
 	__must_hold(&ctx->uring_lock)
 {
 	struct io_kiocb *notif;
@@ -59,99 +50,23 @@ struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx,
 	io_get_task_refs(1);
 	notif->rsrc_node = NULL;
 	io_req_set_rsrc_node(notif, ctx, 0);
-	notif->cqe.user_data = slot->tag;
-	notif->cqe.flags = slot->seq++;
-	notif->cqe.res = 0;
 
 	nd = io_notif_to_data(notif);
 	nd->account_pages = 0;
 	nd->uarg.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN;
 	nd->uarg.callback = io_uring_tx_zerocopy_callback;
-	/* master ref owned by io_notif_slot, will be dropped on flush */
 	refcount_set(&nd->uarg.refcnt, 1);
 	return notif;
 }
 
-void io_notif_slot_flush(struct io_notif_slot *slot)
-	__must_hold(&ctx->uring_lock)
+void io_notif_flush(struct io_kiocb *notif)
+	__must_hold(&slot->notif->ctx->uring_lock)
 {
-	struct io_kiocb *notif = slot->notif;
 	struct io_notif_data *nd = io_notif_to_data(notif);
 
-	slot->notif = NULL;
-
 	/* drop slot's master ref */
-	if (refcount_dec_and_test(&nd->uarg.refcnt))
-		io_notif_complete(notif);
-}
-
-__cold int io_notif_unregister(struct io_ring_ctx *ctx)
-	__must_hold(&ctx->uring_lock)
-{
-	int i;
-
-	if (!ctx->notif_slots)
-		return -ENXIO;
-
-	for (i = 0; i < ctx->nr_notif_slots; i++) {
-		struct io_notif_slot *slot = &ctx->notif_slots[i];
-		struct io_kiocb *notif = slot->notif;
-		struct io_notif_data *nd;
-
-		if (!notif)
-			continue;
-		nd = io_notif_to_data(notif);
-		slot->notif = NULL;
-		if (!refcount_dec_and_test(&nd->uarg.refcnt))
-			continue;
+	if (refcount_dec_and_test(&nd->uarg.refcnt)) {
 		notif->io_task_work.func = __io_notif_complete_tw;
 		io_req_task_work_add(notif);
 	}
-
-	kvfree(ctx->notif_slots);
-	ctx->notif_slots = NULL;
-	ctx->nr_notif_slots = 0;
-	return 0;
-}
-
-__cold int io_notif_register(struct io_ring_ctx *ctx,
-			     void __user *arg, unsigned int size)
-	__must_hold(&ctx->uring_lock)
-{
-	struct io_uring_notification_slot __user *slots;
-	struct io_uring_notification_slot slot;
-	struct io_uring_notification_register reg;
-	unsigned i;
-
-	if (ctx->nr_notif_slots)
-		return -EBUSY;
-	if (size != sizeof(reg))
-		return -EINVAL;
-	if (copy_from_user(&reg, arg, sizeof(reg)))
-		return -EFAULT;
-	if (!reg.nr_slots || reg.nr_slots > IORING_MAX_NOTIF_SLOTS)
-		return -EINVAL;
-	if (reg.resv || reg.resv2 || reg.resv3)
-		return -EINVAL;
-
-	slots = u64_to_user_ptr(reg.data);
-	ctx->notif_slots = kvcalloc(reg.nr_slots, sizeof(ctx->notif_slots[0]),
-				GFP_KERNEL_ACCOUNT);
-	if (!ctx->notif_slots)
-		return -ENOMEM;
-
-	for (i = 0; i < reg.nr_slots; i++, ctx->nr_notif_slots++) {
-		struct io_notif_slot *notif_slot = &ctx->notif_slots[i];
-
-		if (copy_from_user(&slot, &slots[i], sizeof(slot))) {
-			io_notif_unregister(ctx);
-			return -EFAULT;
-		}
-		if (slot.resv[0] | slot.resv[1] | slot.resv[2]) {
-			io_notif_unregister(ctx);
-			return -EINVAL;
-		}
-		notif_slot->tag = slot.tag;
-	}
-	return 0;
 }
diff --git a/io_uring/notif.h b/io_uring/notif.h
index 65f0b42f2555..5b4d710c8ca5 100644
--- a/io_uring/notif.h
+++ b/io_uring/notif.h
@@ -8,7 +8,6 @@
 #include "rsrc.h"
 
 #define IO_NOTIF_SPLICE_BATCH	32
-#define IORING_MAX_NOTIF_SLOTS (1U << 10)
 
 struct io_notif_data {
 	struct file		*file;
@@ -16,63 +15,14 @@ struct io_notif_data {
 	unsigned long		account_pages;
 };
 
-struct io_notif_slot {
-	/*
-	 * Current/active notifier. A slot holds only one active notifier at a
-	 * time and keeps one reference to it. Flush releases the reference and
-	 * lazily replaces it with a new notifier.
-	 */
-	struct io_kiocb		*notif;
-
-	/*
-	 * Default ->user_data for this slot notifiers CQEs
-	 */
-	u64			tag;
-	/*
-	 * Notifiers of a slot live in generations, we create a new notifier
-	 * only after flushing the previous one. Track the sequential number
-	 * for all notifiers and copy it into notifiers's cqe->cflags
-	 */
-	u32			seq;
-};
-
-int io_notif_register(struct io_ring_ctx *ctx,
-		      void __user *arg, unsigned int size);
-int io_notif_unregister(struct io_ring_ctx *ctx);
-
-void io_notif_slot_flush(struct io_notif_slot *slot);
-struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx,
-				struct io_notif_slot *slot);
+void io_notif_flush(struct io_kiocb *notif);
+struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx);
 
 static inline struct io_notif_data *io_notif_to_data(struct io_kiocb *notif)
 {
 	return io_kiocb_to_cmd(notif, struct io_notif_data);
 }
 
-static inline struct io_kiocb *io_get_notif(struct io_ring_ctx *ctx,
-					    struct io_notif_slot *slot)
-{
-	if (!slot->notif)
-		slot->notif = io_alloc_notif(ctx, slot);
-	return slot->notif;
-}
-
-static inline struct io_notif_slot *io_get_notif_slot(struct io_ring_ctx *ctx,
-						      unsigned idx)
-	__must_hold(&ctx->uring_lock)
-{
-	if (idx >= ctx->nr_notif_slots)
-		return NULL;
-	idx = array_index_nospec(idx, ctx->nr_notif_slots);
-	return &ctx->notif_slots[idx];
-}
-
-static inline void io_notif_slot_flush_submit(struct io_notif_slot *slot,
-					      unsigned int issue_flags)
-{
-	io_notif_slot_flush(slot);
-}
-
 static inline int io_notif_account_mem(struct io_kiocb *notif, unsigned len)
 {
 	struct io_ring_ctx *ctx = notif->ctx;
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index 72dd2b2d8a9d..c4dddd0fd709 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -246,13 +246,12 @@ const struct io_op_def io_op_defs[] = {
 		.prep			= io_close_prep,
 		.issue			= io_close,
 	},
-	[IORING_OP_RSRC_UPDATE] = {
+	[IORING_OP_FILES_UPDATE] = {
 		.audit_skip		= 1,
 		.iopoll			= 1,
-		.name			= "RSRC_UPDATE",
-		.prep			= io_rsrc_update_prep,
-		.issue			= io_rsrc_update,
-		.ioprio			= 1,
+		.name			= "FILES_UPDATE",
+		.prep			= io_files_update_prep,
+		.issue			= io_files_update,
 	},
 	[IORING_OP_STATX] = {
 		.audit_skip		= 1,
@@ -471,20 +470,23 @@ const struct io_op_def io_op_defs[] = {
 		.issue			= io_uring_cmd,
 		.prep_async		= io_uring_cmd_prep_async,
 	},
-	[IORING_OP_SENDZC_NOTIF] = {
-		.name			= "SENDZC_NOTIF",
+	[IORING_OP_SEND_ZC] = {
+		.name			= "SEND_ZC",
 		.needs_file		= 1,
 		.unbound_nonreg_file	= 1,
 		.pollout		= 1,
 		.audit_skip		= 1,
 		.ioprio			= 1,
+		.manual_alloc		= 1,
 #if defined(CONFIG_NET)
+		.async_size		= sizeof(struct io_async_msghdr),
 		.prep			= io_sendzc_prep,
 		.issue			= io_sendzc,
+		.prep_async		= io_sendzc_prep_async,
+		.cleanup		= io_sendzc_cleanup,
 #else
 		.prep			= io_eopnotsupp_prep,
 #endif
-
 	},
 };
 
diff --git a/io_uring/opdef.h b/io_uring/opdef.h
index ece8ed4f96c4..763c6e54e2ee 100644
--- a/io_uring/opdef.h
+++ b/io_uring/opdef.h
@@ -25,6 +25,8 @@ struct io_op_def {
 	unsigned		ioprio : 1;
 	/* supports iopoll */
 	unsigned		iopoll : 1;
+	/* opcode specific path will handle ->async_data allocation if needed */
+	unsigned		manual_alloc : 1;
 	/* size of async data needed, if any */
 	unsigned short		async_size;
 
diff --git a/io_uring/poll.c b/io_uring/poll.c
index d5bad0bea6e4..0d9f49c575e0 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -857,7 +857,7 @@ int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (sqe->buf_index || sqe->off || sqe->addr)
 		return -EINVAL;
 	flags = READ_ONCE(sqe->len);
-	if (flags & ~(IORING_POLL_ADD_MULTI|IORING_POLL_ADD_LEVEL))
+	if (flags & ~IORING_POLL_ADD_MULTI)
 		return -EINVAL;
 	if ((flags & IORING_POLL_ADD_MULTI) && (req->flags & REQ_F_CQE_SKIP))
 		return -EINVAL;
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 71359a4d0bd4..cf3272113214 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -15,14 +15,12 @@
 #include "io_uring.h"
 #include "openclose.h"
 #include "rsrc.h"
-#include "notif.h"
 
 struct io_rsrc_update {
 	struct file			*file;
 	u64				arg;
 	u32				nr_args;
 	u32				offset;
-	int				type;
 };
 
 static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
@@ -655,7 +653,7 @@ __cold int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
 	return -EINVAL;
 }
 
-int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_rsrc_update *up = io_kiocb_to_cmd(req, struct io_rsrc_update);
 
@@ -669,7 +667,6 @@ int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (!up->nr_args)
 		return -EINVAL;
 	up->arg = READ_ONCE(sqe->addr);
-	up->type = READ_ONCE(sqe->ioprio);
 	return 0;
 }
 
@@ -712,7 +709,7 @@ static int io_files_update_with_index_alloc(struct io_kiocb *req,
 	return ret;
 }
 
-static int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
+int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_rsrc_update *up = io_kiocb_to_cmd(req, struct io_rsrc_update);
 	struct io_ring_ctx *ctx = req->ctx;
@@ -741,54 +738,6 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
 	return IOU_OK;
 }
 
-static int io_notif_update(struct io_kiocb *req, unsigned int issue_flags)
-{
-	struct io_rsrc_update *up = io_kiocb_to_cmd(req, struct io_rsrc_update);
-	struct io_ring_ctx *ctx = req->ctx;
-	unsigned len = up->nr_args;
-	unsigned idx_end, idx = up->offset;
-	int ret = 0;
-
-	io_ring_submit_lock(ctx, issue_flags);
-	if (unlikely(check_add_overflow(idx, len, &idx_end))) {
-		ret = -EOVERFLOW;
-		goto out;
-	}
-	if (unlikely(idx_end > ctx->nr_notif_slots)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	for (; idx < idx_end; idx++) {
-		struct io_notif_slot *slot = &ctx->notif_slots[idx];
-
-		if (!slot->notif)
-			continue;
-		if (up->arg)
-			slot->tag = up->arg;
-		io_notif_slot_flush_submit(slot, issue_flags);
-	}
-out:
-	io_ring_submit_unlock(ctx, issue_flags);
-	if (ret < 0)
-		req_set_fail(req);
-	io_req_set_res(req, ret, 0);
-	return IOU_OK;
-}
-
-int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags)
-{
-	struct io_rsrc_update *up = io_kiocb_to_cmd(req, struct io_rsrc_update);
-
-	switch (up->type) {
-	case IORING_RSRC_UPDATE_FILES:
-		return io_files_update(req, issue_flags);
-	case IORING_RSRC_UPDATE_NOTIF:
-		return io_notif_update(req, issue_flags);
-	}
-	return -EINVAL;
-}
-
 int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx,
 			  struct io_rsrc_node *node, void *rsrc)
 {
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index f3a9a177941f..9bce15665444 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -167,8 +167,8 @@ static inline u64 *io_get_tag_slot(struct io_rsrc_data *data, unsigned int idx)
 	return &data->tags[table_idx][off];
 }
 
-int io_rsrc_update(struct io_kiocb *req, unsigned int issue_flags);
-int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_files_update(struct io_kiocb *req, unsigned int issue_flags);
+int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 
 int __io_account_mem(struct user_struct *user, unsigned long nr_pages);
 
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 1babd77da79c..76ebcfebc9a6 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -206,6 +206,20 @@ static bool __io_complete_rw_common(struct io_kiocb *req, long res)
 	return false;
 }
 
+static inline int io_fixup_rw_res(struct io_kiocb *req, long res)
+{
+	struct io_async_rw *io = req->async_data;
+
+	/* add previously done IO, if any */
+	if (req_has_async_data(req) && io->bytes_done > 0) {
+		if (res < 0)
+			res = io->bytes_done;
+		else
+			res += io->bytes_done;
+	}
+	return res;
+}
+
 static void io_complete_rw(struct kiocb *kiocb, long res)
 {
 	struct io_rw *rw = container_of(kiocb, struct io_rw, kiocb);
@@ -213,7 +227,7 @@ static void io_complete_rw(struct kiocb *kiocb, long res)
 
 	if (__io_complete_rw_common(req, res))
 		return;
-	io_req_set_res(req, res, 0);
+	io_req_set_res(req, io_fixup_rw_res(req, res), 0);
 	req->io_task_work.func = io_req_task_complete;
 	io_req_task_work_add(req);
 }
@@ -240,22 +254,14 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
 static int kiocb_done(struct io_kiocb *req, ssize_t ret,
 		       unsigned int issue_flags)
 {
-	struct io_async_rw *io = req->async_data;
 	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
-
-	/* add previously done IO, if any */
-	if (req_has_async_data(req) && io->bytes_done > 0) {
-		if (ret < 0)
-			ret = io->bytes_done;
-		else
-			ret += io->bytes_done;
-	}
+	unsigned final_ret = io_fixup_rw_res(req, ret);
 
 	if (req->flags & REQ_F_CUR_POS)
 		req->file->f_pos = rw->kiocb.ki_pos;
 	if (ret >= 0 && (rw->kiocb.ki_complete == io_complete_rw)) {
 		if (!__io_complete_rw_common(req, ret)) {
-			io_req_set_res(req, req->cqe.res,
+			io_req_set_res(req, final_ret,
 				       io_put_kbuf(req, issue_flags));
 			return IOU_OK;
 		}
@@ -268,7 +274,7 @@ static int kiocb_done(struct io_kiocb *req, ssize_t ret,
 		if (io_resubmit_prep(req))
 			io_req_task_queue_reissue(req);
 		else
-			io_req_task_queue_fail(req, ret);
+			io_req_task_queue_fail(req, final_ret);
 	}
 	return IOU_ISSUE_SKIP_COMPLETE;
 }
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index 8e0cc2d9205e..e78b6f980d77 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -3,6 +3,7 @@
 #include <linux/errno.h>
 #include <linux/file.h>
 #include <linux/io_uring.h>
+#include <linux/security.h>
 
 #include <uapi/linux/io_uring.h>
 
@@ -88,6 +89,10 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
 	if (!req->file->f_op->uring_cmd)
 		return -EOPNOTSUPP;
 
+	ret = security_uring_cmd(ioucmd);
+	if (ret)
+		return ret;
+
 	if (ctx->flags & IORING_SETUP_SQE128)
 		issue_flags |= IO_URING_F_SQE128;
 	if (ctx->flags & IORING_SETUP_CQE32)
@@ -112,7 +117,7 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
 		if (ret < 0)
 			req_set_fail(req);
 		io_req_set_res(req, ret, 0);
-		return IOU_OK;
+		return ret;
 	}
 
 	return IOU_ISSUE_SKIP_COMPLETE;
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index 6432a37ac1c9..c565fbf66ac8 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -102,6 +102,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa
 
 	ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, 0);
 	if (ret < 0) {
+		audit_mark->path = NULL;
 		fsnotify_put_mark(&audit_mark->mark);
 		audit_mark = ERR_PTR(ret);
 	}
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index dd8d9ab747c3..79a5da1bc5bb 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1940,6 +1940,7 @@ void __audit_uring_exit(int success, long code)
 		goto out;
 	}
 
+	audit_return_fixup(ctx, success, code);
 	if (ctx->context == AUDIT_CTX_SYSCALL) {
 		/*
 		 * NOTE: See the note in __audit_uring_entry() about the case
@@ -1981,7 +1982,6 @@ void __audit_uring_exit(int success, long code)
 	audit_filter_inodes(current, ctx);
 	if (ctx->current_state != AUDIT_STATE_RECORD)
 		goto out;
-	audit_return_fixup(ctx, success, code);
 	audit_log_exit();
 
 out:
@@ -2065,13 +2065,13 @@ void __audit_syscall_exit(int success, long return_code)
 	if (!list_empty(&context->killed_trees))
 		audit_kill_trees(context);
 
+	audit_return_fixup(context, success, return_code);
 	/* run through both filters to ensure we set the filterkey properly */
 	audit_filter_syscall(current, context);
 	audit_filter_inodes(current, context);
 	if (context->current_state < AUDIT_STATE_RECORD)
 		goto out;
 
-	audit_return_fixup(context, success, return_code);
 	audit_log_exit();
 
 out:
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index fa71d58b7ded..761998fda762 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -335,6 +335,7 @@ BTF_ID(func, bpf_lsm_task_getsecid_obj)
 BTF_ID(func, bpf_lsm_task_prctl)
 BTF_ID(func, bpf_lsm_task_setscheduler)
 BTF_ID(func, bpf_lsm_task_to_inode)
+BTF_ID(func, bpf_lsm_userns_create)
 BTF_SET_END(sleepable_lsm_hooks)
 
 bool bpf_lsm_is_sleepable_hook(u32 btf_id)
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 59b7eb60d5b4..4a400cd63731 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -921,8 +921,10 @@ static void purge_effective_progs(struct cgroup *cgrp, struct bpf_prog *prog,
 				pos++;
 			}
 		}
+
+		/* no link or prog match, skip the cgroup of this layer */
+		continue;
 found:
-		BUG_ON(!cg);
 		progs = rcu_dereference_protected(
 				desc->bpf.effective[atype],
 				lockdep_is_held(&cgroup_mutex));
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c1e10d088dbb..3d9eb3ae334c 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -971,7 +971,7 @@ pure_initcall(bpf_jit_charge_init);
 
 int bpf_jit_charge_modmem(u32 size)
 {
-	if (atomic_long_add_return(size, &bpf_jit_current) > bpf_jit_limit) {
+	if (atomic_long_add_return(size, &bpf_jit_current) > READ_ONCE(bpf_jit_limit)) {
 		if (!bpf_capable()) {
 			atomic_long_sub(size, &bpf_jit_current);
 			return -EPERM;
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 85fa9dbfa8bf..82c61612f382 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -24,7 +24,7 @@ void bpf_sk_reuseport_detach(struct sock *sk)
 	struct sock __rcu **socks;
 
 	write_lock_bh(&sk->sk_callback_lock);
-	socks = __rcu_dereference_sk_user_data_with_flags(sk, SK_USER_DATA_BPF);
+	socks = __locked_read_sk_user_data_with_flags(sk, SK_USER_DATA_BPF);
 	if (socks) {
 		WRITE_ONCE(sk->sk_user_data, NULL);
 		/*
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a4d40d98428a..27760627370d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5197,7 +5197,7 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_sys_bpf:
-		return &bpf_sys_bpf_proto;
+		return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto;
 	case BPF_FUNC_btf_find_by_name_kind:
 		return &bpf_btf_find_by_name_kind_proto;
 	case BPF_FUNC_sys_close:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 096fdac70165..3eadb14e090b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6066,6 +6066,9 @@ skip_type_check:
 			return -EACCES;
 		}
 		meta->mem_size = reg->var_off.value;
+		err = mark_chain_precision(env, regno);
+		if (err)
+			return err;
 		break;
 	case ARG_PTR_TO_INT:
 	case ARG_PTR_TO_LONG:
@@ -7030,8 +7033,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
 	struct bpf_reg_state *regs = cur_regs(env), *reg;
 	struct bpf_map *map = meta->map_ptr;
-	struct tnum range;
-	u64 val;
+	u64 val, max;
 	int err;
 
 	if (func_id != BPF_FUNC_tail_call)
@@ -7041,10 +7043,11 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 		return -EINVAL;
 	}
 
-	range = tnum_range(0, map->max_entries - 1);
 	reg = &regs[BPF_REG_3];
+	val = reg->var_off.value;
+	max = map->max_entries;
 
-	if (!register_is_const(reg) || !tnum_in(range, reg->var_off)) {
+	if (!(register_is_const(reg) && val < max)) {
 		bpf_map_key_store(aux, BPF_MAP_KEY_POISON);
 		return 0;
 	}
@@ -7052,8 +7055,6 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	err = mark_chain_precision(env, BPF_REG_3);
 	if (err)
 		return err;
-
-	val = reg->var_off.value;
 	if (bpf_map_key_unseen(aux))
 		bpf_map_key_store(aux, val);
 	else if (!bpf_map_key_poisoned(aux) &&
diff --git a/kernel/cfi.c b/kernel/cfi.c
index 2046276ee234..08caad776717 100644
--- a/kernel/cfi.c
+++ b/kernel/cfi.c
@@ -1,339 +1,101 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Clang Control Flow Integrity (CFI) error and slowpath handling.
+ * Clang Control Flow Integrity (CFI) error handling.
  *
- * Copyright (C) 2021 Google LLC
+ * Copyright (C) 2022 Google LLC
  */
 
-#include <linux/hardirq.h>
-#include <linux/kallsyms.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/printk.h>
-#include <linux/ratelimit.h>
-#include <linux/rcupdate.h>
-#include <linux/vmalloc.h>
-#include <asm/cacheflush.h>
-#include <asm/set_memory.h>
+#include <linux/cfi.h>
 
-/* Compiler-defined handler names */
-#ifdef CONFIG_CFI_PERMISSIVE
-#define cfi_failure_handler	__ubsan_handle_cfi_check_fail
-#else
-#define cfi_failure_handler	__ubsan_handle_cfi_check_fail_abort
-#endif
-
-static inline void handle_cfi_failure(void *ptr)
+enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr,
+				      unsigned long *target, u32 type)
 {
-	if (IS_ENABLED(CONFIG_CFI_PERMISSIVE))
-		WARN_RATELIMIT(1, "CFI failure (target: %pS):\n", ptr);
+	if (target)
+		pr_err("CFI failure at %pS (target: %pS; expected type: 0x%08x)\n",
+		       (void *)addr, (void *)*target, type);
 	else
-		panic("CFI failure (target: %pS)\n", ptr);
-}
-
-#ifdef CONFIG_MODULES
-#ifdef CONFIG_CFI_CLANG_SHADOW
-/*
- * Index type. A 16-bit index can address at most (2^16)-2 pages (taking
- * into account SHADOW_INVALID), i.e. ~256M with 4k pages.
- */
-typedef u16 shadow_t;
-#define SHADOW_INVALID		((shadow_t)~0UL)
-
-struct cfi_shadow {
-	/* Page index for the beginning of the shadow */
-	unsigned long base;
-	/* An array of __cfi_check locations (as indices to the shadow) */
-	shadow_t shadow[1];
-} __packed;
-
-/*
- * The shadow covers ~128M from the beginning of the module region. If
- * the region is larger, we fall back to __module_address for the rest.
- */
-#define __SHADOW_RANGE		(_UL(SZ_128M) >> PAGE_SHIFT)
-
-/* The in-memory size of struct cfi_shadow, always at least one page */
-#define __SHADOW_PAGES		((__SHADOW_RANGE * sizeof(shadow_t)) >> PAGE_SHIFT)
-#define SHADOW_PAGES		max(1UL, __SHADOW_PAGES)
-#define SHADOW_SIZE		(SHADOW_PAGES << PAGE_SHIFT)
-
-/* The actual size of the shadow array, minus metadata */
-#define SHADOW_ARR_SIZE		(SHADOW_SIZE - offsetof(struct cfi_shadow, shadow))
-#define SHADOW_ARR_SLOTS	(SHADOW_ARR_SIZE / sizeof(shadow_t))
-
-static DEFINE_MUTEX(shadow_update_lock);
-static struct cfi_shadow __rcu *cfi_shadow __read_mostly;
+		pr_err("CFI failure at %pS (no target information)\n",
+		       (void *)addr);
 
-/* Returns the index in the shadow for the given address */
-static inline int ptr_to_shadow(const struct cfi_shadow *s, unsigned long ptr)
-{
-	unsigned long index;
-	unsigned long page = ptr >> PAGE_SHIFT;
-
-	if (unlikely(page < s->base))
-		return -1; /* Outside of module area */
-
-	index = page - s->base;
-
-	if (index >= SHADOW_ARR_SLOTS)
-		return -1; /* Cannot be addressed with shadow */
-
-	return (int)index;
-}
-
-/* Returns the page address for an index in the shadow */
-static inline unsigned long shadow_to_ptr(const struct cfi_shadow *s,
-	int index)
-{
-	if (unlikely(index < 0 || index >= SHADOW_ARR_SLOTS))
-		return 0;
-
-	return (s->base + index) << PAGE_SHIFT;
-}
-
-/* Returns the __cfi_check function address for the given shadow location */
-static inline unsigned long shadow_to_check_fn(const struct cfi_shadow *s,
-	int index)
-{
-	if (unlikely(index < 0 || index >= SHADOW_ARR_SLOTS))
-		return 0;
-
-	if (unlikely(s->shadow[index] == SHADOW_INVALID))
-		return 0;
-
-	/* __cfi_check is always page aligned */
-	return (s->base + s->shadow[index]) << PAGE_SHIFT;
-}
-
-static void prepare_next_shadow(const struct cfi_shadow __rcu *prev,
-		struct cfi_shadow *next)
-{
-	int i, index, check;
-
-	/* Mark everything invalid */
-	memset(next->shadow, 0xFF, SHADOW_ARR_SIZE);
-
-	if (!prev)
-		return; /* No previous shadow */
-
-	/* If the base address didn't change, an update is not needed */
-	if (prev->base == next->base) {
-		memcpy(next->shadow, prev->shadow, SHADOW_ARR_SIZE);
-		return;
-	}
-
-	/* Convert the previous shadow to the new address range */
-	for (i = 0; i < SHADOW_ARR_SLOTS; ++i) {
-		if (prev->shadow[i] == SHADOW_INVALID)
-			continue;
-
-		index = ptr_to_shadow(next, shadow_to_ptr(prev, i));
-		if (index < 0)
-			continue;
-
-		check = ptr_to_shadow(next,
-				shadow_to_check_fn(prev, prev->shadow[i]));
-		if (check < 0)
-			continue;
-
-		next->shadow[index] = (shadow_t)check;
-	}
-}
-
-static void add_module_to_shadow(struct cfi_shadow *s, struct module *mod,
-			unsigned long min_addr, unsigned long max_addr)
-{
-	int check_index;
-	unsigned long check = (unsigned long)mod->cfi_check;
-	unsigned long ptr;
-
-	if (unlikely(!PAGE_ALIGNED(check))) {
-		pr_warn("cfi: not using shadow for module %s\n", mod->name);
-		return;
+	if (IS_ENABLED(CONFIG_CFI_PERMISSIVE)) {
+		__warn(NULL, 0, (void *)addr, 0, regs, NULL);
+		return BUG_TRAP_TYPE_WARN;
 	}
 
-	check_index = ptr_to_shadow(s, check);
-	if (check_index < 0)
-		return; /* Module not addressable with shadow */
-
-	/* For each page, store the check function index in the shadow */
-	for (ptr = min_addr; ptr <= max_addr; ptr += PAGE_SIZE) {
-		int index = ptr_to_shadow(s, ptr);
-
-		if (index >= 0) {
-			/* Each page must only contain one module */
-			WARN_ON_ONCE(s->shadow[index] != SHADOW_INVALID);
-			s->shadow[index] = (shadow_t)check_index;
-		}
-	}
+	return BUG_TRAP_TYPE_BUG;
 }
 
-static void remove_module_from_shadow(struct cfi_shadow *s, struct module *mod,
-		unsigned long min_addr, unsigned long max_addr)
+#ifdef CONFIG_ARCH_USES_CFI_TRAPS
+static inline unsigned long trap_address(s32 *p)
 {
-	unsigned long ptr;
-
-	for (ptr = min_addr; ptr <= max_addr; ptr += PAGE_SIZE) {
-		int index = ptr_to_shadow(s, ptr);
-
-		if (index >= 0)
-			s->shadow[index] = SHADOW_INVALID;
-	}
+	return (unsigned long)((long)p + (long)*p);
 }
 
-typedef void (*update_shadow_fn)(struct cfi_shadow *, struct module *,
-			unsigned long min_addr, unsigned long max_addr);
-
-static void update_shadow(struct module *mod, unsigned long base_addr,
-		update_shadow_fn fn)
+static bool is_trap(unsigned long addr, s32 *start, s32 *end)
 {
-	struct cfi_shadow *prev;
-	struct cfi_shadow *next;
-	unsigned long min_addr, max_addr;
-
-	next = vmalloc(SHADOW_SIZE);
-
-	mutex_lock(&shadow_update_lock);
-	prev = rcu_dereference_protected(cfi_shadow,
-					 mutex_is_locked(&shadow_update_lock));
-
-	if (next) {
-		next->base = base_addr >> PAGE_SHIFT;
-		prepare_next_shadow(prev, next);
+	s32 *p;
 
-		min_addr = (unsigned long)mod->core_layout.base;
-		max_addr = min_addr + mod->core_layout.text_size;
-		fn(next, mod, min_addr & PAGE_MASK, max_addr & PAGE_MASK);
-
-		set_memory_ro((unsigned long)next, SHADOW_PAGES);
-	}
-
-	rcu_assign_pointer(cfi_shadow, next);
-	mutex_unlock(&shadow_update_lock);
-	synchronize_rcu();
-
-	if (prev) {
-		set_memory_rw((unsigned long)prev, SHADOW_PAGES);
-		vfree(prev);
+	for (p = start; p < end; ++p) {
+		if (trap_address(p) == addr)
+			return true;
 	}
-}
 
-void cfi_module_add(struct module *mod, unsigned long base_addr)
-{
-	update_shadow(mod, base_addr, add_module_to_shadow);
+	return false;
 }
 
-void cfi_module_remove(struct module *mod, unsigned long base_addr)
-{
-	update_shadow(mod, base_addr, remove_module_from_shadow);
-}
-
-static inline cfi_check_fn ptr_to_check_fn(const struct cfi_shadow __rcu *s,
-	unsigned long ptr)
+#ifdef CONFIG_MODULES
+/* Populates `kcfi_trap(_end)?` fields in `struct module`. */
+void module_cfi_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
+			 struct module *mod)
 {
-	int index;
-
-	if (unlikely(!s))
-		return NULL; /* No shadow available */
-
-	index = ptr_to_shadow(s, ptr);
-	if (index < 0)
-		return NULL; /* Cannot be addressed with shadow */
+	char *secstrings;
+	unsigned int i;
 
-	return (cfi_check_fn)shadow_to_check_fn(s, index);
-}
-
-static inline cfi_check_fn find_shadow_check_fn(unsigned long ptr)
-{
-	cfi_check_fn fn;
+	mod->kcfi_traps = NULL;
+	mod->kcfi_traps_end = NULL;
 
-	rcu_read_lock_sched_notrace();
-	fn = ptr_to_check_fn(rcu_dereference_sched(cfi_shadow), ptr);
-	rcu_read_unlock_sched_notrace();
+	secstrings = (char *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
-	return fn;
-}
-
-#else /* !CONFIG_CFI_CLANG_SHADOW */
+	for (i = 1; i < hdr->e_shnum; i++) {
+		if (strcmp(secstrings + sechdrs[i].sh_name, "__kcfi_traps"))
+			continue;
 
-static inline cfi_check_fn find_shadow_check_fn(unsigned long ptr)
-{
-	return NULL;
+		mod->kcfi_traps = (s32 *)sechdrs[i].sh_addr;
+		mod->kcfi_traps_end = (s32 *)(sechdrs[i].sh_addr + sechdrs[i].sh_size);
+		break;
+	}
 }
 
-#endif /* CONFIG_CFI_CLANG_SHADOW */
-
-static inline cfi_check_fn find_module_check_fn(unsigned long ptr)
+static bool is_module_cfi_trap(unsigned long addr)
 {
-	cfi_check_fn fn = NULL;
 	struct module *mod;
+	bool found = false;
 
 	rcu_read_lock_sched_notrace();
-	mod = __module_address(ptr);
-	if (mod)
-		fn = mod->cfi_check;
-	rcu_read_unlock_sched_notrace();
-
-	return fn;
-}
-
-static inline cfi_check_fn find_check_fn(unsigned long ptr)
-{
-	cfi_check_fn fn = NULL;
-	unsigned long flags;
-	bool rcu_idle;
-
-	if (is_kernel_text(ptr))
-		return __cfi_check;
 
-	/*
-	 * Indirect call checks can happen when RCU is not watching. Both
-	 * the shadow and __module_address use RCU, so we need to wake it
-	 * up if necessary.
-	 */
-	rcu_idle = !rcu_is_watching();
-	if (rcu_idle) {
-		local_irq_save(flags);
-		ct_irq_enter();
-	}
-
-	if (IS_ENABLED(CONFIG_CFI_CLANG_SHADOW))
-		fn = find_shadow_check_fn(ptr);
-	if (!fn)
-		fn = find_module_check_fn(ptr);
+	mod = __module_address(addr);
+	if (mod)
+		found = is_trap(addr, mod->kcfi_traps, mod->kcfi_traps_end);
 
-	if (rcu_idle) {
-		ct_irq_exit();
-		local_irq_restore(flags);
-	}
+	rcu_read_unlock_sched_notrace();
 
-	return fn;
+	return found;
 }
-
-void __cfi_slowpath_diag(uint64_t id, void *ptr, void *diag)
+#else /* CONFIG_MODULES */
+static inline bool is_module_cfi_trap(unsigned long addr)
 {
-	cfi_check_fn fn = find_check_fn((unsigned long)ptr);
-
-	if (likely(fn))
-		fn(id, ptr, diag);
-	else /* Don't allow unchecked modules */
-		handle_cfi_failure(ptr);
+	return false;
 }
-EXPORT_SYMBOL(__cfi_slowpath_diag);
+#endif /* CONFIG_MODULES */
 
-#else /* !CONFIG_MODULES */
+extern s32 __start___kcfi_traps[];
+extern s32 __stop___kcfi_traps[];
 
-void __cfi_slowpath_diag(uint64_t id, void *ptr, void *diag)
+bool is_cfi_trap(unsigned long addr)
 {
-	handle_cfi_failure(ptr); /* No modules */
-}
-EXPORT_SYMBOL(__cfi_slowpath_diag);
+	if (is_trap(addr, __start___kcfi_traps, __stop___kcfi_traps))
+		return true;
 
-#endif /* CONFIG_MODULES */
-
-void cfi_failure_handler(void *data, void *ptr, void *vtable)
-{
-	handle_cfi_failure(ptr);
+	return is_module_cfi_trap(addr);
 }
-EXPORT_SYMBOL(cfi_failure_handler);
+#endif /* CONFIG_ARCH_USES_CFI_TRAPS */
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 2ade21b54dc4..ff6a8099eb2a 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -59,6 +59,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 	int retval = 0;
 
 	mutex_lock(&cgroup_mutex);
+	cpus_read_lock();
 	percpu_down_write(&cgroup_threadgroup_rwsem);
 	for_each_root(root) {
 		struct cgroup *from_cgrp;
@@ -72,6 +73,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 			break;
 	}
 	percpu_up_write(&cgroup_threadgroup_rwsem);
+	cpus_read_unlock();
 	mutex_unlock(&cgroup_mutex);
 
 	return retval;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index ffaccd6373f1..5f2090d051ac 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1820,6 +1820,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 
 		if (ss->css_rstat_flush) {
 			list_del_rcu(&css->rstat_css_node);
+			synchronize_rcu();
 			list_add_rcu(&css->rstat_css_node,
 				     &dcgrp->rstat_css_list);
 		}
@@ -2370,6 +2371,47 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 EXPORT_SYMBOL_GPL(task_cgroup_path);
 
 /**
+ * cgroup_attach_lock - Lock for ->attach()
+ * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem
+ *
+ * cgroup migration sometimes needs to stabilize threadgroups against forks and
+ * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach()
+ * implementations (e.g. cpuset), also need to disable CPU hotplug.
+ * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can
+ * lead to deadlocks.
+ *
+ * Bringing up a CPU may involve creating and destroying tasks which requires
+ * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside
+ * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while
+ * write-locking threadgroup_rwsem, the locking order is reversed and we end up
+ * waiting for an on-going CPU hotplug operation which in turn is waiting for
+ * the threadgroup_rwsem to be released to create new tasks. For more details:
+ *
+ *   http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu
+ *
+ * Resolve the situation by always acquiring cpus_read_lock() before optionally
+ * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that
+ * CPU hotplug is disabled on entry.
+ */
+static void cgroup_attach_lock(bool lock_threadgroup)
+{
+	cpus_read_lock();
+	if (lock_threadgroup)
+		percpu_down_write(&cgroup_threadgroup_rwsem);
+}
+
+/**
+ * cgroup_attach_unlock - Undo cgroup_attach_lock()
+ * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem
+ */
+static void cgroup_attach_unlock(bool lock_threadgroup)
+{
+	if (lock_threadgroup)
+		percpu_up_write(&cgroup_threadgroup_rwsem);
+	cpus_read_unlock();
+}
+
+/**
  * cgroup_migrate_add_task - add a migration target task to a migration context
  * @task: target task
  * @mgctx: target migration context
@@ -2841,8 +2883,7 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
 }
 
 struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
-					     bool *locked)
-	__acquires(&cgroup_threadgroup_rwsem)
+					     bool *threadgroup_locked)
 {
 	struct task_struct *tsk;
 	pid_t pid;
@@ -2859,12 +2900,8 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
 	 * Therefore, we can skip the global lock.
 	 */
 	lockdep_assert_held(&cgroup_mutex);
-	if (pid || threadgroup) {
-		percpu_down_write(&cgroup_threadgroup_rwsem);
-		*locked = true;
-	} else {
-		*locked = false;
-	}
+	*threadgroup_locked = pid || threadgroup;
+	cgroup_attach_lock(*threadgroup_locked);
 
 	rcu_read_lock();
 	if (pid) {
@@ -2895,17 +2932,14 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
 	goto out_unlock_rcu;
 
 out_unlock_threadgroup:
-	if (*locked) {
-		percpu_up_write(&cgroup_threadgroup_rwsem);
-		*locked = false;
-	}
+	cgroup_attach_unlock(*threadgroup_locked);
+	*threadgroup_locked = false;
 out_unlock_rcu:
 	rcu_read_unlock();
 	return tsk;
 }
 
-void cgroup_procs_write_finish(struct task_struct *task, bool locked)
-	__releases(&cgroup_threadgroup_rwsem)
+void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked)
 {
 	struct cgroup_subsys *ss;
 	int ssid;
@@ -2913,8 +2947,8 @@ void cgroup_procs_write_finish(struct task_struct *task, bool locked)
 	/* release reference from cgroup_procs_write_start() */
 	put_task_struct(task);
 
-	if (locked)
-		percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock(threadgroup_locked);
+
 	for_each_subsys(ss, ssid)
 		if (ss->post_attach)
 			ss->post_attach();
@@ -3000,8 +3034,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	 * write-locking can be skipped safely.
 	 */
 	has_tasks = !list_empty(&mgctx.preloaded_src_csets);
-	if (has_tasks)
-		percpu_down_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_lock(has_tasks);
 
 	/* NULL dst indicates self on default hierarchy */
 	ret = cgroup_migrate_prepare_dst(&mgctx);
@@ -3022,8 +3055,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	ret = cgroup_migrate_execute(&mgctx);
 out_finish:
 	cgroup_migrate_finish(&mgctx);
-	if (has_tasks)
-		percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock(has_tasks);
 	return ret;
 }
 
@@ -3698,7 +3730,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
 	}
 
 	psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
-	new = psi_trigger_create(psi, buf, nbytes, res);
+	new = psi_trigger_create(psi, buf, res);
 	if (IS_ERR(new)) {
 		cgroup_put(cgrp);
 		return PTR_ERR(new);
@@ -4971,13 +5003,13 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	struct task_struct *task;
 	const struct cred *saved_cred;
 	ssize_t ret;
-	bool locked;
+	bool threadgroup_locked;
 
 	dst_cgrp = cgroup_kn_lock_live(of->kn, false);
 	if (!dst_cgrp)
 		return -ENODEV;
 
-	task = cgroup_procs_write_start(buf, threadgroup, &locked);
+	task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked);
 	ret = PTR_ERR_OR_ZERO(task);
 	if (ret)
 		goto out_unlock;
@@ -5003,7 +5035,7 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	ret = cgroup_attach_task(dst_cgrp, task, threadgroup);
 
 out_finish:
-	cgroup_procs_write_finish(task, locked);
+	cgroup_procs_write_finish(task, threadgroup_locked);
 out_unlock:
 	cgroup_kn_unlock(of->kn);
 
@@ -6017,6 +6049,9 @@ struct cgroup *cgroup_get_from_id(u64 id)
 	if (!kn)
 		goto out;
 
+	if (kernfs_type(kn) != KERNFS_DIR)
+		goto put;
+
 	rcu_read_lock();
 
 	cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv);
@@ -6024,7 +6059,7 @@ struct cgroup *cgroup_get_from_id(u64 id)
 		cgrp = NULL;
 
 	rcu_read_unlock();
-
+put:
 	kernfs_put(kn);
 out:
 	return cgrp;
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 58aadfda9b8b..1f3a55297f39 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2289,7 +2289,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 	cgroup_taskset_first(tset, &css);
 	cs = css_cs(css);
 
-	cpus_read_lock();
+	lockdep_assert_cpus_held();	/* see cgroup_attach_lock() */
 	percpu_down_write(&cpuset_rwsem);
 
 	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
@@ -2343,7 +2343,6 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 		wake_up(&cpuset_attach_wq);
 
 	percpu_up_write(&cpuset_rwsem);
-	cpus_read_unlock();
 }
 
 /* The various types of files and directories in a cpuset file system */
diff --git a/kernel/configs/rust.config b/kernel/configs/rust.config
new file mode 100644
index 000000000000..38a7c5362c9c
--- /dev/null
+++ b/kernel/configs/rust.config
@@ -0,0 +1 @@
+CONFIG_RUST=y
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 07b26df453a9..a0eb4d5cf557 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -494,6 +494,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 
 #ifdef CONFIG_KALLSYMS
 	VMCOREINFO_SYMBOL(kallsyms_names);
+	VMCOREINFO_SYMBOL(kallsyms_num_syms);
 	VMCOREINFO_SYMBOL(kallsyms_token_table);
 	VMCOREINFO_SYMBOL(kallsyms_token_index);
 #ifdef CONFIG_KALLSYMS_BASE_RELATIVE
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 2caafd13f8aa..18c93c2276ca 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -350,11 +350,10 @@ static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket,
 						   unsigned long *flags)
 {
 
-	unsigned int max_range = dma_get_max_seg_size(ref->dev);
 	struct dma_debug_entry *entry, index = *ref;
-	unsigned int range = 0;
+	int limit = min(HASH_SIZE, (index.dev_addr >> HASH_FN_SHIFT) + 1);
 
-	while (range <= max_range) {
+	for (int i = 0; i < limit; i++) {
 		entry = __hash_bucket_find(*bucket, ref, containing_match);
 
 		if (entry)
@@ -364,7 +363,6 @@ static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket,
 		 * Nothing found, go back a hash bucket
 		 */
 		put_hash_bucket(*bucket, *flags);
-		range          += (1 << HASH_FN_SHIFT);
 		index.dev_addr -= (1 << HASH_FN_SHIFT);
 		*bucket = get_hash_bucket(&index, flags);
 	}
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 49cbf3e33de7..27f272381cf2 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -707,7 +707,7 @@ int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL_GPL(dma_mmap_noncontiguous);
 
-int dma_supported(struct device *dev, u64 mask)
+static int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
@@ -721,7 +721,6 @@ int dma_supported(struct device *dev, u64 mask)
 		return 1;
 	return ops->dma_supported(dev, mask);
 }
-EXPORT_SYMBOL(dma_supported);
 
 bool dma_pci_p2pdma_supported(struct device *dev)
 {
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index c5a9190b218f..0ef6b12f961d 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -326,9 +326,6 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
 		swiotlb_adjust_nareas(num_possible_cpus());
 
 	nslabs = default_nslabs;
-	if (nslabs < IO_TLB_MIN_SLABS)
-		panic("%s: nslabs = %lu too small\n", __func__, nslabs);
-
 	/*
 	 * By default allocate the bounce buffer memory from low memory, but
 	 * allow to pick a location everywhere for hypervisors with guest
@@ -341,8 +338,7 @@ retry:
 	else
 		tlb = memblock_alloc_low(bytes, PAGE_SIZE);
 	if (!tlb) {
-		pr_warn("%s: Failed to allocate %zu bytes tlb structure\n",
-			__func__, bytes);
+		pr_warn("%s: failed to allocate tlb structure\n", __func__);
 		return;
 	}
 
@@ -579,7 +575,10 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 	}
 }
 
-#define slot_addr(start, idx)	((start) + ((idx) << IO_TLB_SHIFT))
+static inline phys_addr_t slot_addr(phys_addr_t start, phys_addr_t idx)
+{
+	return start + (idx << IO_TLB_SHIFT);
+}
 
 /*
  * Carefully handle integer overflow which can occur when boundary_mask == ~0UL.
@@ -765,7 +764,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 	/*
 	 * When dir == DMA_FROM_DEVICE we could omit the copy from the orig
 	 * to the tlb buffer, if we knew for sure the device will
-	 * overwirte the entire current content. But we don't. Thus
+	 * overwrite the entire current content. But we don't. Thus
 	 * unconditional bounce may prevent leaking swiotlb content (i.e.
 	 * kernel memory) to user-space.
 	 */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2621fd24ad26..ff4bffc502c6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6893,9 +6893,16 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 {
 	struct perf_event *leader = event->group_leader, *sub;
 	u64 read_format = event->attr.read_format;
+	unsigned long flags;
 	u64 values[6];
 	int n = 0;
 
+	/*
+	 * Disabling interrupts avoids all counter scheduling
+	 * (context switches, timer based rotation and IPIs).
+	 */
+	local_irq_save(flags);
+
 	values[n++] = 1 + leader->nr_siblings;
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
@@ -6931,6 +6938,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 
 		__output_copy(handle, values, n * sizeof(u64));
 	}
+
+	local_irq_restore(flags);
 }
 
 #define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\
diff --git a/kernel/fork.c b/kernel/fork.c
index 90c85b17bf69..2b6bd511c6ed 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1225,6 +1225,7 @@ void mmput_async(struct mm_struct *mm)
 		schedule_work(&mm->async_put_work);
 	}
 }
+EXPORT_SYMBOL_GPL(mmput_async);
 #endif
 
 /**
@@ -2046,11 +2047,8 @@ static __latent_entropy struct task_struct *copy_process(
 	/*
 	 * If the new process will be in a different time namespace
 	 * do not allow it to share VM or a thread group with the forking task.
-	 *
-	 * On vfork, the child process enters the target time namespace only
-	 * after exec.
 	 */
-	if ((clone_flags & (CLONE_VM | CLONE_VFORK)) == CLONE_VM) {
+	if (clone_flags & (CLONE_THREAD | CLONE_VM)) {
 		if (nsp->time_ns != nsp->time_ns_for_children)
 			return ERR_PTR(-EINVAL);
 	}
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 3e7e2c2ad2f7..60c20f301a6b 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -50,12 +50,20 @@ static unsigned int kallsyms_expand_symbol(unsigned int off,
 	data = &kallsyms_names[off];
 	len = *data;
 	data++;
+	off++;
+
+	/* If MSB is 1, it is a "big" symbol, so needs an additional byte. */
+	if ((len & 0x80) != 0) {
+		len = (len & 0x7F) | (*data << 7);
+		data++;
+		off++;
+	}
 
 	/*
 	 * Update the offset to return the offset for the next symbol on
 	 * the compressed stream.
 	 */
-	off += len + 1;
+	off += len;
 
 	/*
 	 * For every byte on the compressed symbol data, copy the table
@@ -108,7 +116,7 @@ static char kallsyms_get_symbol_type(unsigned int off)
 static unsigned int get_symbol_offset(unsigned long pos)
 {
 	const u8 *name;
-	int i;
+	int i, len;
 
 	/*
 	 * Use the closest marker we have. We have markers every 256 positions,
@@ -122,8 +130,18 @@ static unsigned int get_symbol_offset(unsigned long pos)
 	 * so we just need to add the len to the current pointer for every
 	 * symbol we wish to skip.
 	 */
-	for (i = 0; i < (pos & 0xFF); i++)
-		name = name + (*name) + 1;
+	for (i = 0; i < (pos & 0xFF); i++) {
+		len = *name;
+
+		/*
+		 * If MSB is 1, it is a "big" symbol, so we need to look into
+		 * the next byte (and skip it, too).
+		 */
+		if ((len & 0x80) != 0)
+			len = ((len & 0x7F) | (name[1] << 7)) + 1;
+
+		name = name + len + 1;
+	}
 
 	return name - kallsyms_names;
 }
@@ -159,7 +177,6 @@ static bool cleanup_symbol_name(char *s)
 	 * character in an identifier in C. Suffixes observed:
 	 * - foo.llvm.[0-9a-f]+
 	 * - foo.[0-9a-f]+
-	 * - foo.[0-9a-f]+.cfi_jt
 	 */
 	res = strchr(s, '.');
 	if (res) {
@@ -167,22 +184,6 @@ static bool cleanup_symbol_name(char *s)
 		return true;
 	}
 
-	if (!IS_ENABLED(CONFIG_CFI_CLANG) ||
-	    !IS_ENABLED(CONFIG_LTO_CLANG_THIN) ||
-	    CONFIG_CLANG_VERSION >= 130000)
-		return false;
-
-	/*
-	 * Prior to LLVM 13, the following suffixes were observed when thinLTO
-	 * and CFI are both enabled:
-	 * - foo$[0-9]+
-	 */
-	res = strrchr(s, '$');
-	if (res) {
-		*res = '\0';
-		return true;
-	}
-
 	return false;
 }
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 80697e5e03e4..ca9d834d0b84 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1562,6 +1562,7 @@ static int check_kprobe_address_safe(struct kprobe *p,
 	/* Ensure it is not in reserved area nor out of text */
 	if (!(core_kernel_text((unsigned long) p->addr) ||
 	    is_module_text_address((unsigned long) p->addr)) ||
+	    in_gate_area_no_mm((unsigned long) p->addr) ||
 	    within_kprobe_blacklist((unsigned long) p->addr) ||
 	    jump_label_text_reserved(p->addr, p->addr) ||
 	    static_call_text_reserved(p->addr, p->addr) ||
@@ -1707,11 +1708,12 @@ static struct kprobe *__disable_kprobe(struct kprobe *p)
 		/* Try to disarm and disable this/parent probe */
 		if (p == orig_p || aggr_kprobe_disabled(orig_p)) {
 			/*
-			 * If 'kprobes_all_disarmed' is set, 'orig_p'
-			 * should have already been disarmed, so
-			 * skip unneed disarming process.
+			 * Don't be lazy here.  Even if 'kprobes_all_disarmed'
+			 * is false, 'orig_p' might not have been armed yet.
+			 * Note arm_all_kprobes() __tries__ to arm all kprobes
+			 * on the best effort basis.
 			 */
-			if (!kprobes_all_disarmed) {
+			if (!kprobes_all_disarmed && !kprobe_disabled(orig_p)) {
 				ret = disarm_kprobe(orig_p, true);
 				if (ret) {
 					p->flags &= ~KPROBE_FLAG_DISABLED;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 3c677918d8f2..28a6b7ab4a0f 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -1050,8 +1050,7 @@ static void __kthread_queue_delayed_work(struct kthread_worker *worker,
 	struct timer_list *timer = &dwork->timer;
 	struct kthread_work *work = &dwork->work;
 
-	WARN_ON_FUNCTION_MISMATCH(timer->function,
-				  kthread_delayed_work_timer_fn);
+	WARN_ON_ONCE(timer->function != kthread_delayed_work_timer_fn);
 
 	/*
 	 * If @delay is 0, queue @dwork->work immediately.  This is for
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index bc475e62279d..ec06ce59d728 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -213,7 +213,7 @@ static int klp_resolve_symbols(Elf_Shdr *sechdrs, const char *strtab,
 	 * we use the smallest/strictest upper bound possible (56, based on
 	 * the current definition of MODULE_NAME_LEN) to prevent overflows.
 	 */
-	BUILD_BUG_ON(MODULE_NAME_LEN < 56 || KSYM_NAME_LEN != 128);
+	BUILD_BUG_ON(MODULE_NAME_LEN < 56 || KSYM_NAME_LEN != 512);
 
 	relas = (Elf_Rela *) relasec->sh_addr;
 	/* For each rela in this klp relocation section */
@@ -227,7 +227,7 @@ static int klp_resolve_symbols(Elf_Shdr *sechdrs, const char *strtab,
 
 		/* Format: .klp.sym.sym_objname.sym_name,sympos */
 		cnt = sscanf(strtab + sym->st_name,
-			     ".klp.sym.%55[^.].%127[^,],%lu",
+			     ".klp.sym.%55[^.].%511[^,],%lu",
 			     sym_objname, sym_name, &sympos);
 		if (cnt != 3) {
 			pr_err("symbol %s has an incorrectly formatted name\n",
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 6a477c622544..70c0b2c6fef8 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -53,6 +53,7 @@
 #include <linux/bsearch.h>
 #include <linux/dynamic_debug.h>
 #include <linux/audit.h>
+#include <linux/cfi.h>
 #include <uapi/linux/module.h>
 #include "internal.h"
 
@@ -1144,8 +1145,6 @@ void __weak module_arch_freeing_init(struct module *mod)
 {
 }
 
-static void cfi_cleanup(struct module *mod);
-
 /* Free a module, remove from lists, etc. */
 static void free_module(struct module *mod)
 {
@@ -1190,9 +1189,6 @@ static void free_module(struct module *mod)
 		       mod->name);
 	mutex_unlock(&module_mutex);
 
-	/* Clean up CFI for the module. */
-	cfi_cleanup(mod);
-
 	/* This may be empty, but that's OK */
 	module_arch_freeing_init(mod);
 	module_memfree(mod->init_layout.base);
@@ -2099,7 +2095,7 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 					      sizeof(*mod->static_call_sites),
 					      &mod->num_static_call_sites);
 #endif
-#ifdef CONFIG_KUNIT
+#if IS_ENABLED(CONFIG_KUNIT)
 	mod->kunit_suites = section_objs(info, ".kunit_test_suites",
 					      sizeof(*mod->kunit_suites),
 					      &mod->num_kunit_suites);
@@ -2602,8 +2598,9 @@ static int complete_formation(struct module *mod, struct load_info *info)
 	if (err < 0)
 		goto out;
 
-	/* This relies on module_mutex for list integrity. */
+	/* These rely on module_mutex for list integrity. */
 	module_bug_finalize(info->hdr, info->sechdrs, mod);
+	module_cfi_finalize(info->hdr, info->sechdrs, mod);
 
 	if (module_check_misalignment(mod))
 		goto out_misaligned;
@@ -2665,8 +2662,6 @@ static int unknown_module_param_cb(char *param, char *val, const char *modname,
 	return 0;
 }
 
-static void cfi_init(struct module *mod);
-
 /*
  * Allocate and load the module: note that size of section 0 is always
  * zero, and we rely on this for optional sections.
@@ -2796,9 +2791,6 @@ static int load_module(struct load_info *info, const char __user *uargs,
 
 	flush_module_icache(mod);
 
-	/* Setup CFI for the module. */
-	cfi_init(mod);
-
 	/* Now copy in args */
 	mod->args = strndup_user(uargs, ~0UL >> 1);
 	if (IS_ERR(mod->args)) {
@@ -2875,7 +2867,6 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	synchronize_rcu();
 	kfree(mod->args);
  free_arch_cleanup:
-	cfi_cleanup(mod);
 	module_arch_cleanup(mod);
  free_modinfo:
 	free_modinfo(mod);
@@ -2961,41 +2952,6 @@ static inline int within(unsigned long addr, void *start, unsigned long size)
 	return ((void *)addr >= start && (void *)addr < start + size);
 }
 
-static void cfi_init(struct module *mod)
-{
-#ifdef CONFIG_CFI_CLANG
-	initcall_t *init;
-#ifdef CONFIG_MODULE_UNLOAD
-	exitcall_t *exit;
-#endif
-
-	rcu_read_lock_sched();
-	mod->cfi_check = (cfi_check_fn)
-		find_kallsyms_symbol_value(mod, "__cfi_check");
-	init = (initcall_t *)
-		find_kallsyms_symbol_value(mod, "__cfi_jt_init_module");
-	/* Fix init/exit functions to point to the CFI jump table */
-	if (init)
-		mod->init = *init;
-#ifdef CONFIG_MODULE_UNLOAD
-	exit = (exitcall_t *)
-		find_kallsyms_symbol_value(mod, "__cfi_jt_cleanup_module");
-	if (exit)
-		mod->exit = *exit;
-#endif
-	rcu_read_unlock_sched();
-
-	cfi_module_add(mod, mod_tree.addr_min);
-#endif
-}
-
-static void cfi_cleanup(struct module *mod)
-{
-#ifdef CONFIG_CFI_CLANG
-	cfi_module_remove(mod, mod_tree.addr_min);
-#endif
-}
-
 /* Keep in sync with MODULE_FLAGS_BUF_SIZE !!! */
 char *module_flags(struct module *mod, char *buf, bool show_state)
 {
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index b4cbb406bc28..eec72ca962e2 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -179,8 +179,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 	if (IS_ERR(new_ns))
 		return  PTR_ERR(new_ns);
 
-	if ((flags & CLONE_VM) == 0)
-		timens_on_fork(new_ns, tsk);
+	timens_on_fork(new_ns, tsk);
 
 	tsk->nsproxy = new_ns;
 	return 0;
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index d8e1b270a065..503c2aa845a4 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -84,10 +84,15 @@ torture_param(int, fwd_progress_holdoff, 60, "Time between forward-progress test
 torture_param(bool, fwd_progress_need_resched, 1, "Hide cond_resched() behind need_resched()");
 torture_param(bool, gp_cond, false, "Use conditional/async GP wait primitives");
 torture_param(bool, gp_cond_exp, false, "Use conditional/async expedited GP wait primitives");
+torture_param(bool, gp_cond_full, false, "Use conditional/async full-state GP wait primitives");
+torture_param(bool, gp_cond_exp_full, false,
+		    "Use conditional/async full-stateexpedited GP wait primitives");
 torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
 torture_param(bool, gp_normal, false, "Use normal (non-expedited) GP wait primitives");
 torture_param(bool, gp_poll, false, "Use polling GP wait primitives");
 torture_param(bool, gp_poll_exp, false, "Use polling expedited GP wait primitives");
+torture_param(bool, gp_poll_full, false, "Use polling full-state GP wait primitives");
+torture_param(bool, gp_poll_exp_full, false, "Use polling full-state expedited GP wait primitives");
 torture_param(bool, gp_sync, false, "Use synchronous GP wait primitives");
 torture_param(int, irqreader, 1, "Allow RCU readers from irq handlers");
 torture_param(int, leakpointer, 0, "Leak pointer dereferences from readers");
@@ -194,16 +199,24 @@ static int rcu_torture_writer_state;
 #define RTWS_DEF_FREE		3
 #define RTWS_EXP_SYNC		4
 #define RTWS_COND_GET		5
-#define RTWS_COND_GET_EXP	6
-#define RTWS_COND_SYNC		7
-#define RTWS_COND_SYNC_EXP	8
-#define RTWS_POLL_GET		9
-#define RTWS_POLL_GET_EXP	10
-#define RTWS_POLL_WAIT		11
-#define RTWS_POLL_WAIT_EXP	12
-#define RTWS_SYNC		13
-#define RTWS_STUTTER		14
-#define RTWS_STOPPING		15
+#define RTWS_COND_GET_FULL	6
+#define RTWS_COND_GET_EXP	7
+#define RTWS_COND_GET_EXP_FULL	8
+#define RTWS_COND_SYNC		9
+#define RTWS_COND_SYNC_FULL	10
+#define RTWS_COND_SYNC_EXP	11
+#define RTWS_COND_SYNC_EXP_FULL	12
+#define RTWS_POLL_GET		13
+#define RTWS_POLL_GET_FULL	14
+#define RTWS_POLL_GET_EXP	15
+#define RTWS_POLL_GET_EXP_FULL	16
+#define RTWS_POLL_WAIT		17
+#define RTWS_POLL_WAIT_FULL	18
+#define RTWS_POLL_WAIT_EXP	19
+#define RTWS_POLL_WAIT_EXP_FULL	20
+#define RTWS_SYNC		21
+#define RTWS_STUTTER		22
+#define RTWS_STOPPING		23
 static const char * const rcu_torture_writer_state_names[] = {
 	"RTWS_FIXED_DELAY",
 	"RTWS_DELAY",
@@ -211,13 +224,21 @@ static const char * const rcu_torture_writer_state_names[] = {
 	"RTWS_DEF_FREE",
 	"RTWS_EXP_SYNC",
 	"RTWS_COND_GET",
+	"RTWS_COND_GET_FULL",
 	"RTWS_COND_GET_EXP",
+	"RTWS_COND_GET_EXP_FULL",
 	"RTWS_COND_SYNC",
+	"RTWS_COND_SYNC_FULL",
 	"RTWS_COND_SYNC_EXP",
+	"RTWS_COND_SYNC_EXP_FULL",
 	"RTWS_POLL_GET",
+	"RTWS_POLL_GET_FULL",
 	"RTWS_POLL_GET_EXP",
+	"RTWS_POLL_GET_EXP_FULL",
 	"RTWS_POLL_WAIT",
+	"RTWS_POLL_WAIT_FULL",
 	"RTWS_POLL_WAIT_EXP",
+	"RTWS_POLL_WAIT_EXP_FULL",
 	"RTWS_SYNC",
 	"RTWS_STUTTER",
 	"RTWS_STOPPING",
@@ -332,13 +353,21 @@ struct rcu_torture_ops {
 	void (*exp_sync)(void);
 	unsigned long (*get_gp_state_exp)(void);
 	unsigned long (*start_gp_poll_exp)(void);
+	void (*start_gp_poll_exp_full)(struct rcu_gp_oldstate *rgosp);
 	bool (*poll_gp_state_exp)(unsigned long oldstate);
 	void (*cond_sync_exp)(unsigned long oldstate);
+	void (*cond_sync_exp_full)(struct rcu_gp_oldstate *rgosp);
 	unsigned long (*get_gp_state)(void);
+	void (*get_gp_state_full)(struct rcu_gp_oldstate *rgosp);
 	unsigned long (*get_gp_completed)(void);
+	void (*get_gp_completed_full)(struct rcu_gp_oldstate *rgosp);
 	unsigned long (*start_gp_poll)(void);
+	void (*start_gp_poll_full)(struct rcu_gp_oldstate *rgosp);
 	bool (*poll_gp_state)(unsigned long oldstate);
+	bool (*poll_gp_state_full)(struct rcu_gp_oldstate *rgosp);
+	bool (*poll_need_2gp)(bool poll, bool poll_full);
 	void (*cond_sync)(unsigned long oldstate);
+	void (*cond_sync_full)(struct rcu_gp_oldstate *rgosp);
 	call_rcu_func_t call;
 	void (*cb_barrier)(void);
 	void (*fqs)(void);
@@ -489,6 +518,11 @@ static void rcu_sync_torture_init(void)
 	INIT_LIST_HEAD(&rcu_torture_removed);
 }
 
+static bool rcu_poll_need_2gp(bool poll, bool poll_full)
+{
+	return poll;
+}
+
 static struct rcu_torture_ops rcu_ops = {
 	.ttype			= RCU_FLAVOR,
 	.init			= rcu_sync_torture_init,
@@ -502,12 +536,19 @@ static struct rcu_torture_ops rcu_ops = {
 	.sync			= synchronize_rcu,
 	.exp_sync		= synchronize_rcu_expedited,
 	.get_gp_state		= get_state_synchronize_rcu,
+	.get_gp_state_full	= get_state_synchronize_rcu_full,
 	.get_gp_completed	= get_completed_synchronize_rcu,
+	.get_gp_completed_full	= get_completed_synchronize_rcu_full,
 	.start_gp_poll		= start_poll_synchronize_rcu,
+	.start_gp_poll_full	= start_poll_synchronize_rcu_full,
 	.poll_gp_state		= poll_state_synchronize_rcu,
+	.poll_gp_state_full	= poll_state_synchronize_rcu_full,
+	.poll_need_2gp		= rcu_poll_need_2gp,
 	.cond_sync		= cond_synchronize_rcu,
+	.cond_sync_full		= cond_synchronize_rcu_full,
 	.get_gp_state_exp	= get_state_synchronize_rcu,
 	.start_gp_poll_exp	= start_poll_synchronize_rcu_expedited,
+	.start_gp_poll_exp_full	= start_poll_synchronize_rcu_expedited_full,
 	.poll_gp_state_exp	= poll_state_synchronize_rcu,
 	.cond_sync_exp		= cond_synchronize_rcu_expedited,
 	.call			= call_rcu,
@@ -709,6 +750,9 @@ static struct rcu_torture_ops srcud_ops = {
 	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
 	.exp_sync	= srcu_torture_synchronize_expedited,
+	.get_gp_state	= srcu_torture_get_gp_state,
+	.start_gp_poll	= srcu_torture_start_gp_poll,
+	.poll_gp_state	= srcu_torture_poll_gp_state,
 	.call		= srcu_torture_call,
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
@@ -1148,15 +1192,35 @@ static int nsynctypes;
  */
 static void rcu_torture_write_types(void)
 {
-	bool gp_cond1 = gp_cond, gp_cond_exp1 = gp_cond_exp, gp_exp1 = gp_exp;
-	bool gp_poll_exp1 = gp_poll_exp, gp_normal1 = gp_normal, gp_poll1 = gp_poll;
-	bool gp_sync1 = gp_sync;
+	bool gp_cond1 = gp_cond, gp_cond_exp1 = gp_cond_exp, gp_cond_full1 = gp_cond_full;
+	bool gp_cond_exp_full1 = gp_cond_exp_full, gp_exp1 = gp_exp, gp_poll_exp1 = gp_poll_exp;
+	bool gp_poll_exp_full1 = gp_poll_exp_full, gp_normal1 = gp_normal, gp_poll1 = gp_poll;
+	bool gp_poll_full1 = gp_poll_full, gp_sync1 = gp_sync;
 
 	/* Initialize synctype[] array.  If none set, take default. */
-	if (!gp_cond1 && !gp_cond_exp1 && !gp_exp1 && !gp_poll_exp &&
-	    !gp_normal1 && !gp_poll1 && !gp_sync1)
-		gp_cond1 = gp_cond_exp1 = gp_exp1 = gp_poll_exp1 =
-			   gp_normal1 = gp_poll1 = gp_sync1 = true;
+	if (!gp_cond1 &&
+	    !gp_cond_exp1 &&
+	    !gp_cond_full1 &&
+	    !gp_cond_exp_full1 &&
+	    !gp_exp1 &&
+	    !gp_poll_exp1 &&
+	    !gp_poll_exp_full1 &&
+	    !gp_normal1 &&
+	    !gp_poll1 &&
+	    !gp_poll_full1 &&
+	    !gp_sync1) {
+		gp_cond1 = true;
+		gp_cond_exp1 = true;
+		gp_cond_full1 = true;
+		gp_cond_exp_full1 = true;
+		gp_exp1 = true;
+		gp_poll_exp1 = true;
+		gp_poll_exp_full1 = true;
+		gp_normal1 = true;
+		gp_poll1 = true;
+		gp_poll_full1 = true;
+		gp_sync1 = true;
+	}
 	if (gp_cond1 && cur_ops->get_gp_state && cur_ops->cond_sync) {
 		synctype[nsynctypes++] = RTWS_COND_GET;
 		pr_info("%s: Testing conditional GPs.\n", __func__);
@@ -1169,6 +1233,19 @@ static void rcu_torture_write_types(void)
 	} else if (gp_cond_exp && (!cur_ops->get_gp_state_exp || !cur_ops->cond_sync_exp)) {
 		pr_alert("%s: gp_cond_exp without primitives.\n", __func__);
 	}
+	if (gp_cond_full1 && cur_ops->get_gp_state && cur_ops->cond_sync_full) {
+		synctype[nsynctypes++] = RTWS_COND_GET_FULL;
+		pr_info("%s: Testing conditional full-state GPs.\n", __func__);
+	} else if (gp_cond_full && (!cur_ops->get_gp_state || !cur_ops->cond_sync_full)) {
+		pr_alert("%s: gp_cond_full without primitives.\n", __func__);
+	}
+	if (gp_cond_exp_full1 && cur_ops->get_gp_state_exp && cur_ops->cond_sync_exp_full) {
+		synctype[nsynctypes++] = RTWS_COND_GET_EXP_FULL;
+		pr_info("%s: Testing conditional full-state expedited GPs.\n", __func__);
+	} else if (gp_cond_exp_full &&
+		   (!cur_ops->get_gp_state_exp || !cur_ops->cond_sync_exp_full)) {
+		pr_alert("%s: gp_cond_exp_full without primitives.\n", __func__);
+	}
 	if (gp_exp1 && cur_ops->exp_sync) {
 		synctype[nsynctypes++] = RTWS_EXP_SYNC;
 		pr_info("%s: Testing expedited GPs.\n", __func__);
@@ -1187,12 +1264,25 @@ static void rcu_torture_write_types(void)
 	} else if (gp_poll && (!cur_ops->start_gp_poll || !cur_ops->poll_gp_state)) {
 		pr_alert("%s: gp_poll without primitives.\n", __func__);
 	}
+	if (gp_poll_full1 && cur_ops->start_gp_poll_full && cur_ops->poll_gp_state_full) {
+		synctype[nsynctypes++] = RTWS_POLL_GET_FULL;
+		pr_info("%s: Testing polling full-state GPs.\n", __func__);
+	} else if (gp_poll_full && (!cur_ops->start_gp_poll_full || !cur_ops->poll_gp_state_full)) {
+		pr_alert("%s: gp_poll_full without primitives.\n", __func__);
+	}
 	if (gp_poll_exp1 && cur_ops->start_gp_poll_exp && cur_ops->poll_gp_state_exp) {
 		synctype[nsynctypes++] = RTWS_POLL_GET_EXP;
 		pr_info("%s: Testing polling expedited GPs.\n", __func__);
 	} else if (gp_poll_exp && (!cur_ops->start_gp_poll_exp || !cur_ops->poll_gp_state_exp)) {
 		pr_alert("%s: gp_poll_exp without primitives.\n", __func__);
 	}
+	if (gp_poll_exp_full1 && cur_ops->start_gp_poll_exp_full && cur_ops->poll_gp_state_full) {
+		synctype[nsynctypes++] = RTWS_POLL_GET_EXP_FULL;
+		pr_info("%s: Testing polling full-state expedited GPs.\n", __func__);
+	} else if (gp_poll_exp_full &&
+		   (!cur_ops->start_gp_poll_exp_full || !cur_ops->poll_gp_state_full)) {
+		pr_alert("%s: gp_poll_exp_full without primitives.\n", __func__);
+	}
 	if (gp_sync1 && cur_ops->sync) {
 		synctype[nsynctypes++] = RTWS_SYNC;
 		pr_info("%s: Testing normal GPs.\n", __func__);
@@ -1202,6 +1292,40 @@ static void rcu_torture_write_types(void)
 }
 
 /*
+ * Do the specified rcu_torture_writer() synchronous grace period,
+ * while also testing out the polled APIs.  Note well that the single-CPU
+ * grace-period optimizations must be accounted for.
+ */
+static void do_rtws_sync(struct torture_random_state *trsp, void (*sync)(void))
+{
+	unsigned long cookie;
+	struct rcu_gp_oldstate cookie_full;
+	bool dopoll;
+	bool dopoll_full;
+	unsigned long r = torture_random(trsp);
+
+	dopoll = cur_ops->get_gp_state && cur_ops->poll_gp_state && !(r & 0x300);
+	dopoll_full = cur_ops->get_gp_state_full && cur_ops->poll_gp_state_full && !(r & 0xc00);
+	if (dopoll || dopoll_full)
+		cpus_read_lock();
+	if (dopoll)
+		cookie = cur_ops->get_gp_state();
+	if (dopoll_full)
+		cur_ops->get_gp_state_full(&cookie_full);
+	if (cur_ops->poll_need_2gp && cur_ops->poll_need_2gp(dopoll, dopoll_full))
+		sync();
+	sync();
+	WARN_ONCE(dopoll && !cur_ops->poll_gp_state(cookie),
+		  "%s: Cookie check 3 failed %pS() online %*pbl.",
+		  __func__, sync, cpumask_pr_args(cpu_online_mask));
+	WARN_ONCE(dopoll_full && !cur_ops->poll_gp_state_full(&cookie_full),
+		  "%s: Cookie check 4 failed %pS() online %*pbl",
+		  __func__, sync, cpumask_pr_args(cpu_online_mask));
+	if (dopoll || dopoll_full)
+		cpus_read_unlock();
+}
+
+/*
  * RCU torture writer kthread.  Repeatedly substitutes a new structure
  * for that pointed to by rcu_torture_current, freeing the old structure
  * after a series of grace periods (the "pipeline").
@@ -1212,8 +1336,10 @@ rcu_torture_writer(void *arg)
 	bool boot_ended;
 	bool can_expedite = !rcu_gp_is_expedited() && !rcu_gp_is_normal();
 	unsigned long cookie;
+	struct rcu_gp_oldstate cookie_full;
 	int expediting = 0;
 	unsigned long gp_snap;
+	struct rcu_gp_oldstate gp_snap_full;
 	int i;
 	int idx;
 	int oldnice = task_nice(current);
@@ -1261,11 +1387,12 @@ rcu_torture_writer(void *arg)
 			atomic_inc(&rcu_torture_wcount[i]);
 			WRITE_ONCE(old_rp->rtort_pipe_count,
 				   old_rp->rtort_pipe_count + 1);
+
+			// Make sure readers block polled grace periods.
 			if (cur_ops->get_gp_state && cur_ops->poll_gp_state) {
 				idx = cur_ops->readlock();
 				cookie = cur_ops->get_gp_state();
-				WARN_ONCE(rcu_torture_writer_state != RTWS_DEF_FREE &&
-					  cur_ops->poll_gp_state(cookie),
+				WARN_ONCE(cur_ops->poll_gp_state(cookie),
 					  "%s: Cookie check 1 failed %s(%d) %lu->%lu\n",
 					  __func__,
 					  rcu_torture_writer_state_getname(),
@@ -1277,6 +1404,21 @@ rcu_torture_writer(void *arg)
 				}
 				cur_ops->readunlock(idx);
 			}
+			if (cur_ops->get_gp_state_full && cur_ops->poll_gp_state_full) {
+				idx = cur_ops->readlock();
+				cur_ops->get_gp_state_full(&cookie_full);
+				WARN_ONCE(cur_ops->poll_gp_state_full(&cookie_full),
+					  "%s: Cookie check 5 failed %s(%d) online %*pbl\n",
+					  __func__,
+					  rcu_torture_writer_state_getname(),
+					  rcu_torture_writer_state,
+					  cpumask_pr_args(cpu_online_mask));
+				if (cur_ops->get_gp_completed_full) {
+					cur_ops->get_gp_completed_full(&cookie_full);
+					WARN_ON_ONCE(!cur_ops->poll_gp_state_full(&cookie_full));
+				}
+				cur_ops->readunlock(idx);
+			}
 			switch (synctype[torture_random(&rand) % nsynctypes]) {
 			case RTWS_DEF_FREE:
 				rcu_torture_writer_state = RTWS_DEF_FREE;
@@ -1284,12 +1426,7 @@ rcu_torture_writer(void *arg)
 				break;
 			case RTWS_EXP_SYNC:
 				rcu_torture_writer_state = RTWS_EXP_SYNC;
-				if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
-					cookie = cur_ops->get_gp_state();
-				cur_ops->exp_sync();
-				cur_ops->exp_sync();
-				if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
-					WARN_ON_ONCE(!cur_ops->poll_gp_state(cookie));
+				do_rtws_sync(&rand, cur_ops->exp_sync);
 				rcu_torture_pipe_update(old_rp);
 				break;
 			case RTWS_COND_GET:
@@ -1308,6 +1445,22 @@ rcu_torture_writer(void *arg)
 				cur_ops->cond_sync_exp(gp_snap);
 				rcu_torture_pipe_update(old_rp);
 				break;
+			case RTWS_COND_GET_FULL:
+				rcu_torture_writer_state = RTWS_COND_GET_FULL;
+				cur_ops->get_gp_state_full(&gp_snap_full);
+				torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand);
+				rcu_torture_writer_state = RTWS_COND_SYNC_FULL;
+				cur_ops->cond_sync_full(&gp_snap_full);
+				rcu_torture_pipe_update(old_rp);
+				break;
+			case RTWS_COND_GET_EXP_FULL:
+				rcu_torture_writer_state = RTWS_COND_GET_EXP_FULL;
+				cur_ops->get_gp_state_full(&gp_snap_full);
+				torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand);
+				rcu_torture_writer_state = RTWS_COND_SYNC_EXP_FULL;
+				cur_ops->cond_sync_exp_full(&gp_snap_full);
+				rcu_torture_pipe_update(old_rp);
+				break;
 			case RTWS_POLL_GET:
 				rcu_torture_writer_state = RTWS_POLL_GET;
 				gp_snap = cur_ops->start_gp_poll();
@@ -1317,6 +1470,15 @@ rcu_torture_writer(void *arg)
 								  &rand);
 				rcu_torture_pipe_update(old_rp);
 				break;
+			case RTWS_POLL_GET_FULL:
+				rcu_torture_writer_state = RTWS_POLL_GET_FULL;
+				cur_ops->start_gp_poll_full(&gp_snap_full);
+				rcu_torture_writer_state = RTWS_POLL_WAIT_FULL;
+				while (!cur_ops->poll_gp_state_full(&gp_snap_full))
+					torture_hrtimeout_jiffies(torture_random(&rand) % 16,
+								  &rand);
+				rcu_torture_pipe_update(old_rp);
+				break;
 			case RTWS_POLL_GET_EXP:
 				rcu_torture_writer_state = RTWS_POLL_GET_EXP;
 				gp_snap = cur_ops->start_gp_poll_exp();
@@ -1326,14 +1488,18 @@ rcu_torture_writer(void *arg)
 								  &rand);
 				rcu_torture_pipe_update(old_rp);
 				break;
+			case RTWS_POLL_GET_EXP_FULL:
+				rcu_torture_writer_state = RTWS_POLL_GET_EXP_FULL;
+				cur_ops->start_gp_poll_exp_full(&gp_snap_full);
+				rcu_torture_writer_state = RTWS_POLL_WAIT_EXP_FULL;
+				while (!cur_ops->poll_gp_state_full(&gp_snap_full))
+					torture_hrtimeout_jiffies(torture_random(&rand) % 16,
+								  &rand);
+				rcu_torture_pipe_update(old_rp);
+				break;
 			case RTWS_SYNC:
 				rcu_torture_writer_state = RTWS_SYNC;
-				if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
-					cookie = cur_ops->get_gp_state();
-				cur_ops->sync();
-				cur_ops->sync();
-				if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
-					WARN_ON_ONCE(!cur_ops->poll_gp_state(cookie));
+				do_rtws_sync(&rand, cur_ops->sync);
 				rcu_torture_pipe_update(old_rp);
 				break;
 			default:
@@ -1400,6 +1566,7 @@ static int
 rcu_torture_fakewriter(void *arg)
 {
 	unsigned long gp_snap;
+	struct rcu_gp_oldstate gp_snap_full;
 	DEFINE_TORTURE_RANDOM(rand);
 
 	VERBOSE_TOROUT_STRING("rcu_torture_fakewriter task started");
@@ -1438,6 +1605,16 @@ rcu_torture_fakewriter(void *arg)
 				torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand);
 				cur_ops->cond_sync_exp(gp_snap);
 				break;
+			case RTWS_COND_GET_FULL:
+				cur_ops->get_gp_state_full(&gp_snap_full);
+				torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand);
+				cur_ops->cond_sync_full(&gp_snap_full);
+				break;
+			case RTWS_COND_GET_EXP_FULL:
+				cur_ops->get_gp_state_full(&gp_snap_full);
+				torture_hrtimeout_jiffies(torture_random(&rand) % 16, &rand);
+				cur_ops->cond_sync_exp_full(&gp_snap_full);
+				break;
 			case RTWS_POLL_GET:
 				gp_snap = cur_ops->start_gp_poll();
 				while (!cur_ops->poll_gp_state(gp_snap)) {
@@ -1445,6 +1622,13 @@ rcu_torture_fakewriter(void *arg)
 								  &rand);
 				}
 				break;
+			case RTWS_POLL_GET_FULL:
+				cur_ops->start_gp_poll_full(&gp_snap_full);
+				while (!cur_ops->poll_gp_state_full(&gp_snap_full)) {
+					torture_hrtimeout_jiffies(torture_random(&rand) % 16,
+								  &rand);
+				}
+				break;
 			case RTWS_POLL_GET_EXP:
 				gp_snap = cur_ops->start_gp_poll_exp();
 				while (!cur_ops->poll_gp_state_exp(gp_snap)) {
@@ -1452,6 +1636,13 @@ rcu_torture_fakewriter(void *arg)
 								  &rand);
 				}
 				break;
+			case RTWS_POLL_GET_EXP_FULL:
+				cur_ops->start_gp_poll_exp_full(&gp_snap_full);
+				while (!cur_ops->poll_gp_state_full(&gp_snap_full)) {
+					torture_hrtimeout_jiffies(torture_random(&rand) % 16,
+								  &rand);
+				}
+				break;
 			case RTWS_SYNC:
 				cur_ops->sync();
 				break;
@@ -1715,7 +1906,9 @@ rcutorture_loop_extend(int *readstate, struct torture_random_state *trsp,
  */
 static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid)
 {
+	bool checkpolling = !(torture_random(trsp) & 0xfff);
 	unsigned long cookie;
+	struct rcu_gp_oldstate cookie_full;
 	int i;
 	unsigned long started;
 	unsigned long completed;
@@ -1731,8 +1924,12 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid)
 	WARN_ON_ONCE(!rcu_is_watching());
 	newstate = rcutorture_extend_mask(readstate, trsp);
 	rcutorture_one_extend(&readstate, newstate, trsp, rtrsp++);
-	if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
-		cookie = cur_ops->get_gp_state();
+	if (checkpolling) {
+		if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
+			cookie = cur_ops->get_gp_state();
+		if (cur_ops->get_gp_state_full && cur_ops->poll_gp_state_full)
+			cur_ops->get_gp_state_full(&cookie_full);
+	}
 	started = cur_ops->get_gp_seq();
 	ts = rcu_trace_clock_local();
 	p = rcu_dereference_check(rcu_torture_current,
@@ -1766,13 +1963,22 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid)
 	}
 	__this_cpu_inc(rcu_torture_batch[completed]);
 	preempt_enable();
-	if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
-		WARN_ONCE(cur_ops->poll_gp_state(cookie),
-			  "%s: Cookie check 2 failed %s(%d) %lu->%lu\n",
-			  __func__,
-			  rcu_torture_writer_state_getname(),
-			  rcu_torture_writer_state,
-			  cookie, cur_ops->get_gp_state());
+	if (checkpolling) {
+		if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
+			WARN_ONCE(cur_ops->poll_gp_state(cookie),
+				  "%s: Cookie check 2 failed %s(%d) %lu->%lu\n",
+				  __func__,
+				  rcu_torture_writer_state_getname(),
+				  rcu_torture_writer_state,
+				  cookie, cur_ops->get_gp_state());
+		if (cur_ops->get_gp_state_full && cur_ops->poll_gp_state_full)
+			WARN_ONCE(cur_ops->poll_gp_state_full(&cookie_full),
+				  "%s: Cookie check 6 failed %s(%d) online %*pbl\n",
+				  __func__,
+				  rcu_torture_writer_state_getname(),
+				  rcu_torture_writer_state,
+				  cpumask_pr_args(cpu_online_mask));
+	}
 	rcutorture_one_extend(&readstate, 0, trsp, rtrsp);
 	WARN_ON_ONCE(readstate);
 	// This next splat is expected behavior if leakpointer, especially
@@ -2600,12 +2806,12 @@ static int rcutorture_oom_notify(struct notifier_block *self,
 	for (i = 0; i < fwd_progress; i++)
 		ncbs += rcu_torture_fwd_prog_cbfree(&rfp[i]);
 	pr_info("%s: Freed %lu RCU callbacks.\n", __func__, ncbs);
-	rcu_barrier();
+	cur_ops->cb_barrier();
 	ncbs = 0;
 	for (i = 0; i < fwd_progress; i++)
 		ncbs += rcu_torture_fwd_prog_cbfree(&rfp[i]);
 	pr_info("%s: Freed %lu RCU callbacks.\n", __func__, ncbs);
-	rcu_barrier();
+	cur_ops->cb_barrier();
 	ncbs = 0;
 	for (i = 0; i < fwd_progress; i++)
 		ncbs += rcu_torture_fwd_prog_cbfree(&rfp[i]);
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 92c002d65482..33adafdad261 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -117,7 +117,7 @@ void srcu_drive_gp(struct work_struct *wp)
 	struct srcu_struct *ssp;
 
 	ssp = container_of(wp, struct srcu_struct, srcu_work);
-	if (ssp->srcu_gp_running || USHORT_CMP_GE(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max)))
+	if (ssp->srcu_gp_running || ULONG_CMP_GE(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max)))
 		return; /* Already running or nothing to do. */
 
 	/* Remove recently arrived callbacks and wait for readers. */
@@ -150,17 +150,17 @@ void srcu_drive_gp(struct work_struct *wp)
 	 * straighten that out.
 	 */
 	WRITE_ONCE(ssp->srcu_gp_running, false);
-	if (USHORT_CMP_LT(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max)))
+	if (ULONG_CMP_LT(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max)))
 		schedule_work(&ssp->srcu_work);
 }
 EXPORT_SYMBOL_GPL(srcu_drive_gp);
 
 static void srcu_gp_start_if_needed(struct srcu_struct *ssp)
 {
-	unsigned short cookie;
+	unsigned long cookie;
 
 	cookie = get_state_synchronize_srcu(ssp);
-	if (USHORT_CMP_GE(READ_ONCE(ssp->srcu_idx_max), cookie))
+	if (ULONG_CMP_GE(READ_ONCE(ssp->srcu_idx_max), cookie))
 		return;
 	WRITE_ONCE(ssp->srcu_idx_max, cookie);
 	if (!READ_ONCE(ssp->srcu_gp_running)) {
@@ -215,7 +215,7 @@ unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp)
 	barrier();
 	ret = (READ_ONCE(ssp->srcu_idx) + 3) & ~0x1;
 	barrier();
-	return ret & USHRT_MAX;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(get_state_synchronize_srcu);
 
@@ -240,10 +240,10 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_srcu);
  */
 bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie)
 {
-	bool ret = USHORT_CMP_GE(READ_ONCE(ssp->srcu_idx), cookie);
+	unsigned long cur_s = READ_ONCE(ssp->srcu_idx);
 
 	barrier();
-	return ret;
+	return ULONG_CMP_GE(cur_s, cookie) || ULONG_CMP_LT(cur_s, cookie - 3);
 }
 EXPORT_SYMBOL_GPL(poll_state_synchronize_srcu);
 
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 83c7e6620d40..f5bf6fb430da 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -560,7 +560,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 static void synchronize_rcu_tasks_generic(struct rcu_tasks *rtp)
 {
 	/* Complain if the scheduler has not started.  */
-	RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
+	WARN_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
 			 "synchronize_rcu_tasks called too soon");
 
 	// If the grace-period kthread is running, use it.
@@ -1500,6 +1500,7 @@ static void rcu_tasks_trace_pregp_step(struct list_head *hop)
 		if (rcu_tasks_trace_pertask_prep(t, true))
 			trc_add_holdout(t, hop);
 		rcu_read_unlock();
+		cond_resched_tasks_rcu_qs();
 	}
 
 	// Only after all running tasks have been accounted for is it
@@ -1520,6 +1521,7 @@ static void rcu_tasks_trace_pregp_step(struct list_head *hop)
 			raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
 		}
 		raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+		cond_resched_tasks_rcu_qs();
 	}
 
 	// Re-enable CPU hotplug now that the holdout list is populated.
@@ -1619,6 +1621,7 @@ static void check_all_holdout_tasks_trace(struct list_head *hop,
 			trc_del_holdout(t);
 		else if (needreport)
 			show_stalled_task_trace(t, firstreport);
+		cond_resched_tasks_rcu_qs();
 	}
 
 	// Re-enable CPU hotplug now that the holdout list scan has completed.
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index f0561ee16b9c..a33a8d4942c3 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -158,6 +158,10 @@ void synchronize_rcu(void)
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
+static void tiny_rcu_leak_callback(struct rcu_head *rhp)
+{
+}
+
 /*
  * Post an RCU callback to be invoked after the end of an RCU grace
  * period.  But since we have but one CPU, that would be after any
@@ -165,9 +169,20 @@ EXPORT_SYMBOL_GPL(synchronize_rcu);
  */
 void call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
+	static atomic_t doublefrees;
 	unsigned long flags;
 
-	debug_rcu_head_queue(head);
+	if (debug_rcu_head_queue(head)) {
+		if (atomic_inc_return(&doublefrees) < 4) {
+			pr_err("%s(): Double-freed CB %p->%pS()!!!  ", __func__, head, head->func);
+			mem_dump_obj(head);
+		}
+
+		if (!__is_kvfree_rcu_offset((unsigned long)head->func))
+			WRITE_ONCE(head->func, tiny_rcu_leak_callback);
+		return;
+	}
+
 	head->func = func;
 	head->next = NULL;
 
@@ -184,6 +199,16 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func)
 EXPORT_SYMBOL_GPL(call_rcu);
 
 /*
+ * Store a grace-period-counter "cookie".  For more information,
+ * see the Tree RCU header comment.
+ */
+void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
+{
+	rgosp->rgos_norm = RCU_GET_STATE_COMPLETED;
+}
+EXPORT_SYMBOL_GPL(get_completed_synchronize_rcu_full);
+
+/*
  * Return a grace-period-counter "cookie".  For more information,
  * see the Tree RCU header comment.
  */
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 79aea7df4345..6bb8e72bc815 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -76,6 +76,7 @@
 /* Data structures. */
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = {
+	.gpwrap = true,
 #ifdef CONFIG_RCU_NOCB_CPU
 	.cblist.flags = SEGCBLIST_RCU_CORE,
 #endif
@@ -1755,6 +1756,8 @@ static noinline void rcu_gp_cleanup(void)
 			dump_blkd_tasks(rnp, 10);
 		WARN_ON_ONCE(rnp->qsmask);
 		WRITE_ONCE(rnp->gp_seq, new_gp_seq);
+		if (!rnp->parent)
+			smp_mb(); // Order against failing poll_state_synchronize_rcu_full().
 		rdp = this_cpu_ptr(&rcu_data);
 		if (rnp == rdp->mynode)
 			needgp = __note_gp_changes(rnp, rdp) || needgp;
@@ -2341,8 +2344,8 @@ void rcu_sched_clock_irq(int user)
 	rcu_flavor_sched_clock_irq(user);
 	if (rcu_pending(user))
 		invoke_rcu_core();
-	if (user)
-		rcu_tasks_classic_qs(current, false);
+	if (user || rcu_is_cpu_rrupt_from_idle())
+		rcu_note_voluntary_context_switch(current);
 	lockdep_assert_irqs_disabled();
 
 	trace_rcu_utilization(TPS("End scheduler-tick"));
@@ -2832,7 +2835,7 @@ EXPORT_SYMBOL_GPL(call_rcu);
 
 
 /* Maximum number of jiffies to wait before draining a batch. */
-#define KFREE_DRAIN_JIFFIES (HZ / 50)
+#define KFREE_DRAIN_JIFFIES (5 * HZ)
 #define KFREE_N_BATCHES 2
 #define FREE_N_CHANNELS 2
 
@@ -3093,6 +3096,21 @@ need_offload_krc(struct kfree_rcu_cpu *krcp)
 	return !!krcp->head;
 }
 
+static void
+schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp)
+{
+	long delay, delay_left;
+
+	delay = READ_ONCE(krcp->count) >= KVFREE_BULK_MAX_ENTR ? 1:KFREE_DRAIN_JIFFIES;
+	if (delayed_work_pending(&krcp->monitor_work)) {
+		delay_left = krcp->monitor_work.timer.expires - jiffies;
+		if (delay < delay_left)
+			mod_delayed_work(system_wq, &krcp->monitor_work, delay);
+		return;
+	}
+	queue_delayed_work(system_wq, &krcp->monitor_work, delay);
+}
+
 /*
  * This function is invoked after the KFREE_DRAIN_JIFFIES timeout.
  */
@@ -3150,7 +3168,7 @@ static void kfree_rcu_monitor(struct work_struct *work)
 	// work to repeat an attempt. Because previous batches are
 	// still in progress.
 	if (need_offload_krc(krcp))
-		schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
+		schedule_delayed_monitor_work(krcp);
 
 	raw_spin_unlock_irqrestore(&krcp->lock, flags);
 }
@@ -3183,15 +3201,16 @@ static void fill_page_cache_func(struct work_struct *work)
 		bnode = (struct kvfree_rcu_bulk_data *)
 			__get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
 
-		if (bnode) {
-			raw_spin_lock_irqsave(&krcp->lock, flags);
-			pushed = put_cached_bnode(krcp, bnode);
-			raw_spin_unlock_irqrestore(&krcp->lock, flags);
+		if (!bnode)
+			break;
 
-			if (!pushed) {
-				free_page((unsigned long) bnode);
-				break;
-			}
+		raw_spin_lock_irqsave(&krcp->lock, flags);
+		pushed = put_cached_bnode(krcp, bnode);
+		raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+		if (!pushed) {
+			free_page((unsigned long) bnode);
+			break;
 		}
 	}
 
@@ -3338,7 +3357,7 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 
 	// Set timer to drain after KFREE_DRAIN_JIFFIES.
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING)
-		schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
+		schedule_delayed_monitor_work(krcp);
 
 unlock_return:
 	krc_this_cpu_unlock(krcp, flags);
@@ -3371,7 +3390,7 @@ kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 		atomic_set(&krcp->backoff_page_cache_fill, 1);
 	}
 
-	return count;
+	return count == 0 ? SHRINK_EMPTY : count;
 }
 
 static unsigned long
@@ -3414,49 +3433,27 @@ void __init kfree_rcu_scheduler_running(void)
 
 		raw_spin_lock_irqsave(&krcp->lock, flags);
 		if (need_offload_krc(krcp))
-			schedule_delayed_work_on(cpu, &krcp->monitor_work, KFREE_DRAIN_JIFFIES);
+			schedule_delayed_monitor_work(krcp);
 		raw_spin_unlock_irqrestore(&krcp->lock, flags);
 	}
 }
 
 /*
  * During early boot, any blocking grace-period wait automatically
- * implies a grace period.  Later on, this is never the case for PREEMPTION.
+ * implies a grace period.
  *
- * However, because a context switch is a grace period for !PREEMPTION, any
- * blocking grace-period wait automatically implies a grace period if
- * there is only one CPU online at any point time during execution of
- * either synchronize_rcu() or synchronize_rcu_expedited().  It is OK to
- * occasionally incorrectly indicate that there are multiple CPUs online
- * when there was in fact only one the whole time, as this just adds some
- * overhead: RCU still operates correctly.
+ * Later on, this could in theory be the case for kernels built with
+ * CONFIG_SMP=y && CONFIG_PREEMPTION=y running on a single CPU, but this
+ * is not a common case.  Furthermore, this optimization would cause
+ * the rcu_gp_oldstate structure to expand by 50%, so this potential
+ * grace-period optimization is ignored once the scheduler is running.
  */
 static int rcu_blocking_is_gp(void)
 {
-	int ret;
-
-	// Invoking preempt_model_*() too early gets a splat.
-	if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE ||
-	    preempt_model_full() || preempt_model_rt())
-		return rcu_scheduler_active == RCU_SCHEDULER_INACTIVE;
+	if (rcu_scheduler_active != RCU_SCHEDULER_INACTIVE)
+		return false;
 	might_sleep();  /* Check for RCU read-side critical section. */
-	preempt_disable();
-	/*
-	 * If the rcu_state.n_online_cpus counter is equal to one,
-	 * there is only one CPU, and that CPU sees all prior accesses
-	 * made by any CPU that was online at the time of its access.
-	 * Furthermore, if this counter is equal to one, its value cannot
-	 * change until after the preempt_enable() below.
-	 *
-	 * Furthermore, if rcu_state.n_online_cpus is equal to one here,
-	 * all later CPUs (both this one and any that come online later
-	 * on) are guaranteed to see all accesses prior to this point
-	 * in the code, without the need for additional memory barriers.
-	 * Those memory barriers are provided by CPU-hotplug code.
-	 */
-	ret = READ_ONCE(rcu_state.n_online_cpus) <= 1;
-	preempt_enable();
-	return ret;
+	return true;
 }
 
 /**
@@ -3499,30 +3496,59 @@ static int rcu_blocking_is_gp(void)
  */
 void synchronize_rcu(void)
 {
+	unsigned long flags;
+	struct rcu_node *rnp;
+
 	RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
 			 lock_is_held(&rcu_lock_map) ||
 			 lock_is_held(&rcu_sched_lock_map),
 			 "Illegal synchronize_rcu() in RCU read-side critical section");
-	if (rcu_blocking_is_gp()) {
-		// Note well that this code runs with !PREEMPT && !SMP.
-		// In addition, all code that advances grace periods runs at
-		// process level.  Therefore, this normal GP overlaps with
-		// other normal GPs only by being fully nested within them,
-		// which allows reuse of ->gp_seq_polled_snap.
-		rcu_poll_gp_seq_start_unlocked(&rcu_state.gp_seq_polled_snap);
-		rcu_poll_gp_seq_end_unlocked(&rcu_state.gp_seq_polled_snap);
-		if (rcu_init_invoked())
-			cond_resched_tasks_rcu_qs();
-		return;  // Context allows vacuous grace periods.
+	if (!rcu_blocking_is_gp()) {
+		if (rcu_gp_is_expedited())
+			synchronize_rcu_expedited();
+		else
+			wait_rcu_gp(call_rcu);
+		return;
 	}
-	if (rcu_gp_is_expedited())
-		synchronize_rcu_expedited();
-	else
-		wait_rcu_gp(call_rcu);
+
+	// Context allows vacuous grace periods.
+	// Note well that this code runs with !PREEMPT && !SMP.
+	// In addition, all code that advances grace periods runs at
+	// process level.  Therefore, this normal GP overlaps with other
+	// normal GPs only by being fully nested within them, which allows
+	// reuse of ->gp_seq_polled_snap.
+	rcu_poll_gp_seq_start_unlocked(&rcu_state.gp_seq_polled_snap);
+	rcu_poll_gp_seq_end_unlocked(&rcu_state.gp_seq_polled_snap);
+
+	// Update the normal grace-period counters to record
+	// this grace period, but only those used by the boot CPU.
+	// The rcu_scheduler_starting() will take care of the rest of
+	// these counters.
+	local_irq_save(flags);
+	WARN_ON_ONCE(num_online_cpus() > 1);
+	rcu_state.gp_seq += (1 << RCU_SEQ_CTR_SHIFT);
+	for (rnp = this_cpu_ptr(&rcu_data)->mynode; rnp; rnp = rnp->parent)
+		rnp->gp_seq_needed = rnp->gp_seq = rcu_state.gp_seq;
+	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
 /**
+ * get_completed_synchronize_rcu_full - Return a full pre-completed polled state cookie
+ * @rgosp: Place to put state cookie
+ *
+ * Stores into @rgosp a value that will always be treated by functions
+ * like poll_state_synchronize_rcu_full() as a cookie whose grace period
+ * has already completed.
+ */
+void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
+{
+	rgosp->rgos_norm = RCU_GET_STATE_COMPLETED;
+	rgosp->rgos_exp = RCU_GET_STATE_COMPLETED;
+}
+EXPORT_SYMBOL_GPL(get_completed_synchronize_rcu_full);
+
+/**
  * get_state_synchronize_rcu - Snapshot current RCU state
  *
  * Returns a cookie that is used by a later call to cond_synchronize_rcu()
@@ -3541,21 +3567,42 @@ unsigned long get_state_synchronize_rcu(void)
 EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
 
 /**
- * start_poll_synchronize_rcu - Snapshot and start RCU grace period
+ * get_state_synchronize_rcu_full - Snapshot RCU state, both normal and expedited
+ * @rgosp: location to place combined normal/expedited grace-period state
  *
- * Returns a cookie that is used by a later call to cond_synchronize_rcu()
- * or poll_state_synchronize_rcu() to determine whether or not a full
- * grace period has elapsed in the meantime.  If the needed grace period
- * is not already slated to start, notifies RCU core of the need for that
- * grace period.
+ * Places the normal and expedited grace-period states in @rgosp.  This
+ * state value can be passed to a later call to cond_synchronize_rcu_full()
+ * or poll_state_synchronize_rcu_full() to determine whether or not a
+ * grace period (whether normal or expedited) has elapsed in the meantime.
+ * The rcu_gp_oldstate structure takes up twice the memory of an unsigned
+ * long, but is guaranteed to see all grace periods.  In contrast, the
+ * combined state occupies less memory, but can sometimes fail to take
+ * grace periods into account.
  *
- * Interrupts must be enabled for the case where it is necessary to awaken
- * the grace-period kthread.
+ * This does not guarantee that the needed grace period will actually
+ * start.
  */
-unsigned long start_poll_synchronize_rcu(void)
+void get_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
+{
+	struct rcu_node *rnp = rcu_get_root();
+
+	/*
+	 * Any prior manipulation of RCU-protected data must happen
+	 * before the loads from ->gp_seq and ->expedited_sequence.
+	 */
+	smp_mb();  /* ^^^ */
+	rgosp->rgos_norm = rcu_seq_snap(&rnp->gp_seq);
+	rgosp->rgos_exp = rcu_seq_snap(&rcu_state.expedited_sequence);
+}
+EXPORT_SYMBOL_GPL(get_state_synchronize_rcu_full);
+
+/*
+ * Helper function for start_poll_synchronize_rcu() and
+ * start_poll_synchronize_rcu_full().
+ */
+static void start_poll_synchronize_rcu_common(void)
 {
 	unsigned long flags;
-	unsigned long gp_seq = get_state_synchronize_rcu();
 	bool needwake;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
@@ -3575,17 +3622,57 @@ unsigned long start_poll_synchronize_rcu(void)
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	if (needwake)
 		rcu_gp_kthread_wake();
+}
+
+/**
+ * start_poll_synchronize_rcu - Snapshot and start RCU grace period
+ *
+ * Returns a cookie that is used by a later call to cond_synchronize_rcu()
+ * or poll_state_synchronize_rcu() to determine whether or not a full
+ * grace period has elapsed in the meantime.  If the needed grace period
+ * is not already slated to start, notifies RCU core of the need for that
+ * grace period.
+ *
+ * Interrupts must be enabled for the case where it is necessary to awaken
+ * the grace-period kthread.
+ */
+unsigned long start_poll_synchronize_rcu(void)
+{
+	unsigned long gp_seq = get_state_synchronize_rcu();
+
+	start_poll_synchronize_rcu_common();
 	return gp_seq;
 }
 EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
 
 /**
- * poll_state_synchronize_rcu - Conditionally wait for an RCU grace period
+ * start_poll_synchronize_rcu_full - Take a full snapshot and start RCU grace period
+ * @rgosp: value from get_state_synchronize_rcu_full() or start_poll_synchronize_rcu_full()
  *
+ * Places the normal and expedited grace-period states in *@rgos.  This
+ * state value can be passed to a later call to cond_synchronize_rcu_full()
+ * or poll_state_synchronize_rcu_full() to determine whether or not a
+ * grace period (whether normal or expedited) has elapsed in the meantime.
+ * If the needed grace period is not already slated to start, notifies
+ * RCU core of the need for that grace period.
+ *
+ * Interrupts must be enabled for the case where it is necessary to awaken
+ * the grace-period kthread.
+ */
+void start_poll_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
+{
+	get_state_synchronize_rcu_full(rgosp);
+
+	start_poll_synchronize_rcu_common();
+}
+EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu_full);
+
+/**
+ * poll_state_synchronize_rcu - Has the specified RCU grace period completed?
  * @oldstate: value from get_state_synchronize_rcu() or start_poll_synchronize_rcu()
  *
  * If a full RCU grace period has elapsed since the earlier call from
- * which oldstate was obtained, return @true, otherwise return @false.
+ * which @oldstate was obtained, return @true, otherwise return @false.
  * If @false is returned, it is the caller's responsibility to invoke this
  * function later on until it does return @true.  Alternatively, the caller
  * can explicitly wait for a grace period, for example, by passing @oldstate
@@ -3594,10 +3681,11 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
  * Yes, this function does not take counter wrap into account.
  * But counter wrap is harmless.  If the counter wraps, we have waited for
  * more than a billion grace periods (and way more on a 64-bit system!).
- * Those needing to keep oldstate values for very long time periods
- * (many hours even on 32-bit systems) should check them occasionally
- * and either refresh them or set a flag indicating that the grace period
- * has completed.
+ * Those needing to keep old state values for very long time periods
+ * (many hours even on 32-bit systems) should check them occasionally and
+ * either refresh them or set a flag indicating that the grace period has
+ * completed.  Alternatively, they can use get_completed_synchronize_rcu()
+ * to get a guaranteed-completed grace-period state.
  *
  * This function provides the same memory-ordering guarantees that
  * would be provided by a synchronize_rcu() that was invoked at the call
@@ -3616,8 +3704,56 @@ bool poll_state_synchronize_rcu(unsigned long oldstate)
 EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu);
 
 /**
- * cond_synchronize_rcu - Conditionally wait for an RCU grace period
+ * poll_state_synchronize_rcu_full - Has the specified RCU grace period completed?
+ * @rgosp: value from get_state_synchronize_rcu_full() or start_poll_synchronize_rcu_full()
  *
+ * If a full RCU grace period has elapsed since the earlier call from
+ * which *rgosp was obtained, return @true, otherwise return @false.
+ * If @false is returned, it is the caller's responsibility to invoke this
+ * function later on until it does return @true.  Alternatively, the caller
+ * can explicitly wait for a grace period, for example, by passing @rgosp
+ * to cond_synchronize_rcu() or by directly invoking synchronize_rcu().
+ *
+ * Yes, this function does not take counter wrap into account.
+ * But counter wrap is harmless.  If the counter wraps, we have waited
+ * for more than a billion grace periods (and way more on a 64-bit
+ * system!).  Those needing to keep rcu_gp_oldstate values for very
+ * long time periods (many hours even on 32-bit systems) should check
+ * them occasionally and either refresh them or set a flag indicating
+ * that the grace period has completed.  Alternatively, they can use
+ * get_completed_synchronize_rcu_full() to get a guaranteed-completed
+ * grace-period state.
+ *
+ * This function provides the same memory-ordering guarantees that would
+ * be provided by a synchronize_rcu() that was invoked at the call to
+ * the function that provided @rgosp, and that returned at the end of this
+ * function.  And this guarantee requires that the root rcu_node structure's
+ * ->gp_seq field be checked instead of that of the rcu_state structure.
+ * The problem is that the just-ending grace-period's callbacks can be
+ * invoked between the time that the root rcu_node structure's ->gp_seq
+ * field is updated and the time that the rcu_state structure's ->gp_seq
+ * field is updated.  Therefore, if a single synchronize_rcu() is to
+ * cause a subsequent poll_state_synchronize_rcu_full() to return @true,
+ * then the root rcu_node structure is the one that needs to be polled.
+ */
+bool poll_state_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
+{
+	struct rcu_node *rnp = rcu_get_root();
+
+	smp_mb(); // Order against root rcu_node structure grace-period cleanup.
+	if (rgosp->rgos_norm == RCU_GET_STATE_COMPLETED ||
+	    rcu_seq_done_exact(&rnp->gp_seq, rgosp->rgos_norm) ||
+	    rgosp->rgos_exp == RCU_GET_STATE_COMPLETED ||
+	    rcu_seq_done_exact(&rcu_state.expedited_sequence, rgosp->rgos_exp)) {
+		smp_mb(); /* Ensure GP ends before subsequent accesses. */
+		return true;
+	}
+	return false;
+}
+EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu_full);
+
+/**
+ * cond_synchronize_rcu - Conditionally wait for an RCU grace period
  * @oldstate: value from get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or start_poll_synchronize_rcu_expedited()
  *
  * If a full RCU grace period has elapsed since the earlier call to
@@ -3641,6 +3777,33 @@ void cond_synchronize_rcu(unsigned long oldstate)
 }
 EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
 
+/**
+ * cond_synchronize_rcu_full - Conditionally wait for an RCU grace period
+ * @rgosp: value from get_state_synchronize_rcu_full(), start_poll_synchronize_rcu_full(), or start_poll_synchronize_rcu_expedited_full()
+ *
+ * If a full RCU grace period has elapsed since the call to
+ * get_state_synchronize_rcu_full(), start_poll_synchronize_rcu_full(),
+ * or start_poll_synchronize_rcu_expedited_full() from which @rgosp was
+ * obtained, just return.  Otherwise, invoke synchronize_rcu() to wait
+ * for a full grace period.
+ *
+ * Yes, this function does not take counter wrap into account.
+ * But counter wrap is harmless.  If the counter wraps, we have waited for
+ * more than 2 billion grace periods (and way more on a 64-bit system!),
+ * so waiting for a couple of additional grace periods should be just fine.
+ *
+ * This function provides the same memory-ordering guarantees that
+ * would be provided by a synchronize_rcu() that was invoked at the call
+ * to the function that provided @rgosp and that returned at the end of
+ * this function.
+ */
+void cond_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
+{
+	if (!poll_state_synchronize_rcu_full(rgosp))
+		synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(cond_synchronize_rcu_full);
+
 /*
  * Check to see if there is any immediate RCU-related work to be done by
  * the current CPU, returning 1 if so and zero otherwise.  The checks are
@@ -4312,9 +4475,20 @@ early_initcall(rcu_spawn_gp_kthread);
  */
 void rcu_scheduler_starting(void)
 {
+	unsigned long flags;
+	struct rcu_node *rnp;
+
 	WARN_ON(num_online_cpus() != 1);
 	WARN_ON(nr_context_switches() > 0);
 	rcu_test_sync_prims();
+
+	// Fix up the ->gp_seq counters.
+	local_irq_save(flags);
+	rcu_for_each_node_breadth_first(rnp)
+		rnp->gp_seq_needed = rnp->gp_seq = rcu_state.gp_seq;
+	local_irq_restore(flags);
+
+	// Switch out of early boot mode.
 	rcu_scheduler_active = RCU_SCHEDULER_INIT;
 	rcu_test_sync_prims();
 }
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index be667583a554..18e9b4cd78ef 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -828,11 +828,13 @@ static void rcu_exp_handler(void *unused)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;
+	bool preempt_bh_enabled = !(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK));
 
 	if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
 	    __this_cpu_read(rcu_data.cpu_no_qs.b.exp))
 		return;
-	if (rcu_is_cpu_rrupt_from_idle()) {
+	if (rcu_is_cpu_rrupt_from_idle() ||
+	    (IS_ENABLED(CONFIG_PREEMPT_COUNT) && preempt_bh_enabled)) {
 		rcu_report_exp_rdp(this_cpu_ptr(&rcu_data));
 		return;
 	}
@@ -906,6 +908,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
 void synchronize_rcu_expedited(void)
 {
 	bool boottime = (rcu_scheduler_active == RCU_SCHEDULER_INIT);
+	unsigned long flags;
 	struct rcu_exp_work rew;
 	struct rcu_node *rnp;
 	unsigned long s;
@@ -924,8 +927,11 @@ void synchronize_rcu_expedited(void)
 		// them, which allows reuse of ->gp_seq_polled_exp_snap.
 		rcu_poll_gp_seq_start_unlocked(&rcu_state.gp_seq_polled_exp_snap);
 		rcu_poll_gp_seq_end_unlocked(&rcu_state.gp_seq_polled_exp_snap);
-		if (rcu_init_invoked())
-			cond_resched();
+
+		local_irq_save(flags);
+		WARN_ON_ONCE(num_online_cpus() > 1);
+		rcu_state.expedited_sequence += (1 << RCU_SEQ_CTR_SHIFT);
+		local_irq_restore(flags);
 		return;  // Context allows vacuous grace periods.
 	}
 
@@ -1028,6 +1034,24 @@ unsigned long start_poll_synchronize_rcu_expedited(void)
 EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu_expedited);
 
 /**
+ * start_poll_synchronize_rcu_expedited_full - Take a full snapshot and start expedited grace period
+ * @rgosp: Place to put snapshot of grace-period state
+ *
+ * Places the normal and expedited grace-period states in rgosp.  This
+ * state value can be passed to a later call to cond_synchronize_rcu_full()
+ * or poll_state_synchronize_rcu_full() to determine whether or not a
+ * grace period (whether normal or expedited) has elapsed in the meantime.
+ * If the needed expedited grace period is not already slated to start,
+ * initiates that grace period.
+ */
+void start_poll_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp)
+{
+	get_state_synchronize_rcu_full(rgosp);
+	(void)start_poll_synchronize_rcu_expedited();
+}
+EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu_expedited_full);
+
+/**
  * cond_synchronize_rcu_expedited - Conditionally wait for an expedited RCU grace period
  *
  * @oldstate: value from get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or start_poll_synchronize_rcu_expedited()
@@ -1053,3 +1077,30 @@ void cond_synchronize_rcu_expedited(unsigned long oldstate)
 		synchronize_rcu_expedited();
 }
 EXPORT_SYMBOL_GPL(cond_synchronize_rcu_expedited);
+
+/**
+ * cond_synchronize_rcu_expedited_full - Conditionally wait for an expedited RCU grace period
+ * @rgosp: value from get_state_synchronize_rcu_full(), start_poll_synchronize_rcu_full(), or start_poll_synchronize_rcu_expedited_full()
+ *
+ * If a full RCU grace period has elapsed since the call to
+ * get_state_synchronize_rcu_full(), start_poll_synchronize_rcu_full(),
+ * or start_poll_synchronize_rcu_expedited_full() from which @rgosp was
+ * obtained, just return.  Otherwise, invoke synchronize_rcu_expedited()
+ * to wait for a full grace period.
+ *
+ * Yes, this function does not take counter wrap into account.
+ * But counter wrap is harmless.  If the counter wraps, we have waited for
+ * more than 2 billion grace periods (and way more on a 64-bit system!),
+ * so waiting for a couple of additional grace periods should be just fine.
+ *
+ * This function provides the same memory-ordering guarantees that
+ * would be provided by a synchronize_rcu() that was invoked at the call
+ * to the function that provided @rgosp and that returned at the end of
+ * this function.
+ */
+void cond_synchronize_rcu_expedited_full(struct rcu_gp_oldstate *rgosp)
+{
+	if (!poll_state_synchronize_rcu_full(rgosp))
+		synchronize_rcu_expedited();
+}
+EXPORT_SYMBOL_GPL(cond_synchronize_rcu_expedited_full);
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index a8f574d8850d..0a5f0ef41484 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -1111,7 +1111,7 @@ int rcu_nocb_cpu_deoffload(int cpu)
 			if (!ret)
 				cpumask_clear_cpu(cpu, rcu_nocb_mask);
 		} else {
-			pr_info("NOCB: Can't CB-deoffload an offline CPU\n");
+			pr_info("NOCB: Cannot CB-deoffload offline CPU %d\n", rdp->cpu);
 			ret = -EINVAL;
 		}
 	}
@@ -1196,7 +1196,7 @@ int rcu_nocb_cpu_offload(int cpu)
 			if (!ret)
 				cpumask_set_cpu(cpu, rcu_nocb_mask);
 		} else {
-			pr_info("NOCB: Can't CB-offload an offline CPU\n");
+			pr_info("NOCB: Cannot CB-offload offline CPU %d\n", rdp->cpu);
 			ret = -EINVAL;
 		}
 	}
@@ -1452,8 +1452,8 @@ static void show_rcu_nocb_gp_state(struct rcu_data *rdp)
 		(long)rdp->nocb_gp_seq,
 		rnp->grplo, rnp->grphi, READ_ONCE(rdp->nocb_gp_loops),
 		rdp->nocb_gp_kthread ? task_state_to_char(rdp->nocb_gp_kthread) : '.',
-		rdp->nocb_cb_kthread ? (int)task_cpu(rdp->nocb_gp_kthread) : -1,
-		show_rcu_should_be_on_cpu(rdp->nocb_cb_kthread));
+		rdp->nocb_gp_kthread ? (int)task_cpu(rdp->nocb_gp_kthread) : -1,
+		show_rcu_should_be_on_cpu(rdp->nocb_gp_kthread));
 }
 
 /* Dump out nocb kthread state for the specified rcu_data structure. */
@@ -1497,7 +1497,7 @@ static void show_rcu_nocb_state(struct rcu_data *rdp)
 		".B"[!!rcu_cblist_n_cbs(&rdp->nocb_bypass)],
 		rcu_segcblist_n_cbs(&rdp->cblist),
 		rdp->nocb_cb_kthread ? task_state_to_char(rdp->nocb_cb_kthread) : '.',
-		rdp->nocb_cb_kthread ? (int)task_cpu(rdp->nocb_gp_kthread) : -1,
+		rdp->nocb_cb_kthread ? (int)task_cpu(rdp->nocb_cb_kthread) : -1,
 		show_rcu_should_be_on_cpu(rdp->nocb_cb_kthread));
 
 	/* It is OK for GP kthreads to have GP state. */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 438ecae6bd7e..e3142ee35fc6 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -641,7 +641,8 @@ static void rcu_read_unlock_special(struct task_struct *t)
 
 		expboost = (t->rcu_blocked_node && READ_ONCE(t->rcu_blocked_node->exp_tasks)) ||
 			   (rdp->grpmask & READ_ONCE(rnp->expmask)) ||
-			   IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ||
+			   (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) &&
+			   ((rdp->grpmask & READ_ONCE(rnp->qsmask)) || t->rcu_blocked_node)) ||
 			   (IS_ENABLED(CONFIG_RCU_BOOST) && irqs_were_disabled &&
 			    t->rcu_blocked_node);
 		// Need to defer quiescent state until everything is enabled.
@@ -718,9 +719,6 @@ static void rcu_flavor_sched_clock_irq(int user)
 	struct task_struct *t = current;
 
 	lockdep_assert_irqs_disabled();
-	if (user || rcu_is_cpu_rrupt_from_idle()) {
-		rcu_note_voluntary_context_switch(current);
-	}
 	if (rcu_preempt_depth() > 0 ||
 	    (preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK))) {
 		/* No QS, force context switch if deferred. */
@@ -824,6 +822,7 @@ void rcu_read_unlock_strict(void)
 	if (irqs_disabled() || preempt_count() || !rcu_state.gp_kthread)
 		return;
 	rdp = this_cpu_ptr(&rcu_data);
+	rdp->cpu_no_qs.b.norm = false;
 	rcu_report_qs_rdp(rdp);
 	udelay(rcu_unlock_delay);
 }
@@ -869,7 +868,7 @@ void rcu_all_qs(void)
 
 	if (!raw_cpu_read(rcu_data.rcu_urgent_qs))
 		return;
-	preempt_disable();
+	preempt_disable();  // For CONFIG_PREEMPT_COUNT=y kernels
 	/* Load rcu_urgent_qs before other flags. */
 	if (!smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) {
 		preempt_enable();
@@ -931,10 +930,13 @@ static notrace bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 	return false;
 }
 
-// Except that we do need to respond to a request by an expedited grace
-// period for a quiescent state from this CPU.  Note that requests from
-// tasks are handled when removing the task from the blocked-tasks list
-// below.
+// Except that we do need to respond to a request by an expedited
+// grace period for a quiescent state from this CPU.  Note that in
+// non-preemptible kernels, there can be no context switches within RCU
+// read-side critical sections, which in turn means that the leaf rcu_node
+// structure's blocked-tasks list is always empty.  is therefore no need to
+// actually check it.  Instead, a quiescent state from this CPU suffices,
+// and this function is only called from such a quiescent state.
 notrace void rcu_preempt_deferred_qs(struct task_struct *t)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
@@ -972,7 +974,6 @@ static void rcu_flavor_sched_clock_irq(int user)
 		 * neither access nor modify, at least not while the
 		 * corresponding CPU is online.
 		 */
-
 		rcu_qs();
 	}
 }
@@ -1238,8 +1239,11 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 		    cpu != outgoingcpu)
 			cpumask_set_cpu(cpu, cm);
 	cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU));
-	if (cpumask_empty(cm))
+	if (cpumask_empty(cm)) {
 		cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU));
+		if (outgoingcpu >= 0)
+			cpumask_clear_cpu(outgoingcpu, cm);
+	}
 	set_cpus_allowed_ptr(t, cm);
 	mutex_unlock(&rnp->boost_kthread_mutex);
 	free_cpumask_var(cm);
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index c3fbbcc09327..5653560573e2 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -368,7 +368,7 @@ static void rcu_dump_cpu_stacks(void)
 			if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
 				if (cpu_is_offline(cpu))
 					pr_err("Offline CPU %d blocking current GP.\n", cpu);
-				else if (!trigger_single_cpu_backtrace(cpu))
+				else
 					dump_cpu_task(cpu);
 			}
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -511,8 +511,7 @@ static void rcu_check_gp_kthread_starvation(void)
 					pr_err("RCU GP kthread last ran on offline CPU %d.\n", cpu);
 				} else  {
 					pr_err("Stack dump where RCU GP kthread last ran:\n");
-					if (!trigger_single_cpu_backtrace(cpu))
-						dump_cpu_task(cpu);
+					dump_cpu_task(cpu);
 				}
 			}
 			wake_up_process(gpk);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ee28253c9ac0..60fdc0faf1c9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -73,6 +73,7 @@
 
 #include <uapi/linux/sched/types.h>
 
+#include <asm/irq_regs.h>
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
 
@@ -11183,6 +11184,19 @@ struct cgroup_subsys cpu_cgrp_subsys = {
 
 void dump_cpu_task(int cpu)
 {
+	if (cpu == smp_processor_id() && in_hardirq()) {
+		struct pt_regs *regs;
+
+		regs = get_irq_regs();
+		if (regs) {
+			show_regs(regs);
+			return;
+		}
+	}
+
+	if (trigger_single_cpu_backtrace(cpu))
+		return;
+
 	pr_info("Task dump for CPU %d:\n", cpu);
 	sched_show_task(cpu_curr(cpu));
 }
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 1207c78f85c1..9161d1136d01 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -25,6 +25,9 @@ struct sugov_policy {
 	unsigned int		next_freq;
 	unsigned int		cached_raw_freq;
 
+	/* max CPU capacity, which is equal for all CPUs in freq. domain */
+	unsigned long		max;
+
 	/* The next fields are only needed if fast switch cannot be used: */
 	struct			irq_work irq_work;
 	struct			kthread_work work;
@@ -48,7 +51,6 @@ struct sugov_cpu {
 
 	unsigned long		util;
 	unsigned long		bw_dl;
-	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
 #ifdef CONFIG_NO_HZ_COMMON
@@ -158,7 +160,6 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
 
-	sg_cpu->max = arch_scale_cpu_capacity(sg_cpu->cpu);
 	sg_cpu->bw_dl = cpu_bw_dl(rq);
 	sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu),
 					  FREQUENCY_UTIL, NULL);
@@ -253,6 +254,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
  */
 static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time)
 {
+	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	unsigned long boost;
 
 	/* No boost currently required */
@@ -280,7 +282,8 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time)
 	 * sg_cpu->util is already in capacity scale; convert iowait_boost
 	 * into the same scale so we can compare.
 	 */
-	boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT;
+	boost = sg_cpu->iowait_boost * sg_policy->max;
+	boost >>= SCHED_CAPACITY_SHIFT;
 	boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL);
 	if (sg_cpu->util < boost)
 		sg_cpu->util = boost;
@@ -337,7 +340,7 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
 	if (!sugov_update_single_common(sg_cpu, time, flags))
 		return;
 
-	next_f = get_next_freq(sg_policy, sg_cpu->util, sg_cpu->max);
+	next_f = get_next_freq(sg_policy, sg_cpu->util, sg_policy->max);
 	/*
 	 * Do not reduce the frequency if the CPU has not been idle
 	 * recently, as the reduction is likely to be premature then.
@@ -373,6 +376,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 				     unsigned int flags)
 {
 	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
+	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	unsigned long prev_util = sg_cpu->util;
 
 	/*
@@ -399,7 +403,8 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 		sg_cpu->util = prev_util;
 
 	cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
-				   map_util_perf(sg_cpu->util), sg_cpu->max);
+				   map_util_perf(sg_cpu->util),
+				   sg_policy->max);
 
 	sg_cpu->sg_policy->last_freq_update_time = time;
 }
@@ -408,25 +413,19 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 {
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	struct cpufreq_policy *policy = sg_policy->policy;
-	unsigned long util = 0, max = 1;
+	unsigned long util = 0;
 	unsigned int j;
 
 	for_each_cpu(j, policy->cpus) {
 		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
-		unsigned long j_util, j_max;
 
 		sugov_get_util(j_sg_cpu);
 		sugov_iowait_apply(j_sg_cpu, time);
-		j_util = j_sg_cpu->util;
-		j_max = j_sg_cpu->max;
 
-		if (j_util * max > j_max * util) {
-			util = j_util;
-			max = j_max;
-		}
+		util = max(j_sg_cpu->util, util);
 	}
 
-	return get_next_freq(sg_policy, util, max);
+	return get_next_freq(sg_policy, util, sg_policy->max);
 }
 
 static void
@@ -752,7 +751,7 @@ static int sugov_start(struct cpufreq_policy *policy)
 {
 	struct sugov_policy *sg_policy = policy->governor_data;
 	void (*uu)(struct update_util_data *data, u64 time, unsigned int flags);
-	unsigned int cpu;
+	unsigned int cpu = cpumask_first(policy->cpus);
 
 	sg_policy->freq_update_delay_ns	= sg_policy->tunables->rate_limit_us * NSEC_PER_USEC;
 	sg_policy->last_freq_update_time	= 0;
@@ -760,6 +759,7 @@ static int sugov_start(struct cpufreq_policy *policy)
 	sg_policy->work_in_progress		= false;
 	sg_policy->limits_changed		= false;
 	sg_policy->cached_raw_freq		= 0;
+	sg_policy->max				= arch_scale_cpu_capacity(cpu);
 
 	sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index bb3d63bdf4ae..667876da8382 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -416,7 +416,7 @@ void update_sched_domain_debugfs(void)
 		char buf[32];
 
 		snprintf(buf, sizeof(buf), "cpu%d", cpu);
-		debugfs_remove(debugfs_lookup(buf, sd_dentry));
+		debugfs_lookup_and_remove(buf, sd_dentry);
 		d_cpu = debugfs_create_dir(buf, sd_dentry);
 
 		i = 0;
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index ec66b40bdd40..ecb4b4ff4ce0 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -190,12 +190,8 @@ static void group_init(struct psi_group *group)
 	/* Init trigger-related members */
 	mutex_init(&group->trigger_lock);
 	INIT_LIST_HEAD(&group->triggers);
-	memset(group->nr_triggers, 0, sizeof(group->nr_triggers));
-	group->poll_states = 0;
 	group->poll_min_period = U32_MAX;
-	memset(group->polling_total, 0, sizeof(group->polling_total));
 	group->polling_next_update = ULLONG_MAX;
-	group->polling_until = 0;
 	init_waitqueue_head(&group->poll_wait);
 	timer_setup(&group->poll_timer, poll_timer_fn, 0);
 	rcu_assign_pointer(group->poll_task, NULL);
@@ -957,7 +953,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup)
 	if (static_branch_likely(&psi_disabled))
 		return 0;
 
-	cgroup->psi = kmalloc(sizeof(struct psi_group), GFP_KERNEL);
+	cgroup->psi = kzalloc(sizeof(struct psi_group), GFP_KERNEL);
 	if (!cgroup->psi)
 		return -ENOMEM;
 
@@ -1091,7 +1087,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
 }
 
 struct psi_trigger *psi_trigger_create(struct psi_group *group,
-			char *buf, size_t nbytes, enum psi_res res)
+			char *buf, enum psi_res res)
 {
 	struct psi_trigger *t;
 	enum psi_states state;
@@ -1320,7 +1316,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
 		return -EBUSY;
 	}
 
-	new = psi_trigger_create(&psi_system, buf, nbytes, res);
+	new = psi_trigger_create(&psi_system, buf, res);
 	if (IS_ERR(new)) {
 		mutex_unlock(&seq->lock);
 		return PTR_ERR(new);
diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c
index d4788f810b55..0b1cd985dc27 100644
--- a/kernel/sched/wait_bit.c
+++ b/kernel/sched/wait_bit.c
@@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 
diff --git a/kernel/smp.c b/kernel/smp.c
index 650810a6f29b..e8cdc025a046 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -370,8 +370,7 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *
 	if (cpu >= 0) {
 		if (static_branch_unlikely(&csdlock_debug_extended))
 			csd_lock_print_extended(csd, cpu);
-		if (!trigger_single_cpu_backtrace(cpu))
-			dump_cpu_task(cpu);
+		dump_cpu_task(cpu);
 		if (!cpu_cur_csd) {
 			pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu);
 			arch_send_call_function_single_ipi(cpu);
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index a492f159624f..860b2dcf3ac4 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -277,6 +277,7 @@ COND_SYSCALL(landlock_restrict_self);
 
 /* mm/fadvise.c */
 COND_SYSCALL(fadvise64_64);
+COND_SYSCALL_COMPAT(fadvise64_64);
 
 /* mm/, CONFIG_MMU only */
 COND_SYSCALL(swapon);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index bc921a3f7ea8..439e2ab6905e 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1861,8 +1861,6 @@ static void ftrace_hash_rec_enable_modify(struct ftrace_ops *ops,
 	ftrace_hash_rec_update_modify(ops, filter_hash, 1);
 }
 
-static bool ops_references_ip(struct ftrace_ops *ops, unsigned long ip);
-
 /*
  * Try to update IPMODIFY flag on each ftrace_rec. Return 0 if it is OK
  * or no-needed to update, -EBUSY if it detects a conflict of the flag
@@ -2974,6 +2972,16 @@ int ftrace_startup(struct ftrace_ops *ops, int command)
 
 	ftrace_startup_enable(command);
 
+	/*
+	 * If ftrace is in an undefined state, we just remove ops from list
+	 * to prevent the NULL pointer, instead of totally rolling it back and
+	 * free trampoline, because those actions could cause further damage.
+	 */
+	if (unlikely(ftrace_disabled)) {
+		__unregister_ftrace_function(ops);
+		return -ENODEV;
+	}
+
 	ops->flags &= ~FTRACE_OPS_FL_ADDING;
 
 	return 0;
@@ -3108,49 +3116,6 @@ static inline int ops_traces_mod(struct ftrace_ops *ops)
 		ftrace_hash_empty(ops->func_hash->notrace_hash);
 }
 
-/*
- * Check if the current ops references the given ip.
- *
- * If the ops traces all functions, then it was already accounted for.
- * If the ops does not trace the current record function, skip it.
- * If the ops ignores the function via notrace filter, skip it.
- */
-static bool
-ops_references_ip(struct ftrace_ops *ops, unsigned long ip)
-{
-	/* If ops isn't enabled, ignore it */
-	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
-		return false;
-
-	/* If ops traces all then it includes this function */
-	if (ops_traces_mod(ops))
-		return true;
-
-	/* The function must be in the filter */
-	if (!ftrace_hash_empty(ops->func_hash->filter_hash) &&
-	    !__ftrace_lookup_ip(ops->func_hash->filter_hash, ip))
-		return false;
-
-	/* If in notrace hash, we ignore it too */
-	if (ftrace_lookup_ip(ops->func_hash->notrace_hash, ip))
-		return false;
-
-	return true;
-}
-
-/*
- * Check if the current ops references the record.
- *
- * If the ops traces all functions, then it was already accounted for.
- * If the ops does not trace the current record function, skip it.
- * If the ops ignores the function via notrace filter, skip it.
- */
-static bool
-ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec)
-{
-	return ops_references_ip(ops, rec->ip);
-}
-
 static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
 {
 	bool init_nop = ftrace_need_init_nop();
@@ -6812,6 +6777,38 @@ static int ftrace_get_trampoline_kallsym(unsigned int symnum,
 	return -ERANGE;
 }
 
+#if defined(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS) || defined(CONFIG_MODULES)
+/*
+ * Check if the current ops references the given ip.
+ *
+ * If the ops traces all functions, then it was already accounted for.
+ * If the ops does not trace the current record function, skip it.
+ * If the ops ignores the function via notrace filter, skip it.
+ */
+static bool
+ops_references_ip(struct ftrace_ops *ops, unsigned long ip)
+{
+	/* If ops isn't enabled, ignore it */
+	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
+		return false;
+
+	/* If ops traces all then it includes this function */
+	if (ops_traces_mod(ops))
+		return true;
+
+	/* The function must be in the filter */
+	if (!ftrace_hash_empty(ops->func_hash->filter_hash) &&
+	    !__ftrace_lookup_ip(ops->func_hash->filter_hash, ip))
+		return false;
+
+	/* If in notrace hash, we ignore it too */
+	if (ftrace_lookup_ip(ops->func_hash->notrace_hash, ip))
+		return false;
+
+	return true;
+}
+#endif
+
 #ifdef CONFIG_MODULES
 
 #define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next)
@@ -6824,7 +6821,7 @@ static int referenced_filters(struct dyn_ftrace *rec)
 	int cnt = 0;
 
 	for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) {
-		if (ops_references_rec(ops, rec)) {
+		if (ops_references_ip(ops, rec->ip)) {
 			if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_DIRECT))
 				continue;
 			if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_IPMODIFY))
diff --git a/kernel/trace/rv/monitors/wip/wip.h b/kernel/trace/rv/monitors/wip/wip.h
index c1c47e2305ef..dacc37b62a2c 100644
--- a/kernel/trace/rv/monitors/wip/wip.h
+++ b/kernel/trace/rv/monitors/wip/wip.h
@@ -27,7 +27,7 @@ struct automaton_wip {
 	bool final_states[state_max_wip];
 };
 
-struct automaton_wip automaton_wip = {
+static struct automaton_wip automaton_wip = {
 	.state_names = {
 		"preemptive",
 		"non_preemptive"
diff --git a/kernel/trace/rv/monitors/wwnr/wwnr.h b/kernel/trace/rv/monitors/wwnr/wwnr.h
index d1afe55cdd4c..118e576b91b4 100644
--- a/kernel/trace/rv/monitors/wwnr/wwnr.h
+++ b/kernel/trace/rv/monitors/wwnr/wwnr.h
@@ -27,7 +27,7 @@ struct automaton_wwnr {
 	bool final_states[state_max_wwnr];
 };
 
-struct automaton_wwnr automaton_wwnr = {
+static struct automaton_wwnr automaton_wwnr = {
 	.state_names = {
 		"not_running",
 		"running"
diff --git a/kernel/trace/rv/reactor_panic.c b/kernel/trace/rv/reactor_panic.c
index b698d05dd069..d65f6c25a87c 100644
--- a/kernel/trace/rv/reactor_panic.c
+++ b/kernel/trace/rv/reactor_panic.c
@@ -24,13 +24,13 @@ static struct rv_reactor rv_panic = {
 	.react = rv_panic_reaction
 };
 
-static int register_react_panic(void)
+static int __init register_react_panic(void)
 {
 	rv_register_reactor(&rv_panic);
 	return 0;
 }
 
-static void unregister_react_panic(void)
+static void __exit unregister_react_panic(void)
 {
 	rv_unregister_reactor(&rv_panic);
 }
diff --git a/kernel/trace/rv/reactor_printk.c b/kernel/trace/rv/reactor_printk.c
index 31899f953af4..4b6b7106a477 100644
--- a/kernel/trace/rv/reactor_printk.c
+++ b/kernel/trace/rv/reactor_printk.c
@@ -23,13 +23,13 @@ static struct rv_reactor rv_printk = {
 	.react = rv_printk_reaction
 };
 
-static int register_react_printk(void)
+static int __init register_react_printk(void)
 {
 	rv_register_reactor(&rv_printk);
 	return 0;
 }
 
-static void unregister_react_printk(void)
+static void __exit unregister_react_printk(void)
 {
 	rv_unregister_reactor(&rv_printk);
 }
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 4a0e9d927443..1783e3478912 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -227,6 +227,7 @@ static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i)
 	struct probe_arg *parg = &ep->tp.args[i];
 	struct ftrace_event_field *field;
 	struct list_head *head;
+	int ret = -ENOENT;
 
 	head = trace_get_fields(ep->event);
 	list_for_each_entry(field, head, link) {
@@ -236,9 +237,20 @@ static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i)
 			return 0;
 		}
 	}
+
+	/*
+	 * Argument not found on event. But allow for comm and COMM
+	 * to be used to get the current->comm.
+	 */
+	if (strcmp(parg->code->data, "COMM") == 0 ||
+	    strcmp(parg->code->data, "comm") == 0) {
+		parg->code->op = FETCH_OP_COMM;
+		ret = 0;
+	}
+
 	kfree(parg->code->data);
 	parg->code->data = NULL;
-	return -ENOENT;
+	return ret;
 }
 
 static int eprobe_event_define_fields(struct trace_event_call *event_call)
@@ -311,6 +323,27 @@ static unsigned long get_event_field(struct fetch_insn *code, void *rec)
 
 	addr = rec + field->offset;
 
+	if (is_string_field(field)) {
+		switch (field->filter_type) {
+		case FILTER_DYN_STRING:
+			val = (unsigned long)(rec + (*(unsigned int *)addr & 0xffff));
+			break;
+		case FILTER_RDYN_STRING:
+			val = (unsigned long)(addr + (*(unsigned int *)addr & 0xffff));
+			break;
+		case FILTER_STATIC_STRING:
+			val = (unsigned long)addr;
+			break;
+		case FILTER_PTR_STRING:
+			val = (unsigned long)(*(char *)addr);
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			return 0;
+		}
+		return val;
+	}
+
 	switch (field->size) {
 	case 1:
 		if (field->is_signed)
@@ -342,16 +375,38 @@ static unsigned long get_event_field(struct fetch_insn *code, void *rec)
 
 static int get_eprobe_size(struct trace_probe *tp, void *rec)
 {
+	struct fetch_insn *code;
 	struct probe_arg *arg;
 	int i, len, ret = 0;
 
 	for (i = 0; i < tp->nr_args; i++) {
 		arg = tp->args + i;
-		if (unlikely(arg->dynamic)) {
+		if (arg->dynamic) {
 			unsigned long val;
 
-			val = get_event_field(arg->code, rec);
-			len = process_fetch_insn_bottom(arg->code + 1, val, NULL, NULL);
+			code = arg->code;
+ retry:
+			switch (code->op) {
+			case FETCH_OP_TP_ARG:
+				val = get_event_field(code, rec);
+				break;
+			case FETCH_OP_IMM:
+				val = code->immediate;
+				break;
+			case FETCH_OP_COMM:
+				val = (unsigned long)current->comm;
+				break;
+			case FETCH_OP_DATA:
+				val = (unsigned long)code->data;
+				break;
+			case FETCH_NOP_SYMBOL:	/* Ignore a place holder */
+				code++;
+				goto retry;
+			default:
+				continue;
+			}
+			code++;
+			len = process_fetch_insn_bottom(code, val, NULL, NULL);
 			if (len > 0)
 				ret += len;
 		}
@@ -369,8 +424,28 @@ process_fetch_insn(struct fetch_insn *code, void *rec, void *dest,
 {
 	unsigned long val;
 
-	val = get_event_field(code, rec);
-	return process_fetch_insn_bottom(code + 1, val, dest, base);
+ retry:
+	switch (code->op) {
+	case FETCH_OP_TP_ARG:
+		val = get_event_field(code, rec);
+		break;
+	case FETCH_OP_IMM:
+		val = code->immediate;
+		break;
+	case FETCH_OP_COMM:
+		val = (unsigned long)current->comm;
+		break;
+	case FETCH_OP_DATA:
+		val = (unsigned long)code->data;
+		break;
+	case FETCH_NOP_SYMBOL:	/* Ignore a place holder */
+		code++;
+		goto retry;
+	default:
+		return -EILSEQ;
+	}
+	code++;
+	return process_fetch_insn_bottom(code, val, dest, base);
 }
 NOKPROBE_SYMBOL(process_fetch_insn)
 
@@ -845,6 +920,10 @@ static int trace_eprobe_tp_update_arg(struct trace_eprobe *ep, const char *argv[
 			trace_probe_log_err(0, BAD_ATTACH_ARG);
 	}
 
+	/* Handle symbols "@" */
+	if (!ret)
+		ret = traceprobe_update_arg(&ep->tp.args[i]);
+
 	return ret;
 }
 
@@ -883,7 +962,7 @@ static int __trace_eprobe_create(int argc, const char *argv[])
 	trace_probe_log_set_index(1);
 	sys_event = argv[1];
 	ret = traceprobe_parse_event_name(&sys_event, &sys_name, buf2, 0);
-	if (!sys_event || !sys_name) {
+	if (ret || !sys_event || !sys_name) {
 		trace_probe_log_err(0, NO_EVENT_INFO);
 		goto parse_error;
 	}
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index a114549720d6..61e3a2620fa3 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -157,7 +157,7 @@ static void perf_trace_event_unreg(struct perf_event *p_event)
 	int i;
 
 	if (--tp_event->perf_refcount > 0)
-		goto out;
+		return;
 
 	tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER, NULL);
 
@@ -176,8 +176,6 @@ static void perf_trace_event_unreg(struct perf_event *p_event)
 			perf_trace_buf[i] = NULL;
 		}
 	}
-out:
-	trace_event_put_ref(tp_event);
 }
 
 static int perf_trace_event_open(struct perf_event *p_event)
@@ -241,6 +239,7 @@ void perf_trace_destroy(struct perf_event *p_event)
 	mutex_lock(&event_mutex);
 	perf_trace_event_close(p_event);
 	perf_trace_event_unreg(p_event);
+	trace_event_put_ref(p_event->tp_event);
 	mutex_unlock(&event_mutex);
 }
 
@@ -292,6 +291,7 @@ void perf_kprobe_destroy(struct perf_event *p_event)
 	mutex_lock(&event_mutex);
 	perf_trace_event_close(p_event);
 	perf_trace_event_unreg(p_event);
+	trace_event_put_ref(p_event->tp_event);
 	mutex_unlock(&event_mutex);
 
 	destroy_local_trace_kprobe(p_event->tp_event);
@@ -347,6 +347,7 @@ void perf_uprobe_destroy(struct perf_event *p_event)
 	mutex_lock(&event_mutex);
 	perf_trace_event_close(p_event);
 	perf_trace_event_unreg(p_event);
+	trace_event_put_ref(p_event->tp_event);
 	mutex_unlock(&event_mutex);
 	destroy_local_trace_uprobe(p_event->tp_event);
 }
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 181f08186d32..0356cae0cf74 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -176,6 +176,7 @@ static int trace_define_generic_fields(void)
 
 	__generic_field(int, CPU, FILTER_CPU);
 	__generic_field(int, cpu, FILTER_CPU);
+	__generic_field(int, common_cpu, FILTER_CPU);
 	__generic_field(char *, COMM, FILTER_COMM);
 	__generic_field(char *, comm, FILTER_COMM);
 
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index cb866c3141af..918730d74932 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -142,7 +142,8 @@ static bool check_user_trigger(struct trace_event_file *file)
 {
 	struct event_trigger_data *data;
 
-	list_for_each_entry_rcu(data, &file->triggers, list) {
+	list_for_each_entry_rcu(data, &file->triggers, list,
+				lockdep_is_held(&event_mutex)) {
 		if (data->flags & EVENT_TRIGGER_FL_PROBE)
 			continue;
 		return true;
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index 95b58bd757ce..1e130da1b742 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -95,14 +95,14 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 	}
 
 	lockdep_hardirqs_on_prepare();
-	lockdep_hardirqs_on(CALLER_ADDR0);
+	lockdep_hardirqs_on(caller_addr);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
 NOKPROBE_SYMBOL(trace_hardirqs_on_caller);
 
 __visible void trace_hardirqs_off_caller(unsigned long caller_addr)
 {
-	lockdep_hardirqs_off(CALLER_ADDR0);
+	lockdep_hardirqs_off(caller_addr);
 
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 850a88abd33b..36dff277de46 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -283,7 +283,14 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 	int ret = 0;
 	int len;
 
-	if (strcmp(arg, "retval") == 0) {
+	if (flags & TPARG_FL_TPOINT) {
+		if (code->data)
+			return -EFAULT;
+		code->data = kstrdup(arg, GFP_KERNEL);
+		if (!code->data)
+			return -ENOMEM;
+		code->op = FETCH_OP_TP_ARG;
+	} else if (strcmp(arg, "retval") == 0) {
 		if (flags & TPARG_FL_RETURN) {
 			code->op = FETCH_OP_RETVAL;
 		} else {
@@ -307,7 +314,7 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 			}
 		} else
 			goto inval_var;
-	} else if (strcmp(arg, "comm") == 0) {
+	} else if (strcmp(arg, "comm") == 0 || strcmp(arg, "COMM") == 0) {
 		code->op = FETCH_OP_COMM;
 #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
 	} else if (((flags & TPARG_FL_MASK) ==
@@ -323,13 +330,6 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 		code->op = FETCH_OP_ARG;
 		code->param = (unsigned int)param - 1;
 #endif
-	} else if (flags & TPARG_FL_TPOINT) {
-		if (code->data)
-			return -EFAULT;
-		code->data = kstrdup(arg, GFP_KERNEL);
-		if (!code->data)
-			return -ENOMEM;
-		code->op = FETCH_OP_TP_ARG;
 	} else
 		goto inval_var;
 
@@ -384,6 +384,11 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
 		break;
 
 	case '%':	/* named register */
+		if (flags & TPARG_FL_TPOINT) {
+			/* eprobes do not handle registers */
+			trace_probe_log_err(offs, BAD_VAR);
+			break;
+		}
 		ret = regs_query_register_offset(arg + 1);
 		if (ret >= 0) {
 			code->op = FETCH_OP_REG;
@@ -617,9 +622,11 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
 
 	/*
 	 * Since $comm and immediate string can not be dereferenced,
-	 * we can find those by strcmp.
+	 * we can find those by strcmp. But ignore for eprobes.
 	 */
-	if (strcmp(arg, "$comm") == 0 || strncmp(arg, "\\\"", 2) == 0) {
+	if (!(flags & TPARG_FL_TPOINT) &&
+	    (strcmp(arg, "$comm") == 0 || strcmp(arg, "$COMM") == 0 ||
+	     strncmp(arg, "\\\"", 2) == 0)) {
 		/* The type of $comm must be "string", and not an array. */
 		if (parg->count || (t && strcmp(t, "string")))
 			goto out;
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 64ea283f2f86..ef42c1a11920 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -571,7 +571,8 @@ static void for_each_tracepoint_range(
 bool trace_module_has_bad_taint(struct module *mod)
 {
 	return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP) |
-			       (1 << TAINT_UNSIGNED_MODULE));
+			       (1 << TAINT_UNSIGNED_MODULE) |
+			       (1 << TAINT_TEST));
 }
 
 static BLOCKING_NOTIFIER_HEAD(tracepoint_notify_list);
@@ -647,7 +648,7 @@ static int tracepoint_module_coming(struct module *mod)
 	/*
 	 * We skip modules that taint the kernel, especially those with different
 	 * module headers (for forced load), to make sure we don't cause a crash.
-	 * Staging, out-of-tree, and unsigned GPL modules are fine.
+	 * Staging, out-of-tree, unsigned GPL, and test modules are fine.
 	 */
 	if (trace_module_has_bad_taint(mod))
 		return 0;
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 5481ba44a8d6..3f464bbda0e9 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -9,6 +9,7 @@
 #include <linux/highuid.h>
 #include <linux/cred.h>
 #include <linux/securebits.h>
+#include <linux/security.h>
 #include <linux/keyctl.h>
 #include <linux/key-type.h>
 #include <keys/user-type.h>
@@ -113,6 +114,10 @@ int create_user_ns(struct cred *new)
 	    !kgid_has_mapping(parent_ns, group))
 		goto fail_dec;
 
+	ret = security_create_user_ns(new);
+	if (ret < 0)
+		goto fail_dec;
+
 	ret = -ENOMEM;
 	ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL);
 	if (!ns)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index aeea9731ef80..7cd5f5e7e0a1 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1651,7 +1651,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 	struct work_struct *work = &dwork->work;
 
 	WARN_ON_ONCE(!wq);
-	WARN_ON_FUNCTION_MISMATCH(timer->function, delayed_work_timer_fn);
+	WARN_ON_ONCE(timer->function != delayed_work_timer_fn);
 	WARN_ON_ONCE(timer_pending(timer));
 	WARN_ON_ONCE(!list_empty(&work->entry));
 
@@ -3066,10 +3066,8 @@ static bool __flush_work(struct work_struct *work, bool from_cancel)
 	if (WARN_ON(!work->func))
 		return false;
 
-	if (!from_cancel) {
-		lock_map_acquire(&work->lockdep_map);
-		lock_map_release(&work->lockdep_map);
-	}
+	lock_map_acquire(&work->lockdep_map);
+	lock_map_release(&work->lockdep_map);
 
 	if (start_flush_work(work, &barr, from_cancel)) {
 		wait_for_completion(&barr.done);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 072e4b289c13..f473f7d8a0a2 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -264,8 +264,10 @@ config DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT
 config DEBUG_INFO_DWARF4
 	bool "Generate DWARF Version 4 debuginfo"
 	select DEBUG_INFO
+	depends on !CC_IS_CLANG || (CC_IS_CLANG && (AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502)))
 	help
-	  Generate DWARF v4 debug info. This requires gcc 4.5+ and gdb 7.0+.
+	  Generate DWARF v4 debug info. This requires gcc 4.5+, binutils 2.35.2
+	  if using clang without clang's integrated assembler, and gdb 7.0+.
 
 	  If you have consumers of DWARF debug info that are not ready for
 	  newer revisions of DWARF, you may wish to choose this or have your
@@ -2029,13 +2031,16 @@ config LKDTM
 	Documentation on how to use the module can be found in
 	Documentation/fault-injection/provoke-crashes.rst
 
-config TEST_CPUMASK
-	tristate "cpumask tests" if !KUNIT_ALL_TESTS
+config CPUMASK_KUNIT_TEST
+	tristate "KUnit test for cpumask" if !KUNIT_ALL_TESTS
 	depends on KUNIT
 	default KUNIT_ALL_TESTS
 	help
 	  Enable to turn on cpumask tests, running at boot or module load time.
 
+	  For more information on KUnit and unit tests in general, please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
 	  If unsure, say N.
 
 config TEST_LIST_SORT
@@ -2506,6 +2511,18 @@ config MEMCPY_KUNIT_TEST
 
 	  If unsure, say N.
 
+config IS_SIGNED_TYPE_KUNIT_TEST
+	tristate "Test is_signed_type() macro" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	default KUNIT_ALL_TESTS
+	help
+	  Builds unit tests for the is_signed_type() macro.
+
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
 config OVERFLOW_KUNIT_TEST
 	tristate "Test check_*_overflow() functions at runtime" if !KUNIT_ALL_TESTS
 	depends on KUNIT
@@ -2530,6 +2547,15 @@ config STACKINIT_KUNIT_TEST
 	  CONFIG_GCC_PLUGIN_STRUCTLEAK, CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF,
 	  or CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF_ALL.
 
+config FORTIFY_KUNIT_TEST
+	tristate "Test fortified str*() and mem*() function internals at runtime" if !KUNIT_ALL_TESTS
+	depends on KUNIT && FORTIFY_SOURCE
+	default KUNIT_ALL_TESTS
+	help
+	  Builds unit tests for checking internals of FORTIFY_SOURCE as used
+	  by the str*() and mem*() family of functions. For testing runtime
+	  traps of FORTIFY_SOURCE, see LKDTM's "FORTIFY_*" tests.
+
 config TEST_UDELAY
 	tristate "udelay test driver"
 	help
@@ -2705,6 +2731,40 @@ config HYPERV_TESTING
 
 endmenu # "Kernel Testing and Coverage"
 
+menu "Rust hacking"
+
+config RUST_DEBUG_ASSERTIONS
+	bool "Debug assertions"
+	depends on RUST
+	help
+	  Enables rustc's `-Cdebug-assertions` codegen option.
+
+	  This flag lets you turn `cfg(debug_assertions)` conditional
+	  compilation on or off. This can be used to enable extra debugging
+	  code in development but not in production. For example, it controls
+	  the behavior of the standard library's `debug_assert!` macro.
+
+	  Note that this will apply to all Rust code, including `core`.
+
+	  If unsure, say N.
+
+config RUST_OVERFLOW_CHECKS
+	bool "Overflow checks"
+	default y
+	depends on RUST
+	help
+	  Enables rustc's `-Coverflow-checks` codegen option.
+
+	  This flag allows you to control the behavior of runtime integer
+	  overflow. When overflow-checks are enabled, a Rust panic will occur
+	  on overflow.
+
+	  Note that this will apply to all Rust code, including `core`.
+
+	  If unsure, say Y.
+
+endmenu # "Rust"
+
 source "Documentation/Kconfig"
 
 endmenu # Kernel hacking
diff --git a/lib/Makefile b/lib/Makefile
index c95212141928..7d7c9f67eff6 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -34,9 +34,10 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
 	 nmi_backtrace.o win_minmax.o memcat_p.o \
-	 buildid.o cpumask.o
+	 buildid.o
 
 lib-$(CONFIG_PRINTK) += dump_stack.o
+lib-$(CONFIG_SMP) += cpumask.o
 
 lib-y	+= kobject.o klist.o
 obj-y	+= lockref.o
@@ -59,6 +60,7 @@ obj-$(CONFIG_TEST_BPF) += test_bpf.o
 obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o
 obj-$(CONFIG_TEST_BITOPS) += test_bitops.o
 CFLAGS_test_bitops.o += -Werror
+obj-$(CONFIG_CPUMASK_KUNIT_TEST) += cpumask_kunit.o
 obj-$(CONFIG_TEST_SYSCTL) += test_sysctl.o
 obj-$(CONFIG_TEST_SIPHASH) += test_siphash.o
 obj-$(CONFIG_HASH_KUNIT_TEST) += test_hash.o
@@ -99,7 +101,6 @@ obj-$(CONFIG_TEST_HMM) += test_hmm.o
 obj-$(CONFIG_TEST_FREE_PAGES) += test_free_pages.o
 obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
 obj-$(CONFIG_TEST_REF_TRACKER) += test_ref_tracker.o
-obj-$(CONFIG_TEST_CPUMASK) += test_cpumask.o
 CFLAGS_test_fprobe.o += $(CC_FLAGS_FTRACE)
 obj-$(CONFIG_FPROBE_SANITY_TEST) += test_fprobe.o
 #
@@ -376,9 +377,11 @@ obj-$(CONFIG_BITS_TEST) += test_bits.o
 obj-$(CONFIG_CMDLINE_KUNIT_TEST) += cmdline_kunit.o
 obj-$(CONFIG_SLUB_KUNIT_TEST) += slub_kunit.o
 obj-$(CONFIG_MEMCPY_KUNIT_TEST) += memcpy_kunit.o
+obj-$(CONFIG_IS_SIGNED_TYPE_KUNIT_TEST) += is_signed_type_kunit.o
 obj-$(CONFIG_OVERFLOW_KUNIT_TEST) += overflow_kunit.o
 CFLAGS_stackinit_kunit.o += $(call cc-disable-warning, switch-unreachable)
 obj-$(CONFIG_STACKINIT_KUNIT_TEST) += stackinit_kunit.o
+obj-$(CONFIG_FORTIFY_KUNIT_TEST) += fortify_kunit.o
 
 obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o
 
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 8baeb37e23d3..f0ae119be8c4 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -109,7 +109,6 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
 }
 #endif
 
-#if NR_CPUS > 1
 /**
  * cpumask_local_spread - select the i'th cpu with local numa cpu's first
  * @i: index number
@@ -197,4 +196,3 @@ unsigned int cpumask_any_distribute(const struct cpumask *srcp)
 	return next;
 }
 EXPORT_SYMBOL(cpumask_any_distribute);
-#endif /* NR_CPUS */
diff --git a/lib/test_cpumask.c b/lib/cpumask_kunit.c
index a31a1622f1f6..ecbeec72221e 100644
--- a/lib/test_cpumask.c
+++ b/lib/cpumask_kunit.c
@@ -9,6 +9,10 @@
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
 
+#define MASK_MSG(m) \
+	"%s contains %sCPUs %*pbl", #m, (cpumask_weight(m) ? "" : "no "), \
+	nr_cpumask_bits, cpumask_bits(m)
+
 #define EXPECT_FOR_EACH_CPU_EQ(test, mask)			\
 	do {							\
 		const cpumask_t *m = (mask);			\
@@ -16,7 +20,7 @@
 		int cpu, iter = 0;				\
 		for_each_cpu(cpu, m)				\
 			iter++;					\
-		KUNIT_EXPECT_EQ((test), mask_weight, iter);	\
+		KUNIT_EXPECT_EQ_MSG((test), mask_weight, iter, MASK_MSG(mask));	\
 	} while (0)
 
 #define EXPECT_FOR_EACH_CPU_NOT_EQ(test, mask)					\
@@ -26,7 +30,7 @@
 		int cpu, iter = 0;						\
 		for_each_cpu_not(cpu, m)					\
 			iter++;							\
-		KUNIT_EXPECT_EQ((test), nr_cpu_ids - mask_weight, iter);	\
+		KUNIT_EXPECT_EQ_MSG((test), nr_cpu_ids - mask_weight, iter, MASK_MSG(mask));	\
 	} while (0)
 
 #define EXPECT_FOR_EACH_CPU_WRAP_EQ(test, mask)			\
@@ -36,7 +40,7 @@
 		int cpu, iter = 0;				\
 		for_each_cpu_wrap(cpu, m, nr_cpu_ids / 2)	\
 			iter++;					\
-		KUNIT_EXPECT_EQ((test), mask_weight, iter);	\
+		KUNIT_EXPECT_EQ_MSG((test), mask_weight, iter, MASK_MSG(mask));	\
 	} while (0)
 
 #define EXPECT_FOR_EACH_CPU_BUILTIN_EQ(test, name)		\
@@ -45,7 +49,7 @@
 		int cpu, iter = 0;				\
 		for_each_##name##_cpu(cpu)			\
 			iter++;					\
-		KUNIT_EXPECT_EQ((test), mask_weight, iter);	\
+		KUNIT_EXPECT_EQ_MSG((test), mask_weight, iter, MASK_MSG(cpu_##name##_mask));	\
 	} while (0)
 
 static cpumask_t mask_empty;
@@ -53,37 +57,43 @@ static cpumask_t mask_all;
 
 static void test_cpumask_weight(struct kunit *test)
 {
-	KUNIT_EXPECT_TRUE(test, cpumask_empty(&mask_empty));
-	KUNIT_EXPECT_TRUE(test, cpumask_full(cpu_possible_mask));
-	KUNIT_EXPECT_TRUE(test, cpumask_full(&mask_all));
+	KUNIT_EXPECT_TRUE_MSG(test, cpumask_empty(&mask_empty), MASK_MSG(&mask_empty));
+	KUNIT_EXPECT_TRUE_MSG(test, cpumask_full(&mask_all), MASK_MSG(&mask_all));
 
-	KUNIT_EXPECT_EQ(test, 0, cpumask_weight(&mask_empty));
-	KUNIT_EXPECT_EQ(test, nr_cpu_ids, cpumask_weight(cpu_possible_mask));
-	KUNIT_EXPECT_EQ(test, nr_cpumask_bits, cpumask_weight(&mask_all));
+	KUNIT_EXPECT_EQ_MSG(test, 0, cpumask_weight(&mask_empty), MASK_MSG(&mask_empty));
+	KUNIT_EXPECT_EQ_MSG(test, nr_cpu_ids, cpumask_weight(cpu_possible_mask),
+			    MASK_MSG(cpu_possible_mask));
+	KUNIT_EXPECT_EQ_MSG(test, nr_cpumask_bits, cpumask_weight(&mask_all), MASK_MSG(&mask_all));
 }
 
 static void test_cpumask_first(struct kunit *test)
 {
-	KUNIT_EXPECT_LE(test, nr_cpu_ids, cpumask_first(&mask_empty));
-	KUNIT_EXPECT_EQ(test, 0, cpumask_first(cpu_possible_mask));
+	KUNIT_EXPECT_LE_MSG(test, nr_cpu_ids, cpumask_first(&mask_empty), MASK_MSG(&mask_empty));
+	KUNIT_EXPECT_EQ_MSG(test, 0, cpumask_first(cpu_possible_mask), MASK_MSG(cpu_possible_mask));
 
-	KUNIT_EXPECT_EQ(test, 0, cpumask_first_zero(&mask_empty));
-	KUNIT_EXPECT_LE(test, nr_cpu_ids, cpumask_first_zero(cpu_possible_mask));
+	KUNIT_EXPECT_EQ_MSG(test, 0, cpumask_first_zero(&mask_empty), MASK_MSG(&mask_empty));
+	KUNIT_EXPECT_LE_MSG(test, nr_cpu_ids, cpumask_first_zero(cpu_possible_mask),
+			    MASK_MSG(cpu_possible_mask));
 }
 
 static void test_cpumask_last(struct kunit *test)
 {
-	KUNIT_EXPECT_LE(test, nr_cpumask_bits, cpumask_last(&mask_empty));
-	KUNIT_EXPECT_EQ(test, nr_cpumask_bits - 1, cpumask_last(cpu_possible_mask));
+	KUNIT_EXPECT_LE_MSG(test, nr_cpumask_bits, cpumask_last(&mask_empty),
+			    MASK_MSG(&mask_empty));
+	KUNIT_EXPECT_EQ_MSG(test, nr_cpu_ids - 1, cpumask_last(cpu_possible_mask),
+			    MASK_MSG(cpu_possible_mask));
 }
 
 static void test_cpumask_next(struct kunit *test)
 {
-	KUNIT_EXPECT_EQ(test, 0, cpumask_next_zero(-1, &mask_empty));
-	KUNIT_EXPECT_LE(test, nr_cpu_ids, cpumask_next_zero(-1, cpu_possible_mask));
-
-	KUNIT_EXPECT_LE(test, nr_cpu_ids, cpumask_next(-1, &mask_empty));
-	KUNIT_EXPECT_EQ(test, 0, cpumask_next(-1, cpu_possible_mask));
+	KUNIT_EXPECT_EQ_MSG(test, 0, cpumask_next_zero(-1, &mask_empty), MASK_MSG(&mask_empty));
+	KUNIT_EXPECT_LE_MSG(test, nr_cpu_ids, cpumask_next_zero(-1, cpu_possible_mask),
+			    MASK_MSG(cpu_possible_mask));
+
+	KUNIT_EXPECT_LE_MSG(test, nr_cpu_ids, cpumask_next(-1, &mask_empty),
+			    MASK_MSG(&mask_empty));
+	KUNIT_EXPECT_EQ_MSG(test, 0, cpumask_next(-1, cpu_possible_mask),
+			    MASK_MSG(cpu_possible_mask));
 }
 
 static void test_cpumask_iterators(struct kunit *test)
diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig
index 9ff549f63540..47816af9a9d7 100644
--- a/lib/crypto/Kconfig
+++ b/lib/crypto/Kconfig
@@ -33,7 +33,6 @@ config CRYPTO_ARCH_HAVE_LIB_CHACHA
 
 config CRYPTO_LIB_CHACHA_GENERIC
 	tristate
-	select XOR_BLOCKS
 	help
 	  This symbol can be depended upon by arch implementations of the
 	  ChaCha library interface that require the generic code as a
diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c
new file mode 100644
index 000000000000..409af07f340a
--- /dev/null
+++ b/lib/fortify_kunit.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Runtime test cases for CONFIG_FORTIFY_SOURCE that aren't expected to
+ * Oops the kernel on success. (For those, see drivers/misc/lkdtm/fortify.c)
+ *
+ * For corner cases with UBSAN, try testing with:
+ *
+ * ./tools/testing/kunit/kunit.py run --arch=x86_64 \
+ *	--kconfig_add CONFIG_FORTIFY_SOURCE=y \
+ *	--kconfig_add CONFIG_UBSAN=y \
+ *	--kconfig_add CONFIG_UBSAN_TRAP=y \
+ *	--kconfig_add CONFIG_UBSAN_BOUNDS=y \
+ *	--kconfig_add CONFIG_UBSAN_LOCAL_BOUNDS=y \
+ *	--make_options LLVM=1 fortify
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <kunit/test.h>
+#include <linux/string.h>
+
+static const char array_of_10[] = "this is 10";
+static const char *ptr_of_11 = "this is 11!";
+static char array_unknown[] = "compiler thinks I might change";
+
+static void known_sizes_test(struct kunit *test)
+{
+	KUNIT_EXPECT_EQ(test, __compiletime_strlen("88888888"), 8);
+	KUNIT_EXPECT_EQ(test, __compiletime_strlen(array_of_10), 10);
+	KUNIT_EXPECT_EQ(test, __compiletime_strlen(ptr_of_11), 11);
+
+	KUNIT_EXPECT_EQ(test, __compiletime_strlen(array_unknown), SIZE_MAX);
+	/* Externally defined and dynamically sized string pointer: */
+	KUNIT_EXPECT_EQ(test, __compiletime_strlen(test->name), SIZE_MAX);
+}
+
+/* This is volatile so the optimizer can't perform DCE below. */
+static volatile int pick;
+
+/* Not inline to keep optimizer from figuring out which string we want. */
+static noinline size_t want_minus_one(int pick)
+{
+	const char *str;
+
+	switch (pick) {
+	case 1:
+		str = "4444";
+		break;
+	case 2:
+		str = "333";
+		break;
+	default:
+		str = "1";
+		break;
+	}
+	return __compiletime_strlen(str);
+}
+
+static void control_flow_split_test(struct kunit *test)
+{
+	KUNIT_EXPECT_EQ(test, want_minus_one(pick), SIZE_MAX);
+}
+
+static struct kunit_case fortify_test_cases[] = {
+	KUNIT_CASE(known_sizes_test),
+	KUNIT_CASE(control_flow_split_test),
+	{}
+};
+
+static struct kunit_suite fortify_test_suite = {
+	.name = "fortify",
+	.test_cases = fortify_test_cases,
+};
+
+kunit_test_suite(fortify_test_suite);
+
+MODULE_LICENSE("GPL");
diff --git a/lib/is_signed_type_kunit.c b/lib/is_signed_type_kunit.c
new file mode 100644
index 000000000000..207207522925
--- /dev/null
+++ b/lib/is_signed_type_kunit.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ *	./tools/testing/kunit/kunit.py run is_signed_type [--raw_output]
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <kunit/test.h>
+#include <linux/compiler.h>
+
+enum unsigned_enum {
+	constant_a = 3,
+};
+
+enum signed_enum {
+	constant_b = -1,
+	constant_c = 2,
+};
+
+static void is_signed_type_test(struct kunit *test)
+{
+	KUNIT_EXPECT_EQ(test, is_signed_type(bool), false);
+	KUNIT_EXPECT_EQ(test, is_signed_type(signed char), true);
+	KUNIT_EXPECT_EQ(test, is_signed_type(unsigned char), false);
+#ifdef __CHAR_UNSIGNED__
+	KUNIT_EXPECT_EQ(test, is_signed_type(char), false);
+#else
+	KUNIT_EXPECT_EQ(test, is_signed_type(char), true);
+#endif
+	KUNIT_EXPECT_EQ(test, is_signed_type(int), true);
+	KUNIT_EXPECT_EQ(test, is_signed_type(unsigned int), false);
+	KUNIT_EXPECT_EQ(test, is_signed_type(long), true);
+	KUNIT_EXPECT_EQ(test, is_signed_type(unsigned long), false);
+	KUNIT_EXPECT_EQ(test, is_signed_type(long long), true);
+	KUNIT_EXPECT_EQ(test, is_signed_type(unsigned long long), false);
+	KUNIT_EXPECT_EQ(test, is_signed_type(enum unsigned_enum), false);
+	KUNIT_EXPECT_EQ(test, is_signed_type(enum signed_enum), true);
+	KUNIT_EXPECT_EQ(test, is_signed_type(void *), false);
+	KUNIT_EXPECT_EQ(test, is_signed_type(const char *), false);
+}
+
+static struct kunit_case is_signed_type_test_cases[] = {
+	KUNIT_CASE(is_signed_type_test),
+	{}
+};
+
+static struct kunit_suite is_signed_type_test_suite = {
+	.name = "is_signed_type",
+	.test_cases = is_signed_type_test_cases,
+};
+
+kunit_test_suite(is_signed_type_test_suite);
+
+MODULE_LICENSE("Dual MIT/GPL");
diff --git a/lib/memcpy_kunit.c b/lib/memcpy_kunit.c
index 62f8ffcbbaa3..2b5cc70ac53f 100644
--- a/lib/memcpy_kunit.c
+++ b/lib/memcpy_kunit.c
@@ -29,9 +29,8 @@ struct some_bytes {
 };
 
 #define check(instance, v) do {	\
-	int i;	\
 	BUILD_BUG_ON(sizeof(instance.data) != 32);	\
-	for (i = 0; i < sizeof(instance.data); i++) {	\
+	for (size_t i = 0; i < sizeof(instance.data); i++) {	\
 		KUNIT_ASSERT_EQ_MSG(test, instance.data[i], v, \
 			"line %d: '%s' not initialized to 0x%02x @ %d (saw 0x%02x)\n", \
 			__LINE__, #instance, v, i, instance.data[i]);	\
@@ -39,9 +38,8 @@ struct some_bytes {
 } while (0)
 
 #define compare(name, one, two) do { \
-	int i; \
 	BUILD_BUG_ON(sizeof(one) != sizeof(two)); \
-	for (i = 0; i < sizeof(one); i++) {	\
+	for (size_t i = 0; i < sizeof(one); i++) {	\
 		KUNIT_EXPECT_EQ_MSG(test, one.data[i], two.data[i], \
 			"line %d: %s.data[%d] (0x%02x) != %s.data[%d] (0x%02x)\n", \
 			__LINE__, #one, i, one.data[i], #two, i, two.data[i]); \
@@ -272,10 +270,63 @@ static void memset_test(struct kunit *test)
 #undef TEST_OP
 }
 
+static void strtomem_test(struct kunit *test)
+{
+	static const char input[sizeof(unsigned long)] = "hi";
+	static const char truncate[] = "this is too long";
+	struct {
+		unsigned long canary1;
+		unsigned char output[sizeof(unsigned long)] __nonstring;
+		unsigned long canary2;
+	} wrap;
+
+	memset(&wrap, 0xFF, sizeof(wrap));
+	KUNIT_EXPECT_EQ_MSG(test, wrap.canary1, ULONG_MAX,
+			    "bad initial canary value");
+	KUNIT_EXPECT_EQ_MSG(test, wrap.canary2, ULONG_MAX,
+			    "bad initial canary value");
+
+	/* Check unpadded copy leaves surroundings untouched. */
+	strtomem(wrap.output, input);
+	KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX);
+	KUNIT_EXPECT_EQ(test, wrap.output[0], input[0]);
+	KUNIT_EXPECT_EQ(test, wrap.output[1], input[1]);
+	for (size_t i = 2; i < sizeof(wrap.output); i++)
+		KUNIT_EXPECT_EQ(test, wrap.output[i], 0xFF);
+	KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX);
+
+	/* Check truncated copy leaves surroundings untouched. */
+	memset(&wrap, 0xFF, sizeof(wrap));
+	strtomem(wrap.output, truncate);
+	KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX);
+	for (size_t i = 0; i < sizeof(wrap.output); i++)
+		KUNIT_EXPECT_EQ(test, wrap.output[i], truncate[i]);
+	KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX);
+
+	/* Check padded copy leaves only string padded. */
+	memset(&wrap, 0xFF, sizeof(wrap));
+	strtomem_pad(wrap.output, input, 0xAA);
+	KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX);
+	KUNIT_EXPECT_EQ(test, wrap.output[0], input[0]);
+	KUNIT_EXPECT_EQ(test, wrap.output[1], input[1]);
+	for (size_t i = 2; i < sizeof(wrap.output); i++)
+		KUNIT_EXPECT_EQ(test, wrap.output[i], 0xAA);
+	KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX);
+
+	/* Check truncated padded copy has no padding. */
+	memset(&wrap, 0xFF, sizeof(wrap));
+	strtomem(wrap.output, truncate);
+	KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX);
+	for (size_t i = 0; i < sizeof(wrap.output); i++)
+		KUNIT_EXPECT_EQ(test, wrap.output[i], truncate[i]);
+	KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX);
+}
+
 static struct kunit_case memcpy_test_cases[] = {
 	KUNIT_CASE(memset_test),
 	KUNIT_CASE(memcpy_test),
 	KUNIT_CASE(memmove_test),
+	KUNIT_CASE(strtomem_test),
 	{}
 };
 
diff --git a/lib/overflow_kunit.c b/lib/overflow_kunit.c
index 7e3e43679b73..f385ca652b74 100644
--- a/lib/overflow_kunit.c
+++ b/lib/overflow_kunit.c
@@ -16,12 +16,15 @@
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 
-#define DEFINE_TEST_ARRAY(t)			\
-	static const struct test_ ## t {	\
-		t a, b;				\
-		t sum, diff, prod;		\
-		bool s_of, d_of, p_of;		\
-	} t ## _tests[]
+#define DEFINE_TEST_ARRAY_TYPED(t1, t2, t)			\
+	static const struct test_ ## t1 ## _ ## t2 ## __ ## t {	\
+		t1 a;						\
+		t2 b;						\
+		t sum, diff, prod;				\
+		bool s_of, d_of, p_of;				\
+	} t1 ## _ ## t2 ## __ ## t ## _tests[]
+
+#define DEFINE_TEST_ARRAY(t)	DEFINE_TEST_ARRAY_TYPED(t, t, t)
 
 DEFINE_TEST_ARRAY(u8) = {
 	{0, 0, 0, 0, 0, false, false, false},
@@ -222,21 +225,27 @@ DEFINE_TEST_ARRAY(s64) = {
 };
 #endif
 
-#define check_one_op(t, fmt, op, sym, a, b, r, of) do {		\
-	t _r;							\
-	bool _of;						\
-								\
-	_of = check_ ## op ## _overflow(a, b, &_r);		\
-	KUNIT_EXPECT_EQ_MSG(test, _of, of,			\
+#define check_one_op(t, fmt, op, sym, a, b, r, of) do {			\
+	int _a_orig = a, _a_bump = a + 1;				\
+	int _b_orig = b, _b_bump = b + 1;				\
+	bool _of;							\
+	t _r;								\
+									\
+	_of = check_ ## op ## _overflow(a, b, &_r);			\
+	KUNIT_EXPECT_EQ_MSG(test, _of, of,				\
 		"expected "fmt" "sym" "fmt" to%s overflow (type %s)\n",	\
-		a, b, of ? "" : " not", #t);			\
-	KUNIT_EXPECT_EQ_MSG(test, _r, r,			\
+		a, b, of ? "" : " not", #t);				\
+	KUNIT_EXPECT_EQ_MSG(test, _r, r,				\
 		"expected "fmt" "sym" "fmt" == "fmt", got "fmt" (type %s)\n", \
-		a, b, r, _r, #t);				\
+		a, b, r, _r, #t);					\
+	/* Check for internal macro side-effects. */			\
+	_of = check_ ## op ## _overflow(_a_orig++, _b_orig++, &_r);	\
+	KUNIT_EXPECT_EQ_MSG(test, _a_orig, _a_bump, "Unexpected " #op " macro side-effect!\n"); \
+	KUNIT_EXPECT_EQ_MSG(test, _b_orig, _b_bump, "Unexpected " #op " macro side-effect!\n"); \
 } while (0)
 
-#define DEFINE_TEST_FUNC(t, fmt)					\
-static void do_test_ ## t(struct kunit *test, const struct test_ ## t *p) \
+#define DEFINE_TEST_FUNC_TYPED(n, t, fmt)				\
+static void do_test_ ## n(struct kunit *test, const struct test_ ## n *p) \
 {							   		\
 	check_one_op(t, fmt, add, "+", p->a, p->b, p->sum, p->s_of);	\
 	check_one_op(t, fmt, add, "+", p->b, p->a, p->sum, p->s_of);	\
@@ -245,15 +254,18 @@ static void do_test_ ## t(struct kunit *test, const struct test_ ## t *p) \
 	check_one_op(t, fmt, mul, "*", p->b, p->a, p->prod, p->p_of);	\
 }									\
 									\
-static void t ## _overflow_test(struct kunit *test) {			\
+static void n ## _overflow_test(struct kunit *test) {			\
 	unsigned i;							\
 									\
-	for (i = 0; i < ARRAY_SIZE(t ## _tests); ++i)			\
-		do_test_ ## t(test, &t ## _tests[i]);			\
+	for (i = 0; i < ARRAY_SIZE(n ## _tests); ++i)			\
+		do_test_ ## n(test, &n ## _tests[i]);			\
 	kunit_info(test, "%zu %s arithmetic tests finished\n",		\
-		ARRAY_SIZE(t ## _tests), #t);				\
+		ARRAY_SIZE(n ## _tests), #n);				\
 }
 
+#define DEFINE_TEST_FUNC(t, fmt)					\
+	DEFINE_TEST_FUNC_TYPED(t ## _ ## t ## __ ## t, t, fmt)
+
 DEFINE_TEST_FUNC(u8, "%d");
 DEFINE_TEST_FUNC(s8, "%d");
 DEFINE_TEST_FUNC(u16, "%d");
@@ -265,9 +277,32 @@ DEFINE_TEST_FUNC(u64, "%llu");
 DEFINE_TEST_FUNC(s64, "%lld");
 #endif
 
-static void overflow_shift_test(struct kunit *test)
-{
-	int count = 0;
+DEFINE_TEST_ARRAY_TYPED(u32, u32, u8) = {
+	{0, 0, 0, 0, 0, false, false, false},
+	{U8_MAX, 2, 1, U8_MAX - 2, U8_MAX - 1, true, false, true},
+	{U8_MAX + 1, 0, 0, 0, 0, true, true, false},
+};
+DEFINE_TEST_FUNC_TYPED(u32_u32__u8, u8, "%d");
+
+DEFINE_TEST_ARRAY_TYPED(u32, u32, int) = {
+	{0, 0, 0, 0, 0, false, false, false},
+	{U32_MAX, 0, -1, -1, 0, true, true, false},
+};
+DEFINE_TEST_FUNC_TYPED(u32_u32__int, int, "%d");
+
+DEFINE_TEST_ARRAY_TYPED(u8, u8, int) = {
+	{0, 0, 0, 0, 0, false, false, false},
+	{U8_MAX, U8_MAX, 2 * U8_MAX, 0, U8_MAX * U8_MAX, false, false, false},
+	{1, 2, 3, -1, 2, false, false, false},
+};
+DEFINE_TEST_FUNC_TYPED(u8_u8__int, int, "%d");
+
+DEFINE_TEST_ARRAY_TYPED(int, int, u8) = {
+	{0, 0, 0, 0, 0, false, false, false},
+	{1, 2, 3, U8_MAX, 2, false, true, false},
+	{-1, 0, U8_MAX, U8_MAX, 0, true, true, false},
+};
+DEFINE_TEST_FUNC_TYPED(int_int__u8, u8, "%d");
 
 /* Args are: value, shift, type, expected result, overflow expected */
 #define TEST_ONE_SHIFT(a, s, t, expect, of)	do {			\
@@ -292,6 +327,10 @@ static void overflow_shift_test(struct kunit *test)
 	count++;							\
 } while (0)
 
+static void shift_sane_test(struct kunit *test)
+{
+	int count = 0;
+
 	/* Sane shifts. */
 	TEST_ONE_SHIFT(1, 0, u8, 1 << 0, false);
 	TEST_ONE_SHIFT(1, 4, u8, 1 << 4, false);
@@ -334,6 +373,13 @@ static void overflow_shift_test(struct kunit *test)
 	TEST_ONE_SHIFT(0, 30, s32, 0, false);
 	TEST_ONE_SHIFT(0, 62, s64, 0, false);
 
+	kunit_info(test, "%d sane shift tests finished\n", count);
+}
+
+static void shift_overflow_test(struct kunit *test)
+{
+	int count = 0;
+
 	/* Overflow: shifted the bit off the end. */
 	TEST_ONE_SHIFT(1, 8, u8, 0, true);
 	TEST_ONE_SHIFT(1, 16, u16, 0, true);
@@ -381,6 +427,13 @@ static void overflow_shift_test(struct kunit *test)
 	/* 0100000100001000001000000010000001000010000001000100010001001011 */
 	TEST_ONE_SHIFT(4686030735197619275LL, 2, s64, 0, true);
 
+	kunit_info(test, "%d overflow shift tests finished\n", count);
+}
+
+static void shift_truncate_test(struct kunit *test)
+{
+	int count = 0;
+
 	/* Overflow: values larger than destination type. */
 	TEST_ONE_SHIFT(0x100, 0, u8, 0, true);
 	TEST_ONE_SHIFT(0xFF, 0, s8, 0, true);
@@ -392,6 +445,33 @@ static void overflow_shift_test(struct kunit *test)
 	TEST_ONE_SHIFT(0xFFFFFFFFUL, 0, int, 0, true);
 	TEST_ONE_SHIFT(0xFFFFFFFFFFFFFFFFULL, 0, s64, 0, true);
 
+	/* Overflow: shifted at or beyond entire type's bit width. */
+	TEST_ONE_SHIFT(0, 8, u8, 0, true);
+	TEST_ONE_SHIFT(0, 9, u8, 0, true);
+	TEST_ONE_SHIFT(0, 8, s8, 0, true);
+	TEST_ONE_SHIFT(0, 9, s8, 0, true);
+	TEST_ONE_SHIFT(0, 16, u16, 0, true);
+	TEST_ONE_SHIFT(0, 17, u16, 0, true);
+	TEST_ONE_SHIFT(0, 16, s16, 0, true);
+	TEST_ONE_SHIFT(0, 17, s16, 0, true);
+	TEST_ONE_SHIFT(0, 32, u32, 0, true);
+	TEST_ONE_SHIFT(0, 33, u32, 0, true);
+	TEST_ONE_SHIFT(0, 32, int, 0, true);
+	TEST_ONE_SHIFT(0, 33, int, 0, true);
+	TEST_ONE_SHIFT(0, 32, s32, 0, true);
+	TEST_ONE_SHIFT(0, 33, s32, 0, true);
+	TEST_ONE_SHIFT(0, 64, u64, 0, true);
+	TEST_ONE_SHIFT(0, 65, u64, 0, true);
+	TEST_ONE_SHIFT(0, 64, s64, 0, true);
+	TEST_ONE_SHIFT(0, 65, s64, 0, true);
+
+	kunit_info(test, "%d truncate shift tests finished\n", count);
+}
+
+static void shift_nonsense_test(struct kunit *test)
+{
+	int count = 0;
+
 	/* Nonsense: negative initial value. */
 	TEST_ONE_SHIFT(-1, 0, s8, 0, true);
 	TEST_ONE_SHIFT(-1, 0, u8, 0, true);
@@ -416,26 +496,6 @@ static void overflow_shift_test(struct kunit *test)
 	TEST_ONE_SHIFT(0, -30, s64, 0, true);
 	TEST_ONE_SHIFT(0, -30, u64, 0, true);
 
-	/* Overflow: shifted at or beyond entire type's bit width. */
-	TEST_ONE_SHIFT(0, 8, u8, 0, true);
-	TEST_ONE_SHIFT(0, 9, u8, 0, true);
-	TEST_ONE_SHIFT(0, 8, s8, 0, true);
-	TEST_ONE_SHIFT(0, 9, s8, 0, true);
-	TEST_ONE_SHIFT(0, 16, u16, 0, true);
-	TEST_ONE_SHIFT(0, 17, u16, 0, true);
-	TEST_ONE_SHIFT(0, 16, s16, 0, true);
-	TEST_ONE_SHIFT(0, 17, s16, 0, true);
-	TEST_ONE_SHIFT(0, 32, u32, 0, true);
-	TEST_ONE_SHIFT(0, 33, u32, 0, true);
-	TEST_ONE_SHIFT(0, 32, int, 0, true);
-	TEST_ONE_SHIFT(0, 33, int, 0, true);
-	TEST_ONE_SHIFT(0, 32, s32, 0, true);
-	TEST_ONE_SHIFT(0, 33, s32, 0, true);
-	TEST_ONE_SHIFT(0, 64, u64, 0, true);
-	TEST_ONE_SHIFT(0, 65, u64, 0, true);
-	TEST_ONE_SHIFT(0, 64, s64, 0, true);
-	TEST_ONE_SHIFT(0, 65, s64, 0, true);
-
 	/*
 	 * Corner case: for unsigned types, we fail when we've shifted
 	 * through the entire width of bits. For signed types, we might
@@ -451,9 +511,9 @@ static void overflow_shift_test(struct kunit *test)
 	TEST_ONE_SHIFT(0, 31, s32, 0, false);
 	TEST_ONE_SHIFT(0, 63, s64, 0, false);
 
-	kunit_info(test, "%d shift tests finished\n", count);
-#undef TEST_ONE_SHIFT
+	kunit_info(test, "%d nonsense shift tests finished\n", count);
 }
+#undef TEST_ONE_SHIFT
 
 /*
  * Deal with the various forms of allocator arguments. See comments above
@@ -649,18 +709,25 @@ static void overflow_size_helpers_test(struct kunit *test)
 }
 
 static struct kunit_case overflow_test_cases[] = {
-	KUNIT_CASE(u8_overflow_test),
-	KUNIT_CASE(s8_overflow_test),
-	KUNIT_CASE(u16_overflow_test),
-	KUNIT_CASE(s16_overflow_test),
-	KUNIT_CASE(u32_overflow_test),
-	KUNIT_CASE(s32_overflow_test),
+	KUNIT_CASE(u8_u8__u8_overflow_test),
+	KUNIT_CASE(s8_s8__s8_overflow_test),
+	KUNIT_CASE(u16_u16__u16_overflow_test),
+	KUNIT_CASE(s16_s16__s16_overflow_test),
+	KUNIT_CASE(u32_u32__u32_overflow_test),
+	KUNIT_CASE(s32_s32__s32_overflow_test),
 /* Clang 13 and earlier generate unwanted libcalls on 32-bit. */
 #if BITS_PER_LONG == 64
-	KUNIT_CASE(u64_overflow_test),
-	KUNIT_CASE(s64_overflow_test),
+	KUNIT_CASE(u64_u64__u64_overflow_test),
+	KUNIT_CASE(s64_s64__s64_overflow_test),
 #endif
-	KUNIT_CASE(overflow_shift_test),
+	KUNIT_CASE(u32_u32__u8_overflow_test),
+	KUNIT_CASE(u32_u32__int_overflow_test),
+	KUNIT_CASE(u8_u8__int_overflow_test),
+	KUNIT_CASE(int_int__u8_overflow_test),
+	KUNIT_CASE(shift_sane_test),
+	KUNIT_CASE(shift_overflow_test),
+	KUNIT_CASE(shift_truncate_test),
+	KUNIT_CASE(shift_nonsense_test),
 	KUNIT_CASE(overflow_allocation_test),
 	KUNIT_CASE(overflow_size_helpers_test),
 	{}
diff --git a/lib/ratelimit.c b/lib/ratelimit.c
index e01a93f46f83..ce945c17980b 100644
--- a/lib/ratelimit.c
+++ b/lib/ratelimit.c
@@ -26,10 +26,16 @@
  */
 int ___ratelimit(struct ratelimit_state *rs, const char *func)
 {
+	/* Paired with WRITE_ONCE() in .proc_handler().
+	 * Changing two values seperately could be inconsistent
+	 * and some message could be lost.  (See: net_ratelimit_state).
+	 */
+	int interval = READ_ONCE(rs->interval);
+	int burst = READ_ONCE(rs->burst);
 	unsigned long flags;
 	int ret;
 
-	if (!rs->interval)
+	if (!interval)
 		return 1;
 
 	/*
@@ -44,7 +50,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func)
 	if (!rs->begin)
 		rs->begin = jiffies;
 
-	if (time_is_before_jiffies(rs->begin + rs->interval)) {
+	if (time_is_before_jiffies(rs->begin + interval)) {
 		if (rs->missed) {
 			if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) {
 				printk_deferred(KERN_WARNING
@@ -56,7 +62,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func)
 		rs->begin   = jiffies;
 		rs->printed = 0;
 	}
-	if (rs->burst && rs->burst > rs->printed) {
+	if (burst && burst > rs->printed) {
 		rs->printed++;
 		ret = 1;
 	} else {
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 3c1853a9d1c0..c414a8d9f1ea 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -2246,6 +2246,9 @@ int __init no_hash_pointers_enable(char *str)
 }
 early_param("no_hash_pointers", no_hash_pointers_enable);
 
+/* Used for Rust formatting ('%pA'). */
+char *rust_fmt_argument(char *buf, char *end, void *ptr);
+
 /*
  * Show a '%p' thing.  A kernel extension is that the '%p' is followed
  * by an extra set of alphanumeric characters that are extended format
@@ -2372,6 +2375,10 @@ early_param("no_hash_pointers", no_hash_pointers_enable);
  *
  * Note: The default behaviour (unadorned %p) is to hash the address,
  * rendering it useful as a unique identifier.
+ *
+ * There is also a '%pA' format specifier, but it is only intended to be used
+ * from Rust code to format core::fmt::Arguments. Do *not* use it from C.
+ * See rust/kernel/print.rs for details.
  */
 static noinline_for_stack
 char *pointer(const char *fmt, char *buf, char *end, void *ptr,
@@ -2444,6 +2451,12 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		return device_node_string(buf, end, ptr, spec, fmt + 1);
 	case 'f':
 		return fwnode_string(buf, end, ptr, spec, fmt + 1);
+	case 'A':
+		if (!IS_ENABLED(CONFIG_RUST)) {
+			WARN_ONCE(1, "Please remove %%pA from non-Rust code\n");
+			return error_string(buf, end, "(%pA?)", spec);
+		}
+		return rust_fmt_argument(buf, end, ptr);
 	case 'x':
 		return pointer_string(buf, end, ptr, spec);
 	case 'e':
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 95550b8fa7fe..de65cb1e5f76 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -260,10 +260,10 @@ void wb_wakeup_delayed(struct bdi_writeback *wb)
 	unsigned long timeout;
 
 	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 	if (test_bit(WB_registered, &wb->state))
 		queue_delayed_work(bdi_wq, &wb->dwork, timeout);
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 }
 
 static void wb_update_bandwidth_workfn(struct work_struct *work)
@@ -334,12 +334,12 @@ static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb);
 static void wb_shutdown(struct bdi_writeback *wb)
 {
 	/* Make sure nobody queues further work */
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 	if (!test_and_clear_bit(WB_registered, &wb->state)) {
-		spin_unlock_bh(&wb->work_lock);
+		spin_unlock_irq(&wb->work_lock);
 		return;
 	}
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 
 	cgwb_remove_from_bdi_list(wb);
 	/*
diff --git a/mm/bootmem_info.c b/mm/bootmem_info.c
index f18a631e7479..b1efebfcf94b 100644
--- a/mm/bootmem_info.c
+++ b/mm/bootmem_info.c
@@ -12,6 +12,7 @@
 #include <linux/memblock.h>
 #include <linux/bootmem_info.h>
 #include <linux/memory_hotplug.h>
+#include <linux/kmemleak.h>
 
 void get_page_bootmem(unsigned long info, struct page *page, unsigned long type)
 {
@@ -33,6 +34,7 @@ void put_page_bootmem(struct page *page)
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
 		INIT_LIST_HEAD(&page->lru);
+		kmemleak_free_part(page_to_virt(page), PAGE_SIZE);
 		free_reserved_page(page);
 	}
 }
diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c
index cb8a7e9926a4..4e51466c4e74 100644
--- a/mm/damon/dbgfs.c
+++ b/mm/damon/dbgfs.c
@@ -818,6 +818,9 @@ static int dbgfs_mk_context(char *name)
 		return -ENOENT;
 
 	new_dir = debugfs_create_dir(name, root);
+	/* Below check is required for a potential duplicated name case */
+	if (IS_ERR(new_dir))
+		return PTR_ERR(new_dir);
 	dbgfs_dirs[dbgfs_nr_ctxs] = new_dir;
 
 	new_ctx = dbgfs_new_ctx();
@@ -881,6 +884,7 @@ static int dbgfs_rm_context(char *name)
 	struct dentry *root, *dir, **new_dirs;
 	struct damon_ctx **new_ctxs;
 	int i, j;
+	int ret = 0;
 
 	if (damon_nr_running_ctxs())
 		return -EBUSY;
@@ -895,14 +899,16 @@ static int dbgfs_rm_context(char *name)
 
 	new_dirs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_dirs),
 			GFP_KERNEL);
-	if (!new_dirs)
-		return -ENOMEM;
+	if (!new_dirs) {
+		ret = -ENOMEM;
+		goto out_dput;
+	}
 
 	new_ctxs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_ctxs),
 			GFP_KERNEL);
 	if (!new_ctxs) {
-		kfree(new_dirs);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out_new_dirs;
 	}
 
 	for (i = 0, j = 0; i < dbgfs_nr_ctxs; i++) {
@@ -922,7 +928,13 @@ static int dbgfs_rm_context(char *name)
 	dbgfs_ctxs = new_ctxs;
 	dbgfs_nr_ctxs--;
 
-	return 0;
+	goto out_dput;
+
+out_new_dirs:
+	kfree(new_dirs);
+out_dput:
+	dput(dir);
+	return ret;
 }
 
 static ssize_t dbgfs_rm_context_write(struct file *file,
diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
index 7488e27c87c3..bdef9682d0a0 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -2182,12 +2182,12 @@ static int damon_sysfs_add_target(struct damon_sysfs_target *sys_target,
 
 	if (!t)
 		return -ENOMEM;
+	damon_add_target(ctx, t);
 	if (damon_target_has_pid(ctx)) {
 		t->pid = find_get_pid(sys_target->pid);
 		if (!t->pid)
 			goto destroy_targets_out;
 	}
-	damon_add_target(ctx, t);
 	err = damon_sysfs_set_regions(t, sys_target->regions);
 	if (err)
 		goto destroy_targets_out;
diff --git a/mm/frontswap.c b/mm/frontswap.c
index 1a97610308cb..279e55b4ed87 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -125,6 +125,9 @@ void frontswap_init(unsigned type, unsigned long *map)
 	 * p->frontswap set to something valid to work properly.
 	 */
 	frontswap_map_set(sis, map);
+
+	if (!frontswap_enabled())
+		return;
 	frontswap_ops->init(type);
 }
 
diff --git a/mm/gup.c b/mm/gup.c
index 732825157430..00926abb4426 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -478,14 +478,42 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
 	return -EEXIST;
 }
 
-/*
- * FOLL_FORCE can write to even unwritable pte's, but only
- * after we've gone through a COW cycle and they are dirty.
- */
-static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
+/* FOLL_FORCE can write to even unwritable PTEs in COW mappings. */
+static inline bool can_follow_write_pte(pte_t pte, struct page *page,
+					struct vm_area_struct *vma,
+					unsigned int flags)
 {
-	return pte_write(pte) ||
-		((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
+	/* If the pte is writable, we can write to the page. */
+	if (pte_write(pte))
+		return true;
+
+	/* Maybe FOLL_FORCE is set to override it? */
+	if (!(flags & FOLL_FORCE))
+		return false;
+
+	/* But FOLL_FORCE has no effect on shared mappings */
+	if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
+		return false;
+
+	/* ... or read-only private ones */
+	if (!(vma->vm_flags & VM_MAYWRITE))
+		return false;
+
+	/* ... or already writable ones that just need to take a write fault */
+	if (vma->vm_flags & VM_WRITE)
+		return false;
+
+	/*
+	 * See can_change_pte_writable(): we broke COW and could map the page
+	 * writable if we have an exclusive anonymous page ...
+	 */
+	if (!page || !PageAnon(page) || !PageAnonExclusive(page))
+		return false;
+
+	/* ... and a write-fault isn't required for other reasons. */
+	if (vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte))
+		return false;
+	return !userfaultfd_pte_wp(vma, pte);
 }
 
 static struct page *follow_page_pte(struct vm_area_struct *vma,
@@ -528,12 +556,19 @@ retry:
 	}
 	if ((flags & FOLL_NUMA) && pte_protnone(pte))
 		goto no_page;
-	if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) {
-		pte_unmap_unlock(ptep, ptl);
-		return NULL;
-	}
 
 	page = vm_normal_page(vma, address, pte);
+
+	/*
+	 * We only care about anon pages in can_follow_write_pte() and don't
+	 * have to worry about pte_devmap() because they are never anon.
+	 */
+	if ((flags & FOLL_WRITE) &&
+	    !can_follow_write_pte(pte, page, vma, flags)) {
+		page = NULL;
+		goto out;
+	}
+
 	if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) {
 		/*
 		 * Only return device mapping pages in the FOLL_GET or FOLL_PIN
@@ -986,17 +1021,6 @@ static int faultin_page(struct vm_area_struct *vma,
 		return -EBUSY;
 	}
 
-	/*
-	 * The VM_FAULT_WRITE bit tells us that do_wp_page has broken COW when
-	 * necessary, even if maybe_mkwrite decided not to set pte_write. We
-	 * can thus safely do subsequent page lookups as if they were reads.
-	 * But only do so when looping for pte_write is futile: in some cases
-	 * userspace may also be wanting to write to the gotten user page,
-	 * which a read fault here might prevent (a readonly page might get
-	 * reCOWed by userspace write).
-	 */
-	if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE))
-		*flags |= FOLL_COW;
 	return 0;
 }
 
@@ -2321,8 +2345,28 @@ static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start,
 }
 
 #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
-static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
-			 unsigned int flags, struct page **pages, int *nr)
+/*
+ * Fast-gup relies on pte change detection to avoid concurrent pgtable
+ * operations.
+ *
+ * To pin the page, fast-gup needs to do below in order:
+ * (1) pin the page (by prefetching pte), then (2) check pte not changed.
+ *
+ * For the rest of pgtable operations where pgtable updates can be racy
+ * with fast-gup, we need to do (1) clear pte, then (2) check whether page
+ * is pinned.
+ *
+ * Above will work for all pte-level operations, including THP split.
+ *
+ * For THP collapse, it's a bit more complicated because fast-gup may be
+ * walking a pgtable page that is being freed (pte is still valid but pmd
+ * can be cleared already).  To avoid race in such condition, we need to
+ * also check pmd here to make sure pmd doesn't change (corresponds to
+ * pmdp_collapse_flush() in the THP collapse code path).
+ */
+static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
+			 unsigned long end, unsigned int flags,
+			 struct page **pages, int *nr)
 {
 	struct dev_pagemap *pgmap = NULL;
 	int nr_start = *nr, ret = 0;
@@ -2368,7 +2412,8 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 			goto pte_unmap;
 		}
 
-		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
+		if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) ||
+		    unlikely(pte_val(pte) != pte_val(*ptep))) {
 			gup_put_folio(folio, 1, flags);
 			goto pte_unmap;
 		}
@@ -2415,8 +2460,9 @@ pte_unmap:
  * get_user_pages_fast_only implementation that can pin pages. Thus it's still
  * useful to have gup_huge_pmd even if we can't operate on ptes.
  */
-static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
-			 unsigned int flags, struct page **pages, int *nr)
+static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
+			 unsigned long end, unsigned int flags,
+			 struct page **pages, int *nr)
 {
 	return 0;
 }
@@ -2740,7 +2786,7 @@ static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned lo
 			if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr,
 					 PMD_SHIFT, next, flags, pages, nr))
 				return 0;
-		} else if (!gup_pte_range(pmd, addr, next, flags, pages, nr))
+		} else if (!gup_pte_range(pmd, pmdp, addr, next, flags, pages, nr))
 			return 0;
 	} while (pmdp++, addr = next, addr != end);
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8a7c1b344abe..f42bb51e023a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1040,12 +1040,6 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
 
 	assert_spin_locked(pmd_lockptr(mm, pmd));
 
-	/*
-	 * When we COW a devmap PMD entry, we split it into PTEs, so we should
-	 * not be in this function with `flags & FOLL_COW` set.
-	 */
-	WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set");
-
 	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
 	if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
 			 (FOLL_PIN | FOLL_GET)))
@@ -1395,14 +1389,42 @@ fallback:
 	return VM_FAULT_FALLBACK;
 }
 
-/*
- * FOLL_FORCE can write to even unwritable pmd's, but only
- * after we've gone through a COW cycle and they are dirty.
- */
-static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
+/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */
+static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page,
+					struct vm_area_struct *vma,
+					unsigned int flags)
 {
-	return pmd_write(pmd) ||
-	       ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
+	/* If the pmd is writable, we can write to the page. */
+	if (pmd_write(pmd))
+		return true;
+
+	/* Maybe FOLL_FORCE is set to override it? */
+	if (!(flags & FOLL_FORCE))
+		return false;
+
+	/* But FOLL_FORCE has no effect on shared mappings */
+	if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
+		return false;
+
+	/* ... or read-only private ones */
+	if (!(vma->vm_flags & VM_MAYWRITE))
+		return false;
+
+	/* ... or already writable ones that just need to take a write fault */
+	if (vma->vm_flags & VM_WRITE)
+		return false;
+
+	/*
+	 * See can_change_pte_writable(): we broke COW and could map the page
+	 * writable if we have an exclusive anonymous page ...
+	 */
+	if (!page || !PageAnon(page) || !PageAnonExclusive(page))
+		return false;
+
+	/* ... and a write-fault isn't required for other reasons. */
+	if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd))
+		return false;
+	return !userfaultfd_huge_pmd_wp(vma, pmd);
 }
 
 struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
@@ -1411,12 +1433,16 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 				   unsigned int flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	struct page *page = NULL;
+	struct page *page;
 
 	assert_spin_locked(pmd_lockptr(mm, pmd));
 
-	if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags))
-		goto out;
+	page = pmd_page(*pmd);
+	VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
+
+	if ((flags & FOLL_WRITE) &&
+	    !can_follow_write_pmd(*pmd, page, vma, flags))
+		return NULL;
 
 	/* Avoid dumping huge zero page */
 	if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))
@@ -1424,10 +1450,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 
 	/* Full NUMA hinting faults to serialise migration in fault paths */
 	if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
-		goto out;
-
-	page = pmd_page(*pmd);
-	VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
+		return NULL;
 
 	if (!pmd_write(*pmd) && gup_must_unshare(flags, page))
 		return ERR_PTR(-EMLINK);
@@ -1444,7 +1467,6 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
 	VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page);
 
-out:
 	return page;
 }
 
@@ -2872,11 +2894,9 @@ static void split_huge_pages_all(void)
 		max_zone_pfn = zone_end_pfn(zone);
 		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) {
 			int nr_pages;
-			if (!pfn_valid(pfn))
-				continue;
 
-			page = pfn_to_page(pfn);
-			if (!get_page_unless_zero(page))
+			page = pfn_to_online_page(pfn);
+			if (!page || !get_page_unless_zero(page))
 				continue;
 
 			if (zone != page_zone(page))
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0aee2f3ae15c..0bdfc7e1c933 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3420,6 +3420,7 @@ static int demote_free_huge_page(struct hstate *h, struct page *page)
 {
 	int i, nid = page_to_nid(page);
 	struct hstate *target_hstate;
+	struct page *subpage;
 	int rc = 0;
 
 	target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order);
@@ -3453,15 +3454,16 @@ static int demote_free_huge_page(struct hstate *h, struct page *page)
 	mutex_lock(&target_hstate->resize_lock);
 	for (i = 0; i < pages_per_huge_page(h);
 				i += pages_per_huge_page(target_hstate)) {
+		subpage = nth_page(page, i);
 		if (hstate_is_gigantic(target_hstate))
-			prep_compound_gigantic_page_for_demote(page + i,
+			prep_compound_gigantic_page_for_demote(subpage,
 							target_hstate->order);
 		else
-			prep_compound_page(page + i, target_hstate->order);
-		set_page_private(page + i, 0);
-		set_page_refcounted(page + i);
-		prep_new_huge_page(target_hstate, page + i, nid);
-		put_page(page + i);
+			prep_compound_page(subpage, target_hstate->order);
+		set_page_private(subpage, 0);
+		set_page_refcounted(subpage);
+		prep_new_huge_page(target_hstate, subpage, nid);
+		put_page(subpage);
 	}
 	mutex_unlock(&target_hstate->resize_lock);
 
@@ -5241,6 +5243,21 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
 	VM_BUG_ON(unshare && (flags & FOLL_WRITE));
 	VM_BUG_ON(!unshare && !(flags & FOLL_WRITE));
 
+	/*
+	 * hugetlb does not support FOLL_FORCE-style write faults that keep the
+	 * PTE mapped R/O such as maybe_mkwrite() would do.
+	 */
+	if (WARN_ON_ONCE(!unshare && !(vma->vm_flags & VM_WRITE)))
+		return VM_FAULT_SIGSEGV;
+
+	/* Let's take out MAP_SHARED mappings first. */
+	if (vma->vm_flags & VM_MAYSHARE) {
+		if (unlikely(unshare))
+			return 0;
+		set_huge_ptep_writable(vma, haddr, ptep);
+		return 0;
+	}
+
 	pte = huge_ptep_get(ptep);
 	old_page = pte_page(pte);
 
@@ -5781,12 +5798,11 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * If we are going to COW/unshare the mapping later, we examine the
 	 * pending reservations for this page now. This will ensure that any
 	 * allocations necessary to record that reservation occur outside the
-	 * spinlock. For private mappings, we also lookup the pagecache
-	 * page now as it is used to determine if a reservation has been
-	 * consumed.
+	 * spinlock. Also lookup the pagecache page now as it is used to
+	 * determine if a reservation has been consumed.
 	 */
 	if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) &&
-	    !huge_pte_write(entry)) {
+	    !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(entry)) {
 		if (vma_needs_reservation(h, vma, haddr) < 0) {
 			ret = VM_FAULT_OOM;
 			goto out_mutex;
@@ -5794,9 +5810,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		/* Just decrements count, does not deallocate */
 		vma_end_reservation(h, vma, haddr);
 
-		if (!(vma->vm_flags & VM_MAYSHARE))
-			pagecache_page = hugetlbfs_pagecache_page(h,
-								vma, haddr);
+		pagecache_page = hugetlbfs_pagecache_page(h, vma, haddr);
 	}
 
 	ptl = huge_pte_lock(h, mm, ptep);
@@ -6029,7 +6043,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	if (!huge_pte_none_mostly(huge_ptep_get(dst_pte)))
 		goto out_release_unlock;
 
-	if (vm_shared) {
+	if (page_in_pagecache) {
 		page_dup_file_rmap(page, true);
 	} else {
 		ClearHPageRestoreReserve(page);
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 01f71786d530..70b7ac66411c 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1083,10 +1083,12 @@ static void collapse_huge_page(struct mm_struct *mm,
 
 	pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */
 	/*
-	 * After this gup_fast can't run anymore. This also removes
-	 * any huge TLB entry from the CPU so we won't allow
-	 * huge and small TLB entries for the same virtual address
-	 * to avoid the risk of CPU bugs in that area.
+	 * This removes any huge TLB entry from the CPU so we won't allow
+	 * huge and small TLB entries for the same virtual address to
+	 * avoid the risk of CPU bugs in that area.
+	 *
+	 * Parallel fast GUP is fine since fast GUP will back off when
+	 * it detects PMD is changed.
 	 */
 	_pmd = pmdp_collapse_flush(vma, address, pmd);
 	spin_unlock(pmd_ptl);
diff --git a/mm/madvise.c b/mm/madvise.c
index 5f0f0948a50e..9ff51650f4f0 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -451,8 +451,11 @@ regular_page:
 			continue;
 		}
 
-		/* Do not interfere with other mappings of this page */
-		if (page_mapcount(page) != 1)
+		/*
+		 * Do not interfere with other mappings of this page and
+		 * non-LRU page.
+		 */
+		if (!PageLRU(page) || page_mapcount(page) != 1)
 			continue;
 
 		VM_BUG_ON_PAGE(PageTransCompound(page), page);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 14439806b5ef..e7ac570dda75 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -345,13 +345,17 @@ static unsigned long dev_pagemap_mapping_shift(struct vm_area_struct *vma,
  * not much we can do.	We just print a message and ignore otherwise.
  */
 
+#define FSDAX_INVALID_PGOFF ULONG_MAX
+
 /*
  * Schedule a process for later kill.
  * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM.
  *
- * Notice: @fsdax_pgoff is used only when @p is a fsdax page.
- *   In other cases, such as anonymous and file-backend page, the address to be
- *   killed can be caculated by @p itself.
+ * Note: @fsdax_pgoff is used only when @p is a fsdax page and a
+ * filesystem with a memory failure handler has claimed the
+ * memory_failure event. In all other cases, page->index and
+ * page->mapping are sufficient for mapping the page back to its
+ * corresponding user virtual address.
  */
 static void add_to_kill(struct task_struct *tsk, struct page *p,
 			pgoff_t fsdax_pgoff, struct vm_area_struct *vma,
@@ -367,11 +371,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
 
 	tk->addr = page_address_in_vma(p, vma);
 	if (is_zone_device_page(p)) {
-		/*
-		 * Since page->mapping is not used for fsdax, we need
-		 * calculate the address based on the vma.
-		 */
-		if (p->pgmap->type == MEMORY_DEVICE_FS_DAX)
+		if (fsdax_pgoff != FSDAX_INVALID_PGOFF)
 			tk->addr = vma_pgoff_address(fsdax_pgoff, 1, vma);
 		tk->size_shift = dev_pagemap_mapping_shift(vma, tk->addr);
 	} else
@@ -523,7 +523,8 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 			if (!page_mapped_in_vma(page, vma))
 				continue;
 			if (vma->vm_mm == t->mm)
-				add_to_kill(t, page, 0, vma, to_kill);
+				add_to_kill(t, page, FSDAX_INVALID_PGOFF, vma,
+					    to_kill);
 		}
 	}
 	read_unlock(&tasklist_lock);
@@ -559,7 +560,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 			 * to be informed of all such data corruptions.
 			 */
 			if (vma->vm_mm == t->mm)
-				add_to_kill(t, page, 0, vma, to_kill);
+				add_to_kill(t, page, FSDAX_INVALID_PGOFF, vma,
+					    to_kill);
 		}
 	}
 	read_unlock(&tasklist_lock);
@@ -743,6 +745,9 @@ static int kill_accessing_process(struct task_struct *p, unsigned long pfn,
 	};
 	priv.tk.tsk = p;
 
+	if (!p->mm)
+		return -EFAULT;
+
 	mmap_read_lock(p->mm);
 	ret = walk_page_range(p->mm, 0, TASK_SIZE, &hwp_walk_ops,
 			      (void *)&priv);
@@ -1928,7 +1933,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 	 * Call driver's implementation to handle the memory failure, otherwise
 	 * fall back to generic handler.
 	 */
-	if (pgmap->ops->memory_failure) {
+	if (pgmap_has_memory_failure(pgmap)) {
 		rc = pgmap->ops->memory_failure(pgmap, pfn, 1, flags);
 		/*
 		 * Fall back to generic handler too if operation is not
diff --git a/mm/memory.c b/mm/memory.c
index 4ba73f5aa8bb..a78814413ac0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4386,14 +4386,20 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 
 	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
 				      vmf->address, &vmf->ptl);
-	ret = 0;
+
 	/* Re-check under ptl */
-	if (likely(!vmf_pte_changed(vmf)))
+	if (likely(!vmf_pte_changed(vmf))) {
 		do_set_pte(vmf, page, vmf->address);
-	else
+
+		/* no need to invalidate: a not-present page won't be cached */
+		update_mmu_cache(vma, vmf->address, vmf->pte);
+
+		ret = 0;
+	} else {
+		update_mmu_tlb(vma, vmf->address, vmf->pte);
 		ret = VM_FAULT_NOPAGE;
+	}
 
-	update_mmu_tlb(vma, vmf->address, vmf->pte);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	return ret;
 }
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 27fb37d65476..dbf6c7a7a7c9 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -7,6 +7,7 @@
 #include <linux/export.h>
 #include <linux/memremap.h>
 #include <linux/migrate.h>
+#include <linux/mm.h>
 #include <linux/mm_inline.h>
 #include <linux/mmu_notifier.h>
 #include <linux/oom.h>
@@ -193,10 +194,10 @@ again:
 			bool anon_exclusive;
 			pte_t swp_pte;
 
+			flush_cache_page(vma, addr, pte_pfn(*ptep));
 			anon_exclusive = PageAnon(page) && PageAnonExclusive(page);
 			if (anon_exclusive) {
-				flush_cache_page(vma, addr, pte_pfn(*ptep));
-				ptep_clear_flush(vma, addr, ptep);
+				pte = ptep_clear_flush(vma, addr, ptep);
 
 				if (page_try_share_anon_rmap(page)) {
 					set_pte_at(mm, addr, ptep, pte);
@@ -206,11 +207,15 @@ again:
 					goto next;
 				}
 			} else {
-				ptep_get_and_clear(mm, addr, ptep);
+				pte = ptep_get_and_clear(mm, addr, ptep);
 			}
 
 			migrate->cpages++;
 
+			/* Set the dirty flag on the folio now the pte is gone. */
+			if (pte_dirty(pte))
+				folio_mark_dirty(page_folio(page));
+
 			/* Setup special migration page table entry */
 			if (mpfn & MIGRATE_PFN_WRITE)
 				entry = make_writable_migration_entry(
@@ -254,13 +259,14 @@ next:
 		migrate->dst[migrate->npages] = 0;
 		migrate->src[migrate->npages++] = mpfn;
 	}
-	arch_leave_lazy_mmu_mode();
-	pte_unmap_unlock(ptep - 1, ptl);
 
 	/* Only flush the TLB if we actually modified any entries */
 	if (unmapped)
 		flush_tlb_range(walk->vma, start, end);
 
+	arch_leave_lazy_mmu_mode();
+	pte_unmap_unlock(ptep - 1, ptl);
+
 	return 0;
 }
 
diff --git a/mm/mmap.c b/mm/mmap.c
index c035020d0c89..9d780f415be3 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1646,8 +1646,11 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot)
 	    pgprot_val(vm_pgprot_modify(vm_page_prot, vm_flags)))
 		return 0;
 
-	/* Do we need to track softdirty? */
-	if (vma_soft_dirty_enabled(vma))
+	/*
+	 * Do we need to track softdirty? hugetlb does not support softdirty
+	 * tracking yet.
+	 */
+	if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma))
 		return 1;
 
 	/* Specialty mapping? */
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 3a23dde73723..bc6bddd156ca 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -196,10 +196,11 @@ static unsigned long change_pte_range(struct mmu_gather *tlb,
 			pages++;
 		} else if (is_swap_pte(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
-			struct page *page = pfn_swap_entry_to_page(entry);
 			pte_t newpte;
 
 			if (is_writable_migration_entry(entry)) {
+				struct page *page = pfn_swap_entry_to_page(entry);
+
 				/*
 				 * A protection check is difficult so
 				 * just be safe and disable write
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index d0d466a5c804..032a7bf8d259 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2892,6 +2892,7 @@ static void wb_inode_writeback_start(struct bdi_writeback *wb)
 
 static void wb_inode_writeback_end(struct bdi_writeback *wb)
 {
+	unsigned long flags;
 	atomic_dec(&wb->writeback_inodes);
 	/*
 	 * Make sure estimate of writeback throughput gets updated after
@@ -2900,7 +2901,10 @@ static void wb_inode_writeback_end(struct bdi_writeback *wb)
 	 * that if multiple inodes end writeback at a similar time, they get
 	 * batched into one bandwidth update.
 	 */
-	queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL);
+	spin_lock_irqsave(&wb->work_lock, flags);
+	if (test_bit(WB_registered, &wb->state))
+		queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL);
+	spin_unlock_irqrestore(&wb->work_lock, flags);
 }
 
 bool __folio_end_writeback(struct folio *folio)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e5486d47406e..d04211f0ef0b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4708,6 +4708,30 @@ void fs_reclaim_release(gfp_t gfp_mask)
 EXPORT_SYMBOL_GPL(fs_reclaim_release);
 #endif
 
+/*
+ * Zonelists may change due to hotplug during allocation. Detect when zonelists
+ * have been rebuilt so allocation retries. Reader side does not lock and
+ * retries the allocation if zonelist changes. Writer side is protected by the
+ * embedded spin_lock.
+ */
+static DEFINE_SEQLOCK(zonelist_update_seq);
+
+static unsigned int zonelist_iter_begin(void)
+{
+	if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE))
+		return read_seqbegin(&zonelist_update_seq);
+
+	return 0;
+}
+
+static unsigned int check_retry_zonelist(unsigned int seq)
+{
+	if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE))
+		return read_seqretry(&zonelist_update_seq, seq);
+
+	return seq;
+}
+
 /* Perform direct synchronous page reclaim */
 static unsigned long
 __perform_reclaim(gfp_t gfp_mask, unsigned int order,
@@ -5001,6 +5025,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	int compaction_retries;
 	int no_progress_loops;
 	unsigned int cpuset_mems_cookie;
+	unsigned int zonelist_iter_cookie;
 	int reserve_flags;
 
 	/*
@@ -5011,11 +5036,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 				(__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
 		gfp_mask &= ~__GFP_ATOMIC;
 
-retry_cpuset:
+restart:
 	compaction_retries = 0;
 	no_progress_loops = 0;
 	compact_priority = DEF_COMPACT_PRIORITY;
 	cpuset_mems_cookie = read_mems_allowed_begin();
+	zonelist_iter_cookie = zonelist_iter_begin();
 
 	/*
 	 * The fast path uses conservative alloc_flags to succeed only until
@@ -5187,9 +5213,13 @@ retry:
 		goto retry;
 
 
-	/* Deal with possible cpuset update races before we start OOM killing */
-	if (check_retry_cpuset(cpuset_mems_cookie, ac))
-		goto retry_cpuset;
+	/*
+	 * Deal with possible cpuset update races or zonelist updates to avoid
+	 * a unnecessary OOM kill.
+	 */
+	if (check_retry_cpuset(cpuset_mems_cookie, ac) ||
+	    check_retry_zonelist(zonelist_iter_cookie))
+		goto restart;
 
 	/* Reclaim has failed us, start killing things */
 	page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress);
@@ -5209,9 +5239,13 @@ retry:
 	}
 
 nopage:
-	/* Deal with possible cpuset update races before we fail */
-	if (check_retry_cpuset(cpuset_mems_cookie, ac))
-		goto retry_cpuset;
+	/*
+	 * Deal with possible cpuset update races or zonelist updates to avoid
+	 * a unnecessary OOM kill.
+	 */
+	if (check_retry_cpuset(cpuset_mems_cookie, ac) ||
+	    check_retry_zonelist(zonelist_iter_cookie))
+		goto restart;
 
 	/*
 	 * Make sure that __GFP_NOFAIL request doesn't leak out and make sure
@@ -5706,6 +5740,18 @@ refill:
 		/* reset page count bias and offset to start of new frag */
 		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
 		offset = size - fragsz;
+		if (unlikely(offset < 0)) {
+			/*
+			 * The caller is trying to allocate a fragment
+			 * with fragsz > PAGE_SIZE but the cache isn't big
+			 * enough to satisfy the request, this may
+			 * happen in low memory conditions.
+			 * We don't release the cache page because
+			 * it could make memory pressure worse
+			 * so we simply return NULL here.
+			 */
+			return NULL;
+		}
 	}
 
 	nc->pagecnt_bias--;
@@ -6514,9 +6560,8 @@ static void __build_all_zonelists(void *data)
 	int nid;
 	int __maybe_unused cpu;
 	pg_data_t *self = data;
-	static DEFINE_SPINLOCK(lock);
 
-	spin_lock(&lock);
+	write_seqlock(&zonelist_update_seq);
 
 #ifdef CONFIG_NUMA
 	memset(node_load, 0, sizeof(node_load));
@@ -6553,7 +6598,7 @@ static void __build_all_zonelists(void *data)
 #endif
 	}
 
-	spin_unlock(&lock);
+	write_sequnlock(&zonelist_update_seq);
 }
 
 static noinline void __init
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 9d73dc38e3d7..eb3a68ca92ad 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -288,6 +288,7 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * @isolate_before:	isolate the pageblock before the boundary_pfn
  * @skip_isolation:	the flag to skip the pageblock isolation in second
  *			isolate_single_pageblock()
+ * @migratetype:	migrate type to set in error recovery.
  *
  * Free and in-use pages can be as big as MAX_ORDER-1 and contain more than one
  * pageblock. When not all pageblocks within a page are isolated at the same
@@ -302,9 +303,9 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * the in-use page then splitting the free page.
  */
 static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
-			gfp_t gfp_flags, bool isolate_before, bool skip_isolation)
+			gfp_t gfp_flags, bool isolate_before, bool skip_isolation,
+			int migratetype)
 {
-	unsigned char saved_mt;
 	unsigned long start_pfn;
 	unsigned long isolate_pageblock;
 	unsigned long pfn;
@@ -328,13 +329,13 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
 	start_pfn  = max(ALIGN_DOWN(isolate_pageblock, MAX_ORDER_NR_PAGES),
 				      zone->zone_start_pfn);
 
-	saved_mt = get_pageblock_migratetype(pfn_to_page(isolate_pageblock));
+	if (skip_isolation) {
+		int mt = get_pageblock_migratetype(pfn_to_page(isolate_pageblock));
 
-	if (skip_isolation)
-		VM_BUG_ON(!is_migrate_isolate(saved_mt));
-	else {
-		ret = set_migratetype_isolate(pfn_to_page(isolate_pageblock), saved_mt, flags,
-				isolate_pageblock, isolate_pageblock + pageblock_nr_pages);
+		VM_BUG_ON(!is_migrate_isolate(mt));
+	} else {
+		ret = set_migratetype_isolate(pfn_to_page(isolate_pageblock), migratetype,
+				flags, isolate_pageblock, isolate_pageblock + pageblock_nr_pages);
 
 		if (ret)
 			return ret;
@@ -475,7 +476,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
 failed:
 	/* restore the original migratetype */
 	if (!skip_isolation)
-		unset_migratetype_isolate(pfn_to_page(isolate_pageblock), saved_mt);
+		unset_migratetype_isolate(pfn_to_page(isolate_pageblock), migratetype);
 	return -EBUSY;
 }
 
@@ -537,7 +538,8 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 	bool skip_isolation = false;
 
 	/* isolate [isolate_start, isolate_start + pageblock_nr_pages) pageblock */
-	ret = isolate_single_pageblock(isolate_start, flags, gfp_flags, false, skip_isolation);
+	ret = isolate_single_pageblock(isolate_start, flags, gfp_flags, false,
+			skip_isolation, migratetype);
 	if (ret)
 		return ret;
 
@@ -545,7 +547,8 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 		skip_isolation = true;
 
 	/* isolate [isolate_end - pageblock_nr_pages, isolate_end) pageblock */
-	ret = isolate_single_pageblock(isolate_end, flags, gfp_flags, true, skip_isolation);
+	ret = isolate_single_pageblock(isolate_end, flags, gfp_flags, true,
+			skip_isolation, migratetype);
 	if (ret) {
 		unset_migratetype_isolate(pfn_to_page(isolate_start), migratetype);
 		return ret;
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 9b3db11a4d1d..fa7a3d21a751 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -110,7 +110,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 	do {
 again:
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(*pmd) || (!walk->vma && !walk->no_vma)) {
+		if (pmd_none(*pmd)) {
 			if (ops->pte_hole)
 				err = ops->pte_hole(addr, next, depth, walk);
 			if (err)
@@ -171,7 +171,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 	do {
  again:
 		next = pud_addr_end(addr, end);
-		if (pud_none(*pud) || (!walk->vma && !walk->no_vma)) {
+		if (pud_none(*pud)) {
 			if (ops->pte_hole)
 				err = ops->pte_hole(addr, next, depth, walk);
 			if (err)
@@ -366,19 +366,19 @@ static int __walk_page_range(unsigned long start, unsigned long end,
 	struct vm_area_struct *vma = walk->vma;
 	const struct mm_walk_ops *ops = walk->ops;
 
-	if (vma && ops->pre_vma) {
+	if (ops->pre_vma) {
 		err = ops->pre_vma(start, end, walk);
 		if (err)
 			return err;
 	}
 
-	if (vma && is_vm_hugetlb_page(vma)) {
+	if (is_vm_hugetlb_page(vma)) {
 		if (ops->hugetlb_entry)
 			err = walk_hugetlb_range(start, end, walk);
 	} else
 		err = walk_pgd_range(start, end, walk);
 
-	if (vma && ops->post_vma)
+	if (ops->post_vma)
 		ops->post_vma(walk);
 
 	return err;
@@ -450,9 +450,13 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
 		if (!vma) { /* after the last vma */
 			walk.vma = NULL;
 			next = end;
+			if (ops->pte_hole)
+				err = ops->pte_hole(start, next, -1, &walk);
 		} else if (start < vma->vm_start) { /* outside vma */
 			walk.vma = NULL;
 			next = min(end, vma->vm_start);
+			if (ops->pte_hole)
+				err = ops->pte_hole(start, next, -1, &walk);
 		} else { /* inside vma */
 			walk.vma = vma;
 			next = min(end, vma->vm_end);
@@ -470,9 +474,8 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
 			}
 			if (err < 0)
 				break;
-		}
-		if (walk.vma || walk.ops->pte_hole)
 			err = __walk_page_range(start, next, &walk);
+		}
 		if (err)
 			break;
 	} while (start = next, start < end);
@@ -501,9 +504,9 @@ int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
 	if (start >= end || !walk.mm)
 		return -EINVAL;
 
-	mmap_assert_locked(walk.mm);
+	mmap_assert_write_locked(walk.mm);
 
-	return __walk_page_range(start, end, &walk);
+	return walk_pgd_range(start, end, &walk);
 }
 
 int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
diff --git a/mm/ptdump.c b/mm/ptdump.c
index eea3d28d173c..8adab455a68b 100644
--- a/mm/ptdump.c
+++ b/mm/ptdump.c
@@ -152,13 +152,13 @@ void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd)
 {
 	const struct ptdump_range *range = st->range;
 
-	mmap_read_lock(mm);
+	mmap_write_lock(mm);
 	while (range->start != range->end) {
 		walk_page_range_novma(mm, range->start, range->end,
 				      &ptdump_ops, pgd, st);
 		range++;
 	}
-	mmap_read_unlock(mm);
+	mmap_write_unlock(mm);
 
 	/* Flush out the last page */
 	st->note_page(st, 0, -1, 0);
diff --git a/mm/rmap.c b/mm/rmap.c
index edc06c52bc82..93d5a6f793d2 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -93,7 +93,8 @@ static inline struct anon_vma *anon_vma_alloc(void)
 	anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
 	if (anon_vma) {
 		atomic_set(&anon_vma->refcount, 1);
-		anon_vma->degree = 1;	/* Reference for first vma */
+		anon_vma->num_children = 0;
+		anon_vma->num_active_vmas = 0;
 		anon_vma->parent = anon_vma;
 		/*
 		 * Initialise the anon_vma root to point to itself. If called
@@ -201,6 +202,7 @@ int __anon_vma_prepare(struct vm_area_struct *vma)
 		anon_vma = anon_vma_alloc();
 		if (unlikely(!anon_vma))
 			goto out_enomem_free_avc;
+		anon_vma->num_children++; /* self-parent link for new root */
 		allocated = anon_vma;
 	}
 
@@ -210,8 +212,7 @@ int __anon_vma_prepare(struct vm_area_struct *vma)
 	if (likely(!vma->anon_vma)) {
 		vma->anon_vma = anon_vma;
 		anon_vma_chain_link(vma, avc, anon_vma);
-		/* vma reference or self-parent link for new root */
-		anon_vma->degree++;
+		anon_vma->num_active_vmas++;
 		allocated = NULL;
 		avc = NULL;
 	}
@@ -296,19 +297,19 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 		anon_vma_chain_link(dst, avc, anon_vma);
 
 		/*
-		 * Reuse existing anon_vma if its degree lower than two,
-		 * that means it has no vma and only one anon_vma child.
+		 * Reuse existing anon_vma if it has no vma and only one
+		 * anon_vma child.
 		 *
-		 * Do not choose parent anon_vma, otherwise first child
-		 * will always reuse it. Root anon_vma is never reused:
+		 * Root anon_vma is never reused:
 		 * it has self-parent reference and at least one child.
 		 */
 		if (!dst->anon_vma && src->anon_vma &&
-		    anon_vma != src->anon_vma && anon_vma->degree < 2)
+		    anon_vma->num_children < 2 &&
+		    anon_vma->num_active_vmas == 0)
 			dst->anon_vma = anon_vma;
 	}
 	if (dst->anon_vma)
-		dst->anon_vma->degree++;
+		dst->anon_vma->num_active_vmas++;
 	unlock_anon_vma_root(root);
 	return 0;
 
@@ -358,6 +359,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	anon_vma = anon_vma_alloc();
 	if (!anon_vma)
 		goto out_error;
+	anon_vma->num_active_vmas++;
 	avc = anon_vma_chain_alloc(GFP_KERNEL);
 	if (!avc)
 		goto out_error_free_anon_vma;
@@ -378,7 +380,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	vma->anon_vma = anon_vma;
 	anon_vma_lock_write(anon_vma);
 	anon_vma_chain_link(vma, avc, anon_vma);
-	anon_vma->parent->degree++;
+	anon_vma->parent->num_children++;
 	anon_vma_unlock_write(anon_vma);
 
 	return 0;
@@ -410,7 +412,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
 		 * to free them outside the lock.
 		 */
 		if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) {
-			anon_vma->parent->degree--;
+			anon_vma->parent->num_children--;
 			continue;
 		}
 
@@ -418,7 +420,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
 		anon_vma_chain_free(avc);
 	}
 	if (vma->anon_vma) {
-		vma->anon_vma->degree--;
+		vma->anon_vma->num_active_vmas--;
 
 		/*
 		 * vma would still be needed after unlink, and anon_vma will be prepared
@@ -436,7 +438,8 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
 	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
 		struct anon_vma *anon_vma = avc->anon_vma;
 
-		VM_WARN_ON(anon_vma->degree);
+		VM_WARN_ON(anon_vma->num_children);
+		VM_WARN_ON(anon_vma->num_active_vmas);
 		put_anon_vma(anon_vma);
 
 		list_del(&avc->same_vma);
diff --git a/mm/secretmem.c b/mm/secretmem.c
index e3e9590c6fb3..3f7154099795 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -285,7 +285,7 @@ static int secretmem_init(void)
 
 	secretmem_mnt = kern_mount(&secretmem_fs);
 	if (IS_ERR(secretmem_mnt))
-		ret = PTR_ERR(secretmem_mnt);
+		return PTR_ERR(secretmem_mnt);
 
 	/* prevent secretmem mappings from ever getting PROT_EXEC */
 	secretmem_mnt->mnt_flags |= MNT_NOEXEC;
diff --git a/mm/shmem.c b/mm/shmem.c
index 5783f11351bb..42e5888bf84d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1659,7 +1659,9 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 		new = page_folio(newpage);
 		mem_cgroup_migrate(old, new);
 		__inc_lruvec_page_state(newpage, NR_FILE_PAGES);
+		__inc_lruvec_page_state(newpage, NR_SHMEM);
 		__dec_lruvec_page_state(oldpage, NR_FILE_PAGES);
+		__dec_lruvec_page_state(oldpage, NR_SHMEM);
 	}
 	xa_unlock_irq(&swap_mapping->i_pages);
 
@@ -1780,6 +1782,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 
 	if (shmem_should_replace_folio(folio, gfp)) {
 		error = shmem_replace_page(&page, gfp, info, index);
+		folio = page_folio(page);
 		if (error)
 			goto failed;
 	}
@@ -2281,16 +2284,34 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
-/* Mask out flags that are inappropriate for the given type of inode. */
-static unsigned shmem_mask_flags(umode_t mode, __u32 flags)
+#ifdef CONFIG_TMPFS_XATTR
+static int shmem_initxattrs(struct inode *, const struct xattr *, void *);
+
+/*
+ * chattr's fsflags are unrelated to extended attributes,
+ * but tmpfs has chosen to enable them under the same config option.
+ */
+static void shmem_set_inode_flags(struct inode *inode, unsigned int fsflags)
+{
+	unsigned int i_flags = 0;
+
+	if (fsflags & FS_NOATIME_FL)
+		i_flags |= S_NOATIME;
+	if (fsflags & FS_APPEND_FL)
+		i_flags |= S_APPEND;
+	if (fsflags & FS_IMMUTABLE_FL)
+		i_flags |= S_IMMUTABLE;
+	/*
+	 * But FS_NODUMP_FL does not require any action in i_flags.
+	 */
+	inode_set_flags(inode, i_flags, S_NOATIME | S_APPEND | S_IMMUTABLE);
+}
+#else
+static void shmem_set_inode_flags(struct inode *inode, unsigned int fsflags)
 {
-	if (S_ISDIR(mode))
-		return flags;
-	else if (S_ISREG(mode))
-		return flags & SHMEM_REG_FLMASK;
-	else
-		return flags & SHMEM_OTHER_FLMASK;
 }
+#define shmem_initxattrs NULL
+#endif
 
 static struct inode *shmem_get_inode(struct super_block *sb, struct inode *dir,
 				     umode_t mode, dev_t dev, unsigned long flags)
@@ -2319,7 +2340,8 @@ static struct inode *shmem_get_inode(struct super_block *sb, struct inode *dir,
 		info->i_crtime = inode->i_mtime;
 		info->fsflags = (dir == NULL) ? 0 :
 			SHMEM_I(dir)->fsflags & SHMEM_FL_INHERITED;
-		info->fsflags = shmem_mask_flags(mode, info->fsflags);
+		if (info->fsflags)
+			shmem_set_inode_flags(inode, info->fsflags);
 		INIT_LIST_HEAD(&info->shrinklist);
 		INIT_LIST_HEAD(&info->swaplist);
 		simple_xattrs_init(&info->xattrs);
@@ -2468,12 +2490,6 @@ out_unacct_blocks:
 static const struct inode_operations shmem_symlink_inode_operations;
 static const struct inode_operations shmem_short_symlink_operations;
 
-#ifdef CONFIG_TMPFS_XATTR
-static int shmem_initxattrs(struct inode *, const struct xattr *, void *);
-#else
-#define shmem_initxattrs NULL
-#endif
-
 static int
 shmem_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
@@ -2826,12 +2842,13 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 
 	if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
 		i_size_write(inode, offset + len);
-	inode->i_ctime = current_time(inode);
 undone:
 	spin_lock(&inode->i_lock);
 	inode->i_private = NULL;
 	spin_unlock(&inode->i_lock);
 out:
+	if (!error)
+		file_modified(file);
 	inode_unlock(inode);
 	return error;
 }
@@ -3179,18 +3196,13 @@ static int shmem_fileattr_set(struct user_namespace *mnt_userns,
 
 	if (fileattr_has_fsx(fa))
 		return -EOPNOTSUPP;
+	if (fa->flags & ~SHMEM_FL_USER_MODIFIABLE)
+		return -EOPNOTSUPP;
 
 	info->fsflags = (info->fsflags & ~SHMEM_FL_USER_MODIFIABLE) |
 		(fa->flags & SHMEM_FL_USER_MODIFIABLE);
 
-	inode->i_flags &= ~(S_APPEND | S_IMMUTABLE | S_NOATIME);
-	if (info->fsflags & FS_APPEND_FL)
-		inode->i_flags |= S_APPEND;
-	if (info->fsflags & FS_IMMUTABLE_FL)
-		inode->i_flags |= S_IMMUTABLE;
-	if (info->fsflags & FS_NOATIME_FL)
-		inode->i_flags |= S_NOATIME;
-
+	shmem_set_inode_flags(inode, info->fsflags);
 	inode->i_ctime = current_time(inode);
 	return 0;
 }
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 17996649cfe3..ccc02573588f 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -392,6 +392,28 @@ kmem_cache_create(const char *name, unsigned int size, unsigned int align,
 }
 EXPORT_SYMBOL(kmem_cache_create);
 
+#ifdef SLAB_SUPPORTS_SYSFS
+/*
+ * For a given kmem_cache, kmem_cache_destroy() should only be called
+ * once or there will be a use-after-free problem. The actual deletion
+ * and release of the kobject does not need slab_mutex or cpu_hotplug_lock
+ * protection. So they are now done without holding those locks.
+ *
+ * Note that there will be a slight delay in the deletion of sysfs files
+ * if kmem_cache_release() is called indrectly from a work function.
+ */
+static void kmem_cache_release(struct kmem_cache *s)
+{
+	sysfs_slab_unlink(s);
+	sysfs_slab_release(s);
+}
+#else
+static void kmem_cache_release(struct kmem_cache *s)
+{
+	slab_kmem_cache_release(s);
+}
+#endif
+
 static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
 {
 	LIST_HEAD(to_destroy);
@@ -418,11 +440,7 @@ static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
 	list_for_each_entry_safe(s, s2, &to_destroy, list) {
 		debugfs_slab_release(s);
 		kfence_shutdown_cache(s);
-#ifdef SLAB_SUPPORTS_SYSFS
-		sysfs_slab_release(s);
-#else
-		slab_kmem_cache_release(s);
-#endif
+		kmem_cache_release(s);
 	}
 }
 
@@ -437,20 +455,11 @@ static int shutdown_cache(struct kmem_cache *s)
 	list_del(&s->list);
 
 	if (s->flags & SLAB_TYPESAFE_BY_RCU) {
-#ifdef SLAB_SUPPORTS_SYSFS
-		sysfs_slab_unlink(s);
-#endif
 		list_add_tail(&s->list, &slab_caches_to_rcu_destroy);
 		schedule_work(&slab_caches_to_rcu_destroy_work);
 	} else {
 		kfence_shutdown_cache(s);
 		debugfs_slab_release(s);
-#ifdef SLAB_SUPPORTS_SYSFS
-		sysfs_slab_unlink(s);
-		sysfs_slab_release(s);
-#else
-		slab_kmem_cache_release(s);
-#endif
 	}
 
 	return 0;
@@ -465,14 +474,19 @@ void slab_kmem_cache_release(struct kmem_cache *s)
 
 void kmem_cache_destroy(struct kmem_cache *s)
 {
+	int refcnt;
+	bool rcu_set;
+
 	if (unlikely(!s) || !kasan_check_byte(s))
 		return;
 
 	cpus_read_lock();
 	mutex_lock(&slab_mutex);
 
-	s->refcount--;
-	if (s->refcount)
+	rcu_set = s->flags & SLAB_TYPESAFE_BY_RCU;
+
+	refcnt = --s->refcount;
+	if (refcnt)
 		goto out_unlock;
 
 	WARN(shutdown_cache(s),
@@ -481,6 +495,8 @@ void kmem_cache_destroy(struct kmem_cache *s)
 out_unlock:
 	mutex_unlock(&slab_mutex);
 	cpus_read_unlock();
+	if (!refcnt && !rcu_set)
+		kmem_cache_release(s);
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
 
diff --git a/mm/slub.c b/mm/slub.c
index 862dbd9af4f5..4b98dff9be8e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -310,6 +310,11 @@ static inline void stat(const struct kmem_cache *s, enum stat_item si)
  */
 static nodemask_t slab_nodes;
 
+/*
+ * Workqueue used for flush_cpu_slab().
+ */
+static struct workqueue_struct *flushwq;
+
 /********************************************************************
  * 			Core slab cache functions
  *******************************************************************/
@@ -2730,7 +2735,7 @@ static void flush_all_cpus_locked(struct kmem_cache *s)
 		INIT_WORK(&sfw->work, flush_cpu_slab);
 		sfw->skip = false;
 		sfw->s = s;
-		schedule_work_on(cpu, &sfw->work);
+		queue_work_on(cpu, flushwq, &sfw->work);
 	}
 
 	for_each_online_cpu(cpu) {
@@ -4858,6 +4863,8 @@ void __init kmem_cache_init(void)
 
 void __init kmem_cache_init_late(void)
 {
+	flushwq = alloc_workqueue("slub_flushwq", WQ_MEM_RECLAIM, 0);
+	WARN_ON(!flushwq);
 }
 
 struct kmem_cache *
@@ -4926,6 +4933,8 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
 	/* Honor the call site pointer we received. */
 	trace_kmalloc(caller, ret, s, size, s->size, gfpflags);
 
+	ret = kasan_kmalloc(s, ret, size, gfpflags);
+
 	return ret;
 }
 EXPORT_SYMBOL(__kmalloc_track_caller);
@@ -4957,6 +4966,8 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 	/* Honor the call site pointer we received. */
 	trace_kmalloc_node(caller, ret, s, size, s->size, gfpflags, node);
 
+	ret = kasan_kmalloc(s, ret, size, gfpflags);
+
 	return ret;
 }
 EXPORT_SYMBOL(__kmalloc_node_track_caller);
@@ -5890,7 +5901,8 @@ static char *create_unique_id(struct kmem_cache *s)
 	char *name = kmalloc(ID_STR_LENGTH, GFP_KERNEL);
 	char *p = name;
 
-	BUG_ON(!name);
+	if (!name)
+		return ERR_PTR(-ENOMEM);
 
 	*p++ = ':';
 	/*
@@ -5948,6 +5960,8 @@ static int sysfs_slab_add(struct kmem_cache *s)
 		 * for the symlinks.
 		 */
 		name = create_unique_id(s);
+		if (IS_ERR(name))
+			return PTR_ERR(name);
 	}
 
 	s->kobj.kset = kset;
diff --git a/mm/swap_state.c b/mm/swap_state.c
index e166051566f4..41afa6d45b23 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -151,7 +151,7 @@ void __delete_from_swap_cache(struct folio *folio,
 
 	for (i = 0; i < nr; i++) {
 		void *entry = xas_store(&xas, shadow);
-		VM_BUG_ON_FOLIO(entry != folio, folio);
+		VM_BUG_ON_PAGE(entry != folio, entry);
 		set_page_private(folio_page(folio, i), 0);
 		xas_next(&xas);
 	}
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 07d3befc80e4..7327b2573f7c 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -703,14 +703,29 @@ ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long start,
 			      mmap_changing, 0);
 }
 
+void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma,
+		   unsigned long start, unsigned long len, bool enable_wp)
+{
+	struct mmu_gather tlb;
+	pgprot_t newprot;
+
+	if (enable_wp)
+		newprot = vm_get_page_prot(dst_vma->vm_flags & ~(VM_WRITE));
+	else
+		newprot = vm_get_page_prot(dst_vma->vm_flags);
+
+	tlb_gather_mmu(&tlb, dst_mm);
+	change_protection(&tlb, dst_vma, start, start + len, newprot,
+			  enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE);
+	tlb_finish_mmu(&tlb);
+}
+
 int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
 			unsigned long len, bool enable_wp,
 			atomic_t *mmap_changing)
 {
 	struct vm_area_struct *dst_vma;
 	unsigned long page_mask;
-	struct mmu_gather tlb;
-	pgprot_t newprot;
 	int err;
 
 	/*
@@ -750,15 +765,7 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
 			goto out_unlock;
 	}
 
-	if (enable_wp)
-		newprot = vm_get_page_prot(dst_vma->vm_flags & ~(VM_WRITE));
-	else
-		newprot = vm_get_page_prot(dst_vma->vm_flags);
-
-	tlb_gather_mmu(&tlb, dst_mm);
-	change_protection(&tlb, dst_vma, start, start + len, newprot,
-			  enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE);
-	tlb_finish_mmu(&tlb);
+	uffd_wp_range(dst_mm, dst_vma, start, len, enable_wp);
 
 	err = 0;
 out_unlock:
diff --git a/mm/util.c b/mm/util.c
index c9439c66d8cf..346e40177bc6 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -619,6 +619,10 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
 	if (ret || size <= PAGE_SIZE)
 		return ret;
 
+	/* non-sleeping allocations are not supported by vmalloc */
+	if (!gfpflags_allow_blocking(flags))
+		return NULL;
+
 	/* Don't even allow crazy sizes */
 	if (unlikely(size > INT_MAX)) {
 		WARN_ON_ONCE(!(flags & __GFP_NOWARN));
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b2b1431352dc..382dbe97329f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2550,8 +2550,8 @@ static void shrink_active_list(unsigned long nr_to_scan,
 		}
 
 		if (unlikely(buffer_heads_over_limit)) {
-			if (folio_get_private(folio) && folio_trylock(folio)) {
-				if (folio_get_private(folio))
+			if (folio_test_private(folio) && folio_trylock(folio)) {
+				if (folio_test_private(folio))
 					filemap_release_folio(folio, 0);
 				folio_unlock(folio);
 			}
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 373d2730fcf2..90af9a8572f5 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1168,8 +1168,15 @@ int fragmentation_index(struct zone *zone, unsigned int order)
 #define TEXT_FOR_HIGHMEM(xx)
 #endif
 
+#ifdef CONFIG_ZONE_DEVICE
+#define TEXT_FOR_DEVICE(xx) xx "_device",
+#else
+#define TEXT_FOR_DEVICE(xx)
+#endif
+
 #define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \
-					TEXT_FOR_HIGHMEM(xx) xx "_movable",
+					TEXT_FOR_HIGHMEM(xx) xx "_movable", \
+					TEXT_FOR_DEVICE(xx)
 
 const char * const vmstat_text[] = {
 	/* enum zone_stat_item counters */
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 34f784a1604b..907c9b1e1e61 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1487,7 +1487,7 @@ void zs_free(struct zs_pool *pool, unsigned long handle)
 	struct size_class *class;
 	enum fullness_group fullness;
 
-	if (unlikely(!handle))
+	if (IS_ERR_OR_NULL((void *)handle))
 		return;
 
 	/*
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index b8f8da7ee3de..41c1ad33d009 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -10,6 +10,7 @@
 #include <linux/atomic.h>
 #include <linux/byteorder/generic.h>
 #include <linux/container_of.h>
+#include <linux/errno.h>
 #include <linux/gfp.h>
 #include <linux/if.h>
 #include <linux/if_arp.h>
@@ -700,6 +701,9 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 	int max_header_len = batadv_max_header_len();
 	int ret;
 
+	if (hard_iface->net_dev->mtu < ETH_MIN_MTU + max_header_len)
+		return -EINVAL;
+
 	if (hard_iface->if_status != BATADV_IF_NOT_IN_USE)
 		goto out;
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 485c814cf44a..6643c9c20fa4 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -4179,6 +4179,17 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, void *data,
 		}
 	}
 
+	if (i == ARRAY_SIZE(hci_cc_table)) {
+		/* Unknown opcode, assume byte 0 contains the status, so
+		 * that e.g. __hci_cmd_sync() properly returns errors
+		 * for vendor specific commands send by HCI drivers.
+		 * If a vendor doesn't actually follow this convention we may
+		 * need to introduce a vendor CC table in order to properly set
+		 * the status.
+		 */
+		*status = skb->data[0];
+	}
+
 	handle_cmd_cnt_and_timer(hdev, ev->ncmd);
 
 	hci_req_cmd_complete(hdev, *opcode, *status, req_complete,
@@ -5790,7 +5801,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status,
 	 */
 	hci_dev_clear_flag(hdev, HCI_LE_ADV);
 
-	conn = hci_lookup_le_connect(hdev);
+	conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, bdaddr);
 	if (!conn) {
 		/* In case of error status and there is no connection pending
 		 * just unlock as there is nothing to cleanup.
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index e6d804b82b67..fbd5613eebfc 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -3018,12 +3018,6 @@ static const struct hci_init_stage amp_init2[] = {
 /* Read Buffer Size (ACL mtu, max pkt, etc.) */
 static int hci_read_buffer_size_sync(struct hci_dev *hdev)
 {
-	/* Use Read LE Buffer Size V2 if supported */
-	if (hdev->commands[41] & 0x20)
-		return __hci_cmd_sync_status(hdev,
-					     HCI_OP_LE_READ_BUFFER_SIZE_V2,
-					     0, NULL, HCI_CMD_TIMEOUT);
-
 	return __hci_cmd_sync_status(hdev, HCI_OP_READ_BUFFER_SIZE,
 				     0, NULL, HCI_CMD_TIMEOUT);
 }
@@ -3237,6 +3231,12 @@ static const struct hci_init_stage hci_init2[] = {
 /* Read LE Buffer Size */
 static int hci_le_read_buffer_size_sync(struct hci_dev *hdev)
 {
+	/* Use Read LE Buffer Size V2 if supported */
+	if (hdev->commands[41] & 0x20)
+		return __hci_cmd_sync_status(hdev,
+					     HCI_OP_LE_READ_BUFFER_SIZE_V2,
+					     0, NULL, HCI_CMD_TIMEOUT);
+
 	return __hci_cmd_sync_status(hdev, HCI_OP_LE_READ_BUFFER_SIZE,
 				     0, NULL, HCI_CMD_TIMEOUT);
 }
@@ -4773,9 +4773,11 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
 		/* Cleanup hci_conn object if it cannot be cancelled as it
 		 * likelly means the controller and host stack are out of sync.
 		 */
-		if (err)
+		if (err) {
+			hci_dev_lock(hdev);
 			hci_conn_failed(conn, err);
-
+			hci_dev_unlock(hdev);
+		}
 		return err;
 	case BT_CONNECT2:
 		return hci_reject_conn_sync(hdev, conn, reason);
@@ -5288,17 +5290,21 @@ int hci_suspend_sync(struct hci_dev *hdev)
 	/* Prevent disconnects from causing scanning to be re-enabled */
 	hci_pause_scan_sync(hdev);
 
-	/* Soft disconnect everything (power off) */
-	err = hci_disconnect_all_sync(hdev, HCI_ERROR_REMOTE_POWER_OFF);
-	if (err) {
-		/* Set state to BT_RUNNING so resume doesn't notify */
-		hdev->suspend_state = BT_RUNNING;
-		hci_resume_sync(hdev);
-		return err;
-	}
+	if (hci_conn_count(hdev)) {
+		/* Soft disconnect everything (power off) */
+		err = hci_disconnect_all_sync(hdev, HCI_ERROR_REMOTE_POWER_OFF);
+		if (err) {
+			/* Set state to BT_RUNNING so resume doesn't notify */
+			hdev->suspend_state = BT_RUNNING;
+			hci_resume_sync(hdev);
+			return err;
+		}
 
-	/* Update event mask so only the allowed event can wakeup the host */
-	hci_set_event_mask_sync(hdev);
+		/* Update event mask so only the allowed event can wakeup the
+		 * host.
+		 */
+		hci_set_event_mask_sync(hdev);
+	}
 
 	/* Only configure accept list if disconnect succeeded and wake
 	 * isn't being prevented.
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 5940744a8cd8..cc20e706c639 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -83,14 +83,14 @@ static void hidp_copy_session(struct hidp_session *session, struct hidp_conninfo
 		ci->product = session->input->id.product;
 		ci->version = session->input->id.version;
 		if (session->input->name)
-			strlcpy(ci->name, session->input->name, 128);
+			strscpy(ci->name, session->input->name, 128);
 		else
-			strlcpy(ci->name, "HID Boot Device", 128);
+			strscpy(ci->name, "HID Boot Device", 128);
 	} else if (session->hid) {
 		ci->vendor  = session->hid->vendor;
 		ci->product = session->hid->product;
 		ci->version = session->hid->version;
-		strlcpy(ci->name, session->hid->name, 128);
+		strscpy(ci->name, session->hid->name, 128);
 	}
 }
 
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index ced8ad4fed4f..613039ba5dbf 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -1309,7 +1309,7 @@ static int iso_sock_shutdown(struct socket *sock, int how)
 	struct sock *sk = sock->sk;
 	int err = 0;
 
-	BT_DBG("sock %p, sk %p", sock, sk);
+	BT_DBG("sock %p, sk %p, how %d", sock, sk, how);
 
 	if (!sk)
 		return 0;
@@ -1317,17 +1317,32 @@ static int iso_sock_shutdown(struct socket *sock, int how)
 	sock_hold(sk);
 	lock_sock(sk);
 
-	if (!sk->sk_shutdown) {
-		sk->sk_shutdown = SHUTDOWN_MASK;
-		iso_sock_clear_timer(sk);
-		__iso_sock_close(sk);
-
-		if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
-		    !(current->flags & PF_EXITING))
-			err = bt_sock_wait_state(sk, BT_CLOSED,
-						 sk->sk_lingertime);
+	switch (how) {
+	case SHUT_RD:
+		if (sk->sk_shutdown & RCV_SHUTDOWN)
+			goto unlock;
+		sk->sk_shutdown |= RCV_SHUTDOWN;
+		break;
+	case SHUT_WR:
+		if (sk->sk_shutdown & SEND_SHUTDOWN)
+			goto unlock;
+		sk->sk_shutdown |= SEND_SHUTDOWN;
+		break;
+	case SHUT_RDWR:
+		if (sk->sk_shutdown & SHUTDOWN_MASK)
+			goto unlock;
+		sk->sk_shutdown |= SHUTDOWN_MASK;
+		break;
 	}
 
+	iso_sock_clear_timer(sk);
+	__iso_sock_close(sk);
+
+	if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+	    !(current->flags & PF_EXITING))
+		err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime);
+
+unlock:
 	release_sock(sk);
 	sock_put(sk);
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index cbe0cae73434..2c9de67daadc 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1992,11 +1992,11 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
 			src_match = !bacmp(&c->src, src);
 			dst_match = !bacmp(&c->dst, dst);
 			if (src_match && dst_match) {
-				c = l2cap_chan_hold_unless_zero(c);
-				if (c) {
-					read_unlock(&chan_list_lock);
-					return c;
-				}
+				if (!l2cap_chan_hold_unless_zero(c))
+					continue;
+
+				read_unlock(&chan_list_lock);
+				return c;
 			}
 
 			/* Closest match */
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 6e31023b84f5..72e6595a71cc 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4547,6 +4547,22 @@ static int set_exp_feature(struct sock *sk, struct hci_dev *hdev,
 			       MGMT_STATUS_NOT_SUPPORTED);
 }
 
+static u32 get_params_flags(struct hci_dev *hdev,
+			    struct hci_conn_params *params)
+{
+	u32 flags = hdev->conn_flags;
+
+	/* Devices using RPAs can only be programmed in the acceptlist if
+	 * LL Privacy has been enable otherwise they cannot mark
+	 * HCI_CONN_FLAG_REMOTE_WAKEUP.
+	 */
+	if ((flags & HCI_CONN_FLAG_REMOTE_WAKEUP) && !use_ll_privacy(hdev) &&
+	    hci_find_irk_by_addr(hdev, &params->addr, params->addr_type))
+		flags &= ~HCI_CONN_FLAG_REMOTE_WAKEUP;
+
+	return flags;
+}
+
 static int get_device_flags(struct sock *sk, struct hci_dev *hdev, void *data,
 			    u16 data_len)
 {
@@ -4578,10 +4594,10 @@ static int get_device_flags(struct sock *sk, struct hci_dev *hdev, void *data,
 	} else {
 		params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr,
 						le_addr_type(cp->addr.type));
-
 		if (!params)
 			goto done;
 
+		supported_flags = get_params_flags(hdev, params);
 		current_flags = params->flags;
 	}
 
@@ -4649,38 +4665,35 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data,
 			bt_dev_warn(hdev, "No such BR/EDR device %pMR (0x%x)",
 				    &cp->addr.bdaddr, cp->addr.type);
 		}
-	} else {
-		params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr,
-						le_addr_type(cp->addr.type));
-		if (params) {
-			/* Devices using RPAs can only be programmed in the
-			 * acceptlist LL Privacy has been enable otherwise they
-			 * cannot mark HCI_CONN_FLAG_REMOTE_WAKEUP.
-			 */
-			if ((current_flags & HCI_CONN_FLAG_REMOTE_WAKEUP) &&
-			    !use_ll_privacy(hdev) &&
-			    hci_find_irk_by_addr(hdev, &params->addr,
-						 params->addr_type)) {
-				bt_dev_warn(hdev,
-					    "Cannot set wakeable for RPA");
-				goto unlock;
-			}
 
-			params->flags = current_flags;
-			status = MGMT_STATUS_SUCCESS;
+		goto unlock;
+	}
 
-			/* Update passive scan if HCI_CONN_FLAG_DEVICE_PRIVACY
-			 * has been set.
-			 */
-			if (params->flags & HCI_CONN_FLAG_DEVICE_PRIVACY)
-				hci_update_passive_scan(hdev);
-		} else {
-			bt_dev_warn(hdev, "No such LE device %pMR (0x%x)",
-				    &cp->addr.bdaddr,
-				    le_addr_type(cp->addr.type));
-		}
+	params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr,
+					le_addr_type(cp->addr.type));
+	if (!params) {
+		bt_dev_warn(hdev, "No such LE device %pMR (0x%x)",
+			    &cp->addr.bdaddr, le_addr_type(cp->addr.type));
+		goto unlock;
 	}
 
+	supported_flags = get_params_flags(hdev, params);
+
+	if ((supported_flags | current_flags) != supported_flags) {
+		bt_dev_warn(hdev, "Bad flag given (0x%x) vs supported (0x%0x)",
+			    current_flags, supported_flags);
+		goto unlock;
+	}
+
+	params->flags = current_flags;
+	status = MGMT_STATUS_SUCCESS;
+
+	/* Update passive scan if HCI_CONN_FLAG_DEVICE_PRIVACY
+	 * has been set.
+	 */
+	if (params->flags & HCI_CONN_FLAG_DEVICE_PRIVACY)
+		hci_update_passive_scan(hdev);
+
 unlock:
 	hci_dev_unlock(hdev);
 
@@ -5054,7 +5067,6 @@ static int remove_adv_monitor(struct sock *sk, struct hci_dev *hdev,
 		else
 			status = MGMT_STATUS_FAILED;
 
-		mgmt_pending_remove(cmd);
 		goto unlock;
 	}
 
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index ff4779036649..f20f4373ff40 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -384,6 +384,7 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_
 				/* - Bridged-and-DNAT'ed traffic doesn't
 				 *   require ip_forwarding. */
 				if (rt->dst.dev == dev) {
+					skb_dst_drop(skb);
 					skb_dst_set(skb, &rt->dst);
 					goto bridged_dnat;
 				}
@@ -413,6 +414,7 @@ bridged_dnat:
 			kfree_skb(skb);
 			return 0;
 		}
+		skb_dst_drop(skb);
 		skb_dst_set_noref(skb, &rt->dst);
 	}
 
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
index e4e0c836c3f5..6b07f30675bb 100644
--- a/net/bridge/br_netfilter_ipv6.c
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -197,6 +197,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 			kfree_skb(skb);
 			return 0;
 		}
+		skb_dst_drop(skb);
 		skb_dst_set_noref(skb, &rt->dst);
 	}
 
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index 1a11064f9990..8f19253024b0 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -36,18 +36,10 @@ static struct ebt_replace_kernel initial_table = {
 	.entries	= (char *)&initial_chain,
 };
 
-static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
-{
-	if (valid_hooks & ~(1 << NF_BR_BROUTING))
-		return -EINVAL;
-	return 0;
-}
-
 static const struct ebt_table broute_table = {
 	.name		= "broute",
 	.table		= &initial_table,
 	.valid_hooks	= 1 << NF_BR_BROUTING,
-	.check		= check,
 	.me		= THIS_MODULE,
 };
 
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index cb949436bc0e..278f324e6752 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = {
 	.entries	= (char *)initial_chains,
 };
 
-static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
-{
-	if (valid_hooks & ~FILTER_VALID_HOOKS)
-		return -EINVAL;
-	return 0;
-}
-
 static const struct ebt_table frame_filter = {
 	.name		= "filter",
 	.table		= &initial_table,
 	.valid_hooks	= FILTER_VALID_HOOKS,
-	.check		= check,
 	.me		= THIS_MODULE,
 };
 
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index 5ee0531ae506..9066f7f376d5 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = {
 	.entries	= (char *)initial_chains,
 };
 
-static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
-{
-	if (valid_hooks & ~NAT_VALID_HOOKS)
-		return -EINVAL;
-	return 0;
-}
-
 static const struct ebt_table frame_nat = {
 	.name		= "nat",
 	.table		= &initial_table,
 	.valid_hooks	= NAT_VALID_HOOKS,
-	.check		= check,
 	.me		= THIS_MODULE,
 };
 
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index f2dbefb61ce8..4f385d52a1c4 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1040,9 +1040,10 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl,
 		goto free_iterate;
 	}
 
-	/* the table doesn't like it */
-	if (t->check && (ret = t->check(newinfo, repl->valid_hooks)))
+	if (repl->valid_hooks != t->valid_hooks) {
+		ret = -EINVAL;
 		goto free_unlock;
+	}
 
 	if (repl->num_counters && repl->num_counters != t->private->nentries) {
 		ret = -EINVAL;
@@ -1231,11 +1232,6 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table,
 	if (ret != 0)
 		goto free_chainstack;
 
-	if (table->check && table->check(newinfo, table->valid_hooks)) {
-		ret = -EINVAL;
-		goto free_chainstack;
-	}
-
 	table->private = newinfo;
 	rwlock_init(&table->lock);
 	mutex_lock(&ebt_mutex);
diff --git a/net/compat.c b/net/compat.c
index fe9be3c56ef7..385f04a6be2f 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -52,6 +52,7 @@ int __get_compat_msghdr(struct msghdr *kmsg,
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
 
 	kmsg->msg_control_is_user = true;
+	kmsg->msg_get_inq = 0;
 	kmsg->msg_control_user = compat_ptr(msg->msg_control);
 	kmsg->msg_controllen = msg->msg_controllen;
 
diff --git a/net/core/.gitignore b/net/core/.gitignore
deleted file mode 100644
index df1e74372cce..000000000000
--- a/net/core/.gitignore
+++ /dev/null
@@ -1 +0,0 @@
-dropreason_str.c
diff --git a/net/core/Makefile b/net/core/Makefile
index e8ce3bd283a6..5857cec87b83 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -5,7 +5,7 @@
 
 obj-y := sock.o request_sock.o skbuff.o datagram.o stream.o scm.o \
 	 gen_stats.o gen_estimator.o net_namespace.o secure_seq.o \
-	 flow_dissector.o dropreason_str.o
+	 flow_dissector.o
 
 obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
 
@@ -40,23 +40,3 @@ obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o
 obj-$(CONFIG_BPF_SYSCALL) += sock_map.o
 obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o
 obj-$(CONFIG_OF)	+= of_net.o
-
-clean-files := dropreason_str.c
-
-quiet_cmd_dropreason_str = GEN     $@
-cmd_dropreason_str = awk -F ',' 'BEGIN{ print "\#include <net/dropreason.h>\n"; \
-	print "const char * const drop_reasons[] = {" }\
-	/^enum skb_drop/ { dr=1; }\
-	/^\};/ { dr=0; }\
-	/^\tSKB_DROP_REASON_/ {\
-		if (dr) {\
-			sub(/\tSKB_DROP_REASON_/, "", $$1);\
-			printf "\t[SKB_DROP_REASON_%s] = \"%s\",\n", $$1, $$1;\
-		}\
-	}\
-	END{ print "};" }' $< > $@
-
-$(obj)/dropreason_str.c: $(srctree)/include/net/dropreason.h
-	$(call cmd,dropreason_str)
-
-$(obj)/dropreason_str.o: $(obj)/dropreason_str.c
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 1b7f385643b4..94374d529ea4 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -310,11 +310,12 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap,
 				 void *owner, u32 size)
 {
+	int optmem_max = READ_ONCE(sysctl_optmem_max);
 	struct sock *sk = (struct sock *)owner;
 
 	/* same check as in sock_kmalloc() */
-	if (size <= sysctl_optmem_max &&
-	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+	if (size <= optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
 		atomic_add(size, &sk->sk_omem_alloc);
 		return 0;
 	}
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 7255531f63ae..e4ff2db40c98 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -677,7 +677,7 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
 				page_ref_sub(last_head, refs);
 				refs = 0;
 			}
-			skb_fill_page_desc(skb, frag++, head, start, size);
+			skb_fill_page_desc_noacc(skb, frag++, head, start, size);
 		}
 		if (refs)
 			page_ref_sub(last_head, refs);
diff --git a/net/core/dev.c b/net/core/dev.c
index 716df64fcfa5..56c8b0921c9f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4624,7 +4624,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
 	struct softnet_data *sd;
 	unsigned int old_flow, new_flow;
 
-	if (qlen < (netdev_max_backlog >> 1))
+	if (qlen < (READ_ONCE(netdev_max_backlog) >> 1))
 		return false;
 
 	sd = this_cpu_ptr(&softnet_data);
@@ -4672,7 +4672,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 	if (!netif_running(skb->dev))
 		goto drop;
 	qlen = skb_queue_len(&sd->input_pkt_queue);
-	if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
+	if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) {
 		if (qlen) {
 enqueue:
 			__skb_queue_tail(&sd->input_pkt_queue, skb);
@@ -4928,7 +4928,7 @@ static int netif_rx_internal(struct sk_buff *skb)
 {
 	int ret;
 
-	net_timestamp_check(netdev_tstamp_prequeue, skb);
+	net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
 
 	trace_netif_rx(skb);
 
@@ -5281,7 +5281,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
 	int ret = NET_RX_DROP;
 	__be16 type;
 
-	net_timestamp_check(!netdev_tstamp_prequeue, skb);
+	net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb);
 
 	trace_netif_receive_skb(skb);
 
@@ -5664,7 +5664,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
 {
 	int ret;
 
-	net_timestamp_check(netdev_tstamp_prequeue, skb);
+	net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
 
 	if (skb_defer_rx_timestamp(skb))
 		return NET_RX_SUCCESS;
@@ -5694,7 +5694,7 @@ void netif_receive_skb_list_internal(struct list_head *head)
 
 	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
-		net_timestamp_check(netdev_tstamp_prequeue, skb);
+		net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
 		skb_list_del_init(skb);
 		if (!skb_defer_rx_timestamp(skb))
 			list_add_tail(&skb->list, &sublist);
@@ -5918,7 +5918,7 @@ static int process_backlog(struct napi_struct *napi, int quota)
 		net_rps_action_and_irq_enable(sd);
 	}
 
-	napi->weight = dev_rx_weight;
+	napi->weight = READ_ONCE(dev_rx_weight);
 	while (again) {
 		struct sk_buff *skb;
 
@@ -6665,8 +6665,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
 	unsigned long time_limit = jiffies +
-		usecs_to_jiffies(netdev_budget_usecs);
-	int budget = netdev_budget;
+		usecs_to_jiffies(READ_ONCE(netdev_budget_usecs));
+	int budget = READ_ONCE(netdev_budget);
 	LIST_HEAD(list);
 	LIST_HEAD(repoll);
 
@@ -10284,7 +10284,7 @@ static struct net_device *netdev_wait_allrefs_any(struct list_head *list)
 				return dev;
 
 		if (time_after(jiffies, warning_time +
-			       netdev_unregister_timeout_secs * HZ)) {
+			       READ_ONCE(netdev_unregister_timeout_secs) * HZ)) {
 			list_for_each_entry(dev, list, todo_list) {
 				pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n",
 					 dev->name, netdev_refcnt_read(dev));
diff --git a/net/core/filter.c b/net/core/filter.c
index e8508aaafd27..c191db80ce93 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1214,10 +1214,11 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
 static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 {
 	u32 filter_size = bpf_prog_size(fp->prog->len);
+	int optmem_max = READ_ONCE(sysctl_optmem_max);
 
 	/* same check as in sock_kmalloc() */
-	if (filter_size <= sysctl_optmem_max &&
-	    atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
+	if (filter_size <= optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + filter_size < optmem_max) {
 		atomic_add(filter_size, &sk->sk_omem_alloc);
 		return true;
 	}
@@ -1548,7 +1549,7 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	if (bpf_prog_size(prog->len) > sysctl_optmem_max)
+	if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max))
 		err = -ENOMEM;
 	else
 		err = reuseport_attach_prog(sk, prog);
@@ -1615,7 +1616,7 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
 		}
 	} else {
 		/* BPF_PROG_TYPE_SOCKET_FILTER */
-		if (bpf_prog_size(prog->len) > sysctl_optmem_max) {
+		if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) {
 			err = -ENOMEM;
 			goto err_prog_put;
 		}
@@ -5034,14 +5035,14 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 		/* Only some socketops are supported */
 		switch (optname) {
 		case SO_RCVBUF:
-			val = min_t(u32, val, sysctl_rmem_max);
+			val = min_t(u32, val, READ_ONCE(sysctl_rmem_max));
 			val = min_t(int, val, INT_MAX / 2);
 			sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
 			WRITE_ONCE(sk->sk_rcvbuf,
 				   max_t(int, val * 2, SOCK_MIN_RCVBUF));
 			break;
 		case SO_SNDBUF:
-			val = min_t(u32, val, sysctl_wmem_max);
+			val = min_t(u32, val, READ_ONCE(sysctl_wmem_max));
 			val = min_t(int, val, INT_MAX / 2);
 			sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
 			WRITE_ONCE(sk->sk_sndbuf,
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 764c4cb3fe8f..5dc3860e9fc7 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1611,9 +1611,8 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys)
 
 	switch (keys->control.addr_type) {
 	case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
-		addr_diff = (__force u32)keys->addrs.v4addrs.dst -
-			    (__force u32)keys->addrs.v4addrs.src;
-		if (addr_diff < 0)
+		if ((__force u32)keys->addrs.v4addrs.dst <
+		    (__force u32)keys->addrs.v4addrs.src)
 			swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst);
 
 		if ((__force u16)keys->ports.dst <
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index a10335b4ba2d..c8d137ef5980 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -345,7 +345,7 @@ static void gnet_stats_add_queue_cpu(struct gnet_stats_queue *qstats,
 	for_each_possible_cpu(i) {
 		const struct gnet_stats_queue *qcpu = per_cpu_ptr(q, i);
 
-		qstats->qlen += qcpu->backlog;
+		qstats->qlen += qcpu->qlen;
 		qstats->backlog += qcpu->backlog;
 		qstats->drops += qcpu->drops;
 		qstats->requeues += qcpu->requeues;
diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c
index 541c7a72a28a..21619c70a82b 100644
--- a/net/core/gro_cells.c
+++ b/net/core/gro_cells.c
@@ -26,7 +26,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
 
 	cell = this_cpu_ptr(gcells->cells);
 
-	if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) {
+	if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(netdev_max_backlog)) {
 drop:
 		dev_core_stats_rx_dropped_inc(dev);
 		kfree_skb(skb);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 6a8c2596ebab..78cc8fb68814 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -307,11 +307,35 @@ static int neigh_del_timer(struct neighbour *n)
 	return 0;
 }
 
-static void pneigh_queue_purge(struct sk_buff_head *list)
+static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net)
 {
+	struct sk_buff_head tmp;
+	unsigned long flags;
 	struct sk_buff *skb;
 
-	while ((skb = skb_dequeue(list)) != NULL) {
+	skb_queue_head_init(&tmp);
+	spin_lock_irqsave(&list->lock, flags);
+	skb = skb_peek(list);
+	while (skb != NULL) {
+		struct sk_buff *skb_next = skb_peek_next(skb, list);
+		struct net_device *dev = skb->dev;
+
+		if (net == NULL || net_eq(dev_net(dev), net)) {
+			struct in_device *in_dev;
+
+			rcu_read_lock();
+			in_dev = __in_dev_get_rcu(dev);
+			if (in_dev)
+				in_dev->arp_parms->qlen--;
+			rcu_read_unlock();
+			__skb_unlink(skb, list);
+			__skb_queue_tail(&tmp, skb);
+		}
+		skb = skb_next;
+	}
+	spin_unlock_irqrestore(&list->lock, flags);
+
+	while ((skb = __skb_dequeue(&tmp))) {
 		dev_put(skb->dev);
 		kfree_skb(skb);
 	}
@@ -385,9 +409,9 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev,
 	write_lock_bh(&tbl->lock);
 	neigh_flush_dev(tbl, dev, skip_perm);
 	pneigh_ifdown_and_unlock(tbl, dev);
-
-	del_timer_sync(&tbl->proxy_timer);
-	pneigh_queue_purge(&tbl->proxy_queue);
+	pneigh_queue_purge(&tbl->proxy_queue, dev_net(dev));
+	if (skb_queue_empty_lockless(&tbl->proxy_queue))
+		del_timer_sync(&tbl->proxy_timer);
 	return 0;
 }
 
@@ -1597,8 +1621,15 @@ static void neigh_proxy_process(struct timer_list *t)
 
 		if (tdif <= 0) {
 			struct net_device *dev = skb->dev;
+			struct in_device *in_dev;
 
+			rcu_read_lock();
+			in_dev = __in_dev_get_rcu(dev);
+			if (in_dev)
+				in_dev->arp_parms->qlen--;
+			rcu_read_unlock();
 			__skb_unlink(skb, &tbl->proxy_queue);
+
 			if (tbl->proxy_redo && netif_running(dev)) {
 				rcu_read_lock();
 				tbl->proxy_redo(skb);
@@ -1623,7 +1654,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
 	unsigned long sched_next = jiffies +
 			prandom_u32_max(NEIGH_VAR(p, PROXY_DELAY));
 
-	if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) {
+	if (p->qlen > NEIGH_VAR(p, PROXY_QLEN)) {
 		kfree_skb(skb);
 		return;
 	}
@@ -1639,6 +1670,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
 	skb_dst_drop(skb);
 	dev_hold(skb->dev);
 	__skb_queue_tail(&tbl->proxy_queue, skb);
+	p->qlen++;
 	mod_timer(&tbl->proxy_timer, sched_next);
 	spin_unlock(&tbl->proxy_queue.lock);
 }
@@ -1671,6 +1703,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
 		refcount_set(&p->refcnt, 1);
 		p->reachable_time =
 				neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
+		p->qlen = 0;
 		netdev_hold(dev, &p->dev_tracker, GFP_KERNEL);
 		p->dev = dev;
 		write_pnet(&p->net, net);
@@ -1736,6 +1769,7 @@ void neigh_table_init(int index, struct neigh_table *tbl)
 	refcount_set(&tbl->parms.refcnt, 1);
 	tbl->parms.reachable_time =
 			  neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME));
+	tbl->parms.qlen = 0;
 
 	tbl->stats = alloc_percpu(struct neigh_statistics);
 	if (!tbl->stats)
@@ -1787,7 +1821,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl)
 	cancel_delayed_work_sync(&tbl->managed_work);
 	cancel_delayed_work_sync(&tbl->gc_work);
 	del_timer_sync(&tbl->proxy_timer);
-	pneigh_queue_purge(&tbl->proxy_queue);
+	pneigh_queue_purge(&tbl->proxy_queue, NULL);
 	neigh_ifdown(tbl, NULL);
 	if (atomic_read(&tbl->entries))
 		pr_crit("neighbour leakage\n");
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 6b9f19122ec1..0ec2f5906a27 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -18,7 +18,6 @@
 #include <linux/user_namespace.h>
 #include <linux/net_namespace.h>
 #include <linux/sched/task.h>
-#include <linux/sched/mm.h>
 #include <linux/uidgid.h>
 #include <linux/cookie.h>
 
@@ -1144,13 +1143,7 @@ static int __register_pernet_operations(struct list_head *list,
 		 * setup_net() and cleanup_net() are not possible.
 		 */
 		for_each_net(net) {
-			struct mem_cgroup *old, *memcg;
-
-			memcg = mem_cgroup_or_root(get_mem_cgroup_from_obj(net));
-			old = set_active_memcg(memcg);
 			error = ops_init(ops, net);
-			set_active_memcg(old);
-			mem_cgroup_put(memcg);
 			if (error)
 				goto out_undo;
 			list_add_tail(&net->exit_list, &net_exit_list);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index ac45328607f7..4b5b15c684ed 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -6070,6 +6070,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (kind == RTNL_KIND_DEL && (nlh->nlmsg_flags & NLM_F_BULK) &&
 	    !(flags & RTNL_FLAG_BULK_DEL_SUPPORTED)) {
 		NL_SET_ERR_MSG(extack, "Bulk delete is not supported");
+		module_put(owner);
 		goto err_unlock;
 	}
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 974bbbbe7138..417463da4fac 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -91,7 +91,11 @@ static struct kmem_cache *skbuff_ext_cache __ro_after_init;
 int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
 EXPORT_SYMBOL(sysctl_max_skb_frags);
 
-/* The array 'drop_reasons' is auto-generated in dropreason_str.c */
+#undef FN
+#define FN(reason) [SKB_DROP_REASON_##reason] = #reason,
+const char * const drop_reasons[] = {
+	DEFINE_DROP_REASON(FN, FN)
+};
 EXPORT_SYMBOL(drop_reasons);
 
 /**
@@ -4205,9 +4209,8 @@ normal:
 				SKB_GSO_CB(nskb)->csum_start =
 					skb_headroom(nskb) + doffset;
 			} else {
-				skb_copy_bits(head_skb, offset,
-					      skb_put(nskb, len),
-					      len);
+				if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len))
+					goto err;
 			}
 			continue;
 		}
@@ -4798,7 +4801,7 @@ static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly)
 {
 	bool ret;
 
-	if (likely(sysctl_tstamp_allow_data || tsonly))
+	if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly))
 		return true;
 
 	read_lock_bh(&sk->sk_callback_lock);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index f47338d89d5d..188f8558d27d 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -461,7 +461,7 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 
 			if (copied == len)
 				break;
-		} while (!sg_is_last(sge));
+		} while ((i != msg_rx->sg.end) && !sg_is_last(sge));
 
 		if (unlikely(peek)) {
 			msg_rx = sk_psock_next_msg(psock, msg_rx);
@@ -471,7 +471,7 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 		}
 
 		msg_rx->sg.start = i;
-		if (!sge->length && sg_is_last(sge)) {
+		if (!sge->length && (i == msg_rx->sg.end || sg_is_last(sge))) {
 			msg_rx = sk_psock_dequeue_msg(psock);
 			kfree_sk_msg(msg_rx);
 		}
@@ -1194,8 +1194,9 @@ static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb)
 		ret = bpf_prog_run_pin_on_cpu(prog, skb);
 		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
 	}
-	if (sk_psock_verdict_apply(psock, skb, ret) < 0)
-		len = 0;
+	ret = sk_psock_verdict_apply(psock, skb, ret);
+	if (ret < 0)
+		len = ret;
 out:
 	rcu_read_unlock();
 	return len;
diff --git a/net/core/sock.c b/net/core/sock.c
index 4cb957d934a2..788c1372663c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1101,7 +1101,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		 * play 'guess the biggest size' games. RCVBUF/SNDBUF
 		 * are treated in BSD as hints
 		 */
-		val = min_t(u32, val, sysctl_wmem_max);
+		val = min_t(u32, val, READ_ONCE(sysctl_wmem_max));
 set_sndbuf:
 		/* Ensure val * 2 fits into an int, to prevent max_t()
 		 * from treating it as a negative value.
@@ -1133,7 +1133,7 @@ set_sndbuf:
 		 * play 'guess the biggest size' games. RCVBUF/SNDBUF
 		 * are treated in BSD as hints
 		 */
-		__sock_set_rcvbuf(sk, min_t(u32, val, sysctl_rmem_max));
+		__sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max)));
 		break;
 
 	case SO_RCVBUFFORCE:
@@ -2536,7 +2536,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
 
 	/* small safe race: SKB_TRUESIZE may differ from final skb->truesize */
 	if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) >
-	    sysctl_optmem_max)
+	    READ_ONCE(sysctl_optmem_max))
 		return NULL;
 
 	skb = alloc_skb(size, priority);
@@ -2554,8 +2554,10 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
  */
 void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
 {
-	if ((unsigned int)size <= sysctl_optmem_max &&
-	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+	int optmem_max = READ_ONCE(sysctl_optmem_max);
+
+	if ((unsigned int)size <= optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
 		void *mem;
 		/* First do the add, to avoid the race if kmalloc
 		 * might sleep.
@@ -3309,8 +3311,8 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	timer_setup(&sk->sk_timer, NULL, 0);
 
 	sk->sk_allocation	=	GFP_KERNEL;
-	sk->sk_rcvbuf		=	sysctl_rmem_default;
-	sk->sk_sndbuf		=	sysctl_wmem_default;
+	sk->sk_rcvbuf		=	READ_ONCE(sysctl_rmem_default);
+	sk->sk_sndbuf		=	READ_ONCE(sysctl_wmem_default);
 	sk->sk_state		=	TCP_CLOSE;
 	sk_set_socket(sk, sock);
 
@@ -3365,7 +3367,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	sk->sk_napi_id		=	0;
-	sk->sk_ll_usec		=	sysctl_net_busy_read;
+	sk->sk_ll_usec		=	READ_ONCE(sysctl_net_busy_read);
 #endif
 
 	sk->sk_max_pacing_rate = ~0UL;
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 71a13596ea2b..725891527814 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -234,14 +234,17 @@ static int set_default_qdisc(struct ctl_table *table, int write,
 static int proc_do_dev_weight(struct ctl_table *table, int write,
 			   void *buffer, size_t *lenp, loff_t *ppos)
 {
-	int ret;
+	static DEFINE_MUTEX(dev_weight_mutex);
+	int ret, weight;
 
+	mutex_lock(&dev_weight_mutex);
 	ret = proc_dointvec(table, write, buffer, lenp, ppos);
-	if (ret != 0)
-		return ret;
-
-	dev_rx_weight = weight_p * dev_weight_rx_bias;
-	dev_tx_weight = weight_p * dev_weight_tx_bias;
+	if (!ret && write) {
+		weight = READ_ONCE(weight_p);
+		WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias);
+		WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias);
+	}
+	mutex_unlock(&dev_weight_mutex);
 
 	return ret;
 }
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 2dd76eb1621c..a8895ee3cd60 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -145,11 +145,14 @@ int dsa_port_set_state(struct dsa_port *dp, u8 state, bool do_fast_age)
 static void dsa_port_set_state_now(struct dsa_port *dp, u8 state,
 				   bool do_fast_age)
 {
+	struct dsa_switch *ds = dp->ds;
 	int err;
 
 	err = dsa_port_set_state(dp, state, do_fast_age);
-	if (err)
-		pr_err("DSA: failed to set STP state %u (%d)\n", state, err);
+	if (err && err != -EOPNOTSUPP) {
+		dev_err(ds->dev, "port %d failed to set STP state %u: %pe\n",
+			dp->index, state, ERR_PTR(err));
+	}
 }
 
 int dsa_port_set_mst_state(struct dsa_port *dp,
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index ad6a6663feeb..1291c2431d44 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -2484,7 +2484,7 @@ static int dsa_slave_changeupper(struct net_device *dev,
 			if (!err)
 				dsa_bridge_mtu_normalization(dp);
 			if (err == -EOPNOTSUPP) {
-				if (!extack->_msg)
+				if (extack && !extack->_msg)
 					NL_SET_ERR_MSG_MOD(extack,
 							   "Offloading not supported");
 				err = 0;
diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c
index eb204ad36eee..846588c0070a 100644
--- a/net/dsa/tag_hellcreek.c
+++ b/net/dsa/tag_hellcreek.c
@@ -45,7 +45,7 @@ static struct sk_buff *hellcreek_rcv(struct sk_buff *skb,
 
 	skb->dev = dsa_master_find_slave(dev, 0, port);
 	if (!skb->dev) {
-		netdev_warn(dev, "Failed to get source port: %d\n", port);
+		netdev_warn_once(dev, "Failed to get source port: %d\n", port);
 		return NULL;
 	}
 
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index 718fb77bb372..7889e1ef7fad 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -200,8 +200,9 @@ static int raw_bind(struct sock *sk, struct sockaddr *_uaddr, int len)
 	int err = 0;
 	struct net_device *dev = NULL;
 
-	if (len < sizeof(*uaddr))
-		return -EINVAL;
+	err = ieee802154_sockaddr_check_size(uaddr, len);
+	if (err < 0)
+		return err;
 
 	uaddr = (struct sockaddr_ieee802154 *)_uaddr;
 	if (uaddr->family != AF_IEEE802154)
@@ -493,7 +494,8 @@ static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len)
 
 	ro->bound = 0;
 
-	if (len < sizeof(*addr))
+	err = ieee802154_sockaddr_check_size(addr, len);
+	if (err < 0)
 		goto out;
 
 	if (addr->family != AF_IEEE802154)
@@ -564,8 +566,9 @@ static int dgram_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct dgram_sock *ro = dgram_sk(sk);
 	int err = 0;
 
-	if (len < sizeof(*addr))
-		return -EINVAL;
+	err = ieee802154_sockaddr_check_size(addr, len);
+	if (err < 0)
+		return err;
 
 	if (addr->family != AF_IEEE802154)
 		return -EINVAL;
@@ -604,6 +607,7 @@ static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	struct ieee802154_mac_cb *cb;
 	struct dgram_sock *ro = dgram_sk(sk);
 	struct ieee802154_addr dst_addr;
+	DECLARE_SOCKADDR(struct sockaddr_ieee802154*, daddr, msg->msg_name);
 	int hlen, tlen;
 	int err;
 
@@ -612,10 +616,20 @@ static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 		return -EOPNOTSUPP;
 	}
 
-	if (!ro->connected && !msg->msg_name)
-		return -EDESTADDRREQ;
-	else if (ro->connected && msg->msg_name)
-		return -EISCONN;
+	if (msg->msg_name) {
+		if (ro->connected)
+			return -EISCONN;
+		if (msg->msg_namelen < IEEE802154_MIN_NAMELEN)
+			return -EINVAL;
+		err = ieee802154_sockaddr_check_size(daddr, msg->msg_namelen);
+		if (err < 0)
+			return err;
+		ieee802154_addr_from_sa(&dst_addr, &daddr->addr);
+	} else {
+		if (!ro->connected)
+			return -EDESTADDRREQ;
+		dst_addr = ro->dst_addr;
+	}
 
 	if (!ro->bound)
 		dev = dev_getfirstbyhwtype(sock_net(sk), ARPHRD_IEEE802154);
@@ -651,16 +665,6 @@ static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	cb = mac_cb_init(skb);
 	cb->type = IEEE802154_FC_TYPE_DATA;
 	cb->ackreq = ro->want_ack;
-
-	if (msg->msg_name) {
-		DECLARE_SOCKADDR(struct sockaddr_ieee802154*,
-				 daddr, msg->msg_name);
-
-		ieee802154_addr_from_sa(&dst_addr, &daddr->addr);
-	} else {
-		dst_addr = ro->dst_addr;
-	}
-
 	cb->secen = ro->secen;
 	cb->secen_override = ro->secen_override;
 	cb->seclevel = ro->seclevel;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 92b778e423df..e8b9a9202fec 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2682,23 +2682,27 @@ static __net_init int devinet_init_net(struct net *net)
 #endif
 
 	if (!net_eq(net, &init_net)) {
-		if (IS_ENABLED(CONFIG_SYSCTL) &&
-		    sysctl_devconf_inherit_init_net == 3) {
+		switch (net_inherit_devconf()) {
+		case 3:
 			/* copy from the current netns */
 			memcpy(all, current->nsproxy->net_ns->ipv4.devconf_all,
 			       sizeof(ipv4_devconf));
 			memcpy(dflt,
 			       current->nsproxy->net_ns->ipv4.devconf_dflt,
 			       sizeof(ipv4_devconf_dflt));
-		} else if (!IS_ENABLED(CONFIG_SYSCTL) ||
-			   sysctl_devconf_inherit_init_net != 2) {
-			/* inherit == 0 or 1: copy from init_net */
+			break;
+		case 0:
+		case 1:
+			/* copy from init_net */
 			memcpy(all, init_net.ipv4.devconf_all,
 			       sizeof(ipv4_devconf));
 			memcpy(dflt, init_net.ipv4.devconf_dflt,
 			       sizeof(ipv4_devconf_dflt));
+			break;
+		case 2:
+			/* use compiled values */
+			break;
 		}
-		/* else inherit == 2: use compiled values */
 	}
 
 #ifdef CONFIG_SYSCTL
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index f361d3d56be2..943edf4ad4db 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -389,7 +389,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	dev_match = dev_match || (res.type == RTN_LOCAL &&
 				  dev == net->loopback_dev);
 	if (dev_match) {
-		ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
+		ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK;
 		return ret;
 	}
 	if (no_addr)
@@ -401,7 +401,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	ret = 0;
 	if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) {
 		if (res.type == RTN_UNICAST)
-			ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
+			ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK;
 	}
 	return ret;
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 5c58e21f724e..f866d6282b2b 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -609,7 +609,7 @@ static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 	ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src,
 			    tunnel_id_to_key32(key->tun_id),
 			    key->tos & ~INET_ECN_MASK, dev_net(dev), 0,
-			    skb->mark, skb_get_hash(skb));
+			    skb->mark, skb_get_hash(skb), key->flow_flags);
 	rt = ip_route_output_key(dev_net(dev), &fl4);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index d7bd1daf022b..04e2034f2f8e 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1730,7 +1730,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
-	sk->sk_sndbuf = sysctl_wmem_default;
+	sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default);
 	ipc.sockc.mark = fl4.flowi4_mark;
 	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
 			     len, 0, &ipc, &rt, MSG_DONTWAIT);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index a8a323ecbb54..e49a61a053a6 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -772,7 +772,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen)
 
 	if (optlen < GROUP_FILTER_SIZE(0))
 		return -EINVAL;
-	if (optlen > sysctl_optmem_max)
+	if (optlen > READ_ONCE(sysctl_optmem_max))
 		return -ENOBUFS;
 
 	gsf = memdup_sockptr(optval, optlen);
@@ -808,7 +808,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < size0)
 		return -EINVAL;
-	if (optlen > sysctl_optmem_max - 4)
+	if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
 		return -ENOBUFS;
 
 	p = kmalloc(optlen + 4, GFP_KERNEL);
@@ -1233,7 +1233,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname,
 
 		if (optlen < IP_MSFILTER_SIZE(0))
 			goto e_inval;
-		if (optlen > sysctl_optmem_max) {
+		if (optlen > READ_ONCE(sysctl_optmem_max)) {
 			err = -ENOBUFS;
 			break;
 		}
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index e65e948cab9f..019f3b0839c5 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -295,7 +295,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 		ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr,
 				    iph->saddr, tunnel->parms.o_key,
 				    RT_TOS(iph->tos), dev_net(dev),
-				    tunnel->parms.link, tunnel->fwmark, 0);
+				    tunnel->parms.link, tunnel->fwmark, 0, 0);
 		rt = ip_route_output_key(tunnel->net, &fl4);
 
 		if (!IS_ERR(rt)) {
@@ -570,7 +570,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 	ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src,
 			    tunnel_id_to_key32(key->tun_id), RT_TOS(tos),
-			    dev_net(dev), 0, skb->mark, skb_get_hash(skb));
+			    dev_net(dev), 0, skb->mark, skb_get_hash(skb),
+			    key->flow_flags);
 	if (tunnel->encap.type != TUNNEL_ENCAP_NONE)
 		goto tx_error;
 
@@ -729,7 +730,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr,
 			    tunnel->parms.o_key, RT_TOS(tos),
 			    dev_net(dev), tunnel->parms.link,
-			    tunnel->fwmark, skb_get_hash(skb));
+			    tunnel->fwmark, skb_get_hash(skb), 0);
 
 	if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
 		goto tx_error;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 73651d17e51f..e11d6b0b62b7 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1004,7 +1004,9 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt,
 
 			rtnl_unicast(skb, net, NETLINK_CB(skb).portid);
 		} else {
+			rcu_read_lock();
 			ip_mr_forward(net, mrt, skb->dev, skb, c, 0);
+			rcu_read_unlock();
 		}
 	}
 }
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 970e9a2cca4a..e373dde1f46f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1000,7 +1000,7 @@ new_segment:
 
 	i = skb_shinfo(skb)->nr_frags;
 	can_coalesce = skb_can_coalesce(skb, i, page, offset);
-	if (!can_coalesce && i >= sysctl_max_skb_frags) {
+	if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) {
 		tcp_mark_push(tp, skb);
 		goto new_segment;
 	}
@@ -1015,7 +1015,7 @@ new_segment:
 		skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
 	} else {
 		get_page(page);
-		skb_fill_page_desc(skb, i, page, offset, copy);
+		skb_fill_page_desc_noacc(skb, i, page, offset, copy);
 	}
 
 	if (!(flags & MSG_NO_SHARED_FRAGS))
@@ -1354,7 +1354,7 @@ new_segment:
 
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
-				if (i >= sysctl_max_skb_frags) {
+				if (i >= READ_ONCE(sysctl_max_skb_frags)) {
 					tcp_mark_push(tp, skb);
 					goto new_segment;
 				}
@@ -1567,17 +1567,11 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
  * calculation of whether or not we must ACK for the sake of
  * a window update.
  */
-void tcp_cleanup_rbuf(struct sock *sk, int copied)
+static void __tcp_cleanup_rbuf(struct sock *sk, int copied)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool time_to_ack = false;
 
-	struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
-
-	WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq),
-	     "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",
-	     tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt);
-
 	if (inet_csk_ack_scheduled(sk)) {
 		const struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -1623,6 +1617,17 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied)
 		tcp_send_ack(sk);
 }
 
+void tcp_cleanup_rbuf(struct sock *sk, int copied)
+{
+	struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq),
+	     "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",
+	     tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt);
+	__tcp_cleanup_rbuf(sk, copied);
+}
+
 static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	__skb_unlink(skb, &sk->sk_receive_queue);
@@ -1757,11 +1762,15 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 		return -ENOTCONN;
 
 	while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) {
+		u8 tcp_flags;
 		int used;
 
 		__skb_unlink(skb, &sk->sk_receive_queue);
+		WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk));
+		tcp_flags = TCP_SKB_CB(skb)->tcp_flags;
 		used = recv_actor(sk, skb);
-		if (used <= 0) {
+		consume_skb(skb);
+		if (used < 0) {
 			if (!copied)
 				copied = used;
 			break;
@@ -1769,13 +1778,10 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 		seq += used;
 		copied += used;
 
-		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
-			consume_skb(skb);
+		if (tcp_flags & TCPHDR_FIN) {
 			++seq;
 			break;
 		}
-		consume_skb(skb);
-		break;
 	}
 	WRITE_ONCE(tp->copied_seq, seq);
 
@@ -1783,7 +1789,7 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 
 	/* Clean up data we have read: This will do ACK frames. */
 	if (copied > 0)
-		tcp_cleanup_rbuf(sk, copied);
+		__tcp_cleanup_rbuf(sk, copied);
 
 	return copied;
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ab5f0ea166f1..bc2ea12221f9 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2513,6 +2513,21 @@ static inline bool tcp_may_undo(const struct tcp_sock *tp)
 	return tp->undo_marker && (!tp->undo_retrans || tcp_packet_delayed(tp));
 }
 
+static bool tcp_is_non_sack_preventing_reopen(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
+		/* Hold old state until something *above* high_seq
+		 * is ACKed. For Reno it is MUST to prevent false
+		 * fast retransmits (RFC2582). SACK TCP is safe. */
+		if (!tcp_any_retrans_done(sk))
+			tp->retrans_stamp = 0;
+		return true;
+	}
+	return false;
+}
+
 /* People celebrate: "We love our President!" */
 static bool tcp_try_undo_recovery(struct sock *sk)
 {
@@ -2535,14 +2550,8 @@ static bool tcp_try_undo_recovery(struct sock *sk)
 	} else if (tp->rack.reo_wnd_persist) {
 		tp->rack.reo_wnd_persist--;
 	}
-	if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
-		/* Hold old state until something *above* high_seq
-		 * is ACKed. For Reno it is MUST to prevent false
-		 * fast retransmits (RFC2582). SACK TCP is safe. */
-		if (!tcp_any_retrans_done(sk))
-			tp->retrans_stamp = 0;
+	if (tcp_is_non_sack_preventing_reopen(sk))
 		return true;
-	}
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	return false;
@@ -2578,6 +2587,8 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
 			NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_TCPSPURIOUSRTOS);
 		inet_csk(sk)->icsk_retransmits = 0;
+		if (tcp_is_non_sack_preventing_reopen(sk))
+			return true;
 		if (frto_undo || tcp_is_sack(tp)) {
 			tcp_set_ca_state(sk, TCP_CA_Open);
 			tp->is_sack_reneg = 0;
@@ -3614,12 +3625,9 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb,
 /* RFC 5961 7 [ACK Throttling] */
 static void tcp_send_challenge_ack(struct sock *sk)
 {
-	/* unprotected vars, we dont care of overwrites */
-	static u32 challenge_timestamp;
-	static unsigned int challenge_count;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
-	u32 count, now;
+	u32 count, now, ack_limit;
 
 	/* First check our per-socket dupack rate limit. */
 	if (__tcp_oow_rate_limited(net,
@@ -3627,18 +3635,22 @@ static void tcp_send_challenge_ack(struct sock *sk)
 				   &tp->last_oow_ack_time))
 		return;
 
+	ack_limit = READ_ONCE(net->ipv4.sysctl_tcp_challenge_ack_limit);
+	if (ack_limit == INT_MAX)
+		goto send_ack;
+
 	/* Then check host-wide RFC 5961 rate limit. */
 	now = jiffies / HZ;
-	if (now != challenge_timestamp) {
-		u32 ack_limit = READ_ONCE(net->ipv4.sysctl_tcp_challenge_ack_limit);
+	if (now != READ_ONCE(net->ipv4.tcp_challenge_timestamp)) {
 		u32 half = (ack_limit + 1) >> 1;
 
-		challenge_timestamp = now;
-		WRITE_ONCE(challenge_count, half + prandom_u32_max(ack_limit));
+		WRITE_ONCE(net->ipv4.tcp_challenge_timestamp, now);
+		WRITE_ONCE(net->ipv4.tcp_challenge_count, half + prandom_u32_max(ack_limit));
 	}
-	count = READ_ONCE(challenge_count);
+	count = READ_ONCE(net->ipv4.tcp_challenge_count);
 	if (count > 0) {
-		WRITE_ONCE(challenge_count, count - 1);
+		WRITE_ONCE(net->ipv4.tcp_challenge_count, count - 1);
+send_ack:
 		NET_INC_STATS(net, LINUX_MIB_TCPCHALLENGEACK);
 		tcp_send_ack(sk);
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 0c83780dc9bf..5b019ba2b9d2 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3139,8 +3139,10 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_tso_win_divisor = 3;
 	/* Default TSQ limit of 16 TSO segments */
 	net->ipv4.sysctl_tcp_limit_output_bytes = 16 * 65536;
-	/* rfc5961 challenge ack rate limiting */
-	net->ipv4.sysctl_tcp_challenge_ack_limit = 1000;
+
+	/* rfc5961 challenge ack rate limiting, per net-ns, disabled by default. */
+	net->ipv4.sysctl_tcp_challenge_ack_limit = INT_MAX;
+
 	net->ipv4.sysctl_tcp_min_tso_segs = 2;
 	net->ipv4.sysctl_tcp_tso_rtt_log = 9;  /* 2^9 = 512 usec */
 	net->ipv4.sysctl_tcp_min_rtt_wlen = 300;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 78b654ff421b..290019de766d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -239,7 +239,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	if (wscale_ok) {
 		/* Set window scaling on max possible window */
 		space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
-		space = max_t(u32, space, sysctl_rmem_max);
+		space = max_t(u32, space, READ_ONCE(sysctl_rmem_max));
 		space = min_t(u32, space, *window_clamp);
 		*rcv_wscale = clamp_t(int, ilog2(space) - 15,
 				      0, TCP_MAX_WSCALE);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 34eda973bbf1..560d9eadeaa5 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -783,6 +783,8 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	 */
 	if (tunnel) {
 		/* ...not for tunnels though: we don't have a sending socket */
+		if (udp_sk(sk)->encap_err_rcv)
+			udp_sk(sk)->encap_err_rcv(sk, skb, iph->ihl << 2);
 		goto out;
 	}
 	if (!inet->recverr) {
@@ -1819,7 +1821,7 @@ int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 			continue;
 		}
 
-		WARN_ON(!skb_set_owner_sk_safe(skb, sk));
+		WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk));
 		used = recv_actor(sk, skb);
 		if (used <= 0) {
 			if (!copied)
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index 8efaf8c3fe2a..8242c8947340 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -72,6 +72,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 
 	udp_sk(sk)->encap_type = cfg->encap_type;
 	udp_sk(sk)->encap_rcv = cfg->encap_rcv;
+	udp_sk(sk)->encap_err_rcv = cfg->encap_err_rcv;
 	udp_sk(sk)->encap_err_lookup = cfg->encap_err_lookup;
 	udp_sk(sk)->encap_destroy = cfg->encap_destroy;
 	udp_sk(sk)->gro_receive = cfg->gro_receive;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index b624e3d8c5f0..10ce86bf228e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3557,11 +3557,15 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 		fallthrough;
 	case NETDEV_UP:
 	case NETDEV_CHANGE:
-		if (dev->flags & IFF_SLAVE)
+		if (idev && idev->cnf.disable_ipv6)
 			break;
 
-		if (idev && idev->cnf.disable_ipv6)
+		if (dev->flags & IFF_SLAVE) {
+			if (event == NETDEV_UP && !IS_ERR_OR_NULL(idev) &&
+			    dev->flags & IFF_UP && dev->flags & IFF_MULTICAST)
+				ipv6_mc_up(idev);
 			break;
+		}
 
 		if (event == NETDEV_UP) {
 			/* restore routes for permanent addresses */
@@ -7162,9 +7166,8 @@ static int __net_init addrconf_init_net(struct net *net)
 	if (!dflt)
 		goto err_alloc_dflt;
 
-	if (IS_ENABLED(CONFIG_SYSCTL) &&
-	    !net_eq(net, &init_net)) {
-		switch (sysctl_devconf_inherit_init_net) {
+	if (!net_eq(net, &init_net)) {
+		switch (net_inherit_devconf()) {
 		case 1:  /* copy from init_net */
 			memcpy(all, init_net.ipv6.devconf_all,
 			       sizeof(ipv6_devconf));
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 2ce0c44d0081..dbb1430d6cc2 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1070,13 +1070,13 @@ static int __init inet6_init(void)
 	for (r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r)
 		INIT_LIST_HEAD(r);
 
+	raw_hashinfo_init(&raw_v6_hashinfo);
+
 	if (disable_ipv6_mod) {
 		pr_info("Loaded, but administratively disabled, reboot required to enable\n");
 		goto out;
 	}
 
-	raw_hashinfo_init(&raw_v6_hashinfo);
-
 	err = proto_register(&tcpv6_prot, 1);
 	if (err)
 		goto out;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 3fda5634578c..79c6a827dea9 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1517,7 +1517,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
  *   ip6_tnl_change() updates the tunnel parameters
  **/
 
-static int
+static void
 ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
 {
 	t->parms.laddr = p->laddr;
@@ -1531,29 +1531,25 @@ ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
 	t->parms.fwmark = p->fwmark;
 	dst_cache_reset(&t->dst_cache);
 	ip6_tnl_link_config(t);
-	return 0;
 }
 
-static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
+static void ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
 {
 	struct net *net = t->net;
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
-	int err;
 
 	ip6_tnl_unlink(ip6n, t);
 	synchronize_net();
-	err = ip6_tnl_change(t, p);
+	ip6_tnl_change(t, p);
 	ip6_tnl_link(ip6n, t);
 	netdev_state_change(t->dev);
-	return err;
 }
 
-static int ip6_tnl0_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
+static void ip6_tnl0_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
 {
 	/* for default tnl0 device allow to change only the proto */
 	t->parms.proto = p->proto;
 	netdev_state_change(t->dev);
-	return 0;
 }
 
 static void
@@ -1667,9 +1663,9 @@ ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
 			} else
 				t = netdev_priv(dev);
 			if (dev == ip6n->fb_tnl_dev)
-				err = ip6_tnl0_update(t, &p1);
+				ip6_tnl0_update(t, &p1);
 			else
-				err = ip6_tnl_update(t, &p1);
+				ip6_tnl_update(t, &p1);
 		}
 		if (!IS_ERR(t)) {
 			err = 0;
@@ -2091,7 +2087,8 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
 	} else
 		t = netdev_priv(dev);
 
-	return ip6_tnl_update(t, &p);
+	ip6_tnl_update(t, &p);
+	return 0;
 }
 
 static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index a9ba41648e36..858fd8a28b5b 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1028,8 +1028,11 @@ static void ip6mr_cache_resolve(struct net *net, struct mr_table *mrt,
 				((struct nlmsgerr *)nlmsg_data(nlh))->error = -EMSGSIZE;
 			}
 			rtnl_unicast(skb, net, NETLINK_CB(skb).portid);
-		} else
+		} else {
+			rcu_read_lock();
 			ip6_mr_forward(net, mrt, skb->dev, skb, c);
+			rcu_read_unlock();
+		}
 	}
 }
 
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 222f6bf220ba..e0dcc7a193df 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -210,7 +210,7 @@ static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < GROUP_FILTER_SIZE(0))
 		return -EINVAL;
-	if (optlen > sysctl_optmem_max)
+	if (optlen > READ_ONCE(sysctl_optmem_max))
 		return -ENOBUFS;
 
 	gsf = memdup_sockptr(optval, optlen);
@@ -244,7 +244,7 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < size0)
 		return -EINVAL;
-	if (optlen > sysctl_optmem_max - 4)
+	if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
 		return -ENOBUFS;
 
 	p = kmalloc(optlen + 4, GFP_KERNEL);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 98453693e400..3a553494ff16 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1378,6 +1378,9 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 	if (!rt && lifetime) {
 		ND_PRINTK(3, info, "RA: adding default router\n");
 
+		if (neigh)
+			neigh_release(neigh);
+
 		rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr,
 					 skb->dev, pref, defrtr_usr_metric);
 		if (!rt) {
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 7dd3629dd19e..38db0064d661 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -86,7 +86,6 @@ static int nf_ct_frag6_sysctl_register(struct net *net)
 	table[1].extra2	= &nf_frag->fqdir->high_thresh;
 	table[2].data	= &nf_frag->fqdir->high_thresh;
 	table[2].extra1	= &nf_frag->fqdir->low_thresh;
-	table[2].extra2	= &nf_frag->fqdir->high_thresh;
 
 	hdr = register_net_sysctl(net, "net/netfilter", table);
 	if (hdr == NULL)
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index 73aaabf0e966..0b0e34ddc64e 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -191,6 +191,11 @@ static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info)
 		goto out_unlock;
 	}
 
+	if (slen > nla_len(info->attrs[SEG6_ATTR_SECRET])) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
+
 	if (hinfo) {
 		err = seg6_hmac_info_del(net, hmackeyid);
 		if (err)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 16c176e7c69a..3366d6a77ff2 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -616,8 +616,11 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	}
 
 	/* Tunnels don't have an application socket: don't pass errors back */
-	if (tunnel)
+	if (tunnel) {
+		if (udp_sk(sk)->encap_err_rcv)
+			udp_sk(sk)->encap_err_rcv(sk, skb, offset);
 		goto out;
+	}
 
 	if (!np->recverr) {
 		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 71899e5a5a11..1215c863e1c4 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1412,12 +1412,6 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 	psock->sk = csk;
 	psock->bpf_prog = prog;
 
-	err = strp_init(&psock->strp, csk, &cb);
-	if (err) {
-		kmem_cache_free(kcm_psockp, psock);
-		goto out;
-	}
-
 	write_lock_bh(&csk->sk_callback_lock);
 
 	/* Check if sk_user_data is already by KCM or someone else.
@@ -1425,13 +1419,18 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 	 */
 	if (csk->sk_user_data) {
 		write_unlock_bh(&csk->sk_callback_lock);
-		strp_stop(&psock->strp);
-		strp_done(&psock->strp);
 		kmem_cache_free(kcm_psockp, psock);
 		err = -EALREADY;
 		goto out;
 	}
 
+	err = strp_init(&psock->strp, csk, &cb);
+	if (err) {
+		write_unlock_bh(&csk->sk_callback_lock);
+		kmem_cache_free(kcm_psockp, psock);
+		goto out;
+	}
+
 	psock->save_data_ready = csk->sk_data_ready;
 	psock->save_write_space = csk->sk_write_space;
 	psock->save_state_change = csk->sk_state_change;
diff --git a/net/key/af_key.c b/net/key/af_key.c
index fda2dcc8a383..c85df5b958d2 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1697,9 +1697,12 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad
 		pfk->registered |= (1<<hdr->sadb_msg_satype);
 	}
 
+	mutex_lock(&pfkey_mutex);
 	xfrm_probe_algs();
 
 	supp_skb = compose_sadb_supported(hdr, GFP_KERNEL | __GFP_ZERO);
+	mutex_unlock(&pfkey_mutex);
+
 	if (!supp_skb) {
 		if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC)
 			pfk->registered &= ~(1<<hdr->sadb_msg_satype);
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index d56890e3fabb..9b283bbc7bb4 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -530,6 +530,10 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata)
 
 	sdata_assert_lock(sdata);
 
+	/* When not connected/joined, sending CSA doesn't make sense. */
+	if (ifibss->state != IEEE80211_IBSS_MLME_JOINED)
+		return -ENOLINK;
+
 	/* update cfg80211 bss information with the new channel */
 	if (!is_zero_ether_addr(ifibss->bssid)) {
 		cbss = cfg80211_get_bss(sdata->local->hw.wiphy,
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 3d4ab711f0d1..fc764984d687 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3420,11 +3420,11 @@ static void ieee80211_destroy_auth_data(struct ieee80211_sub_if_data *sdata,
 		ieee80211_link_info_change_notify(sdata, &sdata->deflink,
 						  BSS_CHANGED_BSSID);
 		sdata->u.mgd.flags = 0;
+
 		mutex_lock(&sdata->local->mtx);
 		ieee80211_link_release_channel(&sdata->deflink);
-		mutex_unlock(&sdata->local->mtx);
-
 		ieee80211_vif_set_links(sdata, 0);
+		mutex_unlock(&sdata->local->mtx);
 	}
 
 	cfg80211_put_bss(sdata->local->hw.wiphy, auth_data->bss);
@@ -3462,10 +3462,6 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata,
 		sdata->u.mgd.flags = 0;
 		sdata->vif.bss_conf.mu_mimo_owner = false;
 
-		mutex_lock(&sdata->local->mtx);
-		ieee80211_link_release_channel(&sdata->deflink);
-		mutex_unlock(&sdata->local->mtx);
-
 		if (status != ASSOC_REJECTED) {
 			struct cfg80211_assoc_failure data = {
 				.timeout = status == ASSOC_TIMEOUT,
@@ -3484,7 +3480,10 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata,
 			cfg80211_assoc_failure(sdata->dev, &data);
 		}
 
+		mutex_lock(&sdata->local->mtx);
+		ieee80211_link_release_channel(&sdata->deflink);
 		ieee80211_vif_set_links(sdata, 0);
+		mutex_unlock(&sdata->local->mtx);
 	}
 
 	kfree(assoc_data);
@@ -4041,7 +4040,6 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link,
 
 	if (!(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HE) &&
 	    (!elems->he_cap || !elems->he_operation)) {
-		mutex_unlock(&sdata->local->sta_mtx);
 		sdata_info(sdata,
 			   "HE AP is missing HE capability/operation\n");
 		ret = false;
@@ -5590,12 +5588,16 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link,
 
 	mutex_lock(&local->sta_mtx);
 	sta = sta_info_get(sdata, sdata->vif.cfg.ap_addr);
-	if (WARN_ON(!sta))
+	if (WARN_ON(!sta)) {
+		mutex_unlock(&local->sta_mtx);
 		goto free;
+	}
 	link_sta = rcu_dereference_protected(sta->link[link->link_id],
 					     lockdep_is_held(&local->sta_mtx));
-	if (WARN_ON(!link_sta))
+	if (WARN_ON(!link_sta)) {
+		mutex_unlock(&local->sta_mtx);
 		goto free;
+	}
 
 	changed |= ieee80211_recalc_twt_req(link, link_sta, elems);
 
@@ -6509,6 +6511,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
 	return 0;
 
 out_err:
+	ieee80211_link_release_channel(&sdata->deflink);
 	ieee80211_vif_set_links(sdata, 0);
 	return err;
 }
diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index 5f27e6746762..788a82f9c74d 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -10,6 +10,7 @@
 #include <linux/random.h>
 #include <linux/moduleparam.h>
 #include <linux/ieee80211.h>
+#include <linux/minmax.h>
 #include <net/mac80211.h>
 #include "rate.h"
 #include "sta_info.h"
@@ -1550,6 +1551,7 @@ minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi)
 {
 	struct ieee80211_sta_rates *rates;
 	int i = 0;
+	int max_rates = min_t(int, mp->hw->max_rates, IEEE80211_TX_RATE_TABLE_SIZE);
 
 	rates = kzalloc(sizeof(*rates), GFP_ATOMIC);
 	if (!rates)
@@ -1559,10 +1561,10 @@ minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi)
 	minstrel_ht_set_rate(mp, mi, rates, i++, mi->max_tp_rate[0]);
 
 	/* Fill up remaining, keep one entry for max_probe_rate */
-	for (; i < (mp->hw->max_rates - 1); i++)
+	for (; i < (max_rates - 1); i++)
 		minstrel_ht_set_rate(mp, mi, rates, i, mi->max_tp_rate[i]);
 
-	if (i < mp->hw->max_rates)
+	if (i < max_rates)
 		minstrel_ht_set_rate(mp, mi, rates, i++, mi->max_prob_rate);
 
 	if (i < IEEE80211_TX_RATE_TABLE_SIZE)
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 57df21e2170a..45d7e71661e3 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -4074,6 +4074,7 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid)
 		.link_id = -1,
 	};
 	struct tid_ampdu_rx *tid_agg_rx;
+	u8 link_id;
 
 	tid_agg_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[tid]);
 	if (!tid_agg_rx)
@@ -4093,6 +4094,9 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid)
 		};
 		drv_event_callback(rx.local, rx.sdata, &event);
 	}
+	/* FIXME: statistics won't be right with this */
+	link_id = sta->sta.valid_links ? ffs(sta->sta.valid_links) - 1 : 0;
+	rx.link = rcu_dereference(sta->sdata->link[link_id]);
 
 	ieee80211_rx_handlers(&rx, &frames);
 }
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index fa8ddf576bc1..c4f2aeb31da3 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -469,16 +469,19 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
 	scan_req = rcu_dereference_protected(local->scan_req,
 					     lockdep_is_held(&local->mtx));
 
-	if (scan_req != local->int_scan_req) {
-		local->scan_info.aborted = aborted;
-		cfg80211_scan_done(scan_req, &local->scan_info);
-	}
 	RCU_INIT_POINTER(local->scan_req, NULL);
 	RCU_INIT_POINTER(local->scan_sdata, NULL);
 
 	local->scanning = 0;
 	local->scan_chandef.chan = NULL;
 
+	synchronize_rcu();
+
+	if (scan_req != local->int_scan_req) {
+		local->scan_info.aborted = aborted;
+		cfg80211_scan_done(scan_req, &local->scan_info);
+	}
+
 	/* Set power back to normal operating levels. */
 	ieee80211_hw_config(local, 0);
 
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index cb23da9aff1e..58998d821778 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -494,7 +494,7 @@ __sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 	sta->sdata = sdata;
 
 	if (sta_info_alloc_link(local, &sta->deflink, gfp))
-		return NULL;
+		goto free;
 
 	if (link_id >= 0) {
 		sta_info_add_link(sta, link_id, &sta->deflink,
@@ -2316,9 +2316,9 @@ static inline u64 sta_get_tidstats_msdu(struct ieee80211_sta_rx_stats *rxstats,
 	u64 value;
 
 	do {
-		start = u64_stats_fetch_begin(&rxstats->syncp);
+		start = u64_stats_fetch_begin_irq(&rxstats->syncp);
 		value = rxstats->msdu[tid];
-	} while (u64_stats_fetch_retry(&rxstats->syncp, start));
+	} while (u64_stats_fetch_retry_irq(&rxstats->syncp, start));
 
 	return value;
 }
@@ -2384,9 +2384,9 @@ static inline u64 sta_get_stats_bytes(struct ieee80211_sta_rx_stats *rxstats)
 	u64 value;
 
 	do {
-		start = u64_stats_fetch_begin(&rxstats->syncp);
+		start = u64_stats_fetch_begin_irq(&rxstats->syncp);
 		value = rxstats->bytes;
-	} while (u64_stats_fetch_retry(&rxstats->syncp, start));
+	} while (u64_stats_fetch_retry_irq(&rxstats->syncp, start));
 
 	return value;
 }
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 8e77fd2e9fdf..3f9ddd7f04b6 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -729,7 +729,7 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local,
 
 		if (!sdata) {
 			skb->dev = NULL;
-		} else {
+		} else if (!dropped) {
 			unsigned int hdr_size =
 				ieee80211_hdrlen(hdr->frame_control);
 
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 45df9932d0ba..13249e97a069 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -5878,6 +5878,9 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev,
 	skb_reset_network_header(skb);
 	skb_reset_mac_header(skb);
 
+	if (local->hw.queues < IEEE80211_NUM_ACS)
+		goto start_xmit;
+
 	/* update QoS header to prioritize control port frames if possible,
 	 * priorization also happens for control port frames send over
 	 * AF_PACKET
@@ -5885,6 +5888,7 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev,
 	rcu_read_lock();
 	err = ieee80211_lookup_ra_sta(sdata, skb, &sta);
 	if (err) {
+		dev_kfree_skb(skb);
 		rcu_read_unlock();
 		return err;
 	}
@@ -5899,11 +5903,12 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev,
 		 * for MLO STA, the SA should be the AP MLD address, but
 		 * the link ID has been selected already
 		 */
-		if (sta->sta.mlo)
+		if (sta && sta->sta.mlo)
 			memcpy(ehdr->h_source, sdata->vif.addr, ETH_ALEN);
 	}
 	rcu_read_unlock();
 
+start_xmit:
 	/* mutex lock is only needed for incrementing the cookie counter */
 	mutex_lock(&local->mtx);
 
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 53826c663723..efcefb2dd882 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -301,14 +301,14 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac)
 	local_bh_disable();
 	spin_lock(&fq->lock);
 
+	sdata->vif.txqs_stopped[ac] = false;
+
 	if (!test_bit(SDATA_STATE_RUNNING, &sdata->state))
 		goto out;
 
 	if (sdata->vif.type == NL80211_IFTYPE_AP)
 		ps = &sdata->bss->ps;
 
-	sdata->vif.txqs_stopped[ac] = false;
-
 	list_for_each_entry_rcu(sta, &local->sta_list, list) {
 		if (sdata != sta->sdata)
 			continue;
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index 93ec2f349748..20f742b5503b 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -351,7 +351,7 @@ static u8 ccmp_gcmp_aad(struct sk_buff *skb, u8 *aad)
 	 * FC | A1 | A2 | A3 | SC | [A4] | [QC] */
 	put_unaligned_be16(len_a, &aad[0]);
 	put_unaligned(mask_fc, (__le16 *)&aad[2]);
-	memcpy(&aad[4], &hdr->addr1, 3 * ETH_ALEN);
+	memcpy(&aad[4], &hdr->addrs, 3 * ETH_ALEN);
 
 	/* Mask Seq#, leave Frag# */
 	aad[22] = *((u8 *) &hdr->seq_ctrl) & 0x0f;
@@ -792,7 +792,7 @@ static void bip_aad(struct sk_buff *skb, u8 *aad)
 				IEEE80211_FCTL_MOREDATA);
 	put_unaligned(mask_fc, (__le16 *) &aad[0]);
 	/* A1 || A2 || A3 */
-	memcpy(aad + 2, &hdr->addr1, 3 * ETH_ALEN);
+	memcpy(aad + 2, &hdr->addrs, 3 * ETH_ALEN);
 }
 
 
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index b8ce84618a55..c439125ef2b9 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -44,7 +44,7 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata,
 
 	switch (mac_cb(skb)->dest.mode) {
 	case IEEE802154_ADDR_NONE:
-		if (mac_cb(skb)->dest.mode != IEEE802154_ADDR_NONE)
+		if (hdr->source.mode != IEEE802154_ADDR_NONE)
 			/* FIXME: check if we are PAN coordinator */
 			skb->pkt_type = PACKET_OTHERHOST;
 		else
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 35b5f806fdda..b52afe316dc4 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1079,9 +1079,9 @@ static void mpls_get_stats(struct mpls_dev *mdev,
 
 		p = per_cpu_ptr(mdev->stats, i);
 		do {
-			start = u64_stats_fetch_begin(&p->syncp);
+			start = u64_stats_fetch_begin_irq(&p->syncp);
 			local = p->stats;
-		} while (u64_stats_fetch_retry(&p->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&p->syncp, start));
 
 		stats->rx_packets	+= local.rx_packets;
 		stats->rx_bytes		+= local.rx_bytes;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index da4257504fad..f8897a70c11d 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -150,9 +150,15 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
 		 MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq,
 		 to->len, MPTCP_SKB_CB(from)->end_seq);
 	MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq;
-	kfree_skb_partial(from, fragstolen);
+
+	/* note the fwd memory can reach a negative value after accounting
+	 * for the delta, but the later skb free will restore a non
+	 * negative one
+	 */
 	atomic_add(delta, &sk->sk_rmem_alloc);
 	mptcp_rmem_charge(sk, delta);
+	kfree_skb_partial(from, fragstolen);
+
 	return true;
 }
 
@@ -1263,7 +1269,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 
 		i = skb_shinfo(skb)->nr_frags;
 		can_coalesce = skb_can_coalesce(skb, i, dfrag->page, offset);
-		if (!can_coalesce && i >= sysctl_max_skb_frags) {
+		if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) {
 			tcp_mark_push(tcp_sk(ssk), skb);
 			goto alloc_skb;
 		}
@@ -2656,7 +2662,7 @@ static void __mptcp_clear_xmit(struct sock *sk)
 		dfrag_clear(sk, dfrag);
 }
 
-static void mptcp_cancel_work(struct sock *sk)
+void mptcp_cancel_work(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
@@ -2796,13 +2802,12 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	sock_put(sk);
 }
 
-static void mptcp_close(struct sock *sk, long timeout)
+bool __mptcp_close(struct sock *sk, long timeout)
 {
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	bool do_cancel_work = false;
 
-	lock_sock(sk);
 	sk->sk_shutdown = SHUTDOWN_MASK;
 
 	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
@@ -2844,6 +2849,17 @@ cleanup:
 	} else {
 		mptcp_reset_timeout(msk, 0);
 	}
+
+	return do_cancel_work;
+}
+
+static void mptcp_close(struct sock *sk, long timeout)
+{
+	bool do_cancel_work;
+
+	lock_sock(sk);
+
+	do_cancel_work = __mptcp_close(sk, timeout);
 	release_sock(sk);
 	if (do_cancel_work)
 		mptcp_cancel_work(sk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 132d50833df1..8f372b8f059c 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -612,6 +612,8 @@ void mptcp_subflow_reset(struct sock *ssk);
 void mptcp_subflow_queue_clean(struct sock *ssk);
 void mptcp_sock_graft(struct sock *sk, struct socket *parent);
 struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);
+bool __mptcp_close(struct sock *sk, long timeout);
+void mptcp_cancel_work(struct sock *sk);
 
 bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
 			   const struct mptcp_addr_info *b, bool use_port);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index c7d49fb6e7bd..07dd23d0fe04 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -602,30 +602,6 @@ static bool subflow_hmac_valid(const struct request_sock *req,
 	return !crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN);
 }
 
-static void mptcp_sock_destruct(struct sock *sk)
-{
-	/* if new mptcp socket isn't accepted, it is free'd
-	 * from the tcp listener sockets request queue, linked
-	 * from req->sk.  The tcp socket is released.
-	 * This calls the ULP release function which will
-	 * also remove the mptcp socket, via
-	 * sock_put(ctx->conn).
-	 *
-	 * Problem is that the mptcp socket will be in
-	 * ESTABLISHED state and will not have the SOCK_DEAD flag.
-	 * Both result in warnings from inet_sock_destruct.
-	 */
-	if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
-		sk->sk_state = TCP_CLOSE;
-		WARN_ON_ONCE(sk->sk_socket);
-		sock_orphan(sk);
-	}
-
-	/* We don't need to clear msk->subflow, as it's still NULL at this point */
-	mptcp_destroy_common(mptcp_sk(sk), 0);
-	inet_sock_destruct(sk);
-}
-
 static void mptcp_force_close(struct sock *sk)
 {
 	/* the msk is not yet exposed to user-space */
@@ -768,7 +744,6 @@ create_child:
 			/* new mpc subflow takes ownership of the newly
 			 * created mptcp socket
 			 */
-			new_msk->sk_destruct = mptcp_sock_destruct;
 			mptcp_sk(new_msk)->setsockopt_seq = ctx->setsockopt_seq;
 			mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1);
 			mptcp_token_accept(subflow_req, mptcp_sk(new_msk));
@@ -1763,13 +1738,19 @@ void mptcp_subflow_queue_clean(struct sock *listener_ssk)
 
 	for (msk = head; msk; msk = next) {
 		struct sock *sk = (struct sock *)msk;
-		bool slow;
+		bool slow, do_cancel_work;
 
+		sock_hold(sk);
 		slow = lock_sock_fast_nested(sk);
 		next = msk->dl_next;
 		msk->first = NULL;
 		msk->dl_next = NULL;
+
+		do_cancel_work = __mptcp_close(sk, 0);
 		unlock_sock_fast(sk, slow);
+		if (do_cancel_work)
+			mptcp_cancel_work(sk);
+		sock_put(sk);
 	}
 
 	/* we are still under the listener msk socket lock */
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 22f15ebf6045..4b8d04640ff3 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -144,7 +144,6 @@ config NF_CONNTRACK_ZONES
 
 config NF_CONNTRACK_PROCFS
 	bool "Supply CT list in procfs (OBSOLETE)"
-	default y
 	depends on PROC_FS
 	help
 	This option enables for the list of known conntrack entries
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 9d43277b8b4f..a56fd0b5a430 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1280,12 +1280,12 @@ static void set_sock_size(struct sock *sk, int mode, int val)
 	lock_sock(sk);
 	if (mode) {
 		val = clamp_t(int, val, (SOCK_MIN_SNDBUF + 1) / 2,
-			      sysctl_wmem_max);
+			      READ_ONCE(sysctl_wmem_max));
 		sk->sk_sndbuf = val * 2;
 		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
 	} else {
 		val = clamp_t(int, val, (SOCK_MIN_RCVBUF + 1) / 2,
-			      sysctl_rmem_max);
+			      READ_ONCE(sysctl_rmem_max));
 		sk->sk_rcvbuf = val * 2;
 		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
 	}
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 71c2f4f95d36..1357a2729a4b 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1782,7 +1782,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 		}
 		spin_unlock_bh(&nf_conntrack_expect_lock);
 	}
-	if (!exp)
+	if (!exp && tmpl)
 		__nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC);
 
 	/* Other CPU might have obtained a pointer to this object before it was
@@ -2068,10 +2068,6 @@ void nf_conntrack_alter_reply(struct nf_conn *ct,
 	ct->tuplehash[IP_CT_DIR_REPLY].tuple = *newreply;
 	if (ct->master || (help && !hlist_empty(&help->expectations)))
 		return;
-
-	rcu_read_lock();
-	__nf_ct_try_assign_helper(ct, NULL, GFP_ATOMIC);
-	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_alter_reply);
 
@@ -2797,7 +2793,6 @@ int nf_conntrack_init_net(struct net *net)
 	nf_conntrack_acct_pernet_init(net);
 	nf_conntrack_tstamp_pernet_init(net);
 	nf_conntrack_ecache_pernet_init(net);
-	nf_conntrack_helper_pernet_init(net);
 	nf_conntrack_proto_pernet_init(net);
 
 	return 0;
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index a414274338cf..617f744a2e3a 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -33,10 +33,6 @@ MODULE_AUTHOR("Rusty Russell <rusty@rustcorp.com.au>");
 MODULE_DESCRIPTION("ftp connection tracking helper");
 MODULE_ALIAS("ip_conntrack_ftp");
 MODULE_ALIAS_NFCT_HELPER(HELPER_NAME);
-
-/* This is slow, but it's simple. --RR */
-static char *ftp_buffer;
-
 static DEFINE_SPINLOCK(nf_ftp_lock);
 
 #define MAX_PORTS 8
@@ -398,6 +394,9 @@ static int help(struct sk_buff *skb,
 		return NF_ACCEPT;
 	}
 
+	if (unlikely(skb_linearize(skb)))
+		return NF_DROP;
+
 	th = skb_header_pointer(skb, protoff, sizeof(_tcph), &_tcph);
 	if (th == NULL)
 		return NF_ACCEPT;
@@ -411,12 +410,9 @@ static int help(struct sk_buff *skb,
 	}
 	datalen = skb->len - dataoff;
 
+	/* seqadj (nat) uses ct->lock internally, nf_nat_ftp would cause deadlock */
 	spin_lock_bh(&nf_ftp_lock);
-	fb_ptr = skb_header_pointer(skb, dataoff, datalen, ftp_buffer);
-	if (!fb_ptr) {
-		spin_unlock_bh(&nf_ftp_lock);
-		return NF_ACCEPT;
-	}
+	fb_ptr = skb->data + dataoff;
 
 	ends_in_nl = (fb_ptr[datalen - 1] == '\n');
 	seq = ntohl(th->seq) + datalen;
@@ -571,7 +567,6 @@ static const struct nf_conntrack_expect_policy ftp_exp_policy = {
 static void __exit nf_conntrack_ftp_fini(void)
 {
 	nf_conntrack_helpers_unregister(ftp, ports_c * 2);
-	kfree(ftp_buffer);
 }
 
 static int __init nf_conntrack_ftp_init(void)
@@ -580,10 +575,6 @@ static int __init nf_conntrack_ftp_init(void)
 
 	NF_CT_HELPER_BUILD_BUG_ON(sizeof(struct nf_ct_ftp_master));
 
-	ftp_buffer = kmalloc(65536, GFP_KERNEL);
-	if (!ftp_buffer)
-		return -ENOMEM;
-
 	if (ports_c == 0)
 		ports[ports_c++] = FTP_PORT;
 
@@ -603,7 +594,6 @@ static int __init nf_conntrack_ftp_init(void)
 	ret = nf_conntrack_helpers_register(ftp, ports_c * 2);
 	if (ret < 0) {
 		pr_err("failed to register helpers\n");
-		kfree(ftp_buffer);
 		return ret;
 	}
 
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index bb76305bb7ff..5a9bce24f3c3 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -34,6 +34,8 @@
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <linux/netfilter/nf_conntrack_h323.h>
 
+#define H323_MAX_SIZE 65535
+
 /* Parameters */
 static unsigned int default_rrq_ttl __read_mostly = 300;
 module_param(default_rrq_ttl, uint, 0600);
@@ -86,6 +88,9 @@ static int get_tpkt_data(struct sk_buff *skb, unsigned int protoff,
 	if (tcpdatalen <= 0)	/* No TCP data */
 		goto clear_out;
 
+	if (tcpdatalen > H323_MAX_SIZE)
+		tcpdatalen = H323_MAX_SIZE;
+
 	if (*data == NULL) {	/* first TPKT */
 		/* Get first TPKT pointer */
 		tpkt = skb_header_pointer(skb, tcpdataoff, tcpdatalen,
@@ -1169,6 +1174,9 @@ static unsigned char *get_udp_data(struct sk_buff *skb, unsigned int protoff,
 	if (dataoff >= skb->len)
 		return NULL;
 	*datalen = skb->len - dataoff;
+	if (*datalen > H323_MAX_SIZE)
+		*datalen = H323_MAX_SIZE;
+
 	return skb_header_pointer(skb, dataoff, *datalen, h323_buffer);
 }
 
@@ -1770,7 +1778,7 @@ static int __init nf_conntrack_h323_init(void)
 
 	NF_CT_HELPER_BUILD_BUG_ON(sizeof(struct nf_ct_h323_master));
 
-	h323_buffer = kmalloc(65536, GFP_KERNEL);
+	h323_buffer = kmalloc(H323_MAX_SIZE + 1, GFP_KERNEL);
 	if (!h323_buffer)
 		return -ENOMEM;
 	ret = h323_helper_init();
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index e96b32221444..ff737a76052e 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -35,11 +35,6 @@ unsigned int nf_ct_helper_hsize __read_mostly;
 EXPORT_SYMBOL_GPL(nf_ct_helper_hsize);
 static unsigned int nf_ct_helper_count __read_mostly;
 
-static bool nf_ct_auto_assign_helper __read_mostly = false;
-module_param_named(nf_conntrack_helper, nf_ct_auto_assign_helper, bool, 0644);
-MODULE_PARM_DESC(nf_conntrack_helper,
-		 "Enable automatic conntrack helper assignment (default 0)");
-
 static DEFINE_MUTEX(nf_ct_nat_helpers_mutex);
 static struct list_head nf_ct_nat_helpers __read_mostly;
 
@@ -51,24 +46,6 @@ static unsigned int helper_hash(const struct nf_conntrack_tuple *tuple)
 		(__force __u16)tuple->src.u.all) % nf_ct_helper_hsize;
 }
 
-static struct nf_conntrack_helper *
-__nf_ct_helper_find(const struct nf_conntrack_tuple *tuple)
-{
-	struct nf_conntrack_helper *helper;
-	struct nf_conntrack_tuple_mask mask = { .src.u.all = htons(0xFFFF) };
-	unsigned int h;
-
-	if (!nf_ct_helper_count)
-		return NULL;
-
-	h = helper_hash(tuple);
-	hlist_for_each_entry_rcu(helper, &nf_ct_helper_hash[h], hnode) {
-		if (nf_ct_tuple_src_mask_cmp(tuple, &helper->tuple, &mask))
-			return helper;
-	}
-	return NULL;
-}
-
 struct nf_conntrack_helper *
 __nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum)
 {
@@ -209,33 +186,11 @@ nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp)
 }
 EXPORT_SYMBOL_GPL(nf_ct_helper_ext_add);
 
-static struct nf_conntrack_helper *
-nf_ct_lookup_helper(struct nf_conn *ct, struct net *net)
-{
-	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
-
-	if (!cnet->sysctl_auto_assign_helper) {
-		if (cnet->auto_assign_helper_warned)
-			return NULL;
-		if (!__nf_ct_helper_find(&ct->tuplehash[IP_CT_DIR_REPLY].tuple))
-			return NULL;
-		pr_info("nf_conntrack: default automatic helper assignment "
-			"has been turned off for security reasons and CT-based "
-			"firewall rule not found. Use the iptables CT target "
-			"to attach helpers instead.\n");
-		cnet->auto_assign_helper_warned = true;
-		return NULL;
-	}
-
-	return __nf_ct_helper_find(&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
-}
-
 int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
 			      gfp_t flags)
 {
 	struct nf_conntrack_helper *helper = NULL;
 	struct nf_conn_help *help;
-	struct net *net = nf_ct_net(ct);
 
 	/* We already got a helper explicitly attached. The function
 	 * nf_conntrack_alter_reply - in case NAT is in use - asks for looking
@@ -246,23 +201,21 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
 	if (test_bit(IPS_HELPER_BIT, &ct->status))
 		return 0;
 
-	if (tmpl != NULL) {
-		help = nfct_help(tmpl);
-		if (help != NULL) {
-			helper = rcu_dereference(help->helper);
-			set_bit(IPS_HELPER_BIT, &ct->status);
-		}
+	if (WARN_ON_ONCE(!tmpl))
+		return 0;
+
+	help = nfct_help(tmpl);
+	if (help != NULL) {
+		helper = rcu_dereference(help->helper);
+		set_bit(IPS_HELPER_BIT, &ct->status);
 	}
 
 	help = nfct_help(ct);
 
 	if (helper == NULL) {
-		helper = nf_ct_lookup_helper(ct, net);
-		if (helper == NULL) {
-			if (help)
-				RCU_INIT_POINTER(help->helper, NULL);
-			return 0;
-		}
+		if (help)
+			RCU_INIT_POINTER(help->helper, NULL);
+		return 0;
 	}
 
 	if (help == NULL) {
@@ -545,19 +498,6 @@ void nf_nat_helper_unregister(struct nf_conntrack_nat_helper *nat)
 }
 EXPORT_SYMBOL_GPL(nf_nat_helper_unregister);
 
-void nf_ct_set_auto_assign_helper_warned(struct net *net)
-{
-	nf_ct_pernet(net)->auto_assign_helper_warned = true;
-}
-EXPORT_SYMBOL_GPL(nf_ct_set_auto_assign_helper_warned);
-
-void nf_conntrack_helper_pernet_init(struct net *net)
-{
-	struct nf_conntrack_net *cnet = nf_ct_pernet(net);
-
-	cnet->sysctl_auto_assign_helper = nf_ct_auto_assign_helper;
-}
-
 int nf_conntrack_helper_init(void)
 {
 	nf_ct_helper_hsize = 1; /* gets rounded up to use one page */
diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c
index 08ee4e760a3d..5703846bea3b 100644
--- a/net/netfilter/nf_conntrack_irc.c
+++ b/net/netfilter/nf_conntrack_irc.c
@@ -39,6 +39,7 @@ unsigned int (*nf_nat_irc_hook)(struct sk_buff *skb,
 EXPORT_SYMBOL_GPL(nf_nat_irc_hook);
 
 #define HELPER_NAME "irc"
+#define MAX_SEARCH_SIZE	4095
 
 MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
 MODULE_DESCRIPTION("IRC (DCC) connection tracking helper");
@@ -121,6 +122,7 @@ static int help(struct sk_buff *skb, unsigned int protoff,
 	int i, ret = NF_ACCEPT;
 	char *addr_beg_p, *addr_end_p;
 	typeof(nf_nat_irc_hook) nf_nat_irc;
+	unsigned int datalen;
 
 	/* If packet is coming from IRC server */
 	if (dir == IP_CT_DIR_REPLY)
@@ -140,8 +142,12 @@ static int help(struct sk_buff *skb, unsigned int protoff,
 	if (dataoff >= skb->len)
 		return NF_ACCEPT;
 
+	datalen = skb->len - dataoff;
+	if (datalen > MAX_SEARCH_SIZE)
+		datalen = MAX_SEARCH_SIZE;
+
 	spin_lock_bh(&irc_buffer_lock);
-	ib_ptr = skb_header_pointer(skb, dataoff, skb->len - dataoff,
+	ib_ptr = skb_header_pointer(skb, dataoff, datalen,
 				    irc_buffer);
 	if (!ib_ptr) {
 		spin_unlock_bh(&irc_buffer_lock);
@@ -149,17 +155,39 @@ static int help(struct sk_buff *skb, unsigned int protoff,
 	}
 
 	data = ib_ptr;
-	data_limit = ib_ptr + skb->len - dataoff;
+	data_limit = ib_ptr + datalen;
+
+	/* Skip any whitespace */
+	while (data < data_limit - 10) {
+		if (*data == ' ' || *data == '\r' || *data == '\n')
+			data++;
+		else
+			break;
+	}
 
-	/* strlen("\1DCC SENT t AAAAAAAA P\1\n")=24
-	 * 5+MINMATCHLEN+strlen("t AAAAAAAA P\1\n")=14 */
-	while (data < data_limit - (19 + MINMATCHLEN)) {
-		if (memcmp(data, "\1DCC ", 5)) {
+	/* strlen("PRIVMSG x ")=10 */
+	if (data < data_limit - 10) {
+		if (strncasecmp("PRIVMSG ", data, 8))
+			goto out;
+		data += 8;
+	}
+
+	/* strlen(" :\1DCC SENT t AAAAAAAA P\1\n")=26
+	 * 7+MINMATCHLEN+strlen("t AAAAAAAA P\1\n")=26
+	 */
+	while (data < data_limit - (21 + MINMATCHLEN)) {
+		/* Find first " :", the start of message */
+		if (memcmp(data, " :", 2)) {
 			data++;
 			continue;
 		}
+		data += 2;
+
+		/* then check that place only for the DCC command */
+		if (memcmp(data, "\1DCC ", 5))
+			goto out;
 		data += 5;
-		/* we have at least (19+MINMATCHLEN)-5 bytes valid data left */
+		/* we have at least (21+MINMATCHLEN)-(2+5) bytes valid data left */
 
 		iph = ip_hdr(skb);
 		pr_debug("DCC found in master %pI4:%u %pI4:%u\n",
@@ -175,7 +203,7 @@ static int help(struct sk_buff *skb, unsigned int protoff,
 			pr_debug("DCC %s detected\n", dccprotos[i]);
 
 			/* we have at least
-			 * (19+MINMATCHLEN)-5-dccprotos[i].matchlen bytes valid
+			 * (21+MINMATCHLEN)-7-dccprotos[i].matchlen bytes valid
 			 * data left (== 14/13 bytes) */
 			if (parse_dcc(data, data_limit, &dcc_ip,
 				       &dcc_port, &addr_beg_p, &addr_end_p)) {
@@ -188,8 +216,9 @@ static int help(struct sk_buff *skb, unsigned int protoff,
 
 			/* dcc_ip can be the internal OR external (NAT'ed) IP */
 			tuple = &ct->tuplehash[dir].tuple;
-			if (tuple->src.u3.ip != dcc_ip &&
-			    tuple->dst.u3.ip != dcc_ip) {
+			if ((tuple->src.u3.ip != dcc_ip &&
+			     ct->tuplehash[!dir].tuple.dst.u3.ip != dcc_ip) ||
+			    dcc_port == 0) {
 				net_warn_ratelimited("Forged DCC command from %pI4: %pI4:%u\n",
 						     &tuple->src.u3.ip,
 						     &dcc_ip, dcc_port);
@@ -251,7 +280,7 @@ static int __init nf_conntrack_irc_init(void)
 	irc_exp_policy.max_expected = max_dcc_channels;
 	irc_exp_policy.timeout = dcc_timeout;
 
-	irc_buffer = kmalloc(65536, GFP_KERNEL);
+	irc_buffer = kmalloc(MAX_SEARCH_SIZE + 1, GFP_KERNEL);
 	if (!irc_buffer)
 		return -ENOMEM;
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 04169b54f2a2..7562b215b932 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2298,11 +2298,6 @@ ctnetlink_create_conntrack(struct net *net,
 			ct->status |= IPS_HELPER;
 			RCU_INIT_POINTER(help->helper, helper);
 		}
-	} else {
-		/* try an implicit helper assignation */
-		err = __nf_ct_try_assign_helper(ct, NULL, GFP_ATOMIC);
-		if (err < 0)
-			goto err2;
 	}
 
 	err = ctnetlink_setup_nat(ct, cda);
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index a63b51dceaf2..a634c72b1ffc 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -655,6 +655,37 @@ static bool tcp_in_window(struct nf_conn *ct,
 		    tn->tcp_be_liberal)
 			res = true;
 		if (!res) {
+			bool seq_ok = before(seq, sender->td_maxend + 1);
+
+			if (!seq_ok) {
+				u32 overshot = end - sender->td_maxend + 1;
+				bool ack_ok;
+
+				ack_ok = after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1);
+
+				if (in_recv_win &&
+				    ack_ok &&
+				    overshot <= receiver->td_maxwin &&
+				    before(sack, receiver->td_end + 1)) {
+					/* Work around TCPs that send more bytes than allowed by
+					 * the receive window.
+					 *
+					 * If the (marked as invalid) packet is allowed to pass by
+					 * the ruleset and the peer acks this data, then its possible
+					 * all future packets will trigger 'ACK is over upper bound' check.
+					 *
+					 * Thus if only the sequence check fails then do update td_end so
+					 * possible ACK for this data can update internal state.
+					 */
+					sender->td_end = end;
+					sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;
+
+					nf_ct_l4proto_log_invalid(skb, ct, hook_state,
+								  "%u bytes more than expected", overshot);
+					return res;
+				}
+			}
+
 			nf_ct_l4proto_log_invalid(skb, ct, hook_state,
 			"%s",
 			before(seq, sender->td_maxend + 1) ?
diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c
index fcb33b1d5456..13dc421fc4f5 100644
--- a/net/netfilter/nf_conntrack_sane.c
+++ b/net/netfilter/nf_conntrack_sane.c
@@ -34,10 +34,6 @@ MODULE_AUTHOR("Michal Schmidt <mschmidt@redhat.com>");
 MODULE_DESCRIPTION("SANE connection tracking helper");
 MODULE_ALIAS_NFCT_HELPER(HELPER_NAME);
 
-static char *sane_buffer;
-
-static DEFINE_SPINLOCK(nf_sane_lock);
-
 #define MAX_PORTS 8
 static u_int16_t ports[MAX_PORTS];
 static unsigned int ports_c;
@@ -67,14 +63,16 @@ static int help(struct sk_buff *skb,
 	unsigned int dataoff, datalen;
 	const struct tcphdr *th;
 	struct tcphdr _tcph;
-	void *sb_ptr;
 	int ret = NF_ACCEPT;
 	int dir = CTINFO2DIR(ctinfo);
 	struct nf_ct_sane_master *ct_sane_info = nfct_help_data(ct);
 	struct nf_conntrack_expect *exp;
 	struct nf_conntrack_tuple *tuple;
-	struct sane_request *req;
 	struct sane_reply_net_start *reply;
+	union {
+		struct sane_request req;
+		struct sane_reply_net_start repl;
+	} buf;
 
 	/* Until there's been traffic both ways, don't look in packets. */
 	if (ctinfo != IP_CT_ESTABLISHED &&
@@ -92,59 +90,62 @@ static int help(struct sk_buff *skb,
 		return NF_ACCEPT;
 
 	datalen = skb->len - dataoff;
-
-	spin_lock_bh(&nf_sane_lock);
-	sb_ptr = skb_header_pointer(skb, dataoff, datalen, sane_buffer);
-	if (!sb_ptr) {
-		spin_unlock_bh(&nf_sane_lock);
-		return NF_ACCEPT;
-	}
-
 	if (dir == IP_CT_DIR_ORIGINAL) {
+		const struct sane_request *req;
+
 		if (datalen != sizeof(struct sane_request))
-			goto out;
+			return NF_ACCEPT;
+
+		req = skb_header_pointer(skb, dataoff, datalen, &buf.req);
+		if (!req)
+			return NF_ACCEPT;
 
-		req = sb_ptr;
 		if (req->RPC_code != htonl(SANE_NET_START)) {
 			/* Not an interesting command */
-			ct_sane_info->state = SANE_STATE_NORMAL;
-			goto out;
+			WRITE_ONCE(ct_sane_info->state, SANE_STATE_NORMAL);
+			return NF_ACCEPT;
 		}
 
 		/* We're interested in the next reply */
-		ct_sane_info->state = SANE_STATE_START_REQUESTED;
-		goto out;
+		WRITE_ONCE(ct_sane_info->state, SANE_STATE_START_REQUESTED);
+		return NF_ACCEPT;
 	}
 
+	/* IP_CT_DIR_REPLY */
+
 	/* Is it a reply to an uninteresting command? */
-	if (ct_sane_info->state != SANE_STATE_START_REQUESTED)
-		goto out;
+	if (READ_ONCE(ct_sane_info->state) != SANE_STATE_START_REQUESTED)
+		return NF_ACCEPT;
 
 	/* It's a reply to SANE_NET_START. */
-	ct_sane_info->state = SANE_STATE_NORMAL;
+	WRITE_ONCE(ct_sane_info->state, SANE_STATE_NORMAL);
 
 	if (datalen < sizeof(struct sane_reply_net_start)) {
 		pr_debug("NET_START reply too short\n");
-		goto out;
+		return NF_ACCEPT;
 	}
 
-	reply = sb_ptr;
+	datalen = sizeof(struct sane_reply_net_start);
+
+	reply = skb_header_pointer(skb, dataoff, datalen, &buf.repl);
+	if (!reply)
+		return NF_ACCEPT;
+
 	if (reply->status != htonl(SANE_STATUS_SUCCESS)) {
 		/* saned refused the command */
 		pr_debug("unsuccessful SANE_STATUS = %u\n",
 			 ntohl(reply->status));
-		goto out;
+		return NF_ACCEPT;
 	}
 
 	/* Invalid saned reply? Ignore it. */
 	if (reply->zero != 0)
-		goto out;
+		return NF_ACCEPT;
 
 	exp = nf_ct_expect_alloc(ct);
 	if (exp == NULL) {
 		nf_ct_helper_log(skb, ct, "cannot alloc expectation");
-		ret = NF_DROP;
-		goto out;
+		return NF_DROP;
 	}
 
 	tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
@@ -162,9 +163,6 @@ static int help(struct sk_buff *skb,
 	}
 
 	nf_ct_expect_put(exp);
-
-out:
-	spin_unlock_bh(&nf_sane_lock);
 	return ret;
 }
 
@@ -178,7 +176,6 @@ static const struct nf_conntrack_expect_policy sane_exp_policy = {
 static void __exit nf_conntrack_sane_fini(void)
 {
 	nf_conntrack_helpers_unregister(sane, ports_c * 2);
-	kfree(sane_buffer);
 }
 
 static int __init nf_conntrack_sane_init(void)
@@ -187,10 +184,6 @@ static int __init nf_conntrack_sane_init(void)
 
 	NF_CT_HELPER_BUILD_BUG_ON(sizeof(struct nf_ct_sane_master));
 
-	sane_buffer = kmalloc(65536, GFP_KERNEL);
-	if (!sane_buffer)
-		return -ENOMEM;
-
 	if (ports_c == 0)
 		ports[ports_c++] = SANE_PORT;
 
@@ -210,7 +203,6 @@ static int __init nf_conntrack_sane_init(void)
 	ret = nf_conntrack_helpers_register(sane, ports_c * 2);
 	if (ret < 0) {
 		pr_err("failed to register helpers\n");
-		kfree(sane_buffer);
 		return ret;
 	}
 
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index daf06f71d31c..77f5e82d8e3f 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -477,7 +477,7 @@ static int ct_sip_walk_headers(const struct nf_conn *ct, const char *dptr,
 				return ret;
 			if (ret == 0)
 				break;
-			dataoff += *matchoff;
+			dataoff = *matchoff;
 		}
 		*in_header = 0;
 	}
@@ -489,7 +489,7 @@ static int ct_sip_walk_headers(const struct nf_conn *ct, const char *dptr,
 			break;
 		if (ret == 0)
 			return ret;
-		dataoff += *matchoff;
+		dataoff = *matchoff;
 	}
 
 	if (in_header)
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 05895878610c..4ffe84c5a82c 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -561,7 +561,6 @@ enum nf_ct_sysctl_index {
 	NF_SYSCTL_CT_LOG_INVALID,
 	NF_SYSCTL_CT_EXPECT_MAX,
 	NF_SYSCTL_CT_ACCT,
-	NF_SYSCTL_CT_HELPER,
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
 	NF_SYSCTL_CT_EVENTS,
 #endif
@@ -680,14 +679,6 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 		.extra1 	= SYSCTL_ZERO,
 		.extra2 	= SYSCTL_ONE,
 	},
-	[NF_SYSCTL_CT_HELPER] = {
-		.procname	= "nf_conntrack_helper",
-		.maxlen		= sizeof(u8),
-		.mode		= 0644,
-		.proc_handler	= proc_dou8vec_minmax,
-		.extra1 	= SYSCTL_ZERO,
-		.extra2 	= SYSCTL_ONE,
-	},
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
 	[NF_SYSCTL_CT_EVENTS] = {
 		.procname	= "nf_conntrack_events",
@@ -1100,7 +1091,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
 	table[NF_SYSCTL_CT_CHECKSUM].data = &net->ct.sysctl_checksum;
 	table[NF_SYSCTL_CT_LOG_INVALID].data = &net->ct.sysctl_log_invalid;
 	table[NF_SYSCTL_CT_ACCT].data = &net->ct.sysctl_acct;
-	table[NF_SYSCTL_CT_HELPER].data = &cnet->sysctl_auto_assign_helper;
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
 	table[NF_SYSCTL_CT_EVENTS].data = &net->ct.sysctl_events;
 #endif
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 765ac779bfc8..81c26a96c30b 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -437,12 +437,17 @@ static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table,
 	}
 }
 
+void nf_flow_table_gc_run(struct nf_flowtable *flow_table)
+{
+	nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
+}
+
 static void nf_flow_offload_work_gc(struct work_struct *work)
 {
 	struct nf_flowtable *flow_table;
 
 	flow_table = container_of(work, struct nf_flowtable, gc_work.work);
-	nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
+	nf_flow_table_gc_run(flow_table);
 	queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ);
 }
 
@@ -600,11 +605,11 @@ void nf_flow_table_free(struct nf_flowtable *flow_table)
 	mutex_unlock(&flowtable_lock);
 
 	cancel_delayed_work_sync(&flow_table->gc_work);
-	nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
-	nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
 	nf_flow_table_offload_flush(flow_table);
-	if (nf_flowtable_hw_offload(flow_table))
-		nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
+	/* ... no more pending work after this stage ... */
+	nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
+	nf_flow_table_gc_run(flow_table);
+	nf_flow_table_offload_flush_cleanup(flow_table);
 	rhashtable_destroy(&flow_table->rhashtable);
 }
 EXPORT_SYMBOL_GPL(nf_flow_table_free);
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index 103b6cbf257f..b04645ced89b 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -1074,6 +1074,14 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable,
 	flow_offload_queue_work(offload);
 }
 
+void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable)
+{
+	if (nf_flowtable_hw_offload(flowtable)) {
+		flush_workqueue(nf_flow_offload_del_wq);
+		nf_flow_table_gc_run(flowtable);
+	}
+}
+
 void nf_flow_table_offload_flush(struct nf_flowtable *flowtable)
 {
 	if (nf_flowtable_hw_offload(flowtable)) {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 3cc88998b879..63c70141b3e5 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -32,7 +32,6 @@ static LIST_HEAD(nf_tables_objects);
 static LIST_HEAD(nf_tables_flowtables);
 static LIST_HEAD(nf_tables_destroy_list);
 static DEFINE_SPINLOCK(nf_tables_destroy_list_lock);
-static u64 table_handle;
 
 enum {
 	NFT_VALIDATE_SKIP	= 0,
@@ -889,7 +888,7 @@ static int nf_tables_dump_tables(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = nft_net->base_seq;
+	cb->seq = READ_ONCE(nft_net->base_seq);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -1235,7 +1234,7 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info,
 	INIT_LIST_HEAD(&table->flowtables);
 	table->family = family;
 	table->flags = flags;
-	table->handle = ++table_handle;
+	table->handle = ++nft_net->table_handle;
 	if (table->flags & NFT_TABLE_F_OWNER)
 		table->nlpid = NETLINK_CB(skb).portid;
 
@@ -1705,7 +1704,7 @@ static int nf_tables_dump_chains(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = nft_net->base_seq;
+	cb->seq = READ_ONCE(nft_net->base_seq);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -2167,8 +2166,10 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family,
 	chain->flags |= NFT_CHAIN_BASE | flags;
 	basechain->policy = NF_ACCEPT;
 	if (chain->flags & NFT_CHAIN_HW_OFFLOAD &&
-	    !nft_chain_offload_support(basechain))
+	    !nft_chain_offload_support(basechain)) {
+		list_splice_init(&basechain->hook_list, &hook->list);
 		return -EOPNOTSUPP;
+	}
 
 	flow_block_init(&basechain->flow_block);
 
@@ -2198,7 +2199,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 	const struct nlattr * const *nla = ctx->nla;
 	struct nft_table *table = ctx->table;
 	struct nft_base_chain *basechain;
-	struct nft_stats __percpu *stats;
 	struct net *net = ctx->net;
 	char name[NFT_NAME_MAXLEN];
 	struct nft_rule_blob *blob;
@@ -2211,6 +2211,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 		return -EOVERFLOW;
 
 	if (nla[NFTA_CHAIN_HOOK]) {
+		struct nft_stats __percpu *stats = NULL;
 		struct nft_chain_hook hook;
 
 		if (flags & NFT_CHAIN_BINDING)
@@ -2236,15 +2237,17 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 				return PTR_ERR(stats);
 			}
 			rcu_assign_pointer(basechain->stats, stats);
-			static_branch_inc(&nft_counters_enabled);
 		}
 
 		err = nft_basechain_init(basechain, family, &hook, flags);
 		if (err < 0) {
 			nft_chain_release_hook(&hook);
 			kfree(basechain);
+			free_percpu(stats);
 			return err;
 		}
+		if (stats)
+			static_branch_inc(&nft_counters_enabled);
 	} else {
 		if (flags & NFT_CHAIN_BASE)
 			return -EINVAL;
@@ -2574,6 +2577,9 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info,
 	nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla);
 
 	if (chain != NULL) {
+		if (chain->flags & NFT_CHAIN_BINDING)
+			return -EINVAL;
+
 		if (info->nlh->nlmsg_flags & NLM_F_EXCL) {
 			NL_SET_BAD_ATTR(extack, attr);
 			return -EEXIST;
@@ -3149,7 +3155,7 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = nft_net->base_seq;
+	cb->seq = READ_ONCE(nft_net->base_seq);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -3907,7 +3913,7 @@ cont:
 		list_for_each_entry(i, &ctx->table->sets, list) {
 			int tmp;
 
-			if (!nft_is_active_next(ctx->net, set))
+			if (!nft_is_active_next(ctx->net, i))
 				continue;
 			if (!sscanf(i->name, name, &tmp))
 				continue;
@@ -4133,7 +4139,7 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = nft_net->base_seq;
+	cb->seq = READ_ONCE(nft_net->base_seq);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (ctx->family != NFPROTO_UNSPEC &&
@@ -4451,6 +4457,11 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
 		err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]);
 		if (err < 0)
 			return err;
+
+		if (desc.field_count > 1 && !(flags & NFT_SET_CONCAT))
+			return -EINVAL;
+	} else if (flags & NFT_SET_CONCAT) {
+		return -EINVAL;
 	}
 
 	if (nla[NFTA_SET_EXPR] || nla[NFTA_SET_EXPRESSIONS])
@@ -5061,6 +5072,8 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
+	cb->seq = READ_ONCE(nft_net->base_seq);
+
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (dump_ctx->ctx.family != NFPROTO_UNSPEC &&
 		    dump_ctx->ctx.family != table->family)
@@ -5196,6 +5209,9 @@ static int nft_setelem_parse_flags(const struct nft_set *set,
 	if (!(set->flags & NFT_SET_INTERVAL) &&
 	    *flags & NFT_SET_ELEM_INTERVAL_END)
 		return -EINVAL;
+	if ((*flags & (NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL)) ==
+	    (NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL))
+		return -EINVAL;
 
 	return 0;
 }
@@ -5599,7 +5615,7 @@ int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set,
 
 		err = nft_expr_clone(expr, set->exprs[i]);
 		if (err < 0) {
-			nft_expr_destroy(ctx, expr);
+			kfree(expr);
 			goto err_expr;
 		}
 		expr_array[i] = expr;
@@ -5842,6 +5858,24 @@ static void nft_setelem_remove(const struct net *net,
 		set->ops->remove(net, set, elem);
 }
 
+static bool nft_setelem_valid_key_end(const struct nft_set *set,
+				      struct nlattr **nla, u32 flags)
+{
+	if ((set->flags & (NFT_SET_CONCAT | NFT_SET_INTERVAL)) ==
+			  (NFT_SET_CONCAT | NFT_SET_INTERVAL)) {
+		if (flags & NFT_SET_ELEM_INTERVAL_END)
+			return false;
+		if (!nla[NFTA_SET_ELEM_KEY_END] &&
+		    !(flags & NFT_SET_ELEM_CATCHALL))
+			return false;
+	} else {
+		if (nla[NFTA_SET_ELEM_KEY_END])
+			return false;
+	}
+
+	return true;
+}
+
 static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			    const struct nlattr *attr, u32 nlmsg_flags)
 {
@@ -5892,6 +5926,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			return -EINVAL;
 	}
 
+	if (set->flags & NFT_SET_OBJECT) {
+		if (!nla[NFTA_SET_ELEM_OBJREF] &&
+		    !(flags & NFT_SET_ELEM_INTERVAL_END))
+			return -EINVAL;
+	} else {
+		if (nla[NFTA_SET_ELEM_OBJREF])
+			return -EINVAL;
+	}
+
+	if (!nft_setelem_valid_key_end(set, nla, flags))
+		return -EINVAL;
+
 	if ((flags & NFT_SET_ELEM_INTERVAL_END) &&
 	     (nla[NFTA_SET_ELEM_DATA] ||
 	      nla[NFTA_SET_ELEM_OBJREF] ||
@@ -5899,6 +5945,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	      nla[NFTA_SET_ELEM_EXPIRATION] ||
 	      nla[NFTA_SET_ELEM_USERDATA] ||
 	      nla[NFTA_SET_ELEM_EXPR] ||
+	      nla[NFTA_SET_ELEM_KEY_END] ||
 	      nla[NFTA_SET_ELEM_EXPRESSIONS]))
 		return -EINVAL;
 
@@ -6029,10 +6076,6 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	}
 
 	if (nla[NFTA_SET_ELEM_OBJREF] != NULL) {
-		if (!(set->flags & NFT_SET_OBJECT)) {
-			err = -EINVAL;
-			goto err_parse_key_end;
-		}
 		obj = nft_obj_lookup(ctx->net, ctx->table,
 				     nla[NFTA_SET_ELEM_OBJREF],
 				     set->objtype, genmask);
@@ -6325,6 +6368,9 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 	if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL))
 		return -EINVAL;
 
+	if (!nft_setelem_valid_key_end(set, nla, flags))
+		return -EINVAL;
+
 	nft_set_ext_prepare(&tmpl);
 
 	if (flags != 0) {
@@ -6941,7 +6987,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = nft_net->base_seq;
+	cb->seq = READ_ONCE(nft_net->base_seq);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -7873,7 +7919,7 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = nft_net->base_seq;
+	cb->seq = READ_ONCE(nft_net->base_seq);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -8806,6 +8852,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 	struct nft_trans_elem *te;
 	struct nft_chain *chain;
 	struct nft_table *table;
+	unsigned int base_seq;
 	LIST_HEAD(adl);
 	int err;
 
@@ -8855,9 +8902,12 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 	 * Bump generation counter, invalidate any dump in progress.
 	 * Cannot fail after this point.
 	 */
-	while (++nft_net->base_seq == 0)
+	base_seq = READ_ONCE(nft_net->base_seq);
+	while (++base_seq == 0)
 		;
 
+	WRITE_ONCE(nft_net->base_seq, base_seq);
+
 	/* step 3. Start new generation, rules_gen_X now in use. */
 	net->nft.gencursor = nft_gencursor_next(net);
 
@@ -9419,13 +9469,9 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
 				break;
 			}
 		}
-
-		cond_resched();
 	}
 
 	list_for_each_entry(set, &ctx->table->sets, list) {
-		cond_resched();
-
 		if (!nft_is_active_next(ctx->net, set))
 			continue;
 		if (!(set->flags & NFT_SET_MAP) ||
@@ -9667,6 +9713,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 			return PTR_ERR(chain);
 		if (nft_is_base_chain(chain))
 			return -EOPNOTSUPP;
+		if (nft_chain_is_bound(chain))
+			return -EINVAL;
 		if (desc->flags & NFT_DATA_DESC_SETELEM &&
 		    chain->flags & NFT_CHAIN_BINDING)
 			return -EINVAL;
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index c24b1240908f..9c44518cb70f 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -44,6 +44,10 @@ MODULE_DESCRIPTION("Netfilter messages via netlink socket");
 
 static unsigned int nfnetlink_pernet_id __read_mostly;
 
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+static DEFINE_SPINLOCK(nfnl_grp_active_lock);
+#endif
+
 struct nfnl_net {
 	struct sock *nfnl;
 };
@@ -654,6 +658,44 @@ static void nfnetlink_rcv(struct sk_buff *skb)
 		netlink_rcv_skb(skb, nfnetlink_rcv_msg);
 }
 
+static void nfnetlink_bind_event(struct net *net, unsigned int group)
+{
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+	int type, group_bit;
+	u8 v;
+
+	/* All NFNLGRP_CONNTRACK_* group bits fit into u8.
+	 * The other groups are not relevant and can be ignored.
+	 */
+	if (group >= 8)
+		return;
+
+	type = nfnl_group2type[group];
+
+	switch (type) {
+	case NFNL_SUBSYS_CTNETLINK:
+		break;
+	case NFNL_SUBSYS_CTNETLINK_EXP:
+		break;
+	default:
+		return;
+	}
+
+	group_bit = (1 << group);
+
+	spin_lock(&nfnl_grp_active_lock);
+	v = READ_ONCE(net->ct.ctnetlink_has_listener);
+	if ((v & group_bit) == 0) {
+		v |= group_bit;
+
+		/* read concurrently without nfnl_grp_active_lock held. */
+		WRITE_ONCE(net->ct.ctnetlink_has_listener, v);
+	}
+
+	spin_unlock(&nfnl_grp_active_lock);
+#endif
+}
+
 static int nfnetlink_bind(struct net *net, int group)
 {
 	const struct nfnetlink_subsystem *ss;
@@ -670,28 +712,45 @@ static int nfnetlink_bind(struct net *net, int group)
 	if (!ss)
 		request_module_nowait("nfnetlink-subsys-%d", type);
 
-#ifdef CONFIG_NF_CONNTRACK_EVENTS
-	if (type == NFNL_SUBSYS_CTNETLINK) {
-		nfnl_lock(NFNL_SUBSYS_CTNETLINK);
-		WRITE_ONCE(net->ct.ctnetlink_has_listener, true);
-		nfnl_unlock(NFNL_SUBSYS_CTNETLINK);
-	}
-#endif
+	nfnetlink_bind_event(net, group);
 	return 0;
 }
 
 static void nfnetlink_unbind(struct net *net, int group)
 {
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
+	int type, group_bit;
+
 	if (group <= NFNLGRP_NONE || group > NFNLGRP_MAX)
 		return;
 
-	if (nfnl_group2type[group] == NFNL_SUBSYS_CTNETLINK) {
-		nfnl_lock(NFNL_SUBSYS_CTNETLINK);
-		if (!nfnetlink_has_listeners(net, group))
-			WRITE_ONCE(net->ct.ctnetlink_has_listener, false);
-		nfnl_unlock(NFNL_SUBSYS_CTNETLINK);
+	type = nfnl_group2type[group];
+
+	switch (type) {
+	case NFNL_SUBSYS_CTNETLINK:
+		break;
+	case NFNL_SUBSYS_CTNETLINK_EXP:
+		break;
+	default:
+		return;
+	}
+
+	/* ctnetlink_has_listener is u8 */
+	if (group >= 8)
+		return;
+
+	group_bit = (1 << group);
+
+	spin_lock(&nfnl_grp_active_lock);
+	if (!nfnetlink_has_listeners(net, group)) {
+		u8 v = READ_ONCE(net->ct.ctnetlink_has_listener);
+
+		v &= ~group_bit;
+
+		/* read concurrently without nfnl_grp_active_lock held. */
+		WRITE_ONCE(net->ct.ctnetlink_has_listener, v);
 	}
+	spin_unlock(&nfnl_grp_active_lock);
 #endif
 }
 
diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index 0fa2e2030427..ee6840bd5933 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -269,6 +269,7 @@ bool nf_osf_find(const struct sk_buff *skb,
 	struct nf_osf_hdr_ctx ctx;
 	const struct tcphdr *tcp;
 	struct tcphdr _tcph;
+	bool found = false;
 
 	memset(&ctx, 0, sizeof(ctx));
 
@@ -283,10 +284,11 @@ bool nf_osf_find(const struct sk_buff *skb,
 
 		data->genre = f->genre;
 		data->version = f->version;
+		found = true;
 		break;
 	}
 
-	return true;
+	return found;
 }
 EXPORT_SYMBOL_GPL(nf_osf_find);
 
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index b04995c3e17f..a3f01f209a53 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -1089,9 +1089,6 @@ static int nft_ct_helper_obj_init(const struct nft_ctx *ctx,
 	if (err < 0)
 		goto err_put_helper;
 
-	/* Avoid the bogus warning, helper will be assigned after CT init */
-	nf_ct_set_auto_assign_helper_warned(ctx->net);
-
 	return 0;
 
 err_put_helper:
diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c
index 0053a697c931..89342ccccdcc 100644
--- a/net/netfilter/nft_osf.c
+++ b/net/netfilter/nft_osf.c
@@ -115,9 +115,21 @@ static int nft_osf_validate(const struct nft_ctx *ctx,
 			    const struct nft_expr *expr,
 			    const struct nft_data **data)
 {
-	return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) |
-						    (1 << NF_INET_PRE_ROUTING) |
-						    (1 << NF_INET_FORWARD));
+	unsigned int hooks;
+
+	switch (ctx->family) {
+	case NFPROTO_IPV4:
+	case NFPROTO_IPV6:
+	case NFPROTO_INET:
+		hooks = (1 << NF_INET_LOCAL_IN) |
+			(1 << NF_INET_PRE_ROUTING) |
+			(1 << NF_INET_FORWARD);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return nft_chain_validate_hooks(ctx->chain, hooks);
 }
 
 static bool nft_osf_reduce(struct nft_regs_track *track,
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 2e7ac007cb30..eb0e40c29712 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -740,17 +740,23 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
 				const struct nlattr * const tb[])
 {
 	struct nft_payload_set *priv = nft_expr_priv(expr);
+	u32 csum_offset, csum_type = NFT_PAYLOAD_CSUM_NONE;
+	int err;
 
 	priv->base        = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
 	priv->offset      = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
 	priv->len         = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
 
 	if (tb[NFTA_PAYLOAD_CSUM_TYPE])
-		priv->csum_type =
-			ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE]));
-	if (tb[NFTA_PAYLOAD_CSUM_OFFSET])
-		priv->csum_offset =
-			ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_OFFSET]));
+		csum_type = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE]));
+	if (tb[NFTA_PAYLOAD_CSUM_OFFSET]) {
+		err = nft_parse_u32_check(tb[NFTA_PAYLOAD_CSUM_OFFSET], U8_MAX,
+					  &csum_offset);
+		if (err < 0)
+			return err;
+
+		priv->csum_offset = csum_offset;
+	}
 	if (tb[NFTA_PAYLOAD_CSUM_FLAGS]) {
 		u32 flags;
 
@@ -761,7 +767,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
 		priv->csum_flags = flags;
 	}
 
-	switch (priv->csum_type) {
+	switch (csum_type) {
 	case NFT_PAYLOAD_CSUM_NONE:
 	case NFT_PAYLOAD_CSUM_INET:
 		break;
@@ -775,6 +781,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
 	default:
 		return -EOPNOTSUPP;
 	}
+	priv->csum_type = csum_type;
 
 	return nft_parse_register_load(tb[NFTA_PAYLOAD_SREG], &priv->sreg,
 				       priv->len);
@@ -833,6 +840,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
 {
 	enum nft_payload_bases base;
 	unsigned int offset, len;
+	int err;
 
 	if (tb[NFTA_PAYLOAD_BASE] == NULL ||
 	    tb[NFTA_PAYLOAD_OFFSET] == NULL ||
@@ -859,8 +867,13 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
 	if (tb[NFTA_PAYLOAD_DREG] == NULL)
 		return ERR_PTR(-EINVAL);
 
-	offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
-	len    = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
+	err = nft_parse_u32_check(tb[NFTA_PAYLOAD_OFFSET], U8_MAX, &offset);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	err = nft_parse_u32_check(tb[NFTA_PAYLOAD_LEN], U8_MAX, &len);
+	if (err < 0)
+		return ERR_PTR(err);
 
 	if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) &&
 	    base != NFT_PAYLOAD_LL_HEADER && base != NFT_PAYLOAD_INNER_HEADER)
diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c
index 68b2eed742df..62da25ad264b 100644
--- a/net/netfilter/nft_tproxy.c
+++ b/net/netfilter/nft_tproxy.c
@@ -312,6 +312,13 @@ static int nft_tproxy_dump(struct sk_buff *skb,
 	return 0;
 }
 
+static int nft_tproxy_validate(const struct nft_ctx *ctx,
+			       const struct nft_expr *expr,
+			       const struct nft_data **data)
+{
+	return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING);
+}
+
 static struct nft_expr_type nft_tproxy_type;
 static const struct nft_expr_ops nft_tproxy_ops = {
 	.type		= &nft_tproxy_type,
@@ -321,6 +328,7 @@ static const struct nft_expr_ops nft_tproxy_ops = {
 	.destroy	= nft_tproxy_destroy,
 	.dump		= nft_tproxy_dump,
 	.reduce		= NFT_REDUCE_READONLY,
+	.validate	= nft_tproxy_validate,
 };
 
 static struct nft_expr_type nft_tproxy_type __read_mostly = {
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 5edaaded706d..983ade4be3b3 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -161,6 +161,7 @@ static const struct nft_expr_ops nft_tunnel_get_ops = {
 
 static struct nft_expr_type nft_tunnel_type __read_mostly = {
 	.name		= "tunnel",
+	.family		= NFPROTO_NETDEV,
 	.ops		= &nft_tunnel_get_ops,
 	.policy		= nft_tunnel_policy,
 	.maxattr	= NFTA_TUNNEL_MAX,
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 1afca2a6c2ac..57010927e20a 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1174,13 +1174,17 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb)
 							     op.policy,
 							     op.maxattr);
 			if (err)
-				return err;
+				goto err_free_state;
 		}
 	}
 
 	if (!ctx->state)
 		return -ENODATA;
 	return 0;
+
+err_free_state:
+	netlink_policy_dump_free(ctx->state);
+	return err;
 }
 
 static void *ctrl_dumppolicy_prep(struct sk_buff *skb,
diff --git a/net/netlink/policy.c b/net/netlink/policy.c
index 8d7c900e27f4..87e3de0fde89 100644
--- a/net/netlink/policy.c
+++ b/net/netlink/policy.c
@@ -144,7 +144,7 @@ int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate,
 
 	err = add_policy(&state, policy, maxtype);
 	if (err)
-		return err;
+		goto err_try_undo;
 
 	for (policy_idx = 0;
 	     policy_idx < state->n_alloc && state->policies[policy_idx].policy;
@@ -164,7 +164,7 @@ int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate,
 						 policy[type].nested_policy,
 						 policy[type].len);
 				if (err)
-					return err;
+					goto err_try_undo;
 				break;
 			default:
 				break;
@@ -174,6 +174,16 @@ int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate,
 
 	*pstate = state;
 	return 0;
+
+err_try_undo:
+	/* Try to preserve reasonable unwind semantics - if we're starting from
+	 * scratch clean up fully, otherwise record what we got and caller will.
+	 */
+	if (!*pstate)
+		netlink_policy_dump_free(state);
+	else
+		*pstate = state;
+	return err;
 }
 
 static bool
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 7e8a39a35627..6c9d153afbee 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1802,7 +1802,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 				ovs_dp_reset_user_features(skb, info);
 		}
 
-		goto err_unlock_and_destroy_meters;
+		goto err_destroy_portids;
 	}
 
 	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
@@ -1817,6 +1817,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	ovs_notify(&dp_datapath_genl_family, reply, info);
 	return 0;
 
+err_destroy_portids:
+	kfree(rcu_dereference_raw(dp->upcall_portids));
 err_unlock_and_destroy_meters:
 	ovs_unlock();
 	ovs_meters_exit(dp);
diff --git a/net/qrtr/mhi.c b/net/qrtr/mhi.c
index 18196e1c8c2f..9ced13c0627a 100644
--- a/net/qrtr/mhi.c
+++ b/net/qrtr/mhi.c
@@ -78,11 +78,6 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev,
 	struct qrtr_mhi_dev *qdev;
 	int rc;
 
-	/* start channels */
-	rc = mhi_prepare_for_transfer_autoqueue(mhi_dev);
-	if (rc)
-		return rc;
-
 	qdev = devm_kzalloc(&mhi_dev->dev, sizeof(*qdev), GFP_KERNEL);
 	if (!qdev)
 		return -ENOMEM;
@@ -96,6 +91,13 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev,
 	if (rc)
 		return rc;
 
+	/* start channels */
+	rc = mhi_prepare_for_transfer_autoqueue(mhi_dev);
+	if (rc) {
+		qrtr_endpoint_unregister(&qdev->ep);
+		return rc;
+	}
+
 	dev_dbg(qdev->dev, "Qualcomm MHI QRTR driver probed\n");
 
 	return 0;
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 6fdedd9dbbc2..cfbf0e129cba 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -363,6 +363,7 @@ static int acquire_refill(struct rds_connection *conn)
 static void release_refill(struct rds_connection *conn)
 {
 	clear_bit(RDS_RECV_REFILL, &conn->c_flags);
+	smp_mb__after_atomic();
 
 	/* We don't use wait_on_bit()/wake_up_bit() because our waking is in a
 	 * hot path and finding waiters is very rare.  We don't want to walk
diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c
index 11c45c8c6c16..036d92c0ad79 100644
--- a/net/rose/rose_loopback.c
+++ b/net/rose/rose_loopback.c
@@ -96,7 +96,8 @@ static void rose_loopback_timer(struct timer_list *unused)
 		}
 
 		if (frametype == ROSE_CALL_REQUEST) {
-			if (!rose_loopback_neigh->dev) {
+			if (!rose_loopback_neigh->dev &&
+			    !rose_loopback_neigh->loopback) {
 				kfree_skb(skb);
 				continue;
 			}
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 571436064cd6..62c70709d798 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -982,6 +982,7 @@ void rxrpc_send_keepalive(struct rxrpc_peer *);
 /*
  * peer_event.c
  */
+void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset);
 void rxrpc_error_report(struct sock *);
 void rxrpc_peer_keepalive_worker(struct work_struct *);
 
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index f8ecad2b730e..2a93e7b5fbd0 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -166,7 +166,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 	_enter("{%d,%d}", call->tx_hard_ack, call->tx_top);
 
 	now = ktime_get_real();
-	max_age = ktime_sub(now, jiffies_to_usecs(call->peer->rto_j));
+	max_age = ktime_sub_us(now, jiffies_to_usecs(call->peer->rto_j));
 
 	spin_lock_bh(&call->lock);
 
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 84d0a4109645..6401cdf7a624 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -285,8 +285,10 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 	_enter("%p,%lx", rx, p->user_call_ID);
 
 	limiter = rxrpc_get_call_slot(p, gfp);
-	if (!limiter)
+	if (!limiter) {
+		release_sock(&rx->sk);
 		return ERR_PTR(-ERESTARTSYS);
+	}
 
 	call = rxrpc_alloc_client_call(rx, srx, gfp, debug_id);
 	if (IS_ERR(call)) {
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 96ecb7356c0f..38ea98ff426b 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -137,6 +137,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 
 	tuncfg.encap_type = UDP_ENCAP_RXRPC;
 	tuncfg.encap_rcv = rxrpc_input_packet;
+	tuncfg.encap_err_rcv = rxrpc_encap_err_rcv;
 	tuncfg.sk_user_data = local;
 	setup_udp_tunnel_sock(net, local->socket, &tuncfg);
 
@@ -405,6 +406,9 @@ static void rxrpc_local_processor(struct work_struct *work)
 		container_of(work, struct rxrpc_local, processor);
 	bool again;
 
+	if (local->dead)
+		return;
+
 	trace_rxrpc_local(local->debug_id, rxrpc_local_processing,
 			  refcount_read(&local->ref), NULL);
 
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index be032850ae8c..32561e9567fe 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -16,22 +16,105 @@
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
 #include <net/ip.h>
+#include <net/icmp.h>
 #include "ar-internal.h"
 
+static void rxrpc_adjust_mtu(struct rxrpc_peer *, unsigned int);
 static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
 static void rxrpc_distribute_error(struct rxrpc_peer *, int,
 				   enum rxrpc_call_completion);
 
 /*
- * Find the peer associated with an ICMP packet.
+ * Find the peer associated with an ICMPv4 packet.
  */
 static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
-						     const struct sk_buff *skb,
+						     struct sk_buff *skb,
+						     unsigned int udp_offset,
+						     unsigned int *info,
 						     struct sockaddr_rxrpc *srx)
 {
-	struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
+	struct iphdr *ip, *ip0 = ip_hdr(skb);
+	struct icmphdr *icmp = icmp_hdr(skb);
+	struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset);
 
-	_enter("");
+	_enter("%u,%u,%u", ip0->protocol, icmp->type, icmp->code);
+
+	switch (icmp->type) {
+	case ICMP_DEST_UNREACH:
+		*info = ntohs(icmp->un.frag.mtu);
+		fallthrough;
+	case ICMP_TIME_EXCEEDED:
+	case ICMP_PARAMETERPROB:
+		ip = (struct iphdr *)((void *)icmp + 8);
+		break;
+	default:
+		return NULL;
+	}
+
+	memset(srx, 0, sizeof(*srx));
+	srx->transport_type = local->srx.transport_type;
+	srx->transport_len = local->srx.transport_len;
+	srx->transport.family = local->srx.transport.family;
+
+	/* Can we see an ICMP4 packet on an ICMP6 listening socket?  and vice
+	 * versa?
+	 */
+	switch (srx->transport.family) {
+	case AF_INET:
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin.sin_addr, &ip->daddr,
+		       sizeof(struct in_addr));
+		break;
+
+#ifdef CONFIG_AF_RXRPC_IPV6
+	case AF_INET6:
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin.sin_addr, &ip->daddr,
+		       sizeof(struct in_addr));
+		break;
+#endif
+
+	default:
+		WARN_ON_ONCE(1);
+		return NULL;
+	}
+
+	_net("ICMP {%pISp}", &srx->transport);
+	return rxrpc_lookup_peer_rcu(local, srx);
+}
+
+#ifdef CONFIG_AF_RXRPC_IPV6
+/*
+ * Find the peer associated with an ICMPv6 packet.
+ */
+static struct rxrpc_peer *rxrpc_lookup_peer_icmp6_rcu(struct rxrpc_local *local,
+						      struct sk_buff *skb,
+						      unsigned int udp_offset,
+						      unsigned int *info,
+						      struct sockaddr_rxrpc *srx)
+{
+	struct icmp6hdr *icmp = icmp6_hdr(skb);
+	struct ipv6hdr *ip, *ip0 = ipv6_hdr(skb);
+	struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset);
+
+	_enter("%u,%u,%u", ip0->nexthdr, icmp->icmp6_type, icmp->icmp6_code);
+
+	switch (icmp->icmp6_type) {
+	case ICMPV6_DEST_UNREACH:
+		*info = ntohl(icmp->icmp6_mtu);
+		fallthrough;
+	case ICMPV6_PKT_TOOBIG:
+	case ICMPV6_TIME_EXCEED:
+	case ICMPV6_PARAMPROB:
+		ip = (struct ipv6hdr *)((void *)icmp + 8);
+		break;
+	default:
+		return NULL;
+	}
 
 	memset(srx, 0, sizeof(*srx));
 	srx->transport_type = local->srx.transport_type;
@@ -43,6 +126,165 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
 	 */
 	switch (srx->transport.family) {
 	case AF_INET:
+		_net("Rx ICMP6 on v4 sock");
+		srx->transport_len = sizeof(srx->transport.sin);
+		srx->transport.family = AF_INET;
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin.sin_addr,
+		       &ip->daddr.s6_addr32[3], sizeof(struct in_addr));
+		break;
+	case AF_INET6:
+		_net("Rx ICMP6");
+		srx->transport.sin.sin_port = udp->dest;
+		memcpy(&srx->transport.sin6.sin6_addr, &ip->daddr,
+		       sizeof(struct in6_addr));
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return NULL;
+	}
+
+	_net("ICMP {%pISp}", &srx->transport);
+	return rxrpc_lookup_peer_rcu(local, srx);
+}
+#endif /* CONFIG_AF_RXRPC_IPV6 */
+
+/*
+ * Handle an error received on the local endpoint as a tunnel.
+ */
+void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb,
+			 unsigned int udp_offset)
+{
+	struct sock_extended_err ee;
+	struct sockaddr_rxrpc srx;
+	struct rxrpc_local *local;
+	struct rxrpc_peer *peer;
+	unsigned int info = 0;
+	int err;
+	u8 version = ip_hdr(skb)->version;
+	u8 type = icmp_hdr(skb)->type;
+	u8 code = icmp_hdr(skb)->code;
+
+	rcu_read_lock();
+	local = rcu_dereference_sk_user_data(sk);
+	if (unlikely(!local)) {
+		rcu_read_unlock();
+		return;
+	}
+
+	rxrpc_new_skb(skb, rxrpc_skb_received);
+
+	switch (ip_hdr(skb)->version) {
+	case IPVERSION:
+		peer = rxrpc_lookup_peer_icmp_rcu(local, skb, udp_offset,
+						  &info, &srx);
+		break;
+#ifdef CONFIG_AF_RXRPC_IPV6
+	case 6:
+		peer = rxrpc_lookup_peer_icmp6_rcu(local, skb, udp_offset,
+						   &info, &srx);
+		break;
+#endif
+	default:
+		rcu_read_unlock();
+		return;
+	}
+
+	if (peer && !rxrpc_get_peer_maybe(peer))
+		peer = NULL;
+	if (!peer) {
+		rcu_read_unlock();
+		return;
+	}
+
+	memset(&ee, 0, sizeof(ee));
+
+	switch (version) {
+	case IPVERSION:
+		switch (type) {
+		case ICMP_DEST_UNREACH:
+			switch (code) {
+			case ICMP_FRAG_NEEDED:
+				rxrpc_adjust_mtu(peer, info);
+				rcu_read_unlock();
+				rxrpc_put_peer(peer);
+				return;
+			default:
+				break;
+			}
+
+			err = EHOSTUNREACH;
+			if (code <= NR_ICMP_UNREACH) {
+				/* Might want to do something different with
+				 * non-fatal errors
+				 */
+				//harderr = icmp_err_convert[code].fatal;
+				err = icmp_err_convert[code].errno;
+			}
+			break;
+
+		case ICMP_TIME_EXCEEDED:
+			err = EHOSTUNREACH;
+			break;
+		default:
+			err = EPROTO;
+			break;
+		}
+
+		ee.ee_origin = SO_EE_ORIGIN_ICMP;
+		ee.ee_type = type;
+		ee.ee_code = code;
+		ee.ee_errno = err;
+		break;
+
+#ifdef CONFIG_AF_RXRPC_IPV6
+	case 6:
+		switch (type) {
+		case ICMPV6_PKT_TOOBIG:
+			rxrpc_adjust_mtu(peer, info);
+			rcu_read_unlock();
+			rxrpc_put_peer(peer);
+			return;
+		}
+
+		icmpv6_err_convert(type, code, &err);
+
+		if (err == EACCES)
+			err = EHOSTUNREACH;
+
+		ee.ee_origin = SO_EE_ORIGIN_ICMP6;
+		ee.ee_type = type;
+		ee.ee_code = code;
+		ee.ee_errno = err;
+		break;
+#endif
+	}
+
+	trace_rxrpc_rx_icmp(peer, &ee, &srx);
+
+	rxrpc_distribute_error(peer, err, RXRPC_CALL_NETWORK_ERROR);
+	rcu_read_unlock();
+	rxrpc_put_peer(peer);
+}
+
+/*
+ * Find the peer associated with a local error.
+ */
+static struct rxrpc_peer *rxrpc_lookup_peer_local_rcu(struct rxrpc_local *local,
+						      const struct sk_buff *skb,
+						      struct sockaddr_rxrpc *srx)
+{
+	struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
+
+	_enter("");
+
+	memset(srx, 0, sizeof(*srx));
+	srx->transport_type = local->srx.transport_type;
+	srx->transport_len = local->srx.transport_len;
+	srx->transport.family = local->srx.transport.family;
+
+	switch (srx->transport.family) {
+	case AF_INET:
 		srx->transport_len = sizeof(srx->transport.sin);
 		srx->transport.family = AF_INET;
 		srx->transport.sin.sin_port = serr->port;
@@ -104,10 +346,8 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
 /*
  * Handle an MTU/fragmentation problem.
  */
-static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *serr)
+static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, unsigned int mtu)
 {
-	u32 mtu = serr->ee.ee_info;
-
 	_net("Rx ICMP Fragmentation Needed (%d)", mtu);
 
 	/* wind down the local interface MTU */
@@ -148,7 +388,7 @@ void rxrpc_error_report(struct sock *sk)
 	struct sock_exterr_skb *serr;
 	struct sockaddr_rxrpc srx;
 	struct rxrpc_local *local;
-	struct rxrpc_peer *peer;
+	struct rxrpc_peer *peer = NULL;
 	struct sk_buff *skb;
 
 	rcu_read_lock();
@@ -172,41 +412,20 @@ void rxrpc_error_report(struct sock *sk)
 	}
 	rxrpc_new_skb(skb, rxrpc_skb_received);
 	serr = SKB_EXT_ERR(skb);
-	if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
-		_leave("UDP empty message");
-		rcu_read_unlock();
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		return;
-	}
 
-	peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx);
-	if (peer && !rxrpc_get_peer_maybe(peer))
-		peer = NULL;
-	if (!peer) {
-		rcu_read_unlock();
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		_leave(" [no peer]");
-		return;
-	}
-
-	trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
-
-	if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
-	     serr->ee.ee_type == ICMP_DEST_UNREACH &&
-	     serr->ee.ee_code == ICMP_FRAG_NEEDED)) {
-		rxrpc_adjust_mtu(peer, serr);
-		rcu_read_unlock();
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		rxrpc_put_peer(peer);
-		_leave(" [MTU update]");
-		return;
+	if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL) {
+		peer = rxrpc_lookup_peer_local_rcu(local, skb, &srx);
+		if (peer && !rxrpc_get_peer_maybe(peer))
+			peer = NULL;
+		if (peer) {
+			trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
+			rxrpc_store_error(peer, serr);
+		}
 	}
 
-	rxrpc_store_error(peer, serr);
 	rcu_read_unlock();
 	rxrpc_free_skb(skb, rxrpc_skb_freed);
 	rxrpc_put_peer(peer);
-
 	_leave("");
 }
 
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 250f23bc1c07..7e39c262fd79 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -771,46 +771,3 @@ call_complete:
 	goto out;
 }
 EXPORT_SYMBOL(rxrpc_kernel_recv_data);
-
-/**
- * rxrpc_kernel_get_reply_time - Get timestamp on first reply packet
- * @sock: The socket that the call exists on
- * @call: The call to query
- * @_ts: Where to put the timestamp
- *
- * Retrieve the timestamp from the first DATA packet of the reply if it is
- * in the ring.  Returns true if successful, false if not.
- */
-bool rxrpc_kernel_get_reply_time(struct socket *sock, struct rxrpc_call *call,
-				 ktime_t *_ts)
-{
-	struct sk_buff *skb;
-	rxrpc_seq_t hard_ack, top, seq;
-	bool success = false;
-
-	mutex_lock(&call->user_mutex);
-
-	if (READ_ONCE(call->state) != RXRPC_CALL_CLIENT_RECV_REPLY)
-		goto out;
-
-	hard_ack = call->rx_hard_ack;
-	if (hard_ack != 0)
-		goto out;
-
-	seq = hard_ack + 1;
-	top = smp_load_acquire(&call->rx_top);
-	if (after(seq, top))
-		goto out;
-
-	skb = call->rxtx_buffer[seq & RXRPC_RXTX_BUFF_MASK];
-	if (!skb)
-		goto out;
-
-	*_ts = skb_get_ktime(skb);
-	success = true;
-
-out:
-	mutex_unlock(&call->user_mutex);
-	return success;
-}
-EXPORT_SYMBOL(rxrpc_kernel_get_reply_time);
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 258917a714c8..78fa0524156f 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -540,7 +540,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
 	 * directly into the target buffer.
 	 */
 	sg = _sg;
-	nsg = skb_shinfo(skb)->nr_frags;
+	nsg = skb_shinfo(skb)->nr_frags + 1;
 	if (nsg <= 4) {
 		nsg = 4;
 	} else {
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 1d38e279e2ef..3c3a626459de 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -51,10 +51,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
 			return sock_intr_errno(*timeo);
 
 		trace_rxrpc_transmit(call, rxrpc_transmit_wait);
-		mutex_unlock(&call->user_mutex);
 		*timeo = schedule_timeout(*timeo);
-		if (mutex_lock_interruptible(&call->user_mutex) < 0)
-			return sock_intr_errno(*timeo);
 	}
 }
 
@@ -290,37 +287,48 @@ out:
 static int rxrpc_send_data(struct rxrpc_sock *rx,
 			   struct rxrpc_call *call,
 			   struct msghdr *msg, size_t len,
-			   rxrpc_notify_end_tx_t notify_end_tx)
+			   rxrpc_notify_end_tx_t notify_end_tx,
+			   bool *_dropped_lock)
 {
 	struct rxrpc_skb_priv *sp;
 	struct sk_buff *skb;
 	struct sock *sk = &rx->sk;
+	enum rxrpc_call_state state;
 	long timeo;
-	bool more;
-	int ret, copied;
+	bool more = msg->msg_flags & MSG_MORE;
+	int ret, copied = 0;
 
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
 	/* this should be in poll */
 	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
+reload:
+	ret = -EPIPE;
 	if (sk->sk_shutdown & SEND_SHUTDOWN)
-		return -EPIPE;
-
-	more = msg->msg_flags & MSG_MORE;
-
+		goto maybe_error;
+	state = READ_ONCE(call->state);
+	ret = -ESHUTDOWN;
+	if (state >= RXRPC_CALL_COMPLETE)
+		goto maybe_error;
+	ret = -EPROTO;
+	if (state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
+	    state != RXRPC_CALL_SERVER_ACK_REQUEST &&
+	    state != RXRPC_CALL_SERVER_SEND_REPLY)
+		goto maybe_error;
+
+	ret = -EMSGSIZE;
 	if (call->tx_total_len != -1) {
-		if (len > call->tx_total_len)
-			return -EMSGSIZE;
-		if (!more && len != call->tx_total_len)
-			return -EMSGSIZE;
+		if (len - copied > call->tx_total_len)
+			goto maybe_error;
+		if (!more && len - copied != call->tx_total_len)
+			goto maybe_error;
 	}
 
 	skb = call->tx_pending;
 	call->tx_pending = NULL;
 	rxrpc_see_skb(skb, rxrpc_skb_seen);
 
-	copied = 0;
 	do {
 		/* Check to see if there's a ping ACK to reply to. */
 		if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE)
@@ -331,16 +339,8 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 
 			_debug("alloc");
 
-			if (!rxrpc_check_tx_space(call, NULL)) {
-				ret = -EAGAIN;
-				if (msg->msg_flags & MSG_DONTWAIT)
-					goto maybe_error;
-				ret = rxrpc_wait_for_tx_window(rx, call,
-							       &timeo,
-							       msg->msg_flags & MSG_WAITALL);
-				if (ret < 0)
-					goto maybe_error;
-			}
+			if (!rxrpc_check_tx_space(call, NULL))
+				goto wait_for_space;
 
 			/* Work out the maximum size of a packet.  Assume that
 			 * the security header is going to be in the padded
@@ -468,6 +468,27 @@ maybe_error:
 efault:
 	ret = -EFAULT;
 	goto out;
+
+wait_for_space:
+	ret = -EAGAIN;
+	if (msg->msg_flags & MSG_DONTWAIT)
+		goto maybe_error;
+	mutex_unlock(&call->user_mutex);
+	*_dropped_lock = true;
+	ret = rxrpc_wait_for_tx_window(rx, call, &timeo,
+				       msg->msg_flags & MSG_WAITALL);
+	if (ret < 0)
+		goto maybe_error;
+	if (call->interruptibility == RXRPC_INTERRUPTIBLE) {
+		if (mutex_lock_interruptible(&call->user_mutex) < 0) {
+			ret = sock_intr_errno(timeo);
+			goto maybe_error;
+		}
+	} else {
+		mutex_lock(&call->user_mutex);
+	}
+	*_dropped_lock = false;
+	goto reload;
 }
 
 /*
@@ -629,6 +650,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 	enum rxrpc_call_state state;
 	struct rxrpc_call *call;
 	unsigned long now, j;
+	bool dropped_lock = false;
 	int ret;
 
 	struct rxrpc_send_params p = {
@@ -737,21 +759,13 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 			ret = rxrpc_send_abort_packet(call);
 	} else if (p.command != RXRPC_CMD_SEND_DATA) {
 		ret = -EINVAL;
-	} else if (rxrpc_is_client_call(call) &&
-		   state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
-		/* request phase complete for this client call */
-		ret = -EPROTO;
-	} else if (rxrpc_is_service_call(call) &&
-		   state != RXRPC_CALL_SERVER_ACK_REQUEST &&
-		   state != RXRPC_CALL_SERVER_SEND_REPLY) {
-		/* Reply phase not begun or not complete for service call. */
-		ret = -EPROTO;
 	} else {
-		ret = rxrpc_send_data(rx, call, msg, len, NULL);
+		ret = rxrpc_send_data(rx, call, msg, len, NULL, &dropped_lock);
 	}
 
 out_put_unlock:
-	mutex_unlock(&call->user_mutex);
+	if (!dropped_lock)
+		mutex_unlock(&call->user_mutex);
 error_put:
 	rxrpc_put_call(call, rxrpc_call_put);
 	_leave(" = %d", ret);
@@ -779,6 +793,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
 			   struct msghdr *msg, size_t len,
 			   rxrpc_notify_end_tx_t notify_end_tx)
 {
+	bool dropped_lock = false;
 	int ret;
 
 	_enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]);
@@ -796,7 +811,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
 	case RXRPC_CALL_SERVER_ACK_REQUEST:
 	case RXRPC_CALL_SERVER_SEND_REPLY:
 		ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len,
-				      notify_end_tx);
+				      notify_end_tx, &dropped_lock);
 		break;
 	case RXRPC_CALL_COMPLETE:
 		read_lock_bh(&call->state_lock);
@@ -810,7 +825,8 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
 		break;
 	}
 
-	mutex_unlock(&call->user_mutex);
+	if (!dropped_lock)
+		mutex_unlock(&call->user_mutex);
 	_leave(" = %d", ret);
 	return ret;
 }
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index d55afb8d14be..5950974ae8f6 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -1394,7 +1394,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 
 	err = tcf_ct_flow_table_get(net, params);
 	if (err)
-		goto cleanup;
+		goto cleanup_params;
 
 	spin_lock_bh(&c->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
@@ -1409,6 +1409,9 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 
 	return res;
 
+cleanup_params:
+	if (params->tmpl)
+		nf_ct_put(params->tmpl);
 cleanup:
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 790d6809be81..51d175f3fbcb 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2137,6 +2137,7 @@ replay:
 	}
 
 	if (chain->tmplt_ops && chain->tmplt_ops != tp->ops) {
+		tfilter_put(tp, fh);
 		NL_SET_ERR_MSG(extack, "Chain template is set to a different filter kind");
 		err = -EINVAL;
 		goto errout;
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 3f935cbbaff6..48712bc51bda 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -424,6 +424,11 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp,
 			return -EINVAL;
 	}
 
+	if (!nhandle) {
+		NL_SET_ERR_MSG(extack, "Replacing with handle of 0 is invalid");
+		return -EINVAL;
+	}
+
 	h1 = to_hash(nhandle);
 	b = rtnl_dereference(head->table[h1]);
 	if (!b) {
@@ -477,6 +482,11 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 	int err;
 	bool new = true;
 
+	if (!handle) {
+		NL_SET_ERR_MSG(extack, "Creating with handle of 0 is invalid");
+		return -EINVAL;
+	}
+
 	if (opt == NULL)
 		return handle ? -EINVAL : 0;
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index d47b9689eba6..7a8ea03f673d 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -409,7 +409,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets)
 
 void __qdisc_run(struct Qdisc *q)
 {
-	int quota = dev_tx_weight;
+	int quota = READ_ONCE(dev_tx_weight);
 	int packets;
 
 	while (qdisc_restart(q, &packets)) {
@@ -1122,6 +1122,21 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 }
 EXPORT_SYMBOL(dev_graft_qdisc);
 
+static void shutdown_scheduler_queue(struct net_device *dev,
+				     struct netdev_queue *dev_queue,
+				     void *_qdisc_default)
+{
+	struct Qdisc *qdisc = dev_queue->qdisc_sleeping;
+	struct Qdisc *qdisc_default = _qdisc_default;
+
+	if (qdisc) {
+		rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
+		dev_queue->qdisc_sleeping = qdisc_default;
+
+		qdisc_put(qdisc);
+	}
+}
+
 static void attach_one_default_qdisc(struct net_device *dev,
 				     struct netdev_queue *dev_queue,
 				     void *_unused)
@@ -1169,6 +1184,7 @@ static void attach_default_qdiscs(struct net_device *dev)
 	if (qdisc == &noop_qdisc) {
 		netdev_warn(dev, "default qdisc (%s) fail, fallback to %s\n",
 			    default_qdisc_ops->id, noqueue_qdisc_ops.id);
+		netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
 		dev->priv_flags |= IFF_NO_QUEUE;
 		netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
 		qdisc = txq->qdisc_sleeping;
@@ -1447,21 +1463,6 @@ void dev_init_scheduler(struct net_device *dev)
 	timer_setup(&dev->watchdog_timer, dev_watchdog, 0);
 }
 
-static void shutdown_scheduler_queue(struct net_device *dev,
-				     struct netdev_queue *dev_queue,
-				     void *_qdisc_default)
-{
-	struct Qdisc *qdisc = dev_queue->qdisc_sleeping;
-	struct Qdisc *qdisc_default = _qdisc_default;
-
-	if (qdisc) {
-		rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
-		dev_queue->qdisc_sleeping = qdisc_default;
-
-		qdisc_put(qdisc);
-	}
-}
-
 void dev_shutdown(struct net_device *dev)
 {
 	netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 3d061a13d7ed..2829455211f8 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -135,15 +135,15 @@ static void increment_one_qlen(u32 sfbhash, u32 slot, struct sfb_sched_data *q)
 	}
 }
 
-static void increment_qlen(const struct sk_buff *skb, struct sfb_sched_data *q)
+static void increment_qlen(const struct sfb_skb_cb *cb, struct sfb_sched_data *q)
 {
 	u32 sfbhash;
 
-	sfbhash = sfb_hash(skb, 0);
+	sfbhash = cb->hashes[0];
 	if (sfbhash)
 		increment_one_qlen(sfbhash, 0, q);
 
-	sfbhash = sfb_hash(skb, 1);
+	sfbhash = cb->hashes[1];
 	if (sfbhash)
 		increment_one_qlen(sfbhash, 1, q);
 }
@@ -281,8 +281,10 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 {
 
 	struct sfb_sched_data *q = qdisc_priv(sch);
+	unsigned int len = qdisc_pkt_len(skb);
 	struct Qdisc *child = q->qdisc;
 	struct tcf_proto *fl;
+	struct sfb_skb_cb cb;
 	int i;
 	u32 p_min = ~0;
 	u32 minqlen = ~0;
@@ -399,11 +401,12 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 enqueue:
+	memcpy(&cb, sfb_skb_cb(skb), sizeof(cb));
 	ret = qdisc_enqueue(skb, child, to_free);
 	if (likely(ret == NET_XMIT_SUCCESS)) {
-		qdisc_qstats_backlog_inc(sch, skb);
+		sch->qstats.backlog += len;
 		sch->q.qlen++;
-		increment_qlen(skb, q);
+		increment_qlen(&cb, q);
 	} else if (net_xmit_drop_count(ret)) {
 		q->stats.childdrop++;
 		qdisc_qstats_drop(sch);
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 0b941dd63d26..86675a79da1e 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -67,6 +67,7 @@ struct taprio_sched {
 	u32 flags;
 	enum tk_offsets tk_offset;
 	int clockid;
+	bool offloaded;
 	atomic64_t picos_per_byte; /* Using picoseconds because for 10Gbps+
 				    * speeds it's sub-nanoseconds per byte
 				    */
@@ -1279,6 +1280,8 @@ static int taprio_enable_offload(struct net_device *dev,
 		goto done;
 	}
 
+	q->offloaded = true;
+
 done:
 	taprio_offload_free(offload);
 
@@ -1293,12 +1296,9 @@ static int taprio_disable_offload(struct net_device *dev,
 	struct tc_taprio_qopt_offload *offload;
 	int err;
 
-	if (!FULL_OFFLOAD_IS_ENABLED(q->flags))
+	if (!q->offloaded)
 		return 0;
 
-	if (!ops->ndo_setup_tc)
-		return -EOPNOTSUPP;
-
 	offload = taprio_offload_alloc(0);
 	if (!offload) {
 		NL_SET_ERR_MSG(extack,
@@ -1314,6 +1314,8 @@ static int taprio_disable_offload(struct net_device *dev,
 		goto out;
 	}
 
+	q->offloaded = false;
+
 out:
 	taprio_offload_free(offload);
 
@@ -1949,12 +1951,14 @@ start_error:
 
 static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl)
 {
-	struct netdev_queue *dev_queue = taprio_queue_get(sch, cl);
+	struct taprio_sched *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	unsigned int ntx = cl - 1;
 
-	if (!dev_queue)
+	if (ntx >= dev->num_tx_queues)
 		return NULL;
 
-	return dev_queue->qdisc_sleeping;
+	return q->qdiscs[ntx];
 }
 
 static unsigned long taprio_find(struct Qdisc *sch, u32 classid)
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 72102277449e..36079fdde2cb 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -356,6 +356,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
 	struct nlattr *tb[TCA_TBF_MAX + 1];
 	struct tc_tbf_qopt *qopt;
 	struct Qdisc *child = NULL;
+	struct Qdisc *old = NULL;
 	struct psched_ratecfg rate;
 	struct psched_ratecfg peak;
 	u64 max_size;
@@ -447,7 +448,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
 	sch_tree_lock(sch);
 	if (child) {
 		qdisc_tree_flush_backlog(q->qdisc);
-		qdisc_put(q->qdisc);
+		old = q->qdisc;
 		q->qdisc = child;
 	}
 	q->limit = qopt->limit;
@@ -467,6 +468,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
 	memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg));
 
 	sch_tree_unlock(sch);
+	qdisc_put(old);
 	err = 0;
 
 	tbf_offload_change(sch);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 79c1318af1fe..0939cc3b915a 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1855,7 +1855,6 @@ static void smc_listen_out_connected(struct smc_sock *new_smc)
 {
 	struct sock *newsmcsk = &new_smc->sk;
 
-	sk_refcnt_debug_inc(newsmcsk);
 	if (newsmcsk->sk_state == SMC_INIT)
 		newsmcsk->sk_state = SMC_ACTIVE;
 
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index ff49a11f57b8..df89c2e08cbf 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -757,6 +757,7 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk,
 	lnk->lgr = lgr;
 	smc_lgr_hold(lgr); /* lgr_put in smcr_link_clear() */
 	lnk->link_idx = link_idx;
+	lnk->wr_rx_id_compl = 0;
 	smc_ibdev_cnt_inc(lnk);
 	smcr_copy_dev_info_to_link(lnk);
 	atomic_set(&lnk->conn_cnt, 0);
@@ -2238,7 +2239,7 @@ out:
 static int smcr_buf_map_usable_links(struct smc_link_group *lgr,
 				     struct smc_buf_desc *buf_desc, bool is_rmb)
 {
-	int i, rc = 0;
+	int i, rc = 0, cnt = 0;
 
 	/* protect against parallel link reconfiguration */
 	mutex_lock(&lgr->llc_conf_mutex);
@@ -2251,9 +2252,12 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr,
 			rc = -ENOMEM;
 			goto out;
 		}
+		cnt++;
 	}
 out:
 	mutex_unlock(&lgr->llc_conf_mutex);
+	if (!rc && !cnt)
+		rc = -EINVAL;
 	return rc;
 }
 
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index fe8b524ad846..285f9bd8e232 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -115,8 +115,10 @@ struct smc_link {
 	dma_addr_t		wr_rx_dma_addr;	/* DMA address of wr_rx_bufs */
 	dma_addr_t		wr_rx_v2_dma_addr; /* DMA address of v2 rx buf*/
 	u64			wr_rx_id;	/* seq # of last recv WR */
+	u64			wr_rx_id_compl; /* seq # of last completed WR */
 	u32			wr_rx_cnt;	/* number of WR recv buffers */
 	unsigned long		wr_rx_tstamp;	/* jiffies when last buf rx */
+	wait_queue_head_t       wr_rx_empty_wait; /* wait for RQ empty */
 
 	struct ib_reg_wr	wr_reg;		/* WR register memory region */
 	wait_queue_head_t	wr_reg_wait;	/* wait for wr_reg result */
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 26f8f240d9e8..b0678a417e09 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -454,6 +454,7 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
 
 	for (i = 0; i < num; i++) {
 		link = wc[i].qp->qp_context;
+		link->wr_rx_id_compl = wc[i].wr_id;
 		if (wc[i].status == IB_WC_SUCCESS) {
 			link->wr_rx_tstamp = jiffies;
 			smc_wr_rx_demultiplex(&wc[i]);
@@ -465,6 +466,8 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
 			case IB_WC_RNR_RETRY_EXC_ERR:
 			case IB_WC_WR_FLUSH_ERR:
 				smcr_link_down_cond_sched(link);
+				if (link->wr_rx_id_compl == link->wr_rx_id)
+					wake_up(&link->wr_rx_empty_wait);
 				break;
 			default:
 				smc_wr_rx_post(link); /* refill WR RX */
@@ -639,6 +642,7 @@ void smc_wr_free_link(struct smc_link *lnk)
 		return;
 	ibdev = lnk->smcibdev->ibdev;
 
+	smc_wr_drain_cq(lnk);
 	smc_wr_wakeup_reg_wait(lnk);
 	smc_wr_wakeup_tx_wait(lnk);
 
@@ -889,6 +893,7 @@ int smc_wr_create_link(struct smc_link *lnk)
 	atomic_set(&lnk->wr_tx_refcnt, 0);
 	init_waitqueue_head(&lnk->wr_reg_wait);
 	atomic_set(&lnk->wr_reg_refcnt, 0);
+	init_waitqueue_head(&lnk->wr_rx_empty_wait);
 	return rc;
 
 dma_unmap:
diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h
index a54e90a1110f..45e9b894d3f8 100644
--- a/net/smc/smc_wr.h
+++ b/net/smc/smc_wr.h
@@ -73,6 +73,11 @@ static inline void smc_wr_tx_link_put(struct smc_link *link)
 		wake_up_all(&link->wr_tx_wait);
 }
 
+static inline void smc_wr_drain_cq(struct smc_link *lnk)
+{
+	wait_event(lnk->wr_rx_empty_wait, lnk->wr_rx_id_compl == lnk->wr_rx_id);
+}
+
 static inline void smc_wr_wakeup_tx_wait(struct smc_link *lnk)
 {
 	wake_up_all(&lnk->wr_tx_wait);
diff --git a/net/socket.c b/net/socket.c
index 9b27c5e4e5ba..7378375d3a5b 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1801,7 +1801,7 @@ int __sys_listen(int fd, int backlog)
 
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (sock) {
-		somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn;
+		somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn);
 		if ((unsigned int)backlog > somaxconn)
 			backlog = somaxconn;
 
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index b098e707ad41..c284efa3d1ef 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1902,7 +1902,7 @@ call_encode(struct rpc_task *task)
 			break;
 		case -EKEYEXPIRED:
 			if (!task->tk_cred_retry) {
-				rpc_exit(task, task->tk_status);
+				rpc_call_rpcerror(task, task->tk_status);
 			} else {
 				task->tk_action = call_refresh;
 				task->tk_cred_retry--;
@@ -2873,6 +2873,9 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt,
 
 	task = rpc_call_null_helper(clnt, xprt, NULL, RPC_TASK_ASYNC,
 			&rpc_cb_add_xprt_call_ops, data);
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+
 	data->xps->xps_nunique_destaddr_xprts++;
 	rpc_put_task(task);
 success:
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 7c9a0d0b1230..149171774bc6 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1205,7 +1205,7 @@ svc_generic_init_request(struct svc_rqst *rqstp,
 		goto err_bad_proc;
 
 	/* Initialize storage for argp and resp */
-	memset(rqstp->rq_argp, 0, procp->pc_argsize);
+	memset(rqstp->rq_argp, 0, procp->pc_argzero);
 	memset(rqstp->rq_resp, 0, procp->pc_ressize);
 
 	/* Bump per-procedure stats counter */
@@ -1434,8 +1434,7 @@ svc_process(struct svc_rqst *rqstp)
 {
 	struct kvec		*argv = &rqstp->rq_arg.head[0];
 	struct kvec		*resv = &rqstp->rq_res.head[0];
-	struct svc_serv		*serv = rqstp->rq_server;
-	u32			dir;
+	__be32			dir;
 
 #if IS_ENABLED(CONFIG_FAIL_SUNRPC)
 	if (!fail_sunrpc.ignore_server_disconnect &&
@@ -1450,7 +1449,7 @@ svc_process(struct svc_rqst *rqstp)
 	rqstp->rq_next_page = &rqstp->rq_respages[1];
 	resv->iov_base = page_address(rqstp->rq_respages[0]);
 	resv->iov_len = 0;
-	rqstp->rq_res.pages = rqstp->rq_respages + 1;
+	rqstp->rq_res.pages = rqstp->rq_next_page;
 	rqstp->rq_res.len = 0;
 	rqstp->rq_res.page_base = 0;
 	rqstp->rq_res.page_len = 0;
@@ -1458,18 +1457,17 @@ svc_process(struct svc_rqst *rqstp)
 	rqstp->rq_res.tail[0].iov_base = NULL;
 	rqstp->rq_res.tail[0].iov_len = 0;
 
-	dir  = svc_getnl(argv);
-	if (dir != 0) {
-		/* direction != CALL */
-		svc_printk(rqstp, "bad direction %d, dropping request\n", dir);
-		serv->sv_stats->rpcbadfmt++;
+	dir = svc_getu32(argv);
+	if (dir != rpc_call)
+		goto out_baddir;
+	if (!svc_process_common(rqstp, argv, resv))
 		goto out_drop;
-	}
-
-	/* Returns 1 for send, 0 for drop */
-	if (likely(svc_process_common(rqstp, argv, resv)))
-		return svc_send(rqstp);
+	return svc_send(rqstp);
 
+out_baddir:
+	svc_printk(rqstp, "bad direction 0x%08x, dropping request\n",
+		   be32_to_cpu(dir));
+	rqstp->rq_server->sv_stats->rpcbadfmt++;
 out_drop:
 	svc_drop(rqstp);
 	return 0;
@@ -1556,8 +1554,12 @@ out:
 EXPORT_SYMBOL_GPL(bc_svc_process);
 #endif /* CONFIG_SUNRPC_BACKCHANNEL */
 
-/*
- * Return (transport-specific) limit on the rpc payload.
+/**
+ * svc_max_payload - Return transport-specific limit on the RPC payload
+ * @rqstp: RPC transaction context
+ *
+ * Returns the maximum number of payload bytes the current transport
+ * allows.
  */
 u32 svc_max_payload(const struct svc_rqst *rqstp)
 {
diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c
index 7330eb9a70cf..c65c90ad626a 100644
--- a/net/sunrpc/sysfs.c
+++ b/net/sunrpc/sysfs.c
@@ -291,8 +291,10 @@ static ssize_t rpc_sysfs_xprt_state_change(struct kobject *kobj,
 	int offline = 0, online = 0, remove = 0;
 	struct rpc_xprt_switch *xps = rpc_sysfs_xprt_kobj_get_xprt_switch(kobj);
 
-	if (!xprt)
-		return 0;
+	if (!xprt || !xps) {
+		count = 0;
+		goto out_put;
+	}
 
 	if (!strncmp(buf, "offline", 7))
 		offline = 1;
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 482586c23fdd..336a7c7833e4 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -947,6 +947,28 @@ void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p,
 EXPORT_SYMBOL_GPL(xdr_init_encode);
 
 /**
+ * xdr_init_encode_pages - Initialize an xdr_stream for encoding into pages
+ * @xdr: pointer to xdr_stream struct
+ * @buf: pointer to XDR buffer into which to encode data
+ * @pages: list of pages to decode into
+ * @rqst: pointer to controlling rpc_rqst, for debugging
+ *
+ */
+void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
+			   struct page **pages, struct rpc_rqst *rqst)
+{
+	xdr_reset_scratch_buffer(xdr);
+
+	xdr->buf = buf;
+	xdr->page_ptr = pages;
+	xdr->iov = NULL;
+	xdr->p = page_address(*pages);
+	xdr->end = (void *)xdr->p + min_t(u32, buf->buflen, PAGE_SIZE);
+	xdr->rqst = rqst;
+}
+EXPORT_SYMBOL_GPL(xdr_init_encode_pages);
+
+/**
  * __xdr_commit_encode - Ensure all data is written to buffer
  * @xdr: pointer to xdr_stream
  *
@@ -1575,7 +1597,7 @@ EXPORT_SYMBOL_GPL(xdr_buf_from_iov);
  *
  * @buf and @subbuf may be pointers to the same struct xdr_buf.
  *
- * Returns -1 if base of length are out of bounds.
+ * Returns -1 if base or length are out of bounds.
  */
 int xdr_buf_subsegment(const struct xdr_buf *buf, struct xdr_buf *subbuf,
 		       unsigned int base, unsigned int len)
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index d71eec494826..f8fae7815649 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1179,11 +1179,8 @@ xprt_request_dequeue_receive_locked(struct rpc_task *task)
 {
 	struct rpc_rqst *req = task->tk_rqstp;
 
-	if (test_and_clear_bit(RPC_TASK_NEED_RECV, &task->tk_runstate)) {
+	if (test_and_clear_bit(RPC_TASK_NEED_RECV, &task->tk_runstate))
 		xprt_request_rb_remove(req->rq_xprt, req);
-		xdr_free_bvec(&req->rq_rcv_buf);
-		req->rq_private_buf.bvec = NULL;
-	}
 }
 
 /**
@@ -1221,6 +1218,8 @@ void xprt_complete_rqst(struct rpc_task *task, int copied)
 
 	xprt->stat.recvs++;
 
+	xdr_free_bvec(&req->rq_rcv_buf);
+	req->rq_private_buf.bvec = NULL;
 	req->rq_private_buf.len = copied;
 	/* Ensure all writes are done before we update */
 	/* req->rq_reply_bytes_recvd */
@@ -1453,6 +1452,7 @@ xprt_request_dequeue_xprt(struct rpc_task *task)
 		xprt_request_dequeue_transmit_locked(task);
 		xprt_request_dequeue_receive_locked(task);
 		spin_unlock(&xprt->queue_lock);
+		xdr_free_bvec(&req->rq_rcv_buf);
 	}
 }
 
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index 2f4d23238a7e..9618e4429f0f 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -160,7 +160,7 @@ static void map_set(u64 *up_map, int i, unsigned int v)
 
 static int map_get(u64 up_map, int i)
 {
-	return (up_map & (1 << i)) >> i;
+	return (up_map & (1ULL << i)) >> i;
 }
 
 static struct tipc_peer *peer_prev(struct tipc_peer *peer)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index f76119f62f1b..fe27241cd13f 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2702,7 +2702,9 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 			crypto_info->version != TLS_1_3_VERSION &&
 			!!(tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC);
 
-		tls_strp_init(&sw_ctx_rx->strp, sk);
+		rc = tls_strp_init(&sw_ctx_rx->strp, sk);
+		if (rc)
+			goto free_aead;
 	}
 
 	goto out;
diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c
index aab43469a2f0..0878b162890a 100644
--- a/net/wireless/debugfs.c
+++ b/net/wireless/debugfs.c
@@ -65,9 +65,10 @@ static ssize_t ht40allow_map_read(struct file *file,
 {
 	struct wiphy *wiphy = file->private_data;
 	char *buf;
-	unsigned int offset = 0, buf_size = PAGE_SIZE, i, r;
+	unsigned int offset = 0, buf_size = PAGE_SIZE, i;
 	enum nl80211_band band;
 	struct ieee80211_supported_band *sband;
+	ssize_t r;
 
 	buf = kzalloc(buf_size, GFP_KERNEL);
 	if (!buf)
diff --git a/net/wireless/lib80211_crypt_ccmp.c b/net/wireless/lib80211_crypt_ccmp.c
index 6a5f08f7491e..cca5e1cf089e 100644
--- a/net/wireless/lib80211_crypt_ccmp.c
+++ b/net/wireless/lib80211_crypt_ccmp.c
@@ -136,7 +136,7 @@ static int ccmp_init_iv_and_aad(const struct ieee80211_hdr *hdr,
 	pos = (u8 *) hdr;
 	aad[0] = pos[0] & 0x8f;
 	aad[1] = pos[1] & 0xc7;
-	memcpy(aad + 2, hdr->addr1, 3 * ETH_ALEN);
+	memcpy(aad + 2, &hdr->addrs, 3 * ETH_ALEN);
 	pos = (u8 *) & hdr->seq_ctrl;
 	aad[20] = pos[0] & 0x0f;
 	aad[21] = 0;		/* all bits masked */
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 2c127951764a..775836f6785a 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1361,7 +1361,7 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate)
 		 25599, /*  4.166666... */
 		 17067, /*  2.777777... */
 		 12801, /*  2.083333... */
-		 11769, /*  1.851851... */
+		 11377, /*  1.851725... */
 		 10239, /*  1.666666... */
 		  8532, /*  1.388888... */
 		  7680, /*  1.250000... */
@@ -1444,7 +1444,7 @@ static u32 cfg80211_calculate_bitrate_eht(struct rate_info *rate)
 		 25599, /*  4.166666... */
 		 17067, /*  2.777777... */
 		 12801, /*  2.083333... */
-		 11769, /*  1.851851... */
+		 11377, /*  1.851725... */
 		 10239, /*  1.666666... */
 		  8532, /*  1.388888... */
 		  7680, /*  1.250000... */
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index f70112176b7c..a71a8c6edf55 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -379,6 +379,16 @@ static void xp_check_dma_contiguity(struct xsk_dma_map *dma_map)
 
 static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_map)
 {
+	if (!pool->unaligned) {
+		u32 i;
+
+		for (i = 0; i < pool->heads_cnt; i++) {
+			struct xdp_buff_xsk *xskb = &pool->heads[i];
+
+			xp_init_xskb_dma(xskb, pool, dma_map->dma_pages, xskb->orig_addr);
+		}
+	}
+
 	pool->dma_pages = kvcalloc(dma_map->dma_pages_cnt, sizeof(*pool->dma_pages), GFP_KERNEL);
 	if (!pool->dma_pages)
 		return -ENOMEM;
@@ -428,12 +438,6 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 
 	if (pool->unaligned)
 		xp_check_dma_contiguity(dma_map);
-	else
-		for (i = 0; i < pool->heads_cnt; i++) {
-			struct xdp_buff_xsk *xskb = &pool->heads[i];
-
-			xp_init_xskb_dma(xskb, pool, dma_map->dma_pages, xskb->orig_addr);
-		}
 
 	err = xp_init_dma_info(pool, dma_map);
 	if (err) {
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index 82d14eea1b5a..974eb97b77d2 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -168,7 +168,7 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb)
 {
 	struct espintcp_ctx *ctx = espintcp_getctx(sk);
 
-	if (skb_queue_len(&ctx->out_queue) >= netdev_max_backlog)
+	if (skb_queue_len(&ctx->out_queue) >= READ_ONCE(netdev_max_backlog))
 		return -ENOBUFS;
 
 	__skb_queue_tail(&ctx->out_queue, skb);
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 144238a50f3d..b2f4ec9c537f 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -669,7 +669,6 @@ resume:
 
 		x->curlft.bytes += skb->len;
 		x->curlft.packets++;
-		x->curlft.use_time = ktime_get_real_seconds();
 
 		spin_unlock(&x->lock);
 
@@ -783,7 +782,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb,
 
 	trans = this_cpu_ptr(&xfrm_trans_tasklet);
 
-	if (skb_queue_len(&trans->queue) >= netdev_max_backlog)
+	if (skb_queue_len(&trans->queue) >= READ_ONCE(netdev_max_backlog))
 		return -ENOBUFS;
 
 	BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb));
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 555ab35cd119..9a5e79a38c67 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -534,7 +534,6 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
 
 		x->curlft.bytes += skb->len;
 		x->curlft.packets++;
-		x->curlft.use_time = ktime_get_real_seconds();
 
 		spin_unlock_bh(&x->lock);
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index f1a0bab920a5..cc6ab79609e2 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3162,7 +3162,7 @@ ok:
 	return dst;
 
 nopol:
-	if (!(dst_orig->dev->flags & IFF_LOOPBACK) &&
+	if ((!dst_orig->dev || !(dst_orig->dev->flags & IFF_LOOPBACK)) &&
 	    net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) {
 		err = -EPERM;
 		goto error;
@@ -3599,6 +3599,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		if (pols[1]) {
 			if (IS_ERR(pols[1])) {
 				XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
+				xfrm_pol_put(pols[0]);
 				return 0;
 			}
 			pols[1]->curlft.use_time = ktime_get_real_seconds();
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 52e60e607f8a..91c32a3b6924 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1592,6 +1592,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
 	x->replay = orig->replay;
 	x->preplay = orig->preplay;
 	x->mapping_maxage = orig->mapping_maxage;
+	x->lastused = orig->lastused;
 	x->new_mapping = 0;
 	x->new_mapping_sport = 0;
 
diff --git a/rust/.gitignore b/rust/.gitignore
new file mode 100644
index 000000000000..9bd1af8e05a1
--- /dev/null
+++ b/rust/.gitignore
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+
+target.json
+bindings_generated.rs
+bindings_helpers_generated.rs
+exports_*_generated.h
+doc/
+test/
diff --git a/rust/Makefile b/rust/Makefile
new file mode 100644
index 000000000000..7700d3853404
--- /dev/null
+++ b/rust/Makefile
@@ -0,0 +1,381 @@
+# SPDX-License-Identifier: GPL-2.0
+
+always-$(CONFIG_RUST) += target.json
+no-clean-files += target.json
+
+obj-$(CONFIG_RUST) += core.o compiler_builtins.o
+always-$(CONFIG_RUST) += exports_core_generated.h
+
+# Missing prototypes are expected in the helpers since these are exported
+# for Rust only, thus there is no header nor prototypes.
+obj-$(CONFIG_RUST) += helpers.o
+CFLAGS_REMOVE_helpers.o = -Wmissing-prototypes -Wmissing-declarations
+
+always-$(CONFIG_RUST) += libmacros.so
+no-clean-files += libmacros.so
+
+always-$(CONFIG_RUST) += bindings/bindings_generated.rs bindings/bindings_helpers_generated.rs
+obj-$(CONFIG_RUST) += alloc.o bindings.o kernel.o
+always-$(CONFIG_RUST) += exports_alloc_generated.h exports_bindings_generated.h \
+    exports_kernel_generated.h
+
+obj-$(CONFIG_RUST) += exports.o
+
+# Avoids running `$(RUSTC)` for the sysroot when it may not be available.
+ifdef CONFIG_RUST
+
+# `$(rust_flags)` is passed in case the user added `--sysroot`.
+rustc_sysroot := $(shell $(RUSTC) $(rust_flags) --print sysroot)
+rustc_host_target := $(shell $(RUSTC) --version --verbose | grep -F 'host: ' | cut -d' ' -f2)
+RUST_LIB_SRC ?= $(rustc_sysroot)/lib/rustlib/src/rust/library
+
+ifeq ($(quiet),silent_)
+cargo_quiet=-q
+rust_test_quiet=-q
+rustdoc_test_quiet=--test-args -q
+else ifeq ($(quiet),quiet_)
+rust_test_quiet=-q
+rustdoc_test_quiet=--test-args -q
+else
+cargo_quiet=--verbose
+endif
+
+core-cfgs = \
+    --cfg no_fp_fmt_parse
+
+alloc-cfgs = \
+    --cfg no_fmt \
+    --cfg no_global_oom_handling \
+    --cfg no_macros \
+    --cfg no_rc \
+    --cfg no_str \
+    --cfg no_string \
+    --cfg no_sync \
+    --cfg no_thin
+
+quiet_cmd_rustdoc = RUSTDOC $(if $(rustdoc_host),H, ) $<
+      cmd_rustdoc = \
+	OBJTREE=$(abspath $(objtree)) \
+	$(RUSTDOC) $(if $(rustdoc_host),$(rust_common_flags),$(rust_flags)) \
+		$(rustc_target_flags) -L$(objtree)/$(obj) \
+		--output $(objtree)/$(obj)/doc \
+		--crate-name $(subst rustdoc-,,$@) \
+		@$(objtree)/include/generated/rustc_cfg $<
+
+# The `html_logo_url` and `html_favicon_url` forms of the `doc` attribute
+# can be used to specify a custom logo. However:
+#   - The given value is used as-is, thus it cannot be relative or a local file
+#     (unlike the non-custom case) since the generated docs have subfolders.
+#   - It requires adding it to every crate.
+#   - It requires changing `core` which comes from the sysroot.
+#
+# Using `-Zcrate-attr` would solve the last two points, but not the first.
+# The https://github.com/rust-lang/rfcs/pull/3226 RFC suggests two new
+# command-like flags to solve the issue. Meanwhile, we use the non-custom case
+# and then retouch the generated files.
+rustdoc: rustdoc-core rustdoc-macros rustdoc-compiler_builtins \
+    rustdoc-alloc rustdoc-kernel
+	$(Q)cp $(srctree)/Documentation/images/logo.svg $(objtree)/$(obj)/doc
+	$(Q)cp $(srctree)/Documentation/images/COPYING-logo $(objtree)/$(obj)/doc
+	$(Q)find $(objtree)/$(obj)/doc -name '*.html' -type f -print0 | xargs -0 sed -Ei \
+		-e 's:rust-logo\.svg:logo.svg:g' \
+		-e 's:rust-logo\.png:logo.svg:g' \
+		-e 's:favicon\.svg:logo.svg:g' \
+		-e 's:<link rel="alternate icon" type="image/png" href="[./]*favicon-(16x16|32x32)\.png">::g'
+	$(Q)echo '.logo-container > img { object-fit: contain; }' \
+		>> $(objtree)/$(obj)/doc/rustdoc.css
+
+rustdoc-macros: private rustdoc_host = yes
+rustdoc-macros: private rustc_target_flags = --crate-type proc-macro \
+    --extern proc_macro
+rustdoc-macros: $(src)/macros/lib.rs FORCE
+	$(call if_changed,rustdoc)
+
+rustdoc-core: private rustc_target_flags = $(core-cfgs)
+rustdoc-core: $(RUST_LIB_SRC)/core/src/lib.rs FORCE
+	$(call if_changed,rustdoc)
+
+rustdoc-compiler_builtins: $(src)/compiler_builtins.rs rustdoc-core FORCE
+	$(call if_changed,rustdoc)
+
+# We need to allow `rustdoc::broken_intra_doc_links` because some
+# `no_global_oom_handling` functions refer to non-`no_global_oom_handling`
+# functions. Ideally `rustdoc` would have a way to distinguish broken links
+# due to things that are "configured out" vs. entirely non-existing ones.
+rustdoc-alloc: private rustc_target_flags = $(alloc-cfgs) \
+    -Arustdoc::broken_intra_doc_links
+rustdoc-alloc: $(src)/alloc/lib.rs rustdoc-core rustdoc-compiler_builtins FORCE
+	$(call if_changed,rustdoc)
+
+rustdoc-kernel: private rustc_target_flags = --extern alloc \
+    --extern macros=$(objtree)/$(obj)/libmacros.so \
+    --extern bindings
+rustdoc-kernel: $(src)/kernel/lib.rs rustdoc-core rustdoc-macros \
+    rustdoc-compiler_builtins rustdoc-alloc $(obj)/libmacros.so \
+    $(obj)/bindings.o FORCE
+	$(call if_changed,rustdoc)
+
+quiet_cmd_rustc_test_library = RUSTC TL $<
+      cmd_rustc_test_library = \
+	OBJTREE=$(abspath $(objtree)) \
+	$(RUSTC) $(rust_common_flags) \
+		@$(objtree)/include/generated/rustc_cfg $(rustc_target_flags) \
+		--crate-type $(if $(rustc_test_library_proc),proc-macro,rlib) \
+		--out-dir $(objtree)/$(obj)/test --cfg testlib \
+		--sysroot $(objtree)/$(obj)/test/sysroot \
+		-L$(objtree)/$(obj)/test \
+		--crate-name $(subst rusttest-,,$(subst rusttestlib-,,$@)) $<
+
+rusttestlib-macros: private rustc_target_flags = --extern proc_macro
+rusttestlib-macros: private rustc_test_library_proc = yes
+rusttestlib-macros: $(src)/macros/lib.rs rusttest-prepare FORCE
+	$(call if_changed,rustc_test_library)
+
+rusttestlib-bindings: $(src)/bindings/lib.rs rusttest-prepare FORCE
+	$(call if_changed,rustc_test_library)
+
+quiet_cmd_rustdoc_test = RUSTDOC T $<
+      cmd_rustdoc_test = \
+	OBJTREE=$(abspath $(objtree)) \
+	$(RUSTDOC) --test $(rust_common_flags) \
+		@$(objtree)/include/generated/rustc_cfg \
+		$(rustc_target_flags) $(rustdoc_test_target_flags) \
+		--sysroot $(objtree)/$(obj)/test/sysroot $(rustdoc_test_quiet) \
+		-L$(objtree)/$(obj)/test --output $(objtree)/$(obj)/doc \
+		--crate-name $(subst rusttest-,,$@) $<
+
+# We cannot use `-Zpanic-abort-tests` because some tests are dynamic,
+# so for the moment we skip `-Cpanic=abort`.
+quiet_cmd_rustc_test = RUSTC T  $<
+      cmd_rustc_test = \
+	OBJTREE=$(abspath $(objtree)) \
+	$(RUSTC) --test $(rust_common_flags) \
+		@$(objtree)/include/generated/rustc_cfg \
+		$(rustc_target_flags) --out-dir $(objtree)/$(obj)/test \
+		--sysroot $(objtree)/$(obj)/test/sysroot \
+		-L$(objtree)/$(obj)/test \
+		--crate-name $(subst rusttest-,,$@) $<; \
+	$(objtree)/$(obj)/test/$(subst rusttest-,,$@) $(rust_test_quiet) \
+		$(rustc_test_run_flags)
+
+rusttest: rusttest-macros rusttest-kernel
+
+# This prepares a custom sysroot with our custom `alloc` instead of
+# the standard one.
+#
+# This requires several hacks:
+#   - Unlike `core` and `alloc`, `std` depends on more than a dozen crates,
+#     including third-party crates that need to be downloaded, plus custom
+#     `build.rs` steps. Thus hardcoding things here is not maintainable.
+#   - `cargo` knows how to build the standard library, but it is an unstable
+#     feature so far (`-Zbuild-std`).
+#   - `cargo` only considers the use case of building the standard library
+#     to use it in a given package. Thus we need to create a dummy package
+#     and pick the generated libraries from there.
+#   - Since we only keep a subset of upstream `alloc` in-tree, we need
+#     to recreate it on the fly by putting our sources on top.
+#   - The usual ways of modifying the dependency graph in `cargo` do not seem
+#     to apply for the `-Zbuild-std` steps, thus we have to mislead it
+#     by modifying the sources in the sysroot.
+#   - To avoid messing with the user's Rust installation, we create a clone
+#     of the sysroot. However, `cargo` ignores `RUSTFLAGS` in the `-Zbuild-std`
+#     steps, thus we use a wrapper binary passed via `RUSTC` to pass the flag.
+#
+# In the future, we hope to avoid the whole ordeal by either:
+#   - Making the `test` crate not depend on `std` (either improving upstream
+#     or having our own custom crate).
+#   - Making the tests run in kernel space (requires the previous point).
+#   - Making `std` and friends be more like a "normal" crate, so that
+#     `-Zbuild-std` and related hacks are not needed.
+quiet_cmd_rustsysroot = RUSTSYSROOT
+      cmd_rustsysroot = \
+	rm -rf $(objtree)/$(obj)/test; \
+	mkdir -p $(objtree)/$(obj)/test; \
+	cp -a $(rustc_sysroot) $(objtree)/$(obj)/test/sysroot; \
+	cp -r $(srctree)/$(src)/alloc/* \
+		$(objtree)/$(obj)/test/sysroot/lib/rustlib/src/rust/library/alloc/src; \
+	echo '\#!/bin/sh' > $(objtree)/$(obj)/test/rustc_sysroot; \
+	echo "$(RUSTC) --sysroot=$(abspath $(objtree)/$(obj)/test/sysroot) \"\$$@\"" \
+		>> $(objtree)/$(obj)/test/rustc_sysroot; \
+	chmod u+x $(objtree)/$(obj)/test/rustc_sysroot; \
+	$(CARGO) -q new $(objtree)/$(obj)/test/dummy; \
+	RUSTC=$(objtree)/$(obj)/test/rustc_sysroot $(CARGO) $(cargo_quiet) \
+		test -Zbuild-std --target $(rustc_host_target) \
+		--manifest-path $(objtree)/$(obj)/test/dummy/Cargo.toml; \
+	rm $(objtree)/$(obj)/test/sysroot/lib/rustlib/$(rustc_host_target)/lib/*; \
+	cp $(objtree)/$(obj)/test/dummy/target/$(rustc_host_target)/debug/deps/* \
+		$(objtree)/$(obj)/test/sysroot/lib/rustlib/$(rustc_host_target)/lib
+
+rusttest-prepare: FORCE
+	$(call if_changed,rustsysroot)
+
+rusttest-macros: private rustc_target_flags = --extern proc_macro
+rusttest-macros: private rustdoc_test_target_flags = --crate-type proc-macro
+rusttest-macros: $(src)/macros/lib.rs rusttest-prepare FORCE
+	$(call if_changed,rustc_test)
+	$(call if_changed,rustdoc_test)
+
+rusttest-kernel: private rustc_target_flags = --extern alloc \
+    --extern macros --extern bindings
+rusttest-kernel: $(src)/kernel/lib.rs rusttest-prepare \
+    rusttestlib-macros rusttestlib-bindings FORCE
+	$(call if_changed,rustc_test)
+	$(call if_changed,rustc_test_library)
+
+filechk_rust_target = $(objtree)/scripts/generate_rust_target < $<
+
+$(obj)/target.json: $(objtree)/include/config/auto.conf FORCE
+	$(call filechk,rust_target)
+
+ifdef CONFIG_CC_IS_CLANG
+bindgen_c_flags = $(c_flags)
+else
+# bindgen relies on libclang to parse C. Ideally, bindgen would support a GCC
+# plugin backend and/or the Clang driver would be perfectly compatible with GCC.
+#
+# For the moment, here we are tweaking the flags on the fly. This is a hack,
+# and some kernel configurations may not work (e.g. `GCC_PLUGIN_RANDSTRUCT`
+# if we end up using one of those structs).
+bindgen_skip_c_flags := -mno-fp-ret-in-387 -mpreferred-stack-boundary=% \
+	-mskip-rax-setup -mgeneral-regs-only -msign-return-address=% \
+	-mindirect-branch=thunk-extern -mindirect-branch-register \
+	-mfunction-return=thunk-extern -mrecord-mcount -mabi=lp64 \
+	-mindirect-branch-cs-prefix -mstack-protector-guard% -mtraceback=no \
+	-mno-pointers-to-nested-functions -mno-string \
+	-mno-strict-align -mstrict-align \
+	-fconserve-stack -falign-jumps=% -falign-loops=% \
+	-femit-struct-debug-baseonly -fno-ipa-cp-clone -fno-ipa-sra \
+	-fno-partial-inlining -fplugin-arg-arm_ssp_per_task_plugin-% \
+	-fno-reorder-blocks -fno-allow-store-data-races -fasan-shadow-offset=% \
+	-fzero-call-used-regs=% -fno-stack-clash-protection \
+	-fno-inline-functions-called-once \
+	--param=% --param asan-%
+
+# Derived from `scripts/Makefile.clang`.
+BINDGEN_TARGET_x86	:= x86_64-linux-gnu
+BINDGEN_TARGET		:= $(BINDGEN_TARGET_$(SRCARCH))
+
+# All warnings are inhibited since GCC builds are very experimental,
+# many GCC warnings are not supported by Clang, they may only appear in
+# some configurations, with new GCC versions, etc.
+bindgen_extra_c_flags = -w --target=$(BINDGEN_TARGET)
+
+bindgen_c_flags = $(filter-out $(bindgen_skip_c_flags), $(c_flags)) \
+	$(bindgen_extra_c_flags)
+endif
+
+ifdef CONFIG_LTO
+bindgen_c_flags_lto = $(filter-out $(CC_FLAGS_LTO), $(bindgen_c_flags))
+else
+bindgen_c_flags_lto = $(bindgen_c_flags)
+endif
+
+bindgen_c_flags_final = $(bindgen_c_flags_lto) -D__BINDGEN__
+
+quiet_cmd_bindgen = BINDGEN $@
+      cmd_bindgen = \
+	$(BINDGEN) $< $(bindgen_target_flags) \
+		--use-core --with-derive-default --ctypes-prefix core::ffi --no-layout-tests \
+		--no-debug '.*' \
+		--size_t-is-usize -o $@ -- $(bindgen_c_flags_final) -DMODULE \
+		$(bindgen_target_cflags) $(bindgen_target_extra)
+
+$(obj)/bindings/bindings_generated.rs: private bindgen_target_flags = \
+    $(shell grep -v '^\#\|^$$' $(srctree)/$(src)/bindgen_parameters)
+$(obj)/bindings/bindings_generated.rs: $(src)/bindings/bindings_helper.h \
+    $(src)/bindgen_parameters FORCE
+	$(call if_changed_dep,bindgen)
+
+# See `CFLAGS_REMOVE_helpers.o` above. In addition, Clang on C does not warn
+# with `-Wmissing-declarations` (unlike GCC), so it is not strictly needed here
+# given it is `libclang`; but for consistency, future Clang changes and/or
+# a potential future GCC backend for `bindgen`, we disable it too.
+$(obj)/bindings/bindings_helpers_generated.rs: private bindgen_target_flags = \
+    --blacklist-type '.*' --whitelist-var '' \
+    --whitelist-function 'rust_helper_.*'
+$(obj)/bindings/bindings_helpers_generated.rs: private bindgen_target_cflags = \
+    -I$(objtree)/$(obj) -Wno-missing-prototypes -Wno-missing-declarations
+$(obj)/bindings/bindings_helpers_generated.rs: private bindgen_target_extra = ; \
+    sed -Ei 's/pub fn rust_helper_([a-zA-Z0-9_]*)/#[link_name="rust_helper_\1"]\n    pub fn \1/g' $@
+$(obj)/bindings/bindings_helpers_generated.rs: $(src)/helpers.c FORCE
+	$(call if_changed_dep,bindgen)
+
+quiet_cmd_exports = EXPORTS $@
+      cmd_exports = \
+	$(NM) -p --defined-only $< \
+		| grep -E ' (T|R|D) ' | cut -d ' ' -f 3 \
+		| xargs -Isymbol \
+		echo 'EXPORT_SYMBOL_RUST_GPL(symbol);' > $@
+
+$(obj)/exports_core_generated.h: $(obj)/core.o FORCE
+	$(call if_changed,exports)
+
+$(obj)/exports_alloc_generated.h: $(obj)/alloc.o FORCE
+	$(call if_changed,exports)
+
+$(obj)/exports_bindings_generated.h: $(obj)/bindings.o FORCE
+	$(call if_changed,exports)
+
+$(obj)/exports_kernel_generated.h: $(obj)/kernel.o FORCE
+	$(call if_changed,exports)
+
+quiet_cmd_rustc_procmacro = $(RUSTC_OR_CLIPPY_QUIET) P $@
+      cmd_rustc_procmacro = \
+	$(RUSTC_OR_CLIPPY) $(rust_common_flags) \
+		--emit=dep-info,link --extern proc_macro \
+		--crate-type proc-macro --out-dir $(objtree)/$(obj) \
+		--crate-name $(patsubst lib%.so,%,$(notdir $@)) $<; \
+	mv $(objtree)/$(obj)/$(patsubst lib%.so,%,$(notdir $@)).d $(depfile); \
+	sed -i '/^\#/d' $(depfile)
+
+# Procedural macros can only be used with the `rustc` that compiled it.
+# Therefore, to get `libmacros.so` automatically recompiled when the compiler
+# version changes, we add `core.o` as a dependency (even if it is not needed).
+$(obj)/libmacros.so: $(src)/macros/lib.rs $(obj)/core.o FORCE
+	$(call if_changed_dep,rustc_procmacro)
+
+quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L $@
+      cmd_rustc_library = \
+	OBJTREE=$(abspath $(objtree)) \
+	$(if $(skip_clippy),$(RUSTC),$(RUSTC_OR_CLIPPY)) \
+		$(filter-out $(skip_flags),$(rust_flags) $(rustc_target_flags)) \
+		--emit=dep-info,obj,metadata --crate-type rlib \
+		--out-dir $(objtree)/$(obj) -L$(objtree)/$(obj) \
+		--crate-name $(patsubst %.o,%,$(notdir $@)) $<; \
+	mv $(objtree)/$(obj)/$(patsubst %.o,%,$(notdir $@)).d $(depfile); \
+	sed -i '/^\#/d' $(depfile) \
+	$(if $(rustc_objcopy),;$(OBJCOPY) $(rustc_objcopy) $@)
+
+rust-analyzer:
+	$(Q)$(srctree)/scripts/generate_rust_analyzer.py $(srctree) $(objtree) \
+		$(RUST_LIB_SRC) > $(objtree)/rust-project.json
+
+$(obj)/core.o: private skip_clippy = 1
+$(obj)/core.o: private skip_flags = -Dunreachable_pub
+$(obj)/core.o: private rustc_target_flags = $(core-cfgs)
+$(obj)/core.o: $(RUST_LIB_SRC)/core/src/lib.rs $(obj)/target.json FORCE
+	$(call if_changed_dep,rustc_library)
+
+$(obj)/compiler_builtins.o: private rustc_objcopy = -w -W '__*'
+$(obj)/compiler_builtins.o: $(src)/compiler_builtins.rs $(obj)/core.o FORCE
+	$(call if_changed_dep,rustc_library)
+
+$(obj)/alloc.o: private skip_clippy = 1
+$(obj)/alloc.o: private skip_flags = -Dunreachable_pub
+$(obj)/alloc.o: private rustc_target_flags = $(alloc-cfgs)
+$(obj)/alloc.o: $(src)/alloc/lib.rs $(obj)/compiler_builtins.o FORCE
+	$(call if_changed_dep,rustc_library)
+
+$(obj)/bindings.o: $(src)/bindings/lib.rs \
+    $(obj)/compiler_builtins.o \
+    $(obj)/bindings/bindings_generated.rs \
+    $(obj)/bindings/bindings_helpers_generated.rs FORCE
+	$(call if_changed_dep,rustc_library)
+
+$(obj)/kernel.o: private rustc_target_flags = --extern alloc \
+    --extern macros --extern bindings
+$(obj)/kernel.o: $(src)/kernel/lib.rs $(obj)/alloc.o \
+    $(obj)/libmacros.so $(obj)/bindings.o FORCE
+	$(call if_changed_dep,rustc_library)
+
+endif # CONFIG_RUST
diff --git a/rust/alloc/README.md b/rust/alloc/README.md
new file mode 100644
index 000000000000..c89c753720b5
--- /dev/null
+++ b/rust/alloc/README.md
@@ -0,0 +1,33 @@
+# `alloc`
+
+These source files come from the Rust standard library, hosted in
+the <https://github.com/rust-lang/rust> repository, licensed under
+"Apache-2.0 OR MIT" and adapted for kernel use. For copyright details,
+see <https://github.com/rust-lang/rust/blob/master/COPYRIGHT>.
+
+Please note that these files should be kept as close as possible to
+upstream. In general, only additions should be performed (e.g. new
+methods). Eventually, changes should make it into upstream so that,
+at some point, this fork can be dropped from the kernel tree.
+
+
+## Rationale
+
+On one hand, kernel folks wanted to keep `alloc` in-tree to have more
+freedom in both workflow and actual features if actually needed
+(e.g. receiver types if we ended up using them), which is reasonable.
+
+On the other hand, Rust folks wanted to keep `alloc` as close as
+upstream as possible and avoid as much divergence as possible, which
+is also reasonable.
+
+We agreed on a middle-ground: we would keep a subset of `alloc`
+in-tree that would be as small and as close as possible to upstream.
+Then, upstream can start adding the functions that we add to `alloc`
+etc., until we reach a point where the kernel already knows exactly
+what it needs in `alloc` and all the new methods are merged into
+upstream, so that we can drop `alloc` from the kernel tree and go back
+to using the upstream one.
+
+By doing this, the kernel can go a bit faster now, and Rust can
+slowly incorporate and discuss the changes as needed.
diff --git a/rust/alloc/alloc.rs b/rust/alloc/alloc.rs
new file mode 100644
index 000000000000..ca224a541770
--- /dev/null
+++ b/rust/alloc/alloc.rs
@@ -0,0 +1,440 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+//! Memory allocation APIs
+
+#![stable(feature = "alloc_module", since = "1.28.0")]
+
+#[cfg(not(test))]
+use core::intrinsics;
+use core::intrinsics::{min_align_of_val, size_of_val};
+
+use core::ptr::Unique;
+#[cfg(not(test))]
+use core::ptr::{self, NonNull};
+
+#[stable(feature = "alloc_module", since = "1.28.0")]
+#[doc(inline)]
+pub use core::alloc::*;
+
+use core::marker::Destruct;
+
+#[cfg(test)]
+mod tests;
+
+extern "Rust" {
+    // These are the magic symbols to call the global allocator.  rustc generates
+    // them to call `__rg_alloc` etc. if there is a `#[global_allocator]` attribute
+    // (the code expanding that attribute macro generates those functions), or to call
+    // the default implementations in libstd (`__rdl_alloc` etc. in `library/std/src/alloc.rs`)
+    // otherwise.
+    // The rustc fork of LLVM also special-cases these function names to be able to optimize them
+    // like `malloc`, `realloc`, and `free`, respectively.
+    #[rustc_allocator]
+    #[rustc_allocator_nounwind]
+    fn __rust_alloc(size: usize, align: usize) -> *mut u8;
+    #[rustc_allocator_nounwind]
+    fn __rust_dealloc(ptr: *mut u8, size: usize, align: usize);
+    #[rustc_allocator_nounwind]
+    fn __rust_realloc(ptr: *mut u8, old_size: usize, align: usize, new_size: usize) -> *mut u8;
+    #[rustc_allocator_nounwind]
+    fn __rust_alloc_zeroed(size: usize, align: usize) -> *mut u8;
+}
+
+/// The global memory allocator.
+///
+/// This type implements the [`Allocator`] trait by forwarding calls
+/// to the allocator registered with the `#[global_allocator]` attribute
+/// if there is one, or the `std` crate’s default.
+///
+/// Note: while this type is unstable, the functionality it provides can be
+/// accessed through the [free functions in `alloc`](self#functions).
+#[unstable(feature = "allocator_api", issue = "32838")]
+#[derive(Copy, Clone, Default, Debug)]
+#[cfg(not(test))]
+pub struct Global;
+
+#[cfg(test)]
+pub use std::alloc::Global;
+
+/// Allocate memory with the global allocator.
+///
+/// This function forwards calls to the [`GlobalAlloc::alloc`] method
+/// of the allocator registered with the `#[global_allocator]` attribute
+/// if there is one, or the `std` crate’s default.
+///
+/// This function is expected to be deprecated in favor of the `alloc` method
+/// of the [`Global`] type when it and the [`Allocator`] trait become stable.
+///
+/// # Safety
+///
+/// See [`GlobalAlloc::alloc`].
+///
+/// # Examples
+///
+/// ```
+/// use std::alloc::{alloc, dealloc, Layout};
+///
+/// unsafe {
+///     let layout = Layout::new::<u16>();
+///     let ptr = alloc(layout);
+///
+///     *(ptr as *mut u16) = 42;
+///     assert_eq!(*(ptr as *mut u16), 42);
+///
+///     dealloc(ptr, layout);
+/// }
+/// ```
+#[stable(feature = "global_alloc", since = "1.28.0")]
+#[must_use = "losing the pointer will leak memory"]
+#[inline]
+pub unsafe fn alloc(layout: Layout) -> *mut u8 {
+    unsafe { __rust_alloc(layout.size(), layout.align()) }
+}
+
+/// Deallocate memory with the global allocator.
+///
+/// This function forwards calls to the [`GlobalAlloc::dealloc`] method
+/// of the allocator registered with the `#[global_allocator]` attribute
+/// if there is one, or the `std` crate’s default.
+///
+/// This function is expected to be deprecated in favor of the `dealloc` method
+/// of the [`Global`] type when it and the [`Allocator`] trait become stable.
+///
+/// # Safety
+///
+/// See [`GlobalAlloc::dealloc`].
+#[stable(feature = "global_alloc", since = "1.28.0")]
+#[inline]
+pub unsafe fn dealloc(ptr: *mut u8, layout: Layout) {
+    unsafe { __rust_dealloc(ptr, layout.size(), layout.align()) }
+}
+
+/// Reallocate memory with the global allocator.
+///
+/// This function forwards calls to the [`GlobalAlloc::realloc`] method
+/// of the allocator registered with the `#[global_allocator]` attribute
+/// if there is one, or the `std` crate’s default.
+///
+/// This function is expected to be deprecated in favor of the `realloc` method
+/// of the [`Global`] type when it and the [`Allocator`] trait become stable.
+///
+/// # Safety
+///
+/// See [`GlobalAlloc::realloc`].
+#[stable(feature = "global_alloc", since = "1.28.0")]
+#[must_use = "losing the pointer will leak memory"]
+#[inline]
+pub unsafe fn realloc(ptr: *mut u8, layout: Layout, new_size: usize) -> *mut u8 {
+    unsafe { __rust_realloc(ptr, layout.size(), layout.align(), new_size) }
+}
+
+/// Allocate zero-initialized memory with the global allocator.
+///
+/// This function forwards calls to the [`GlobalAlloc::alloc_zeroed`] method
+/// of the allocator registered with the `#[global_allocator]` attribute
+/// if there is one, or the `std` crate’s default.
+///
+/// This function is expected to be deprecated in favor of the `alloc_zeroed` method
+/// of the [`Global`] type when it and the [`Allocator`] trait become stable.
+///
+/// # Safety
+///
+/// See [`GlobalAlloc::alloc_zeroed`].
+///
+/// # Examples
+///
+/// ```
+/// use std::alloc::{alloc_zeroed, dealloc, Layout};
+///
+/// unsafe {
+///     let layout = Layout::new::<u16>();
+///     let ptr = alloc_zeroed(layout);
+///
+///     assert_eq!(*(ptr as *mut u16), 0);
+///
+///     dealloc(ptr, layout);
+/// }
+/// ```
+#[stable(feature = "global_alloc", since = "1.28.0")]
+#[must_use = "losing the pointer will leak memory"]
+#[inline]
+pub unsafe fn alloc_zeroed(layout: Layout) -> *mut u8 {
+    unsafe { __rust_alloc_zeroed(layout.size(), layout.align()) }
+}
+
+#[cfg(not(test))]
+impl Global {
+    #[inline]
+    fn alloc_impl(&self, layout: Layout, zeroed: bool) -> Result<NonNull<[u8]>, AllocError> {
+        match layout.size() {
+            0 => Ok(NonNull::slice_from_raw_parts(layout.dangling(), 0)),
+            // SAFETY: `layout` is non-zero in size,
+            size => unsafe {
+                let raw_ptr = if zeroed { alloc_zeroed(layout) } else { alloc(layout) };
+                let ptr = NonNull::new(raw_ptr).ok_or(AllocError)?;
+                Ok(NonNull::slice_from_raw_parts(ptr, size))
+            },
+        }
+    }
+
+    // SAFETY: Same as `Allocator::grow`
+    #[inline]
+    unsafe fn grow_impl(
+        &self,
+        ptr: NonNull<u8>,
+        old_layout: Layout,
+        new_layout: Layout,
+        zeroed: bool,
+    ) -> Result<NonNull<[u8]>, AllocError> {
+        debug_assert!(
+            new_layout.size() >= old_layout.size(),
+            "`new_layout.size()` must be greater than or equal to `old_layout.size()`"
+        );
+
+        match old_layout.size() {
+            0 => self.alloc_impl(new_layout, zeroed),
+
+            // SAFETY: `new_size` is non-zero as `old_size` is greater than or equal to `new_size`
+            // as required by safety conditions. Other conditions must be upheld by the caller
+            old_size if old_layout.align() == new_layout.align() => unsafe {
+                let new_size = new_layout.size();
+
+                // `realloc` probably checks for `new_size >= old_layout.size()` or something similar.
+                intrinsics::assume(new_size >= old_layout.size());
+
+                let raw_ptr = realloc(ptr.as_ptr(), old_layout, new_size);
+                let ptr = NonNull::new(raw_ptr).ok_or(AllocError)?;
+                if zeroed {
+                    raw_ptr.add(old_size).write_bytes(0, new_size - old_size);
+                }
+                Ok(NonNull::slice_from_raw_parts(ptr, new_size))
+            },
+
+            // SAFETY: because `new_layout.size()` must be greater than or equal to `old_size`,
+            // both the old and new memory allocation are valid for reads and writes for `old_size`
+            // bytes. Also, because the old allocation wasn't yet deallocated, it cannot overlap
+            // `new_ptr`. Thus, the call to `copy_nonoverlapping` is safe. The safety contract
+            // for `dealloc` must be upheld by the caller.
+            old_size => unsafe {
+                let new_ptr = self.alloc_impl(new_layout, zeroed)?;
+                ptr::copy_nonoverlapping(ptr.as_ptr(), new_ptr.as_mut_ptr(), old_size);
+                self.deallocate(ptr, old_layout);
+                Ok(new_ptr)
+            },
+        }
+    }
+}
+
+#[unstable(feature = "allocator_api", issue = "32838")]
+#[cfg(not(test))]
+unsafe impl Allocator for Global {
+    #[inline]
+    fn allocate(&self, layout: Layout) -> Result<NonNull<[u8]>, AllocError> {
+        self.alloc_impl(layout, false)
+    }
+
+    #[inline]
+    fn allocate_zeroed(&self, layout: Layout) -> Result<NonNull<[u8]>, AllocError> {
+        self.alloc_impl(layout, true)
+    }
+
+    #[inline]
+    unsafe fn deallocate(&self, ptr: NonNull<u8>, layout: Layout) {
+        if layout.size() != 0 {
+            // SAFETY: `layout` is non-zero in size,
+            // other conditions must be upheld by the caller
+            unsafe { dealloc(ptr.as_ptr(), layout) }
+        }
+    }
+
+    #[inline]
+    unsafe fn grow(
+        &self,
+        ptr: NonNull<u8>,
+        old_layout: Layout,
+        new_layout: Layout,
+    ) -> Result<NonNull<[u8]>, AllocError> {
+        // SAFETY: all conditions must be upheld by the caller
+        unsafe { self.grow_impl(ptr, old_layout, new_layout, false) }
+    }
+
+    #[inline]
+    unsafe fn grow_zeroed(
+        &self,
+        ptr: NonNull<u8>,
+        old_layout: Layout,
+        new_layout: Layout,
+    ) -> Result<NonNull<[u8]>, AllocError> {
+        // SAFETY: all conditions must be upheld by the caller
+        unsafe { self.grow_impl(ptr, old_layout, new_layout, true) }
+    }
+
+    #[inline]
+    unsafe fn shrink(
+        &self,
+        ptr: NonNull<u8>,
+        old_layout: Layout,
+        new_layout: Layout,
+    ) -> Result<NonNull<[u8]>, AllocError> {
+        debug_assert!(
+            new_layout.size() <= old_layout.size(),
+            "`new_layout.size()` must be smaller than or equal to `old_layout.size()`"
+        );
+
+        match new_layout.size() {
+            // SAFETY: conditions must be upheld by the caller
+            0 => unsafe {
+                self.deallocate(ptr, old_layout);
+                Ok(NonNull::slice_from_raw_parts(new_layout.dangling(), 0))
+            },
+
+            // SAFETY: `new_size` is non-zero. Other conditions must be upheld by the caller
+            new_size if old_layout.align() == new_layout.align() => unsafe {
+                // `realloc` probably checks for `new_size <= old_layout.size()` or something similar.
+                intrinsics::assume(new_size <= old_layout.size());
+
+                let raw_ptr = realloc(ptr.as_ptr(), old_layout, new_size);
+                let ptr = NonNull::new(raw_ptr).ok_or(AllocError)?;
+                Ok(NonNull::slice_from_raw_parts(ptr, new_size))
+            },
+
+            // SAFETY: because `new_size` must be smaller than or equal to `old_layout.size()`,
+            // both the old and new memory allocation are valid for reads and writes for `new_size`
+            // bytes. Also, because the old allocation wasn't yet deallocated, it cannot overlap
+            // `new_ptr`. Thus, the call to `copy_nonoverlapping` is safe. The safety contract
+            // for `dealloc` must be upheld by the caller.
+            new_size => unsafe {
+                let new_ptr = self.allocate(new_layout)?;
+                ptr::copy_nonoverlapping(ptr.as_ptr(), new_ptr.as_mut_ptr(), new_size);
+                self.deallocate(ptr, old_layout);
+                Ok(new_ptr)
+            },
+        }
+    }
+}
+
+/// The allocator for unique pointers.
+#[cfg(all(not(no_global_oom_handling), not(test)))]
+#[lang = "exchange_malloc"]
+#[inline]
+unsafe fn exchange_malloc(size: usize, align: usize) -> *mut u8 {
+    let layout = unsafe { Layout::from_size_align_unchecked(size, align) };
+    match Global.allocate(layout) {
+        Ok(ptr) => ptr.as_mut_ptr(),
+        Err(_) => handle_alloc_error(layout),
+    }
+}
+
+#[cfg_attr(not(test), lang = "box_free")]
+#[inline]
+#[rustc_const_unstable(feature = "const_box", issue = "92521")]
+// This signature has to be the same as `Box`, otherwise an ICE will happen.
+// When an additional parameter to `Box` is added (like `A: Allocator`), this has to be added here as
+// well.
+// For example if `Box` is changed to  `struct Box<T: ?Sized, A: Allocator>(Unique<T>, A)`,
+// this function has to be changed to `fn box_free<T: ?Sized, A: Allocator>(Unique<T>, A)` as well.
+pub(crate) const unsafe fn box_free<T: ?Sized, A: ~const Allocator + ~const Destruct>(
+    ptr: Unique<T>,
+    alloc: A,
+) {
+    unsafe {
+        let size = size_of_val(ptr.as_ref());
+        let align = min_align_of_val(ptr.as_ref());
+        let layout = Layout::from_size_align_unchecked(size, align);
+        alloc.deallocate(From::from(ptr.cast()), layout)
+    }
+}
+
+// # Allocation error handler
+
+#[cfg(not(no_global_oom_handling))]
+extern "Rust" {
+    // This is the magic symbol to call the global alloc error handler.  rustc generates
+    // it to call `__rg_oom` if there is a `#[alloc_error_handler]`, or to call the
+    // default implementations below (`__rdl_oom`) otherwise.
+    fn __rust_alloc_error_handler(size: usize, align: usize) -> !;
+}
+
+/// Abort on memory allocation error or failure.
+///
+/// Callers of memory allocation APIs wishing to abort computation
+/// in response to an allocation error are encouraged to call this function,
+/// rather than directly invoking `panic!` or similar.
+///
+/// The default behavior of this function is to print a message to standard error
+/// and abort the process.
+/// It can be replaced with [`set_alloc_error_hook`] and [`take_alloc_error_hook`].
+///
+/// [`set_alloc_error_hook`]: ../../std/alloc/fn.set_alloc_error_hook.html
+/// [`take_alloc_error_hook`]: ../../std/alloc/fn.take_alloc_error_hook.html
+#[stable(feature = "global_alloc", since = "1.28.0")]
+#[rustc_const_unstable(feature = "const_alloc_error", issue = "92523")]
+#[cfg(all(not(no_global_oom_handling), not(test)))]
+#[cold]
+pub const fn handle_alloc_error(layout: Layout) -> ! {
+    const fn ct_error(_: Layout) -> ! {
+        panic!("allocation failed");
+    }
+
+    fn rt_error(layout: Layout) -> ! {
+        unsafe {
+            __rust_alloc_error_handler(layout.size(), layout.align());
+        }
+    }
+
+    unsafe { core::intrinsics::const_eval_select((layout,), ct_error, rt_error) }
+}
+
+// For alloc test `std::alloc::handle_alloc_error` can be used directly.
+#[cfg(all(not(no_global_oom_handling), test))]
+pub use std::alloc::handle_alloc_error;
+
+#[cfg(all(not(no_global_oom_handling), not(test)))]
+#[doc(hidden)]
+#[allow(unused_attributes)]
+#[unstable(feature = "alloc_internals", issue = "none")]
+pub mod __alloc_error_handler {
+    use crate::alloc::Layout;
+
+    // called via generated `__rust_alloc_error_handler`
+
+    // if there is no `#[alloc_error_handler]`
+    #[rustc_std_internal_symbol]
+    pub unsafe extern "C-unwind" fn __rdl_oom(size: usize, _align: usize) -> ! {
+        panic!("memory allocation of {size} bytes failed")
+    }
+
+    // if there is an `#[alloc_error_handler]`
+    #[rustc_std_internal_symbol]
+    pub unsafe extern "C-unwind" fn __rg_oom(size: usize, align: usize) -> ! {
+        let layout = unsafe { Layout::from_size_align_unchecked(size, align) };
+        extern "Rust" {
+            #[lang = "oom"]
+            fn oom_impl(layout: Layout) -> !;
+        }
+        unsafe { oom_impl(layout) }
+    }
+}
+
+/// Specialize clones into pre-allocated, uninitialized memory.
+/// Used by `Box::clone` and `Rc`/`Arc::make_mut`.
+pub(crate) trait WriteCloneIntoRaw: Sized {
+    unsafe fn write_clone_into_raw(&self, target: *mut Self);
+}
+
+impl<T: Clone> WriteCloneIntoRaw for T {
+    #[inline]
+    default unsafe fn write_clone_into_raw(&self, target: *mut Self) {
+        // Having allocated *first* may allow the optimizer to create
+        // the cloned value in-place, skipping the local and move.
+        unsafe { target.write(self.clone()) };
+    }
+}
+
+impl<T: Copy> WriteCloneIntoRaw for T {
+    #[inline]
+    unsafe fn write_clone_into_raw(&self, target: *mut Self) {
+        // We can always copy in-place, without ever involving a local value.
+        unsafe { target.copy_from_nonoverlapping(self, 1) };
+    }
+}
diff --git a/rust/alloc/borrow.rs b/rust/alloc/borrow.rs
new file mode 100644
index 000000000000..dde4957200d4
--- /dev/null
+++ b/rust/alloc/borrow.rs
@@ -0,0 +1,498 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+//! A module for working with borrowed data.
+
+#![stable(feature = "rust1", since = "1.0.0")]
+
+use core::cmp::Ordering;
+use core::hash::{Hash, Hasher};
+use core::ops::Deref;
+#[cfg(not(no_global_oom_handling))]
+use core::ops::{Add, AddAssign};
+
+#[stable(feature = "rust1", since = "1.0.0")]
+pub use core::borrow::{Borrow, BorrowMut};
+
+use core::fmt;
+#[cfg(not(no_global_oom_handling))]
+use crate::string::String;
+
+use Cow::*;
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<'a, B: ?Sized> Borrow<B> for Cow<'a, B>
+where
+    B: ToOwned,
+    <B as ToOwned>::Owned: 'a,
+{
+    fn borrow(&self) -> &B {
+        &**self
+    }
+}
+
+/// A generalization of `Clone` to borrowed data.
+///
+/// Some types make it possible to go from borrowed to owned, usually by
+/// implementing the `Clone` trait. But `Clone` works only for going from `&T`
+/// to `T`. The `ToOwned` trait generalizes `Clone` to construct owned data
+/// from any borrow of a given type.
+#[cfg_attr(not(test), rustc_diagnostic_item = "ToOwned")]
+#[stable(feature = "rust1", since = "1.0.0")]
+pub trait ToOwned {
+    /// The resulting type after obtaining ownership.
+    #[stable(feature = "rust1", since = "1.0.0")]
+    type Owned: Borrow<Self>;
+
+    /// Creates owned data from borrowed data, usually by cloning.
+    ///
+    /// # Examples
+    ///
+    /// Basic usage:
+    ///
+    /// ```
+    /// let s: &str = "a";
+    /// let ss: String = s.to_owned();
+    ///
+    /// let v: &[i32] = &[1, 2];
+    /// let vv: Vec<i32> = v.to_owned();
+    /// ```
+    #[stable(feature = "rust1", since = "1.0.0")]
+    #[must_use = "cloning is often expensive and is not expected to have side effects"]
+    fn to_owned(&self) -> Self::Owned;
+
+    /// Uses borrowed data to replace owned data, usually by cloning.
+    ///
+    /// This is borrow-generalized version of `Clone::clone_from`.
+    ///
+    /// # Examples
+    ///
+    /// Basic usage:
+    ///
+    /// ```
+    /// # #![feature(toowned_clone_into)]
+    /// let mut s: String = String::new();
+    /// "hello".clone_into(&mut s);
+    ///
+    /// let mut v: Vec<i32> = Vec::new();
+    /// [1, 2][..].clone_into(&mut v);
+    /// ```
+    #[unstable(feature = "toowned_clone_into", reason = "recently added", issue = "41263")]
+    fn clone_into(&self, target: &mut Self::Owned) {
+        *target = self.to_owned();
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T> ToOwned for T
+where
+    T: Clone,
+{
+    type Owned = T;
+    fn to_owned(&self) -> T {
+        self.clone()
+    }
+
+    fn clone_into(&self, target: &mut T) {
+        target.clone_from(self);
+    }
+}
+
+/// A clone-on-write smart pointer.
+///
+/// The type `Cow` is a smart pointer providing clone-on-write functionality: it
+/// can enclose and provide immutable access to borrowed data, and clone the
+/// data lazily when mutation or ownership is required. The type is designed to
+/// work with general borrowed data via the `Borrow` trait.
+///
+/// `Cow` implements `Deref`, which means that you can call
+/// non-mutating methods directly on the data it encloses. If mutation
+/// is desired, `to_mut` will obtain a mutable reference to an owned
+/// value, cloning if necessary.
+///
+/// If you need reference-counting pointers, note that
+/// [`Rc::make_mut`][crate::rc::Rc::make_mut] and
+/// [`Arc::make_mut`][crate::sync::Arc::make_mut] can provide clone-on-write
+/// functionality as well.
+///
+/// # Examples
+///
+/// ```
+/// use std::borrow::Cow;
+///
+/// fn abs_all(input: &mut Cow<[i32]>) {
+///     for i in 0..input.len() {
+///         let v = input[i];
+///         if v < 0 {
+///             // Clones into a vector if not already owned.
+///             input.to_mut()[i] = -v;
+///         }
+///     }
+/// }
+///
+/// // No clone occurs because `input` doesn't need to be mutated.
+/// let slice = [0, 1, 2];
+/// let mut input = Cow::from(&slice[..]);
+/// abs_all(&mut input);
+///
+/// // Clone occurs because `input` needs to be mutated.
+/// let slice = [-1, 0, 1];
+/// let mut input = Cow::from(&slice[..]);
+/// abs_all(&mut input);
+///
+/// // No clone occurs because `input` is already owned.
+/// let mut input = Cow::from(vec![-1, 0, 1]);
+/// abs_all(&mut input);
+/// ```
+///
+/// Another example showing how to keep `Cow` in a struct:
+///
+/// ```
+/// use std::borrow::Cow;
+///
+/// struct Items<'a, X: 'a> where [X]: ToOwned<Owned = Vec<X>> {
+///     values: Cow<'a, [X]>,
+/// }
+///
+/// impl<'a, X: Clone + 'a> Items<'a, X> where [X]: ToOwned<Owned = Vec<X>> {
+///     fn new(v: Cow<'a, [X]>) -> Self {
+///         Items { values: v }
+///     }
+/// }
+///
+/// // Creates a container from borrowed values of a slice
+/// let readonly = [1, 2];
+/// let borrowed = Items::new((&readonly[..]).into());
+/// match borrowed {
+///     Items { values: Cow::Borrowed(b) } => println!("borrowed {b:?}"),
+///     _ => panic!("expect borrowed value"),
+/// }
+///
+/// let mut clone_on_write = borrowed;
+/// // Mutates the data from slice into owned vec and pushes a new value on top
+/// clone_on_write.values.to_mut().push(3);
+/// println!("clone_on_write = {:?}", clone_on_write.values);
+///
+/// // The data was mutated. Let's check it out.
+/// match clone_on_write {
+///     Items { values: Cow::Owned(_) } => println!("clone_on_write contains owned data"),
+///     _ => panic!("expect owned data"),
+/// }
+/// ```
+#[stable(feature = "rust1", since = "1.0.0")]
+#[cfg_attr(not(test), rustc_diagnostic_item = "Cow")]
+pub enum Cow<'a, B: ?Sized + 'a>
+where
+    B: ToOwned,
+{
+    /// Borrowed data.
+    #[stable(feature = "rust1", since = "1.0.0")]
+    Borrowed(#[stable(feature = "rust1", since = "1.0.0")] &'a B),
+
+    /// Owned data.
+    #[stable(feature = "rust1", since = "1.0.0")]
+    Owned(#[stable(feature = "rust1", since = "1.0.0")] <B as ToOwned>::Owned),
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<B: ?Sized + ToOwned> Clone for Cow<'_, B> {
+    fn clone(&self) -> Self {
+        match *self {
+            Borrowed(b) => Borrowed(b),
+            Owned(ref o) => {
+                let b: &B = o.borrow();
+                Owned(b.to_owned())
+            }
+        }
+    }
+
+    fn clone_from(&mut self, source: &Self) {
+        match (self, source) {
+            (&mut Owned(ref mut dest), &Owned(ref o)) => o.borrow().clone_into(dest),
+            (t, s) => *t = s.clone(),
+        }
+    }
+}
+
+impl<B: ?Sized + ToOwned> Cow<'_, B> {
+    /// Returns true if the data is borrowed, i.e. if `to_mut` would require additional work.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(cow_is_borrowed)]
+    /// use std::borrow::Cow;
+    ///
+    /// let cow = Cow::Borrowed("moo");
+    /// assert!(cow.is_borrowed());
+    ///
+    /// let bull: Cow<'_, str> = Cow::Owned("...moo?".to_string());
+    /// assert!(!bull.is_borrowed());
+    /// ```
+    #[unstable(feature = "cow_is_borrowed", issue = "65143")]
+    #[rustc_const_unstable(feature = "const_cow_is_borrowed", issue = "65143")]
+    pub const fn is_borrowed(&self) -> bool {
+        match *self {
+            Borrowed(_) => true,
+            Owned(_) => false,
+        }
+    }
+
+    /// Returns true if the data is owned, i.e. if `to_mut` would be a no-op.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(cow_is_borrowed)]
+    /// use std::borrow::Cow;
+    ///
+    /// let cow: Cow<'_, str> = Cow::Owned("moo".to_string());
+    /// assert!(cow.is_owned());
+    ///
+    /// let bull = Cow::Borrowed("...moo?");
+    /// assert!(!bull.is_owned());
+    /// ```
+    #[unstable(feature = "cow_is_borrowed", issue = "65143")]
+    #[rustc_const_unstable(feature = "const_cow_is_borrowed", issue = "65143")]
+    pub const fn is_owned(&self) -> bool {
+        !self.is_borrowed()
+    }
+
+    /// Acquires a mutable reference to the owned form of the data.
+    ///
+    /// Clones the data if it is not already owned.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use std::borrow::Cow;
+    ///
+    /// let mut cow = Cow::Borrowed("foo");
+    /// cow.to_mut().make_ascii_uppercase();
+    ///
+    /// assert_eq!(
+    ///   cow,
+    ///   Cow::Owned(String::from("FOO")) as Cow<str>
+    /// );
+    /// ```
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn to_mut(&mut self) -> &mut <B as ToOwned>::Owned {
+        match *self {
+            Borrowed(borrowed) => {
+                *self = Owned(borrowed.to_owned());
+                match *self {
+                    Borrowed(..) => unreachable!(),
+                    Owned(ref mut owned) => owned,
+                }
+            }
+            Owned(ref mut owned) => owned,
+        }
+    }
+
+    /// Extracts the owned data.
+    ///
+    /// Clones the data if it is not already owned.
+    ///
+    /// # Examples
+    ///
+    /// Calling `into_owned` on a `Cow::Borrowed` returns a clone of the borrowed data:
+    ///
+    /// ```
+    /// use std::borrow::Cow;
+    ///
+    /// let s = "Hello world!";
+    /// let cow = Cow::Borrowed(s);
+    ///
+    /// assert_eq!(
+    ///   cow.into_owned(),
+    ///   String::from(s)
+    /// );
+    /// ```
+    ///
+    /// Calling `into_owned` on a `Cow::Owned` returns the owned data. The data is moved out of the
+    /// `Cow` without being cloned.
+    ///
+    /// ```
+    /// use std::borrow::Cow;
+    ///
+    /// let s = "Hello world!";
+    /// let cow: Cow<str> = Cow::Owned(String::from(s));
+    ///
+    /// assert_eq!(
+    ///   cow.into_owned(),
+    ///   String::from(s)
+    /// );
+    /// ```
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn into_owned(self) -> <B as ToOwned>::Owned {
+        match self {
+            Borrowed(borrowed) => borrowed.to_owned(),
+            Owned(owned) => owned,
+        }
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+#[rustc_const_unstable(feature = "const_deref", issue = "88955")]
+impl<B: ?Sized + ToOwned> const Deref for Cow<'_, B>
+where
+    B::Owned: ~const Borrow<B>,
+{
+    type Target = B;
+
+    fn deref(&self) -> &B {
+        match *self {
+            Borrowed(borrowed) => borrowed,
+            Owned(ref owned) => owned.borrow(),
+        }
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<B: ?Sized> Eq for Cow<'_, B> where B: Eq + ToOwned {}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<B: ?Sized> Ord for Cow<'_, B>
+where
+    B: Ord + ToOwned,
+{
+    #[inline]
+    fn cmp(&self, other: &Self) -> Ordering {
+        Ord::cmp(&**self, &**other)
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<'a, 'b, B: ?Sized, C: ?Sized> PartialEq<Cow<'b, C>> for Cow<'a, B>
+where
+    B: PartialEq<C> + ToOwned,
+    C: ToOwned,
+{
+    #[inline]
+    fn eq(&self, other: &Cow<'b, C>) -> bool {
+        PartialEq::eq(&**self, &**other)
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<'a, B: ?Sized> PartialOrd for Cow<'a, B>
+where
+    B: PartialOrd + ToOwned,
+{
+    #[inline]
+    fn partial_cmp(&self, other: &Cow<'a, B>) -> Option<Ordering> {
+        PartialOrd::partial_cmp(&**self, &**other)
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<B: ?Sized> fmt::Debug for Cow<'_, B>
+where
+    B: fmt::Debug + ToOwned<Owned: fmt::Debug>,
+{
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        match *self {
+            Borrowed(ref b) => fmt::Debug::fmt(b, f),
+            Owned(ref o) => fmt::Debug::fmt(o, f),
+        }
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<B: ?Sized> fmt::Display for Cow<'_, B>
+where
+    B: fmt::Display + ToOwned<Owned: fmt::Display>,
+{
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        match *self {
+            Borrowed(ref b) => fmt::Display::fmt(b, f),
+            Owned(ref o) => fmt::Display::fmt(o, f),
+        }
+    }
+}
+
+#[stable(feature = "default", since = "1.11.0")]
+impl<B: ?Sized> Default for Cow<'_, B>
+where
+    B: ToOwned<Owned: Default>,
+{
+    /// Creates an owned Cow<'a, B> with the default value for the contained owned value.
+    fn default() -> Self {
+        Owned(<B as ToOwned>::Owned::default())
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<B: ?Sized> Hash for Cow<'_, B>
+where
+    B: Hash + ToOwned,
+{
+    #[inline]
+    fn hash<H: Hasher>(&self, state: &mut H) {
+        Hash::hash(&**self, state)
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: ?Sized + ToOwned> AsRef<T> for Cow<'_, T> {
+    fn as_ref(&self) -> &T {
+        self
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "cow_add", since = "1.14.0")]
+impl<'a> Add<&'a str> for Cow<'a, str> {
+    type Output = Cow<'a, str>;
+
+    #[inline]
+    fn add(mut self, rhs: &'a str) -> Self::Output {
+        self += rhs;
+        self
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "cow_add", since = "1.14.0")]
+impl<'a> Add<Cow<'a, str>> for Cow<'a, str> {
+    type Output = Cow<'a, str>;
+
+    #[inline]
+    fn add(mut self, rhs: Cow<'a, str>) -> Self::Output {
+        self += rhs;
+        self
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "cow_add", since = "1.14.0")]
+impl<'a> AddAssign<&'a str> for Cow<'a, str> {
+    fn add_assign(&mut self, rhs: &'a str) {
+        if self.is_empty() {
+            *self = Cow::Borrowed(rhs)
+        } else if !rhs.is_empty() {
+            if let Cow::Borrowed(lhs) = *self {
+                let mut s = String::with_capacity(lhs.len() + rhs.len());
+                s.push_str(lhs);
+                *self = Cow::Owned(s);
+            }
+            self.to_mut().push_str(rhs);
+        }
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "cow_add", since = "1.14.0")]
+impl<'a> AddAssign<Cow<'a, str>> for Cow<'a, str> {
+    fn add_assign(&mut self, rhs: Cow<'a, str>) {
+        if self.is_empty() {
+            *self = rhs
+        } else if !rhs.is_empty() {
+            if let Cow::Borrowed(lhs) = *self {
+                let mut s = String::with_capacity(lhs.len() + rhs.len());
+                s.push_str(lhs);
+                *self = Cow::Owned(s);
+            }
+            self.to_mut().push_str(&rhs);
+        }
+    }
+}
diff --git a/rust/alloc/boxed.rs b/rust/alloc/boxed.rs
new file mode 100644
index 000000000000..dcfe87b14f3a
--- /dev/null
+++ b/rust/alloc/boxed.rs
@@ -0,0 +1,2028 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+//! A pointer type for heap allocation.
+//!
+//! [`Box<T>`], casually referred to as a 'box', provides the simplest form of
+//! heap allocation in Rust. Boxes provide ownership for this allocation, and
+//! drop their contents when they go out of scope. Boxes also ensure that they
+//! never allocate more than `isize::MAX` bytes.
+//!
+//! # Examples
+//!
+//! Move a value from the stack to the heap by creating a [`Box`]:
+//!
+//! ```
+//! let val: u8 = 5;
+//! let boxed: Box<u8> = Box::new(val);
+//! ```
+//!
+//! Move a value from a [`Box`] back to the stack by [dereferencing]:
+//!
+//! ```
+//! let boxed: Box<u8> = Box::new(5);
+//! let val: u8 = *boxed;
+//! ```
+//!
+//! Creating a recursive data structure:
+//!
+//! ```
+//! #[derive(Debug)]
+//! enum List<T> {
+//!     Cons(T, Box<List<T>>),
+//!     Nil,
+//! }
+//!
+//! let list: List<i32> = List::Cons(1, Box::new(List::Cons(2, Box::new(List::Nil))));
+//! println!("{list:?}");
+//! ```
+//!
+//! This will print `Cons(1, Cons(2, Nil))`.
+//!
+//! Recursive structures must be boxed, because if the definition of `Cons`
+//! looked like this:
+//!
+//! ```compile_fail,E0072
+//! # enum List<T> {
+//! Cons(T, List<T>),
+//! # }
+//! ```
+//!
+//! It wouldn't work. This is because the size of a `List` depends on how many
+//! elements are in the list, and so we don't know how much memory to allocate
+//! for a `Cons`. By introducing a [`Box<T>`], which has a defined size, we know how
+//! big `Cons` needs to be.
+//!
+//! # Memory layout
+//!
+//! For non-zero-sized values, a [`Box`] will use the [`Global`] allocator for
+//! its allocation. It is valid to convert both ways between a [`Box`] and a
+//! raw pointer allocated with the [`Global`] allocator, given that the
+//! [`Layout`] used with the allocator is correct for the type. More precisely,
+//! a `value: *mut T` that has been allocated with the [`Global`] allocator
+//! with `Layout::for_value(&*value)` may be converted into a box using
+//! [`Box::<T>::from_raw(value)`]. Conversely, the memory backing a `value: *mut
+//! T` obtained from [`Box::<T>::into_raw`] may be deallocated using the
+//! [`Global`] allocator with [`Layout::for_value(&*value)`].
+//!
+//! For zero-sized values, the `Box` pointer still has to be [valid] for reads
+//! and writes and sufficiently aligned. In particular, casting any aligned
+//! non-zero integer literal to a raw pointer produces a valid pointer, but a
+//! pointer pointing into previously allocated memory that since got freed is
+//! not valid. The recommended way to build a Box to a ZST if `Box::new` cannot
+//! be used is to use [`ptr::NonNull::dangling`].
+//!
+//! So long as `T: Sized`, a `Box<T>` is guaranteed to be represented
+//! as a single pointer and is also ABI-compatible with C pointers
+//! (i.e. the C type `T*`). This means that if you have extern "C"
+//! Rust functions that will be called from C, you can define those
+//! Rust functions using `Box<T>` types, and use `T*` as corresponding
+//! type on the C side. As an example, consider this C header which
+//! declares functions that create and destroy some kind of `Foo`
+//! value:
+//!
+//! ```c
+//! /* C header */
+//!
+//! /* Returns ownership to the caller */
+//! struct Foo* foo_new(void);
+//!
+//! /* Takes ownership from the caller; no-op when invoked with null */
+//! void foo_delete(struct Foo*);
+//! ```
+//!
+//! These two functions might be implemented in Rust as follows. Here, the
+//! `struct Foo*` type from C is translated to `Box<Foo>`, which captures
+//! the ownership constraints. Note also that the nullable argument to
+//! `foo_delete` is represented in Rust as `Option<Box<Foo>>`, since `Box<Foo>`
+//! cannot be null.
+//!
+//! ```
+//! #[repr(C)]
+//! pub struct Foo;
+//!
+//! #[no_mangle]
+//! pub extern "C" fn foo_new() -> Box<Foo> {
+//!     Box::new(Foo)
+//! }
+//!
+//! #[no_mangle]
+//! pub extern "C" fn foo_delete(_: Option<Box<Foo>>) {}
+//! ```
+//!
+//! Even though `Box<T>` has the same representation and C ABI as a C pointer,
+//! this does not mean that you can convert an arbitrary `T*` into a `Box<T>`
+//! and expect things to work. `Box<T>` values will always be fully aligned,
+//! non-null pointers. Moreover, the destructor for `Box<T>` will attempt to
+//! free the value with the global allocator. In general, the best practice
+//! is to only use `Box<T>` for pointers that originated from the global
+//! allocator.
+//!
+//! **Important.** At least at present, you should avoid using
+//! `Box<T>` types for functions that are defined in C but invoked
+//! from Rust. In those cases, you should directly mirror the C types
+//! as closely as possible. Using types like `Box<T>` where the C
+//! definition is just using `T*` can lead to undefined behavior, as
+//! described in [rust-lang/unsafe-code-guidelines#198][ucg#198].
+//!
+//! [ucg#198]: https://github.com/rust-lang/unsafe-code-guidelines/issues/198
+//! [dereferencing]: core::ops::Deref
+//! [`Box::<T>::from_raw(value)`]: Box::from_raw
+//! [`Global`]: crate::alloc::Global
+//! [`Layout`]: crate::alloc::Layout
+//! [`Layout::for_value(&*value)`]: crate::alloc::Layout::for_value
+//! [valid]: ptr#safety
+
+#![stable(feature = "rust1", since = "1.0.0")]
+
+use core::any::Any;
+use core::async_iter::AsyncIterator;
+use core::borrow;
+use core::cmp::Ordering;
+use core::convert::{From, TryFrom};
+use core::fmt;
+use core::future::Future;
+use core::hash::{Hash, Hasher};
+#[cfg(not(no_global_oom_handling))]
+use core::iter::FromIterator;
+use core::iter::{FusedIterator, Iterator};
+use core::marker::{Destruct, Unpin, Unsize};
+use core::mem;
+use core::ops::{
+    CoerceUnsized, Deref, DerefMut, DispatchFromDyn, Generator, GeneratorState, Receiver,
+};
+use core::pin::Pin;
+use core::ptr::{self, Unique};
+use core::task::{Context, Poll};
+
+#[cfg(not(no_global_oom_handling))]
+use crate::alloc::{handle_alloc_error, WriteCloneIntoRaw};
+use crate::alloc::{AllocError, Allocator, Global, Layout};
+#[cfg(not(no_global_oom_handling))]
+use crate::borrow::Cow;
+use crate::raw_vec::RawVec;
+#[cfg(not(no_global_oom_handling))]
+use crate::str::from_boxed_utf8_unchecked;
+#[cfg(not(no_global_oom_handling))]
+use crate::vec::Vec;
+
+#[cfg(not(no_thin))]
+#[unstable(feature = "thin_box", issue = "92791")]
+pub use thin::ThinBox;
+
+#[cfg(not(no_thin))]
+mod thin;
+
+/// A pointer type for heap allocation.
+///
+/// See the [module-level documentation](../../std/boxed/index.html) for more.
+#[lang = "owned_box"]
+#[fundamental]
+#[stable(feature = "rust1", since = "1.0.0")]
+// The declaration of the `Box` struct must be kept in sync with the
+// `alloc::alloc::box_free` function or ICEs will happen. See the comment
+// on `box_free` for more details.
+pub struct Box<
+    T: ?Sized,
+    #[unstable(feature = "allocator_api", issue = "32838")] A: Allocator = Global,
+>(Unique<T>, A);
+
+impl<T> Box<T> {
+    /// Allocates memory on the heap and then places `x` into it.
+    ///
+    /// This doesn't actually allocate if `T` is zero-sized.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let five = Box::new(5);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[inline(always)]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    #[must_use]
+    pub fn new(x: T) -> Self {
+        box x
+    }
+
+    /// Constructs a new box with uninitialized contents.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(new_uninit)]
+    ///
+    /// let mut five = Box::<u32>::new_uninit();
+    ///
+    /// let five = unsafe {
+    ///     // Deferred initialization:
+    ///     five.as_mut_ptr().write(5);
+    ///
+    ///     five.assume_init()
+    /// };
+    ///
+    /// assert_eq!(*five, 5)
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[unstable(feature = "new_uninit", issue = "63291")]
+    #[must_use]
+    #[inline]
+    pub fn new_uninit() -> Box<mem::MaybeUninit<T>> {
+        Self::new_uninit_in(Global)
+    }
+
+    /// Constructs a new `Box` with uninitialized contents, with the memory
+    /// being filled with `0` bytes.
+    ///
+    /// See [`MaybeUninit::zeroed`][zeroed] for examples of correct and incorrect usage
+    /// of this method.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(new_uninit)]
+    ///
+    /// let zero = Box::<u32>::new_zeroed();
+    /// let zero = unsafe { zero.assume_init() };
+    ///
+    /// assert_eq!(*zero, 0)
+    /// ```
+    ///
+    /// [zeroed]: mem::MaybeUninit::zeroed
+    #[cfg(not(no_global_oom_handling))]
+    #[inline]
+    #[unstable(feature = "new_uninit", issue = "63291")]
+    #[must_use]
+    pub fn new_zeroed() -> Box<mem::MaybeUninit<T>> {
+        Self::new_zeroed_in(Global)
+    }
+
+    /// Constructs a new `Pin<Box<T>>`. If `T` does not implement `Unpin`, then
+    /// `x` will be pinned in memory and unable to be moved.
+    #[cfg(not(no_global_oom_handling))]
+    #[stable(feature = "pin", since = "1.33.0")]
+    #[must_use]
+    #[inline(always)]
+    pub fn pin(x: T) -> Pin<Box<T>> {
+        (box x).into()
+    }
+
+    /// Allocates memory on the heap then places `x` into it,
+    /// returning an error if the allocation fails
+    ///
+    /// This doesn't actually allocate if `T` is zero-sized.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api)]
+    ///
+    /// let five = Box::try_new(5)?;
+    /// # Ok::<(), std::alloc::AllocError>(())
+    /// ```
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    #[inline]
+    pub fn try_new(x: T) -> Result<Self, AllocError> {
+        Self::try_new_in(x, Global)
+    }
+
+    /// Constructs a new box with uninitialized contents on the heap,
+    /// returning an error if the allocation fails
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api, new_uninit)]
+    ///
+    /// let mut five = Box::<u32>::try_new_uninit()?;
+    ///
+    /// let five = unsafe {
+    ///     // Deferred initialization:
+    ///     five.as_mut_ptr().write(5);
+    ///
+    ///     five.assume_init()
+    /// };
+    ///
+    /// assert_eq!(*five, 5);
+    /// # Ok::<(), std::alloc::AllocError>(())
+    /// ```
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    // #[unstable(feature = "new_uninit", issue = "63291")]
+    #[inline]
+    pub fn try_new_uninit() -> Result<Box<mem::MaybeUninit<T>>, AllocError> {
+        Box::try_new_uninit_in(Global)
+    }
+
+    /// Constructs a new `Box` with uninitialized contents, with the memory
+    /// being filled with `0` bytes on the heap
+    ///
+    /// See [`MaybeUninit::zeroed`][zeroed] for examples of correct and incorrect usage
+    /// of this method.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api, new_uninit)]
+    ///
+    /// let zero = Box::<u32>::try_new_zeroed()?;
+    /// let zero = unsafe { zero.assume_init() };
+    ///
+    /// assert_eq!(*zero, 0);
+    /// # Ok::<(), std::alloc::AllocError>(())
+    /// ```
+    ///
+    /// [zeroed]: mem::MaybeUninit::zeroed
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    // #[unstable(feature = "new_uninit", issue = "63291")]
+    #[inline]
+    pub fn try_new_zeroed() -> Result<Box<mem::MaybeUninit<T>>, AllocError> {
+        Box::try_new_zeroed_in(Global)
+    }
+}
+
+impl<T, A: Allocator> Box<T, A> {
+    /// Allocates memory in the given allocator then places `x` into it.
+    ///
+    /// This doesn't actually allocate if `T` is zero-sized.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api)]
+    ///
+    /// use std::alloc::System;
+    ///
+    /// let five = Box::new_in(5, System);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    #[must_use]
+    #[inline]
+    pub const fn new_in(x: T, alloc: A) -> Self
+    where
+        A: ~const Allocator + ~const Destruct,
+    {
+        let mut boxed = Self::new_uninit_in(alloc);
+        unsafe {
+            boxed.as_mut_ptr().write(x);
+            boxed.assume_init()
+        }
+    }
+
+    /// Allocates memory in the given allocator then places `x` into it,
+    /// returning an error if the allocation fails
+    ///
+    /// This doesn't actually allocate if `T` is zero-sized.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api)]
+    ///
+    /// use std::alloc::System;
+    ///
+    /// let five = Box::try_new_in(5, System)?;
+    /// # Ok::<(), std::alloc::AllocError>(())
+    /// ```
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    #[inline]
+    pub const fn try_new_in(x: T, alloc: A) -> Result<Self, AllocError>
+    where
+        T: ~const Destruct,
+        A: ~const Allocator + ~const Destruct,
+    {
+        let mut boxed = Self::try_new_uninit_in(alloc)?;
+        unsafe {
+            boxed.as_mut_ptr().write(x);
+            Ok(boxed.assume_init())
+        }
+    }
+
+    /// Constructs a new box with uninitialized contents in the provided allocator.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api, new_uninit)]
+    ///
+    /// use std::alloc::System;
+    ///
+    /// let mut five = Box::<u32, _>::new_uninit_in(System);
+    ///
+    /// let five = unsafe {
+    ///     // Deferred initialization:
+    ///     five.as_mut_ptr().write(5);
+    ///
+    ///     five.assume_init()
+    /// };
+    ///
+    /// assert_eq!(*five, 5)
+    /// ```
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    #[cfg(not(no_global_oom_handling))]
+    #[must_use]
+    // #[unstable(feature = "new_uninit", issue = "63291")]
+    pub const fn new_uninit_in(alloc: A) -> Box<mem::MaybeUninit<T>, A>
+    where
+        A: ~const Allocator + ~const Destruct,
+    {
+        let layout = Layout::new::<mem::MaybeUninit<T>>();
+        // NOTE: Prefer match over unwrap_or_else since closure sometimes not inlineable.
+        // That would make code size bigger.
+        match Box::try_new_uninit_in(alloc) {
+            Ok(m) => m,
+            Err(_) => handle_alloc_error(layout),
+        }
+    }
+
+    /// Constructs a new box with uninitialized contents in the provided allocator,
+    /// returning an error if the allocation fails
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api, new_uninit)]
+    ///
+    /// use std::alloc::System;
+    ///
+    /// let mut five = Box::<u32, _>::try_new_uninit_in(System)?;
+    ///
+    /// let five = unsafe {
+    ///     // Deferred initialization:
+    ///     five.as_mut_ptr().write(5);
+    ///
+    ///     five.assume_init()
+    /// };
+    ///
+    /// assert_eq!(*five, 5);
+    /// # Ok::<(), std::alloc::AllocError>(())
+    /// ```
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    // #[unstable(feature = "new_uninit", issue = "63291")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    pub const fn try_new_uninit_in(alloc: A) -> Result<Box<mem::MaybeUninit<T>, A>, AllocError>
+    where
+        A: ~const Allocator + ~const Destruct,
+    {
+        let layout = Layout::new::<mem::MaybeUninit<T>>();
+        let ptr = alloc.allocate(layout)?.cast();
+        unsafe { Ok(Box::from_raw_in(ptr.as_ptr(), alloc)) }
+    }
+
+    /// Constructs a new `Box` with uninitialized contents, with the memory
+    /// being filled with `0` bytes in the provided allocator.
+    ///
+    /// See [`MaybeUninit::zeroed`][zeroed] for examples of correct and incorrect usage
+    /// of this method.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api, new_uninit)]
+    ///
+    /// use std::alloc::System;
+    ///
+    /// let zero = Box::<u32, _>::new_zeroed_in(System);
+    /// let zero = unsafe { zero.assume_init() };
+    ///
+    /// assert_eq!(*zero, 0)
+    /// ```
+    ///
+    /// [zeroed]: mem::MaybeUninit::zeroed
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    #[cfg(not(no_global_oom_handling))]
+    // #[unstable(feature = "new_uninit", issue = "63291")]
+    #[must_use]
+    pub const fn new_zeroed_in(alloc: A) -> Box<mem::MaybeUninit<T>, A>
+    where
+        A: ~const Allocator + ~const Destruct,
+    {
+        let layout = Layout::new::<mem::MaybeUninit<T>>();
+        // NOTE: Prefer match over unwrap_or_else since closure sometimes not inlineable.
+        // That would make code size bigger.
+        match Box::try_new_zeroed_in(alloc) {
+            Ok(m) => m,
+            Err(_) => handle_alloc_error(layout),
+        }
+    }
+
+    /// Constructs a new `Box` with uninitialized contents, with the memory
+    /// being filled with `0` bytes in the provided allocator,
+    /// returning an error if the allocation fails,
+    ///
+    /// See [`MaybeUninit::zeroed`][zeroed] for examples of correct and incorrect usage
+    /// of this method.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api, new_uninit)]
+    ///
+    /// use std::alloc::System;
+    ///
+    /// let zero = Box::<u32, _>::try_new_zeroed_in(System)?;
+    /// let zero = unsafe { zero.assume_init() };
+    ///
+    /// assert_eq!(*zero, 0);
+    /// # Ok::<(), std::alloc::AllocError>(())
+    /// ```
+    ///
+    /// [zeroed]: mem::MaybeUninit::zeroed
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    // #[unstable(feature = "new_uninit", issue = "63291")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    pub const fn try_new_zeroed_in(alloc: A) -> Result<Box<mem::MaybeUninit<T>, A>, AllocError>
+    where
+        A: ~const Allocator + ~const Destruct,
+    {
+        let layout = Layout::new::<mem::MaybeUninit<T>>();
+        let ptr = alloc.allocate_zeroed(layout)?.cast();
+        unsafe { Ok(Box::from_raw_in(ptr.as_ptr(), alloc)) }
+    }
+
+    /// Constructs a new `Pin<Box<T, A>>`. If `T` does not implement `Unpin`, then
+    /// `x` will be pinned in memory and unable to be moved.
+    #[cfg(not(no_global_oom_handling))]
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    #[must_use]
+    #[inline(always)]
+    pub const fn pin_in(x: T, alloc: A) -> Pin<Self>
+    where
+        A: 'static + ~const Allocator + ~const Destruct,
+    {
+        Self::into_pin(Self::new_in(x, alloc))
+    }
+
+    /// Converts a `Box<T>` into a `Box<[T]>`
+    ///
+    /// This conversion does not allocate on the heap and happens in place.
+    #[unstable(feature = "box_into_boxed_slice", issue = "71582")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    pub const fn into_boxed_slice(boxed: Self) -> Box<[T], A> {
+        let (raw, alloc) = Box::into_raw_with_allocator(boxed);
+        unsafe { Box::from_raw_in(raw as *mut [T; 1], alloc) }
+    }
+
+    /// Consumes the `Box`, returning the wrapped value.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(box_into_inner)]
+    ///
+    /// let c = Box::new(5);
+    ///
+    /// assert_eq!(Box::into_inner(c), 5);
+    /// ```
+    #[unstable(feature = "box_into_inner", issue = "80437")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    #[inline]
+    pub const fn into_inner(boxed: Self) -> T
+    where
+        Self: ~const Destruct,
+    {
+        *boxed
+    }
+}
+
+impl<T> Box<[T]> {
+    /// Constructs a new boxed slice with uninitialized contents.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(new_uninit)]
+    ///
+    /// let mut values = Box::<[u32]>::new_uninit_slice(3);
+    ///
+    /// let values = unsafe {
+    ///     // Deferred initialization:
+    ///     values[0].as_mut_ptr().write(1);
+    ///     values[1].as_mut_ptr().write(2);
+    ///     values[2].as_mut_ptr().write(3);
+    ///
+    ///     values.assume_init()
+    /// };
+    ///
+    /// assert_eq!(*values, [1, 2, 3])
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[unstable(feature = "new_uninit", issue = "63291")]
+    #[must_use]
+    pub fn new_uninit_slice(len: usize) -> Box<[mem::MaybeUninit<T>]> {
+        unsafe { RawVec::with_capacity(len).into_box(len) }
+    }
+
+    /// Constructs a new boxed slice with uninitialized contents, with the memory
+    /// being filled with `0` bytes.
+    ///
+    /// See [`MaybeUninit::zeroed`][zeroed] for examples of correct and incorrect usage
+    /// of this method.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(new_uninit)]
+    ///
+    /// let values = Box::<[u32]>::new_zeroed_slice(3);
+    /// let values = unsafe { values.assume_init() };
+    ///
+    /// assert_eq!(*values, [0, 0, 0])
+    /// ```
+    ///
+    /// [zeroed]: mem::MaybeUninit::zeroed
+    #[cfg(not(no_global_oom_handling))]
+    #[unstable(feature = "new_uninit", issue = "63291")]
+    #[must_use]
+    pub fn new_zeroed_slice(len: usize) -> Box<[mem::MaybeUninit<T>]> {
+        unsafe { RawVec::with_capacity_zeroed(len).into_box(len) }
+    }
+
+    /// Constructs a new boxed slice with uninitialized contents. Returns an error if
+    /// the allocation fails
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api, new_uninit)]
+    ///
+    /// let mut values = Box::<[u32]>::try_new_uninit_slice(3)?;
+    /// let values = unsafe {
+    ///     // Deferred initialization:
+    ///     values[0].as_mut_ptr().write(1);
+    ///     values[1].as_mut_ptr().write(2);
+    ///     values[2].as_mut_ptr().write(3);
+    ///     values.assume_init()
+    /// };
+    ///
+    /// assert_eq!(*values, [1, 2, 3]);
+    /// # Ok::<(), std::alloc::AllocError>(())
+    /// ```
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    #[inline]
+    pub fn try_new_uninit_slice(len: usize) -> Result<Box<[mem::MaybeUninit<T>]>, AllocError> {
+        unsafe {
+            let layout = match Layout::array::<mem::MaybeUninit<T>>(len) {
+                Ok(l) => l,
+                Err(_) => return Err(AllocError),
+            };
+            let ptr = Global.allocate(layout)?;
+            Ok(RawVec::from_raw_parts_in(ptr.as_mut_ptr() as *mut _, len, Global).into_box(len))
+        }
+    }
+
+    /// Constructs a new boxed slice with uninitialized contents, with the memory
+    /// being filled with `0` bytes. Returns an error if the allocation fails
+    ///
+    /// See [`MaybeUninit::zeroed`][zeroed] for examples of correct and incorrect usage
+    /// of this method.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api, new_uninit)]
+    ///
+    /// let values = Box::<[u32]>::try_new_zeroed_slice(3)?;
+    /// let values = unsafe { values.assume_init() };
+    ///
+    /// assert_eq!(*values, [0, 0, 0]);
+    /// # Ok::<(), std::alloc::AllocError>(())
+    /// ```
+    ///
+    /// [zeroed]: mem::MaybeUninit::zeroed
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    #[inline]
+    pub fn try_new_zeroed_slice(len: usize) -> Result<Box<[mem::MaybeUninit<T>]>, AllocError> {
+        unsafe {
+            let layout = match Layout::array::<mem::MaybeUninit<T>>(len) {
+                Ok(l) => l,
+                Err(_) => return Err(AllocError),
+            };
+            let ptr = Global.allocate_zeroed(layout)?;
+            Ok(RawVec::from_raw_parts_in(ptr.as_mut_ptr() as *mut _, len, Global).into_box(len))
+        }
+    }
+}
+
+impl<T, A: Allocator> Box<[T], A> {
+    /// Constructs a new boxed slice with uninitialized contents in the provided allocator.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api, new_uninit)]
+    ///
+    /// use std::alloc::System;
+    ///
+    /// let mut values = Box::<[u32], _>::new_uninit_slice_in(3, System);
+    ///
+    /// let values = unsafe {
+    ///     // Deferred initialization:
+    ///     values[0].as_mut_ptr().write(1);
+    ///     values[1].as_mut_ptr().write(2);
+    ///     values[2].as_mut_ptr().write(3);
+    ///
+    ///     values.assume_init()
+    /// };
+    ///
+    /// assert_eq!(*values, [1, 2, 3])
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    // #[unstable(feature = "new_uninit", issue = "63291")]
+    #[must_use]
+    pub fn new_uninit_slice_in(len: usize, alloc: A) -> Box<[mem::MaybeUninit<T>], A> {
+        unsafe { RawVec::with_capacity_in(len, alloc).into_box(len) }
+    }
+
+    /// Constructs a new boxed slice with uninitialized contents in the provided allocator,
+    /// with the memory being filled with `0` bytes.
+    ///
+    /// See [`MaybeUninit::zeroed`][zeroed] for examples of correct and incorrect usage
+    /// of this method.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api, new_uninit)]
+    ///
+    /// use std::alloc::System;
+    ///
+    /// let values = Box::<[u32], _>::new_zeroed_slice_in(3, System);
+    /// let values = unsafe { values.assume_init() };
+    ///
+    /// assert_eq!(*values, [0, 0, 0])
+    /// ```
+    ///
+    /// [zeroed]: mem::MaybeUninit::zeroed
+    #[cfg(not(no_global_oom_handling))]
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    // #[unstable(feature = "new_uninit", issue = "63291")]
+    #[must_use]
+    pub fn new_zeroed_slice_in(len: usize, alloc: A) -> Box<[mem::MaybeUninit<T>], A> {
+        unsafe { RawVec::with_capacity_zeroed_in(len, alloc).into_box(len) }
+    }
+}
+
+impl<T, A: Allocator> Box<mem::MaybeUninit<T>, A> {
+    /// Converts to `Box<T, A>`.
+    ///
+    /// # Safety
+    ///
+    /// As with [`MaybeUninit::assume_init`],
+    /// it is up to the caller to guarantee that the value
+    /// really is in an initialized state.
+    /// Calling this when the content is not yet fully initialized
+    /// causes immediate undefined behavior.
+    ///
+    /// [`MaybeUninit::assume_init`]: mem::MaybeUninit::assume_init
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(new_uninit)]
+    ///
+    /// let mut five = Box::<u32>::new_uninit();
+    ///
+    /// let five: Box<u32> = unsafe {
+    ///     // Deferred initialization:
+    ///     five.as_mut_ptr().write(5);
+    ///
+    ///     five.assume_init()
+    /// };
+    ///
+    /// assert_eq!(*five, 5)
+    /// ```
+    #[unstable(feature = "new_uninit", issue = "63291")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    #[inline]
+    pub const unsafe fn assume_init(self) -> Box<T, A> {
+        let (raw, alloc) = Box::into_raw_with_allocator(self);
+        unsafe { Box::from_raw_in(raw as *mut T, alloc) }
+    }
+
+    /// Writes the value and converts to `Box<T, A>`.
+    ///
+    /// This method converts the box similarly to [`Box::assume_init`] but
+    /// writes `value` into it before conversion thus guaranteeing safety.
+    /// In some scenarios use of this method may improve performance because
+    /// the compiler may be able to optimize copying from stack.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(new_uninit)]
+    ///
+    /// let big_box = Box::<[usize; 1024]>::new_uninit();
+    ///
+    /// let mut array = [0; 1024];
+    /// for (i, place) in array.iter_mut().enumerate() {
+    ///     *place = i;
+    /// }
+    ///
+    /// // The optimizer may be able to elide this copy, so previous code writes
+    /// // to heap directly.
+    /// let big_box = Box::write(big_box, array);
+    ///
+    /// for (i, x) in big_box.iter().enumerate() {
+    ///     assert_eq!(*x, i);
+    /// }
+    /// ```
+    #[unstable(feature = "new_uninit", issue = "63291")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    #[inline]
+    pub const fn write(mut boxed: Self, value: T) -> Box<T, A> {
+        unsafe {
+            (*boxed).write(value);
+            boxed.assume_init()
+        }
+    }
+}
+
+impl<T, A: Allocator> Box<[mem::MaybeUninit<T>], A> {
+    /// Converts to `Box<[T], A>`.
+    ///
+    /// # Safety
+    ///
+    /// As with [`MaybeUninit::assume_init`],
+    /// it is up to the caller to guarantee that the values
+    /// really are in an initialized state.
+    /// Calling this when the content is not yet fully initialized
+    /// causes immediate undefined behavior.
+    ///
+    /// [`MaybeUninit::assume_init`]: mem::MaybeUninit::assume_init
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(new_uninit)]
+    ///
+    /// let mut values = Box::<[u32]>::new_uninit_slice(3);
+    ///
+    /// let values = unsafe {
+    ///     // Deferred initialization:
+    ///     values[0].as_mut_ptr().write(1);
+    ///     values[1].as_mut_ptr().write(2);
+    ///     values[2].as_mut_ptr().write(3);
+    ///
+    ///     values.assume_init()
+    /// };
+    ///
+    /// assert_eq!(*values, [1, 2, 3])
+    /// ```
+    #[unstable(feature = "new_uninit", issue = "63291")]
+    #[inline]
+    pub unsafe fn assume_init(self) -> Box<[T], A> {
+        let (raw, alloc) = Box::into_raw_with_allocator(self);
+        unsafe { Box::from_raw_in(raw as *mut [T], alloc) }
+    }
+}
+
+impl<T: ?Sized> Box<T> {
+    /// Constructs a box from a raw pointer.
+    ///
+    /// After calling this function, the raw pointer is owned by the
+    /// resulting `Box`. Specifically, the `Box` destructor will call
+    /// the destructor of `T` and free the allocated memory. For this
+    /// to be safe, the memory must have been allocated in accordance
+    /// with the [memory layout] used by `Box` .
+    ///
+    /// # Safety
+    ///
+    /// This function is unsafe because improper use may lead to
+    /// memory problems. For example, a double-free may occur if the
+    /// function is called twice on the same raw pointer.
+    ///
+    /// The safety conditions are described in the [memory layout] section.
+    ///
+    /// # Examples
+    ///
+    /// Recreate a `Box` which was previously converted to a raw pointer
+    /// using [`Box::into_raw`]:
+    /// ```
+    /// let x = Box::new(5);
+    /// let ptr = Box::into_raw(x);
+    /// let x = unsafe { Box::from_raw(ptr) };
+    /// ```
+    /// Manually create a `Box` from scratch by using the global allocator:
+    /// ```
+    /// use std::alloc::{alloc, Layout};
+    ///
+    /// unsafe {
+    ///     let ptr = alloc(Layout::new::<i32>()) as *mut i32;
+    ///     // In general .write is required to avoid attempting to destruct
+    ///     // the (uninitialized) previous contents of `ptr`, though for this
+    ///     // simple example `*ptr = 5` would have worked as well.
+    ///     ptr.write(5);
+    ///     let x = Box::from_raw(ptr);
+    /// }
+    /// ```
+    ///
+    /// [memory layout]: self#memory-layout
+    /// [`Layout`]: crate::Layout
+    #[stable(feature = "box_raw", since = "1.4.0")]
+    #[inline]
+    pub unsafe fn from_raw(raw: *mut T) -> Self {
+        unsafe { Self::from_raw_in(raw, Global) }
+    }
+}
+
+impl<T: ?Sized, A: Allocator> Box<T, A> {
+    /// Constructs a box from a raw pointer in the given allocator.
+    ///
+    /// After calling this function, the raw pointer is owned by the
+    /// resulting `Box`. Specifically, the `Box` destructor will call
+    /// the destructor of `T` and free the allocated memory. For this
+    /// to be safe, the memory must have been allocated in accordance
+    /// with the [memory layout] used by `Box` .
+    ///
+    /// # Safety
+    ///
+    /// This function is unsafe because improper use may lead to
+    /// memory problems. For example, a double-free may occur if the
+    /// function is called twice on the same raw pointer.
+    ///
+    ///
+    /// # Examples
+    ///
+    /// Recreate a `Box` which was previously converted to a raw pointer
+    /// using [`Box::into_raw_with_allocator`]:
+    /// ```
+    /// #![feature(allocator_api)]
+    ///
+    /// use std::alloc::System;
+    ///
+    /// let x = Box::new_in(5, System);
+    /// let (ptr, alloc) = Box::into_raw_with_allocator(x);
+    /// let x = unsafe { Box::from_raw_in(ptr, alloc) };
+    /// ```
+    /// Manually create a `Box` from scratch by using the system allocator:
+    /// ```
+    /// #![feature(allocator_api, slice_ptr_get)]
+    ///
+    /// use std::alloc::{Allocator, Layout, System};
+    ///
+    /// unsafe {
+    ///     let ptr = System.allocate(Layout::new::<i32>())?.as_mut_ptr() as *mut i32;
+    ///     // In general .write is required to avoid attempting to destruct
+    ///     // the (uninitialized) previous contents of `ptr`, though for this
+    ///     // simple example `*ptr = 5` would have worked as well.
+    ///     ptr.write(5);
+    ///     let x = Box::from_raw_in(ptr, System);
+    /// }
+    /// # Ok::<(), std::alloc::AllocError>(())
+    /// ```
+    ///
+    /// [memory layout]: self#memory-layout
+    /// [`Layout`]: crate::Layout
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    #[inline]
+    pub const unsafe fn from_raw_in(raw: *mut T, alloc: A) -> Self {
+        Box(unsafe { Unique::new_unchecked(raw) }, alloc)
+    }
+
+    /// Consumes the `Box`, returning a wrapped raw pointer.
+    ///
+    /// The pointer will be properly aligned and non-null.
+    ///
+    /// After calling this function, the caller is responsible for the
+    /// memory previously managed by the `Box`. In particular, the
+    /// caller should properly destroy `T` and release the memory, taking
+    /// into account the [memory layout] used by `Box`. The easiest way to
+    /// do this is to convert the raw pointer back into a `Box` with the
+    /// [`Box::from_raw`] function, allowing the `Box` destructor to perform
+    /// the cleanup.
+    ///
+    /// Note: this is an associated function, which means that you have
+    /// to call it as `Box::into_raw(b)` instead of `b.into_raw()`. This
+    /// is so that there is no conflict with a method on the inner type.
+    ///
+    /// # Examples
+    /// Converting the raw pointer back into a `Box` with [`Box::from_raw`]
+    /// for automatic cleanup:
+    /// ```
+    /// let x = Box::new(String::from("Hello"));
+    /// let ptr = Box::into_raw(x);
+    /// let x = unsafe { Box::from_raw(ptr) };
+    /// ```
+    /// Manual cleanup by explicitly running the destructor and deallocating
+    /// the memory:
+    /// ```
+    /// use std::alloc::{dealloc, Layout};
+    /// use std::ptr;
+    ///
+    /// let x = Box::new(String::from("Hello"));
+    /// let p = Box::into_raw(x);
+    /// unsafe {
+    ///     ptr::drop_in_place(p);
+    ///     dealloc(p as *mut u8, Layout::new::<String>());
+    /// }
+    /// ```
+    ///
+    /// [memory layout]: self#memory-layout
+    #[stable(feature = "box_raw", since = "1.4.0")]
+    #[inline]
+    pub fn into_raw(b: Self) -> *mut T {
+        Self::into_raw_with_allocator(b).0
+    }
+
+    /// Consumes the `Box`, returning a wrapped raw pointer and the allocator.
+    ///
+    /// The pointer will be properly aligned and non-null.
+    ///
+    /// After calling this function, the caller is responsible for the
+    /// memory previously managed by the `Box`. In particular, the
+    /// caller should properly destroy `T` and release the memory, taking
+    /// into account the [memory layout] used by `Box`. The easiest way to
+    /// do this is to convert the raw pointer back into a `Box` with the
+    /// [`Box::from_raw_in`] function, allowing the `Box` destructor to perform
+    /// the cleanup.
+    ///
+    /// Note: this is an associated function, which means that you have
+    /// to call it as `Box::into_raw_with_allocator(b)` instead of `b.into_raw_with_allocator()`. This
+    /// is so that there is no conflict with a method on the inner type.
+    ///
+    /// # Examples
+    /// Converting the raw pointer back into a `Box` with [`Box::from_raw_in`]
+    /// for automatic cleanup:
+    /// ```
+    /// #![feature(allocator_api)]
+    ///
+    /// use std::alloc::System;
+    ///
+    /// let x = Box::new_in(String::from("Hello"), System);
+    /// let (ptr, alloc) = Box::into_raw_with_allocator(x);
+    /// let x = unsafe { Box::from_raw_in(ptr, alloc) };
+    /// ```
+    /// Manual cleanup by explicitly running the destructor and deallocating
+    /// the memory:
+    /// ```
+    /// #![feature(allocator_api)]
+    ///
+    /// use std::alloc::{Allocator, Layout, System};
+    /// use std::ptr::{self, NonNull};
+    ///
+    /// let x = Box::new_in(String::from("Hello"), System);
+    /// let (ptr, alloc) = Box::into_raw_with_allocator(x);
+    /// unsafe {
+    ///     ptr::drop_in_place(ptr);
+    ///     let non_null = NonNull::new_unchecked(ptr);
+    ///     alloc.deallocate(non_null.cast(), Layout::new::<String>());
+    /// }
+    /// ```
+    ///
+    /// [memory layout]: self#memory-layout
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    #[inline]
+    pub const fn into_raw_with_allocator(b: Self) -> (*mut T, A) {
+        let (leaked, alloc) = Box::into_unique(b);
+        (leaked.as_ptr(), alloc)
+    }
+
+    #[unstable(
+        feature = "ptr_internals",
+        issue = "none",
+        reason = "use `Box::leak(b).into()` or `Unique::from(Box::leak(b))` instead"
+    )]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    #[inline]
+    #[doc(hidden)]
+    pub const fn into_unique(b: Self) -> (Unique<T>, A) {
+        // Box is recognized as a "unique pointer" by Stacked Borrows, but internally it is a
+        // raw pointer for the type system. Turning it directly into a raw pointer would not be
+        // recognized as "releasing" the unique pointer to permit aliased raw accesses,
+        // so all raw pointer methods have to go through `Box::leak`. Turning *that* to a raw pointer
+        // behaves correctly.
+        let alloc = unsafe { ptr::read(&b.1) };
+        (Unique::from(Box::leak(b)), alloc)
+    }
+
+    /// Returns a reference to the underlying allocator.
+    ///
+    /// Note: this is an associated function, which means that you have
+    /// to call it as `Box::allocator(&b)` instead of `b.allocator()`. This
+    /// is so that there is no conflict with a method on the inner type.
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    #[inline]
+    pub const fn allocator(b: &Self) -> &A {
+        &b.1
+    }
+
+    /// Consumes and leaks the `Box`, returning a mutable reference,
+    /// `&'a mut T`. Note that the type `T` must outlive the chosen lifetime
+    /// `'a`. If the type has only static references, or none at all, then this
+    /// may be chosen to be `'static`.
+    ///
+    /// This function is mainly useful for data that lives for the remainder of
+    /// the program's life. Dropping the returned reference will cause a memory
+    /// leak. If this is not acceptable, the reference should first be wrapped
+    /// with the [`Box::from_raw`] function producing a `Box`. This `Box` can
+    /// then be dropped which will properly destroy `T` and release the
+    /// allocated memory.
+    ///
+    /// Note: this is an associated function, which means that you have
+    /// to call it as `Box::leak(b)` instead of `b.leak()`. This
+    /// is so that there is no conflict with a method on the inner type.
+    ///
+    /// # Examples
+    ///
+    /// Simple usage:
+    ///
+    /// ```
+    /// let x = Box::new(41);
+    /// let static_ref: &'static mut usize = Box::leak(x);
+    /// *static_ref += 1;
+    /// assert_eq!(*static_ref, 42);
+    /// ```
+    ///
+    /// Unsized data:
+    ///
+    /// ```
+    /// let x = vec![1, 2, 3].into_boxed_slice();
+    /// let static_ref = Box::leak(x);
+    /// static_ref[0] = 4;
+    /// assert_eq!(*static_ref, [4, 2, 3]);
+    /// ```
+    #[stable(feature = "box_leak", since = "1.26.0")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    #[inline]
+    pub const fn leak<'a>(b: Self) -> &'a mut T
+    where
+        A: 'a,
+    {
+        unsafe { &mut *mem::ManuallyDrop::new(b).0.as_ptr() }
+    }
+
+    /// Converts a `Box<T>` into a `Pin<Box<T>>`
+    ///
+    /// This conversion does not allocate on the heap and happens in place.
+    ///
+    /// This is also available via [`From`].
+    #[unstable(feature = "box_into_pin", issue = "62370")]
+    #[rustc_const_unstable(feature = "const_box", issue = "92521")]
+    pub const fn into_pin(boxed: Self) -> Pin<Self>
+    where
+        A: 'static,
+    {
+        // It's not possible to move or replace the insides of a `Pin<Box<T>>`
+        // when `T: !Unpin`,  so it's safe to pin it directly without any
+        // additional requirements.
+        unsafe { Pin::new_unchecked(boxed) }
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+unsafe impl<#[may_dangle] T: ?Sized, A: Allocator> Drop for Box<T, A> {
+    fn drop(&mut self) {
+        // FIXME: Do nothing, drop is currently performed by compiler.
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: Default> Default for Box<T> {
+    /// Creates a `Box<T>`, with the `Default` value for T.
+    fn default() -> Self {
+        box T::default()
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+#[rustc_const_unstable(feature = "const_default_impls", issue = "87864")]
+impl<T> const Default for Box<[T]> {
+    fn default() -> Self {
+        let ptr: Unique<[T]> = Unique::<[T; 0]>::dangling();
+        Box(ptr, Global)
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "default_box_extra", since = "1.17.0")]
+#[rustc_const_unstable(feature = "const_default_impls", issue = "87864")]
+impl const Default for Box<str> {
+    fn default() -> Self {
+        // SAFETY: This is the same as `Unique::cast<U>` but with an unsized `U = str`.
+        let ptr: Unique<str> = unsafe {
+            let bytes: Unique<[u8]> = Unique::<[u8; 0]>::dangling();
+            Unique::new_unchecked(bytes.as_ptr() as *mut str)
+        };
+        Box(ptr, Global)
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: Clone, A: Allocator + Clone> Clone for Box<T, A> {
+    /// Returns a new box with a `clone()` of this box's contents.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let x = Box::new(5);
+    /// let y = x.clone();
+    ///
+    /// // The value is the same
+    /// assert_eq!(x, y);
+    ///
+    /// // But they are unique objects
+    /// assert_ne!(&*x as *const i32, &*y as *const i32);
+    /// ```
+    #[inline]
+    fn clone(&self) -> Self {
+        // Pre-allocate memory to allow writing the cloned value directly.
+        let mut boxed = Self::new_uninit_in(self.1.clone());
+        unsafe {
+            (**self).write_clone_into_raw(boxed.as_mut_ptr());
+            boxed.assume_init()
+        }
+    }
+
+    /// Copies `source`'s contents into `self` without creating a new allocation.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let x = Box::new(5);
+    /// let mut y = Box::new(10);
+    /// let yp: *const i32 = &*y;
+    ///
+    /// y.clone_from(&x);
+    ///
+    /// // The value is the same
+    /// assert_eq!(x, y);
+    ///
+    /// // And no allocation occurred
+    /// assert_eq!(yp, &*y);
+    /// ```
+    #[inline]
+    fn clone_from(&mut self, source: &Self) {
+        (**self).clone_from(&(**source));
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "box_slice_clone", since = "1.3.0")]
+impl Clone for Box<str> {
+    fn clone(&self) -> Self {
+        // this makes a copy of the data
+        let buf: Box<[u8]> = self.as_bytes().into();
+        unsafe { from_boxed_utf8_unchecked(buf) }
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: ?Sized + PartialEq, A: Allocator> PartialEq for Box<T, A> {
+    #[inline]
+    fn eq(&self, other: &Self) -> bool {
+        PartialEq::eq(&**self, &**other)
+    }
+    #[inline]
+    fn ne(&self, other: &Self) -> bool {
+        PartialEq::ne(&**self, &**other)
+    }
+}
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: ?Sized + PartialOrd, A: Allocator> PartialOrd for Box<T, A> {
+    #[inline]
+    fn partial_cmp(&self, other: &Self) -> Option<Ordering> {
+        PartialOrd::partial_cmp(&**self, &**other)
+    }
+    #[inline]
+    fn lt(&self, other: &Self) -> bool {
+        PartialOrd::lt(&**self, &**other)
+    }
+    #[inline]
+    fn le(&self, other: &Self) -> bool {
+        PartialOrd::le(&**self, &**other)
+    }
+    #[inline]
+    fn ge(&self, other: &Self) -> bool {
+        PartialOrd::ge(&**self, &**other)
+    }
+    #[inline]
+    fn gt(&self, other: &Self) -> bool {
+        PartialOrd::gt(&**self, &**other)
+    }
+}
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: ?Sized + Ord, A: Allocator> Ord for Box<T, A> {
+    #[inline]
+    fn cmp(&self, other: &Self) -> Ordering {
+        Ord::cmp(&**self, &**other)
+    }
+}
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: ?Sized + Eq, A: Allocator> Eq for Box<T, A> {}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: ?Sized + Hash, A: Allocator> Hash for Box<T, A> {
+    fn hash<H: Hasher>(&self, state: &mut H) {
+        (**self).hash(state);
+    }
+}
+
+#[stable(feature = "indirect_hasher_impl", since = "1.22.0")]
+impl<T: ?Sized + Hasher, A: Allocator> Hasher for Box<T, A> {
+    fn finish(&self) -> u64 {
+        (**self).finish()
+    }
+    fn write(&mut self, bytes: &[u8]) {
+        (**self).write(bytes)
+    }
+    fn write_u8(&mut self, i: u8) {
+        (**self).write_u8(i)
+    }
+    fn write_u16(&mut self, i: u16) {
+        (**self).write_u16(i)
+    }
+    fn write_u32(&mut self, i: u32) {
+        (**self).write_u32(i)
+    }
+    fn write_u64(&mut self, i: u64) {
+        (**self).write_u64(i)
+    }
+    fn write_u128(&mut self, i: u128) {
+        (**self).write_u128(i)
+    }
+    fn write_usize(&mut self, i: usize) {
+        (**self).write_usize(i)
+    }
+    fn write_i8(&mut self, i: i8) {
+        (**self).write_i8(i)
+    }
+    fn write_i16(&mut self, i: i16) {
+        (**self).write_i16(i)
+    }
+    fn write_i32(&mut self, i: i32) {
+        (**self).write_i32(i)
+    }
+    fn write_i64(&mut self, i: i64) {
+        (**self).write_i64(i)
+    }
+    fn write_i128(&mut self, i: i128) {
+        (**self).write_i128(i)
+    }
+    fn write_isize(&mut self, i: isize) {
+        (**self).write_isize(i)
+    }
+    fn write_length_prefix(&mut self, len: usize) {
+        (**self).write_length_prefix(len)
+    }
+    fn write_str(&mut self, s: &str) {
+        (**self).write_str(s)
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "from_for_ptrs", since = "1.6.0")]
+impl<T> From<T> for Box<T> {
+    /// Converts a `T` into a `Box<T>`
+    ///
+    /// The conversion allocates on the heap and moves `t`
+    /// from the stack into it.
+    ///
+    /// # Examples
+    ///
+    /// ```rust
+    /// let x = 5;
+    /// let boxed = Box::new(5);
+    ///
+    /// assert_eq!(Box::from(x), boxed);
+    /// ```
+    fn from(t: T) -> Self {
+        Box::new(t)
+    }
+}
+
+#[stable(feature = "pin", since = "1.33.0")]
+#[rustc_const_unstable(feature = "const_box", issue = "92521")]
+impl<T: ?Sized, A: Allocator> const From<Box<T, A>> for Pin<Box<T, A>>
+where
+    A: 'static,
+{
+    /// Converts a `Box<T>` into a `Pin<Box<T>>`
+    ///
+    /// This conversion does not allocate on the heap and happens in place.
+    fn from(boxed: Box<T, A>) -> Self {
+        Box::into_pin(boxed)
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "box_from_slice", since = "1.17.0")]
+impl<T: Copy> From<&[T]> for Box<[T]> {
+    /// Converts a `&[T]` into a `Box<[T]>`
+    ///
+    /// This conversion allocates on the heap
+    /// and performs a copy of `slice`.
+    ///
+    /// # Examples
+    /// ```rust
+    /// // create a &[u8] which will be used to create a Box<[u8]>
+    /// let slice: &[u8] = &[104, 101, 108, 108, 111];
+    /// let boxed_slice: Box<[u8]> = Box::from(slice);
+    ///
+    /// println!("{boxed_slice:?}");
+    /// ```
+    fn from(slice: &[T]) -> Box<[T]> {
+        let len = slice.len();
+        let buf = RawVec::with_capacity(len);
+        unsafe {
+            ptr::copy_nonoverlapping(slice.as_ptr(), buf.ptr(), len);
+            buf.into_box(slice.len()).assume_init()
+        }
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "box_from_cow", since = "1.45.0")]
+impl<T: Copy> From<Cow<'_, [T]>> for Box<[T]> {
+    /// Converts a `Cow<'_, [T]>` into a `Box<[T]>`
+    ///
+    /// When `cow` is the `Cow::Borrowed` variant, this
+    /// conversion allocates on the heap and copies the
+    /// underlying slice. Otherwise, it will try to reuse the owned
+    /// `Vec`'s allocation.
+    #[inline]
+    fn from(cow: Cow<'_, [T]>) -> Box<[T]> {
+        match cow {
+            Cow::Borrowed(slice) => Box::from(slice),
+            Cow::Owned(slice) => Box::from(slice),
+        }
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "box_from_slice", since = "1.17.0")]
+impl From<&str> for Box<str> {
+    /// Converts a `&str` into a `Box<str>`
+    ///
+    /// This conversion allocates on the heap
+    /// and performs a copy of `s`.
+    ///
+    /// # Examples
+    ///
+    /// ```rust
+    /// let boxed: Box<str> = Box::from("hello");
+    /// println!("{boxed}");
+    /// ```
+    #[inline]
+    fn from(s: &str) -> Box<str> {
+        unsafe { from_boxed_utf8_unchecked(Box::from(s.as_bytes())) }
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "box_from_cow", since = "1.45.0")]
+impl From<Cow<'_, str>> for Box<str> {
+    /// Converts a `Cow<'_, str>` into a `Box<str>`
+    ///
+    /// When `cow` is the `Cow::Borrowed` variant, this
+    /// conversion allocates on the heap and copies the
+    /// underlying `str`. Otherwise, it will try to reuse the owned
+    /// `String`'s allocation.
+    ///
+    /// # Examples
+    ///
+    /// ```rust
+    /// use std::borrow::Cow;
+    ///
+    /// let unboxed = Cow::Borrowed("hello");
+    /// let boxed: Box<str> = Box::from(unboxed);
+    /// println!("{boxed}");
+    /// ```
+    ///
+    /// ```rust
+    /// # use std::borrow::Cow;
+    /// let unboxed = Cow::Owned("hello".to_string());
+    /// let boxed: Box<str> = Box::from(unboxed);
+    /// println!("{boxed}");
+    /// ```
+    #[inline]
+    fn from(cow: Cow<'_, str>) -> Box<str> {
+        match cow {
+            Cow::Borrowed(s) => Box::from(s),
+            Cow::Owned(s) => Box::from(s),
+        }
+    }
+}
+
+#[stable(feature = "boxed_str_conv", since = "1.19.0")]
+impl<A: Allocator> From<Box<str, A>> for Box<[u8], A> {
+    /// Converts a `Box<str>` into a `Box<[u8]>`
+    ///
+    /// This conversion does not allocate on the heap and happens in place.
+    ///
+    /// # Examples
+    /// ```rust
+    /// // create a Box<str> which will be used to create a Box<[u8]>
+    /// let boxed: Box<str> = Box::from("hello");
+    /// let boxed_str: Box<[u8]> = Box::from(boxed);
+    ///
+    /// // create a &[u8] which will be used to create a Box<[u8]>
+    /// let slice: &[u8] = &[104, 101, 108, 108, 111];
+    /// let boxed_slice = Box::from(slice);
+    ///
+    /// assert_eq!(boxed_slice, boxed_str);
+    /// ```
+    #[inline]
+    fn from(s: Box<str, A>) -> Self {
+        let (raw, alloc) = Box::into_raw_with_allocator(s);
+        unsafe { Box::from_raw_in(raw as *mut [u8], alloc) }
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "box_from_array", since = "1.45.0")]
+impl<T, const N: usize> From<[T; N]> for Box<[T]> {
+    /// Converts a `[T; N]` into a `Box<[T]>`
+    ///
+    /// This conversion moves the array to newly heap-allocated memory.
+    ///
+    /// # Examples
+    ///
+    /// ```rust
+    /// let boxed: Box<[u8]> = Box::from([4, 2]);
+    /// println!("{boxed:?}");
+    /// ```
+    fn from(array: [T; N]) -> Box<[T]> {
+        box array
+    }
+}
+
+#[stable(feature = "boxed_slice_try_from", since = "1.43.0")]
+impl<T, const N: usize> TryFrom<Box<[T]>> for Box<[T; N]> {
+    type Error = Box<[T]>;
+
+    /// Attempts to convert a `Box<[T]>` into a `Box<[T; N]>`.
+    ///
+    /// The conversion occurs in-place and does not require a
+    /// new memory allocation.
+    ///
+    /// # Errors
+    ///
+    /// Returns the old `Box<[T]>` in the `Err` variant if
+    /// `boxed_slice.len()` does not equal `N`.
+    fn try_from(boxed_slice: Box<[T]>) -> Result<Self, Self::Error> {
+        if boxed_slice.len() == N {
+            Ok(unsafe { Box::from_raw(Box::into_raw(boxed_slice) as *mut [T; N]) })
+        } else {
+            Err(boxed_slice)
+        }
+    }
+}
+
+impl<A: Allocator> Box<dyn Any, A> {
+    /// Attempt to downcast the box to a concrete type.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use std::any::Any;
+    ///
+    /// fn print_if_string(value: Box<dyn Any>) {
+    ///     if let Ok(string) = value.downcast::<String>() {
+    ///         println!("String ({}): {}", string.len(), string);
+    ///     }
+    /// }
+    ///
+    /// let my_string = "Hello World".to_string();
+    /// print_if_string(Box::new(my_string));
+    /// print_if_string(Box::new(0i8));
+    /// ```
+    #[inline]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn downcast<T: Any>(self) -> Result<Box<T, A>, Self> {
+        if self.is::<T>() { unsafe { Ok(self.downcast_unchecked::<T>()) } } else { Err(self) }
+    }
+
+    /// Downcasts the box to a concrete type.
+    ///
+    /// For a safe alternative see [`downcast`].
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(downcast_unchecked)]
+    ///
+    /// use std::any::Any;
+    ///
+    /// let x: Box<dyn Any> = Box::new(1_usize);
+    ///
+    /// unsafe {
+    ///     assert_eq!(*x.downcast_unchecked::<usize>(), 1);
+    /// }
+    /// ```
+    ///
+    /// # Safety
+    ///
+    /// The contained value must be of type `T`. Calling this method
+    /// with the incorrect type is *undefined behavior*.
+    ///
+    /// [`downcast`]: Self::downcast
+    #[inline]
+    #[unstable(feature = "downcast_unchecked", issue = "90850")]
+    pub unsafe fn downcast_unchecked<T: Any>(self) -> Box<T, A> {
+        debug_assert!(self.is::<T>());
+        unsafe {
+            let (raw, alloc): (*mut dyn Any, _) = Box::into_raw_with_allocator(self);
+            Box::from_raw_in(raw as *mut T, alloc)
+        }
+    }
+}
+
+impl<A: Allocator> Box<dyn Any + Send, A> {
+    /// Attempt to downcast the box to a concrete type.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use std::any::Any;
+    ///
+    /// fn print_if_string(value: Box<dyn Any + Send>) {
+    ///     if let Ok(string) = value.downcast::<String>() {
+    ///         println!("String ({}): {}", string.len(), string);
+    ///     }
+    /// }
+    ///
+    /// let my_string = "Hello World".to_string();
+    /// print_if_string(Box::new(my_string));
+    /// print_if_string(Box::new(0i8));
+    /// ```
+    #[inline]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn downcast<T: Any>(self) -> Result<Box<T, A>, Self> {
+        if self.is::<T>() { unsafe { Ok(self.downcast_unchecked::<T>()) } } else { Err(self) }
+    }
+
+    /// Downcasts the box to a concrete type.
+    ///
+    /// For a safe alternative see [`downcast`].
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(downcast_unchecked)]
+    ///
+    /// use std::any::Any;
+    ///
+    /// let x: Box<dyn Any + Send> = Box::new(1_usize);
+    ///
+    /// unsafe {
+    ///     assert_eq!(*x.downcast_unchecked::<usize>(), 1);
+    /// }
+    /// ```
+    ///
+    /// # Safety
+    ///
+    /// The contained value must be of type `T`. Calling this method
+    /// with the incorrect type is *undefined behavior*.
+    ///
+    /// [`downcast`]: Self::downcast
+    #[inline]
+    #[unstable(feature = "downcast_unchecked", issue = "90850")]
+    pub unsafe fn downcast_unchecked<T: Any>(self) -> Box<T, A> {
+        debug_assert!(self.is::<T>());
+        unsafe {
+            let (raw, alloc): (*mut (dyn Any + Send), _) = Box::into_raw_with_allocator(self);
+            Box::from_raw_in(raw as *mut T, alloc)
+        }
+    }
+}
+
+impl<A: Allocator> Box<dyn Any + Send + Sync, A> {
+    /// Attempt to downcast the box to a concrete type.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use std::any::Any;
+    ///
+    /// fn print_if_string(value: Box<dyn Any + Send + Sync>) {
+    ///     if let Ok(string) = value.downcast::<String>() {
+    ///         println!("String ({}): {}", string.len(), string);
+    ///     }
+    /// }
+    ///
+    /// let my_string = "Hello World".to_string();
+    /// print_if_string(Box::new(my_string));
+    /// print_if_string(Box::new(0i8));
+    /// ```
+    #[inline]
+    #[stable(feature = "box_send_sync_any_downcast", since = "1.51.0")]
+    pub fn downcast<T: Any>(self) -> Result<Box<T, A>, Self> {
+        if self.is::<T>() { unsafe { Ok(self.downcast_unchecked::<T>()) } } else { Err(self) }
+    }
+
+    /// Downcasts the box to a concrete type.
+    ///
+    /// For a safe alternative see [`downcast`].
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(downcast_unchecked)]
+    ///
+    /// use std::any::Any;
+    ///
+    /// let x: Box<dyn Any + Send + Sync> = Box::new(1_usize);
+    ///
+    /// unsafe {
+    ///     assert_eq!(*x.downcast_unchecked::<usize>(), 1);
+    /// }
+    /// ```
+    ///
+    /// # Safety
+    ///
+    /// The contained value must be of type `T`. Calling this method
+    /// with the incorrect type is *undefined behavior*.
+    ///
+    /// [`downcast`]: Self::downcast
+    #[inline]
+    #[unstable(feature = "downcast_unchecked", issue = "90850")]
+    pub unsafe fn downcast_unchecked<T: Any>(self) -> Box<T, A> {
+        debug_assert!(self.is::<T>());
+        unsafe {
+            let (raw, alloc): (*mut (dyn Any + Send + Sync), _) =
+                Box::into_raw_with_allocator(self);
+            Box::from_raw_in(raw as *mut T, alloc)
+        }
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: fmt::Display + ?Sized, A: Allocator> fmt::Display for Box<T, A> {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        fmt::Display::fmt(&**self, f)
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: fmt::Debug + ?Sized, A: Allocator> fmt::Debug for Box<T, A> {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        fmt::Debug::fmt(&**self, f)
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: ?Sized, A: Allocator> fmt::Pointer for Box<T, A> {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        // It's not possible to extract the inner Uniq directly from the Box,
+        // instead we cast it to a *const which aliases the Unique
+        let ptr: *const T = &**self;
+        fmt::Pointer::fmt(&ptr, f)
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+#[rustc_const_unstable(feature = "const_box", issue = "92521")]
+impl<T: ?Sized, A: Allocator> const Deref for Box<T, A> {
+    type Target = T;
+
+    fn deref(&self) -> &T {
+        &**self
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+#[rustc_const_unstable(feature = "const_box", issue = "92521")]
+impl<T: ?Sized, A: Allocator> const DerefMut for Box<T, A> {
+    fn deref_mut(&mut self) -> &mut T {
+        &mut **self
+    }
+}
+
+#[unstable(feature = "receiver_trait", issue = "none")]
+impl<T: ?Sized, A: Allocator> Receiver for Box<T, A> {}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<I: Iterator + ?Sized, A: Allocator> Iterator for Box<I, A> {
+    type Item = I::Item;
+    fn next(&mut self) -> Option<I::Item> {
+        (**self).next()
+    }
+    fn size_hint(&self) -> (usize, Option<usize>) {
+        (**self).size_hint()
+    }
+    fn nth(&mut self, n: usize) -> Option<I::Item> {
+        (**self).nth(n)
+    }
+    fn last(self) -> Option<I::Item> {
+        BoxIter::last(self)
+    }
+}
+
+trait BoxIter {
+    type Item;
+    fn last(self) -> Option<Self::Item>;
+}
+
+impl<I: Iterator + ?Sized, A: Allocator> BoxIter for Box<I, A> {
+    type Item = I::Item;
+    default fn last(self) -> Option<I::Item> {
+        #[inline]
+        fn some<T>(_: Option<T>, x: T) -> Option<T> {
+            Some(x)
+        }
+
+        self.fold(None, some)
+    }
+}
+
+/// Specialization for sized `I`s that uses `I`s implementation of `last()`
+/// instead of the default.
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<I: Iterator, A: Allocator> BoxIter for Box<I, A> {
+    fn last(self) -> Option<I::Item> {
+        (*self).last()
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<I: DoubleEndedIterator + ?Sized, A: Allocator> DoubleEndedIterator for Box<I, A> {
+    fn next_back(&mut self) -> Option<I::Item> {
+        (**self).next_back()
+    }
+    fn nth_back(&mut self, n: usize) -> Option<I::Item> {
+        (**self).nth_back(n)
+    }
+}
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<I: ExactSizeIterator + ?Sized, A: Allocator> ExactSizeIterator for Box<I, A> {
+    fn len(&self) -> usize {
+        (**self).len()
+    }
+    fn is_empty(&self) -> bool {
+        (**self).is_empty()
+    }
+}
+
+#[stable(feature = "fused", since = "1.26.0")]
+impl<I: FusedIterator + ?Sized, A: Allocator> FusedIterator for Box<I, A> {}
+
+#[stable(feature = "boxed_closure_impls", since = "1.35.0")]
+impl<Args, F: FnOnce<Args> + ?Sized, A: Allocator> FnOnce<Args> for Box<F, A> {
+    type Output = <F as FnOnce<Args>>::Output;
+
+    extern "rust-call" fn call_once(self, args: Args) -> Self::Output {
+        <F as FnOnce<Args>>::call_once(*self, args)
+    }
+}
+
+#[stable(feature = "boxed_closure_impls", since = "1.35.0")]
+impl<Args, F: FnMut<Args> + ?Sized, A: Allocator> FnMut<Args> for Box<F, A> {
+    extern "rust-call" fn call_mut(&mut self, args: Args) -> Self::Output {
+        <F as FnMut<Args>>::call_mut(self, args)
+    }
+}
+
+#[stable(feature = "boxed_closure_impls", since = "1.35.0")]
+impl<Args, F: Fn<Args> + ?Sized, A: Allocator> Fn<Args> for Box<F, A> {
+    extern "rust-call" fn call(&self, args: Args) -> Self::Output {
+        <F as Fn<Args>>::call(self, args)
+    }
+}
+
+#[unstable(feature = "coerce_unsized", issue = "27732")]
+impl<T: ?Sized + Unsize<U>, U: ?Sized, A: Allocator> CoerceUnsized<Box<U, A>> for Box<T, A> {}
+
+#[unstable(feature = "dispatch_from_dyn", issue = "none")]
+impl<T: ?Sized + Unsize<U>, U: ?Sized> DispatchFromDyn<Box<U>> for Box<T, Global> {}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "boxed_slice_from_iter", since = "1.32.0")]
+impl<I> FromIterator<I> for Box<[I]> {
+    fn from_iter<T: IntoIterator<Item = I>>(iter: T) -> Self {
+        iter.into_iter().collect::<Vec<_>>().into_boxed_slice()
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "box_slice_clone", since = "1.3.0")]
+impl<T: Clone, A: Allocator + Clone> Clone for Box<[T], A> {
+    fn clone(&self) -> Self {
+        let alloc = Box::allocator(self).clone();
+        self.to_vec_in(alloc).into_boxed_slice()
+    }
+
+    fn clone_from(&mut self, other: &Self) {
+        if self.len() == other.len() {
+            self.clone_from_slice(&other);
+        } else {
+            *self = other.clone();
+        }
+    }
+}
+
+#[stable(feature = "box_borrow", since = "1.1.0")]
+impl<T: ?Sized, A: Allocator> borrow::Borrow<T> for Box<T, A> {
+    fn borrow(&self) -> &T {
+        &**self
+    }
+}
+
+#[stable(feature = "box_borrow", since = "1.1.0")]
+impl<T: ?Sized, A: Allocator> borrow::BorrowMut<T> for Box<T, A> {
+    fn borrow_mut(&mut self) -> &mut T {
+        &mut **self
+    }
+}
+
+#[stable(since = "1.5.0", feature = "smart_ptr_as_ref")]
+impl<T: ?Sized, A: Allocator> AsRef<T> for Box<T, A> {
+    fn as_ref(&self) -> &T {
+        &**self
+    }
+}
+
+#[stable(since = "1.5.0", feature = "smart_ptr_as_ref")]
+impl<T: ?Sized, A: Allocator> AsMut<T> for Box<T, A> {
+    fn as_mut(&mut self) -> &mut T {
+        &mut **self
+    }
+}
+
+/* Nota bene
+ *
+ *  We could have chosen not to add this impl, and instead have written a
+ *  function of Pin<Box<T>> to Pin<T>. Such a function would not be sound,
+ *  because Box<T> implements Unpin even when T does not, as a result of
+ *  this impl.
+ *
+ *  We chose this API instead of the alternative for a few reasons:
+ *      - Logically, it is helpful to understand pinning in regard to the
+ *        memory region being pointed to. For this reason none of the
+ *        standard library pointer types support projecting through a pin
+ *        (Box<T> is the only pointer type in std for which this would be
+ *        safe.)
+ *      - It is in practice very useful to have Box<T> be unconditionally
+ *        Unpin because of trait objects, for which the structural auto
+ *        trait functionality does not apply (e.g., Box<dyn Foo> would
+ *        otherwise not be Unpin).
+ *
+ *  Another type with the same semantics as Box but only a conditional
+ *  implementation of `Unpin` (where `T: Unpin`) would be valid/safe, and
+ *  could have a method to project a Pin<T> from it.
+ */
+#[stable(feature = "pin", since = "1.33.0")]
+#[rustc_const_unstable(feature = "const_box", issue = "92521")]
+impl<T: ?Sized, A: Allocator> const Unpin for Box<T, A> where A: 'static {}
+
+#[unstable(feature = "generator_trait", issue = "43122")]
+impl<G: ?Sized + Generator<R> + Unpin, R, A: Allocator> Generator<R> for Box<G, A>
+where
+    A: 'static,
+{
+    type Yield = G::Yield;
+    type Return = G::Return;
+
+    fn resume(mut self: Pin<&mut Self>, arg: R) -> GeneratorState<Self::Yield, Self::Return> {
+        G::resume(Pin::new(&mut *self), arg)
+    }
+}
+
+#[unstable(feature = "generator_trait", issue = "43122")]
+impl<G: ?Sized + Generator<R>, R, A: Allocator> Generator<R> for Pin<Box<G, A>>
+where
+    A: 'static,
+{
+    type Yield = G::Yield;
+    type Return = G::Return;
+
+    fn resume(mut self: Pin<&mut Self>, arg: R) -> GeneratorState<Self::Yield, Self::Return> {
+        G::resume((*self).as_mut(), arg)
+    }
+}
+
+#[stable(feature = "futures_api", since = "1.36.0")]
+impl<F: ?Sized + Future + Unpin, A: Allocator> Future for Box<F, A>
+where
+    A: 'static,
+{
+    type Output = F::Output;
+
+    fn poll(mut self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<Self::Output> {
+        F::poll(Pin::new(&mut *self), cx)
+    }
+}
+
+#[unstable(feature = "async_iterator", issue = "79024")]
+impl<S: ?Sized + AsyncIterator + Unpin> AsyncIterator for Box<S> {
+    type Item = S::Item;
+
+    fn poll_next(mut self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<Option<Self::Item>> {
+        Pin::new(&mut **self).poll_next(cx)
+    }
+
+    fn size_hint(&self) -> (usize, Option<usize>) {
+        (**self).size_hint()
+    }
+}
diff --git a/rust/alloc/collections/mod.rs b/rust/alloc/collections/mod.rs
new file mode 100644
index 000000000000..1eec265b28f8
--- /dev/null
+++ b/rust/alloc/collections/mod.rs
@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+//! Collection types.
+
+#![stable(feature = "rust1", since = "1.0.0")]
+
+#[cfg(not(no_global_oom_handling))]
+pub mod binary_heap;
+#[cfg(not(no_global_oom_handling))]
+mod btree;
+#[cfg(not(no_global_oom_handling))]
+pub mod linked_list;
+#[cfg(not(no_global_oom_handling))]
+pub mod vec_deque;
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+pub mod btree_map {
+    //! An ordered map based on a B-Tree.
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub use super::btree::map::*;
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+pub mod btree_set {
+    //! An ordered set based on a B-Tree.
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub use super::btree::set::*;
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+#[doc(no_inline)]
+pub use binary_heap::BinaryHeap;
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+#[doc(no_inline)]
+pub use btree_map::BTreeMap;
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+#[doc(no_inline)]
+pub use btree_set::BTreeSet;
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+#[doc(no_inline)]
+pub use linked_list::LinkedList;
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+#[doc(no_inline)]
+pub use vec_deque::VecDeque;
+
+use crate::alloc::{Layout, LayoutError};
+use core::fmt::Display;
+
+/// The error type for `try_reserve` methods.
+#[derive(Clone, PartialEq, Eq, Debug)]
+#[stable(feature = "try_reserve", since = "1.57.0")]
+pub struct TryReserveError {
+    kind: TryReserveErrorKind,
+}
+
+impl TryReserveError {
+    /// Details about the allocation that caused the error
+    #[inline]
+    #[must_use]
+    #[unstable(
+        feature = "try_reserve_kind",
+        reason = "Uncertain how much info should be exposed",
+        issue = "48043"
+    )]
+    pub fn kind(&self) -> TryReserveErrorKind {
+        self.kind.clone()
+    }
+}
+
+/// Details of the allocation that caused a `TryReserveError`
+#[derive(Clone, PartialEq, Eq, Debug)]
+#[unstable(
+    feature = "try_reserve_kind",
+    reason = "Uncertain how much info should be exposed",
+    issue = "48043"
+)]
+pub enum TryReserveErrorKind {
+    /// Error due to the computed capacity exceeding the collection's maximum
+    /// (usually `isize::MAX` bytes).
+    CapacityOverflow,
+
+    /// The memory allocator returned an error
+    AllocError {
+        /// The layout of allocation request that failed
+        layout: Layout,
+
+        #[doc(hidden)]
+        #[unstable(
+            feature = "container_error_extra",
+            issue = "none",
+            reason = "\
+            Enable exposing the allocator’s custom error value \
+            if an associated type is added in the future: \
+            https://github.com/rust-lang/wg-allocators/issues/23"
+        )]
+        non_exhaustive: (),
+    },
+}
+
+#[unstable(
+    feature = "try_reserve_kind",
+    reason = "Uncertain how much info should be exposed",
+    issue = "48043"
+)]
+impl From<TryReserveErrorKind> for TryReserveError {
+    #[inline]
+    fn from(kind: TryReserveErrorKind) -> Self {
+        Self { kind }
+    }
+}
+
+#[unstable(feature = "try_reserve_kind", reason = "new API", issue = "48043")]
+impl From<LayoutError> for TryReserveErrorKind {
+    /// Always evaluates to [`TryReserveErrorKind::CapacityOverflow`].
+    #[inline]
+    fn from(_: LayoutError) -> Self {
+        TryReserveErrorKind::CapacityOverflow
+    }
+}
+
+#[stable(feature = "try_reserve", since = "1.57.0")]
+impl Display for TryReserveError {
+    fn fmt(
+        &self,
+        fmt: &mut core::fmt::Formatter<'_>,
+    ) -> core::result::Result<(), core::fmt::Error> {
+        fmt.write_str("memory allocation failed")?;
+        let reason = match self.kind {
+            TryReserveErrorKind::CapacityOverflow => {
+                " because the computed capacity exceeded the collection's maximum"
+            }
+            TryReserveErrorKind::AllocError { .. } => {
+                " because the memory allocator returned a error"
+            }
+        };
+        fmt.write_str(reason)
+    }
+}
+
+/// An intermediate trait for specialization of `Extend`.
+#[doc(hidden)]
+trait SpecExtend<I: IntoIterator> {
+    /// Extends `self` with the contents of the given iterator.
+    fn spec_extend(&mut self, iter: I);
+}
diff --git a/rust/alloc/lib.rs b/rust/alloc/lib.rs
new file mode 100644
index 000000000000..233bcd5e4654
--- /dev/null
+++ b/rust/alloc/lib.rs
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+//! # The Rust core allocation and collections library
+//!
+//! This library provides smart pointers and collections for managing
+//! heap-allocated values.
+//!
+//! This library, like libcore, normally doesn’t need to be used directly
+//! since its contents are re-exported in the [`std` crate](../std/index.html).
+//! Crates that use the `#![no_std]` attribute however will typically
+//! not depend on `std`, so they’d use this crate instead.
+//!
+//! ## Boxed values
+//!
+//! The [`Box`] type is a smart pointer type. There can only be one owner of a
+//! [`Box`], and the owner can decide to mutate the contents, which live on the
+//! heap.
+//!
+//! This type can be sent among threads efficiently as the size of a `Box` value
+//! is the same as that of a pointer. Tree-like data structures are often built
+//! with boxes because each node often has only one owner, the parent.
+//!
+//! ## Reference counted pointers
+//!
+//! The [`Rc`] type is a non-threadsafe reference-counted pointer type intended
+//! for sharing memory within a thread. An [`Rc`] pointer wraps a type, `T`, and
+//! only allows access to `&T`, a shared reference.
+//!
+//! This type is useful when inherited mutability (such as using [`Box`]) is too
+//! constraining for an application, and is often paired with the [`Cell`] or
+//! [`RefCell`] types in order to allow mutation.
+//!
+//! ## Atomically reference counted pointers
+//!
+//! The [`Arc`] type is the threadsafe equivalent of the [`Rc`] type. It
+//! provides all the same functionality of [`Rc`], except it requires that the
+//! contained type `T` is shareable. Additionally, [`Arc<T>`][`Arc`] is itself
+//! sendable while [`Rc<T>`][`Rc`] is not.
+//!
+//! This type allows for shared access to the contained data, and is often
+//! paired with synchronization primitives such as mutexes to allow mutation of
+//! shared resources.
+//!
+//! ## Collections
+//!
+//! Implementations of the most common general purpose data structures are
+//! defined in this library. They are re-exported through the
+//! [standard collections library](../std/collections/index.html).
+//!
+//! ## Heap interfaces
+//!
+//! The [`alloc`](alloc/index.html) module defines the low-level interface to the
+//! default global allocator. It is not compatible with the libc allocator API.
+//!
+//! [`Arc`]: sync
+//! [`Box`]: boxed
+//! [`Cell`]: core::cell
+//! [`Rc`]: rc
+//! [`RefCell`]: core::cell
+
+// To run liballoc tests without x.py without ending up with two copies of liballoc, Miri needs to be
+// able to "empty" this crate. See <https://github.com/rust-lang/miri-test-libstd/issues/4>.
+// rustc itself never sets the feature, so this line has no affect there.
+#![cfg(any(not(feature = "miri-test-libstd"), test, doctest))]
+#![allow(unused_attributes)]
+#![stable(feature = "alloc", since = "1.36.0")]
+#![doc(
+    html_playground_url = "https://play.rust-lang.org/",
+    issue_tracker_base_url = "https://github.com/rust-lang/rust/issues/",
+    test(no_crate_inject, attr(allow(unused_variables), deny(warnings)))
+)]
+#![doc(cfg_hide(
+    not(test),
+    not(any(test, bootstrap)),
+    any(not(feature = "miri-test-libstd"), test, doctest),
+    no_global_oom_handling,
+    not(no_global_oom_handling),
+    target_has_atomic = "ptr"
+))]
+#![no_std]
+#![needs_allocator]
+//
+// Lints:
+#![deny(unsafe_op_in_unsafe_fn)]
+#![warn(deprecated_in_future)]
+#![warn(missing_debug_implementations)]
+#![warn(missing_docs)]
+#![allow(explicit_outlives_requirements)]
+//
+// Library features:
+#![cfg_attr(not(no_global_oom_handling), feature(alloc_c_string))]
+#![feature(alloc_layout_extra)]
+#![feature(allocator_api)]
+#![feature(array_chunks)]
+#![feature(array_methods)]
+#![feature(array_windows)]
+#![feature(assert_matches)]
+#![feature(async_iterator)]
+#![feature(coerce_unsized)]
+#![cfg_attr(not(no_global_oom_handling), feature(const_alloc_error))]
+#![feature(const_box)]
+#![cfg_attr(not(no_global_oom_handling), feature(const_btree_new))]
+#![feature(const_cow_is_borrowed)]
+#![feature(const_convert)]
+#![feature(const_size_of_val)]
+#![feature(const_align_of_val)]
+#![feature(const_ptr_read)]
+#![feature(const_maybe_uninit_write)]
+#![feature(const_maybe_uninit_as_mut_ptr)]
+#![feature(const_refs_to_cell)]
+#![feature(core_c_str)]
+#![feature(core_intrinsics)]
+#![feature(core_ffi_c)]
+#![feature(const_eval_select)]
+#![feature(const_pin)]
+#![feature(cstr_from_bytes_until_nul)]
+#![feature(dispatch_from_dyn)]
+#![feature(exact_size_is_empty)]
+#![feature(extend_one)]
+#![feature(fmt_internals)]
+#![feature(fn_traits)]
+#![feature(hasher_prefixfree_extras)]
+#![feature(inplace_iteration)]
+#![feature(iter_advance_by)]
+#![feature(layout_for_ptr)]
+#![feature(maybe_uninit_slice)]
+#![cfg_attr(test, feature(new_uninit))]
+#![feature(nonnull_slice_from_raw_parts)]
+#![feature(pattern)]
+#![feature(ptr_internals)]
+#![feature(ptr_metadata)]
+#![feature(ptr_sub_ptr)]
+#![feature(receiver_trait)]
+#![feature(set_ptr_value)]
+#![feature(slice_group_by)]
+#![feature(slice_ptr_get)]
+#![feature(slice_ptr_len)]
+#![feature(slice_range)]
+#![feature(str_internals)]
+#![feature(strict_provenance)]
+#![feature(trusted_len)]
+#![feature(trusted_random_access)]
+#![feature(try_trait_v2)]
+#![feature(unchecked_math)]
+#![feature(unicode_internals)]
+#![feature(unsize)]
+//
+// Language features:
+#![feature(allocator_internals)]
+#![feature(allow_internal_unstable)]
+#![feature(associated_type_bounds)]
+#![feature(box_syntax)]
+#![feature(cfg_sanitize)]
+#![feature(const_deref)]
+#![feature(const_mut_refs)]
+#![feature(const_ptr_write)]
+#![feature(const_precise_live_drops)]
+#![feature(const_trait_impl)]
+#![feature(const_try)]
+#![feature(dropck_eyepatch)]
+#![feature(exclusive_range_pattern)]
+#![feature(fundamental)]
+#![cfg_attr(not(test), feature(generator_trait))]
+#![feature(hashmap_internals)]
+#![feature(lang_items)]
+#![feature(let_else)]
+#![feature(min_specialization)]
+#![feature(negative_impls)]
+#![feature(never_type)]
+#![feature(nll)] // Not necessary, but here to test the `nll` feature.
+#![feature(rustc_allow_const_fn_unstable)]
+#![feature(rustc_attrs)]
+#![feature(slice_internals)]
+#![feature(staged_api)]
+#![cfg_attr(test, feature(test))]
+#![feature(unboxed_closures)]
+#![feature(unsized_fn_params)]
+#![feature(c_unwind)]
+//
+// Rustdoc features:
+#![feature(doc_cfg)]
+#![feature(doc_cfg_hide)]
+// Technically, this is a bug in rustdoc: rustdoc sees the documentation on `#[lang = slice_alloc]`
+// blocks is for `&[T]`, which also has documentation using this feature in `core`, and gets mad
+// that the feature-gate isn't enabled. Ideally, it wouldn't check for the feature gate for docs
+// from other crates, but since this can only appear for lang items, it doesn't seem worth fixing.
+#![feature(intra_doc_pointers)]
+
+// Allow testing this library
+#[cfg(test)]
+#[macro_use]
+extern crate std;
+#[cfg(test)]
+extern crate test;
+
+// Module with internal macros used by other modules (needs to be included before other modules).
+#[cfg(not(no_macros))]
+#[macro_use]
+mod macros;
+
+mod raw_vec;
+
+// Heaps provided for low-level allocation strategies
+
+pub mod alloc;
+
+// Primitive types using the heaps above
+
+// Need to conditionally define the mod from `boxed.rs` to avoid
+// duplicating the lang-items when building in test cfg; but also need
+// to allow code to have `use boxed::Box;` declarations.
+#[cfg(not(test))]
+pub mod boxed;
+#[cfg(test)]
+mod boxed {
+    pub use std::boxed::Box;
+}
+pub mod borrow;
+pub mod collections;
+#[cfg(not(no_global_oom_handling))]
+pub mod ffi;
+#[cfg(not(no_fmt))]
+pub mod fmt;
+#[cfg(not(no_rc))]
+pub mod rc;
+pub mod slice;
+#[cfg(not(no_str))]
+pub mod str;
+#[cfg(not(no_string))]
+pub mod string;
+#[cfg(not(no_sync))]
+#[cfg(target_has_atomic = "ptr")]
+pub mod sync;
+#[cfg(all(not(no_global_oom_handling), target_has_atomic = "ptr"))]
+pub mod task;
+#[cfg(test)]
+mod tests;
+pub mod vec;
+
+#[doc(hidden)]
+#[unstable(feature = "liballoc_internals", issue = "none", reason = "implementation detail")]
+pub mod __export {
+    pub use core::format_args;
+}
diff --git a/rust/alloc/raw_vec.rs b/rust/alloc/raw_vec.rs
new file mode 100644
index 000000000000..daf5f2da7168
--- /dev/null
+++ b/rust/alloc/raw_vec.rs
@@ -0,0 +1,527 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+#![unstable(feature = "raw_vec_internals", reason = "unstable const warnings", issue = "none")]
+
+use core::alloc::LayoutError;
+use core::cmp;
+use core::intrinsics;
+use core::mem::{self, ManuallyDrop, MaybeUninit};
+use core::ops::Drop;
+use core::ptr::{self, NonNull, Unique};
+use core::slice;
+
+#[cfg(not(no_global_oom_handling))]
+use crate::alloc::handle_alloc_error;
+use crate::alloc::{Allocator, Global, Layout};
+use crate::boxed::Box;
+use crate::collections::TryReserveError;
+use crate::collections::TryReserveErrorKind::*;
+
+#[cfg(test)]
+mod tests;
+
+#[cfg(not(no_global_oom_handling))]
+enum AllocInit {
+    /// The contents of the new memory are uninitialized.
+    Uninitialized,
+    /// The new memory is guaranteed to be zeroed.
+    Zeroed,
+}
+
+/// A low-level utility for more ergonomically allocating, reallocating, and deallocating
+/// a buffer of memory on the heap without having to worry about all the corner cases
+/// involved. This type is excellent for building your own data structures like Vec and VecDeque.
+/// In particular:
+///
+/// * Produces `Unique::dangling()` on zero-sized types.
+/// * Produces `Unique::dangling()` on zero-length allocations.
+/// * Avoids freeing `Unique::dangling()`.
+/// * Catches all overflows in capacity computations (promotes them to "capacity overflow" panics).
+/// * Guards against 32-bit systems allocating more than isize::MAX bytes.
+/// * Guards against overflowing your length.
+/// * Calls `handle_alloc_error` for fallible allocations.
+/// * Contains a `ptr::Unique` and thus endows the user with all related benefits.
+/// * Uses the excess returned from the allocator to use the largest available capacity.
+///
+/// This type does not in anyway inspect the memory that it manages. When dropped it *will*
+/// free its memory, but it *won't* try to drop its contents. It is up to the user of `RawVec`
+/// to handle the actual things *stored* inside of a `RawVec`.
+///
+/// Note that the excess of a zero-sized types is always infinite, so `capacity()` always returns
+/// `usize::MAX`. This means that you need to be careful when round-tripping this type with a
+/// `Box<[T]>`, since `capacity()` won't yield the length.
+#[allow(missing_debug_implementations)]
+pub(crate) struct RawVec<T, A: Allocator = Global> {
+    ptr: Unique<T>,
+    cap: usize,
+    alloc: A,
+}
+
+impl<T> RawVec<T, Global> {
+    /// HACK(Centril): This exists because stable `const fn` can only call stable `const fn`, so
+    /// they cannot call `Self::new()`.
+    ///
+    /// If you change `RawVec<T>::new` or dependencies, please take care to not introduce anything
+    /// that would truly const-call something unstable.
+    pub const NEW: Self = Self::new();
+
+    /// Creates the biggest possible `RawVec` (on the system heap)
+    /// without allocating. If `T` has positive size, then this makes a
+    /// `RawVec` with capacity `0`. If `T` is zero-sized, then it makes a
+    /// `RawVec` with capacity `usize::MAX`. Useful for implementing
+    /// delayed allocation.
+    #[must_use]
+    pub const fn new() -> Self {
+        Self::new_in(Global)
+    }
+
+    /// Creates a `RawVec` (on the system heap) with exactly the
+    /// capacity and alignment requirements for a `[T; capacity]`. This is
+    /// equivalent to calling `RawVec::new` when `capacity` is `0` or `T` is
+    /// zero-sized. Note that if `T` is zero-sized this means you will
+    /// *not* get a `RawVec` with the requested capacity.
+    ///
+    /// # Panics
+    ///
+    /// Panics if the requested capacity exceeds `isize::MAX` bytes.
+    ///
+    /// # Aborts
+    ///
+    /// Aborts on OOM.
+    #[cfg(not(any(no_global_oom_handling, test)))]
+    #[must_use]
+    #[inline]
+    pub fn with_capacity(capacity: usize) -> Self {
+        Self::with_capacity_in(capacity, Global)
+    }
+
+    /// Like `with_capacity`, but guarantees the buffer is zeroed.
+    #[cfg(not(any(no_global_oom_handling, test)))]
+    #[must_use]
+    #[inline]
+    pub fn with_capacity_zeroed(capacity: usize) -> Self {
+        Self::with_capacity_zeroed_in(capacity, Global)
+    }
+}
+
+impl<T, A: Allocator> RawVec<T, A> {
+    // Tiny Vecs are dumb. Skip to:
+    // - 8 if the element size is 1, because any heap allocators is likely
+    //   to round up a request of less than 8 bytes to at least 8 bytes.
+    // - 4 if elements are moderate-sized (<= 1 KiB).
+    // - 1 otherwise, to avoid wasting too much space for very short Vecs.
+    pub(crate) const MIN_NON_ZERO_CAP: usize = if mem::size_of::<T>() == 1 {
+        8
+    } else if mem::size_of::<T>() <= 1024 {
+        4
+    } else {
+        1
+    };
+
+    /// Like `new`, but parameterized over the choice of allocator for
+    /// the returned `RawVec`.
+    pub const fn new_in(alloc: A) -> Self {
+        // `cap: 0` means "unallocated". zero-sized types are ignored.
+        Self { ptr: Unique::dangling(), cap: 0, alloc }
+    }
+
+    /// Like `with_capacity`, but parameterized over the choice of
+    /// allocator for the returned `RawVec`.
+    #[cfg(not(no_global_oom_handling))]
+    #[inline]
+    pub fn with_capacity_in(capacity: usize, alloc: A) -> Self {
+        Self::allocate_in(capacity, AllocInit::Uninitialized, alloc)
+    }
+
+    /// Like `with_capacity_zeroed`, but parameterized over the choice
+    /// of allocator for the returned `RawVec`.
+    #[cfg(not(no_global_oom_handling))]
+    #[inline]
+    pub fn with_capacity_zeroed_in(capacity: usize, alloc: A) -> Self {
+        Self::allocate_in(capacity, AllocInit::Zeroed, alloc)
+    }
+
+    /// Converts the entire buffer into `Box<[MaybeUninit<T>]>` with the specified `len`.
+    ///
+    /// Note that this will correctly reconstitute any `cap` changes
+    /// that may have been performed. (See description of type for details.)
+    ///
+    /// # Safety
+    ///
+    /// * `len` must be greater than or equal to the most recently requested capacity, and
+    /// * `len` must be less than or equal to `self.capacity()`.
+    ///
+    /// Note, that the requested capacity and `self.capacity()` could differ, as
+    /// an allocator could overallocate and return a greater memory block than requested.
+    pub unsafe fn into_box(self, len: usize) -> Box<[MaybeUninit<T>], A> {
+        // Sanity-check one half of the safety requirement (we cannot check the other half).
+        debug_assert!(
+            len <= self.capacity(),
+            "`len` must be smaller than or equal to `self.capacity()`"
+        );
+
+        let me = ManuallyDrop::new(self);
+        unsafe {
+            let slice = slice::from_raw_parts_mut(me.ptr() as *mut MaybeUninit<T>, len);
+            Box::from_raw_in(slice, ptr::read(&me.alloc))
+        }
+    }
+
+    #[cfg(not(no_global_oom_handling))]
+    fn allocate_in(capacity: usize, init: AllocInit, alloc: A) -> Self {
+        // Don't allocate here because `Drop` will not deallocate when `capacity` is 0.
+        if mem::size_of::<T>() == 0 || capacity == 0 {
+            Self::new_in(alloc)
+        } else {
+            // We avoid `unwrap_or_else` here because it bloats the amount of
+            // LLVM IR generated.
+            let layout = match Layout::array::<T>(capacity) {
+                Ok(layout) => layout,
+                Err(_) => capacity_overflow(),
+            };
+            match alloc_guard(layout.size()) {
+                Ok(_) => {}
+                Err(_) => capacity_overflow(),
+            }
+            let result = match init {
+                AllocInit::Uninitialized => alloc.allocate(layout),
+                AllocInit::Zeroed => alloc.allocate_zeroed(layout),
+            };
+            let ptr = match result {
+                Ok(ptr) => ptr,
+                Err(_) => handle_alloc_error(layout),
+            };
+
+            // Allocators currently return a `NonNull<[u8]>` whose length
+            // matches the size requested. If that ever changes, the capacity
+            // here should change to `ptr.len() / mem::size_of::<T>()`.
+            Self {
+                ptr: unsafe { Unique::new_unchecked(ptr.cast().as_ptr()) },
+                cap: capacity,
+                alloc,
+            }
+        }
+    }
+
+    /// Reconstitutes a `RawVec` from a pointer, capacity, and allocator.
+    ///
+    /// # Safety
+    ///
+    /// The `ptr` must be allocated (via the given allocator `alloc`), and with the given
+    /// `capacity`.
+    /// The `capacity` cannot exceed `isize::MAX` for sized types. (only a concern on 32-bit
+    /// systems). ZST vectors may have a capacity up to `usize::MAX`.
+    /// If the `ptr` and `capacity` come from a `RawVec` created via `alloc`, then this is
+    /// guaranteed.
+    #[inline]
+    pub unsafe fn from_raw_parts_in(ptr: *mut T, capacity: usize, alloc: A) -> Self {
+        Self { ptr: unsafe { Unique::new_unchecked(ptr) }, cap: capacity, alloc }
+    }
+
+    /// Gets a raw pointer to the start of the allocation. Note that this is
+    /// `Unique::dangling()` if `capacity == 0` or `T` is zero-sized. In the former case, you must
+    /// be careful.
+    #[inline]
+    pub fn ptr(&self) -> *mut T {
+        self.ptr.as_ptr()
+    }
+
+    /// Gets the capacity of the allocation.
+    ///
+    /// This will always be `usize::MAX` if `T` is zero-sized.
+    #[inline(always)]
+    pub fn capacity(&self) -> usize {
+        if mem::size_of::<T>() == 0 { usize::MAX } else { self.cap }
+    }
+
+    /// Returns a shared reference to the allocator backing this `RawVec`.
+    pub fn allocator(&self) -> &A {
+        &self.alloc
+    }
+
+    fn current_memory(&self) -> Option<(NonNull<u8>, Layout)> {
+        if mem::size_of::<T>() == 0 || self.cap == 0 {
+            None
+        } else {
+            // We have an allocated chunk of memory, so we can bypass runtime
+            // checks to get our current layout.
+            unsafe {
+                let layout = Layout::array::<T>(self.cap).unwrap_unchecked();
+                Some((self.ptr.cast().into(), layout))
+            }
+        }
+    }
+
+    /// Ensures that the buffer contains at least enough space to hold `len +
+    /// additional` elements. If it doesn't already have enough capacity, will
+    /// reallocate enough space plus comfortable slack space to get amortized
+    /// *O*(1) behavior. Will limit this behavior if it would needlessly cause
+    /// itself to panic.
+    ///
+    /// If `len` exceeds `self.capacity()`, this may fail to actually allocate
+    /// the requested space. This is not really unsafe, but the unsafe
+    /// code *you* write that relies on the behavior of this function may break.
+    ///
+    /// This is ideal for implementing a bulk-push operation like `extend`.
+    ///
+    /// # Panics
+    ///
+    /// Panics if the new capacity exceeds `isize::MAX` bytes.
+    ///
+    /// # Aborts
+    ///
+    /// Aborts on OOM.
+    #[cfg(not(no_global_oom_handling))]
+    #[inline]
+    pub fn reserve(&mut self, len: usize, additional: usize) {
+        // Callers expect this function to be very cheap when there is already sufficient capacity.
+        // Therefore, we move all the resizing and error-handling logic from grow_amortized and
+        // handle_reserve behind a call, while making sure that this function is likely to be
+        // inlined as just a comparison and a call if the comparison fails.
+        #[cold]
+        fn do_reserve_and_handle<T, A: Allocator>(
+            slf: &mut RawVec<T, A>,
+            len: usize,
+            additional: usize,
+        ) {
+            handle_reserve(slf.grow_amortized(len, additional));
+        }
+
+        if self.needs_to_grow(len, additional) {
+            do_reserve_and_handle(self, len, additional);
+        }
+    }
+
+    /// A specialized version of `reserve()` used only by the hot and
+    /// oft-instantiated `Vec::push()`, which does its own capacity check.
+    #[cfg(not(no_global_oom_handling))]
+    #[inline(never)]
+    pub fn reserve_for_push(&mut self, len: usize) {
+        handle_reserve(self.grow_amortized(len, 1));
+    }
+
+    /// The same as `reserve`, but returns on errors instead of panicking or aborting.
+    pub fn try_reserve(&mut self, len: usize, additional: usize) -> Result<(), TryReserveError> {
+        if self.needs_to_grow(len, additional) {
+            self.grow_amortized(len, additional)
+        } else {
+            Ok(())
+        }
+    }
+
+    /// The same as `reserve_for_push`, but returns on errors instead of panicking or aborting.
+    #[inline(never)]
+    pub fn try_reserve_for_push(&mut self, len: usize) -> Result<(), TryReserveError> {
+        self.grow_amortized(len, 1)
+    }
+
+    /// Ensures that the buffer contains at least enough space to hold `len +
+    /// additional` elements. If it doesn't already, will reallocate the
+    /// minimum possible amount of memory necessary. Generally this will be
+    /// exactly the amount of memory necessary, but in principle the allocator
+    /// is free to give back more than we asked for.
+    ///
+    /// If `len` exceeds `self.capacity()`, this may fail to actually allocate
+    /// the requested space. This is not really unsafe, but the unsafe code
+    /// *you* write that relies on the behavior of this function may break.
+    ///
+    /// # Panics
+    ///
+    /// Panics if the new capacity exceeds `isize::MAX` bytes.
+    ///
+    /// # Aborts
+    ///
+    /// Aborts on OOM.
+    #[cfg(not(no_global_oom_handling))]
+    pub fn reserve_exact(&mut self, len: usize, additional: usize) {
+        handle_reserve(self.try_reserve_exact(len, additional));
+    }
+
+    /// The same as `reserve_exact`, but returns on errors instead of panicking or aborting.
+    pub fn try_reserve_exact(
+        &mut self,
+        len: usize,
+        additional: usize,
+    ) -> Result<(), TryReserveError> {
+        if self.needs_to_grow(len, additional) { self.grow_exact(len, additional) } else { Ok(()) }
+    }
+
+    /// Shrinks the buffer down to the specified capacity. If the given amount
+    /// is 0, actually completely deallocates.
+    ///
+    /// # Panics
+    ///
+    /// Panics if the given amount is *larger* than the current capacity.
+    ///
+    /// # Aborts
+    ///
+    /// Aborts on OOM.
+    #[cfg(not(no_global_oom_handling))]
+    pub fn shrink_to_fit(&mut self, cap: usize) {
+        handle_reserve(self.shrink(cap));
+    }
+}
+
+impl<T, A: Allocator> RawVec<T, A> {
+    /// Returns if the buffer needs to grow to fulfill the needed extra capacity.
+    /// Mainly used to make inlining reserve-calls possible without inlining `grow`.
+    fn needs_to_grow(&self, len: usize, additional: usize) -> bool {
+        additional > self.capacity().wrapping_sub(len)
+    }
+
+    fn set_ptr_and_cap(&mut self, ptr: NonNull<[u8]>, cap: usize) {
+        // Allocators currently return a `NonNull<[u8]>` whose length matches
+        // the size requested. If that ever changes, the capacity here should
+        // change to `ptr.len() / mem::size_of::<T>()`.
+        self.ptr = unsafe { Unique::new_unchecked(ptr.cast().as_ptr()) };
+        self.cap = cap;
+    }
+
+    // This method is usually instantiated many times. So we want it to be as
+    // small as possible, to improve compile times. But we also want as much of
+    // its contents to be statically computable as possible, to make the
+    // generated code run faster. Therefore, this method is carefully written
+    // so that all of the code that depends on `T` is within it, while as much
+    // of the code that doesn't depend on `T` as possible is in functions that
+    // are non-generic over `T`.
+    fn grow_amortized(&mut self, len: usize, additional: usize) -> Result<(), TryReserveError> {
+        // This is ensured by the calling contexts.
+        debug_assert!(additional > 0);
+
+        if mem::size_of::<T>() == 0 {
+            // Since we return a capacity of `usize::MAX` when `elem_size` is
+            // 0, getting to here necessarily means the `RawVec` is overfull.
+            return Err(CapacityOverflow.into());
+        }
+
+        // Nothing we can really do about these checks, sadly.
+        let required_cap = len.checked_add(additional).ok_or(CapacityOverflow)?;
+
+        // This guarantees exponential growth. The doubling cannot overflow
+        // because `cap <= isize::MAX` and the type of `cap` is `usize`.
+        let cap = cmp::max(self.cap * 2, required_cap);
+        let cap = cmp::max(Self::MIN_NON_ZERO_CAP, cap);
+
+        let new_layout = Layout::array::<T>(cap);
+
+        // `finish_grow` is non-generic over `T`.
+        let ptr = finish_grow(new_layout, self.current_memory(), &mut self.alloc)?;
+        self.set_ptr_and_cap(ptr, cap);
+        Ok(())
+    }
+
+    // The constraints on this method are much the same as those on
+    // `grow_amortized`, but this method is usually instantiated less often so
+    // it's less critical.
+    fn grow_exact(&mut self, len: usize, additional: usize) -> Result<(), TryReserveError> {
+        if mem::size_of::<T>() == 0 {
+            // Since we return a capacity of `usize::MAX` when the type size is
+            // 0, getting to here necessarily means the `RawVec` is overfull.
+            return Err(CapacityOverflow.into());
+        }
+
+        let cap = len.checked_add(additional).ok_or(CapacityOverflow)?;
+        let new_layout = Layout::array::<T>(cap);
+
+        // `finish_grow` is non-generic over `T`.
+        let ptr = finish_grow(new_layout, self.current_memory(), &mut self.alloc)?;
+        self.set_ptr_and_cap(ptr, cap);
+        Ok(())
+    }
+
+    #[allow(dead_code)]
+    fn shrink(&mut self, cap: usize) -> Result<(), TryReserveError> {
+        assert!(cap <= self.capacity(), "Tried to shrink to a larger capacity");
+
+        let (ptr, layout) = if let Some(mem) = self.current_memory() { mem } else { return Ok(()) };
+
+        let ptr = unsafe {
+            // `Layout::array` cannot overflow here because it would have
+            // overflowed earlier when capacity was larger.
+            let new_layout = Layout::array::<T>(cap).unwrap_unchecked();
+            self.alloc
+                .shrink(ptr, layout, new_layout)
+                .map_err(|_| AllocError { layout: new_layout, non_exhaustive: () })?
+        };
+        self.set_ptr_and_cap(ptr, cap);
+        Ok(())
+    }
+}
+
+// This function is outside `RawVec` to minimize compile times. See the comment
+// above `RawVec::grow_amortized` for details. (The `A` parameter isn't
+// significant, because the number of different `A` types seen in practice is
+// much smaller than the number of `T` types.)
+#[inline(never)]
+fn finish_grow<A>(
+    new_layout: Result<Layout, LayoutError>,
+    current_memory: Option<(NonNull<u8>, Layout)>,
+    alloc: &mut A,
+) -> Result<NonNull<[u8]>, TryReserveError>
+where
+    A: Allocator,
+{
+    // Check for the error here to minimize the size of `RawVec::grow_*`.
+    let new_layout = new_layout.map_err(|_| CapacityOverflow)?;
+
+    alloc_guard(new_layout.size())?;
+
+    let memory = if let Some((ptr, old_layout)) = current_memory {
+        debug_assert_eq!(old_layout.align(), new_layout.align());
+        unsafe {
+            // The allocator checks for alignment equality
+            intrinsics::assume(old_layout.align() == new_layout.align());
+            alloc.grow(ptr, old_layout, new_layout)
+        }
+    } else {
+        alloc.allocate(new_layout)
+    };
+
+    memory.map_err(|_| AllocError { layout: new_layout, non_exhaustive: () }.into())
+}
+
+unsafe impl<#[may_dangle] T, A: Allocator> Drop for RawVec<T, A> {
+    /// Frees the memory owned by the `RawVec` *without* trying to drop its contents.
+    fn drop(&mut self) {
+        if let Some((ptr, layout)) = self.current_memory() {
+            unsafe { self.alloc.deallocate(ptr, layout) }
+        }
+    }
+}
+
+// Central function for reserve error handling.
+#[cfg(not(no_global_oom_handling))]
+#[inline]
+fn handle_reserve(result: Result<(), TryReserveError>) {
+    match result.map_err(|e| e.kind()) {
+        Err(CapacityOverflow) => capacity_overflow(),
+        Err(AllocError { layout, .. }) => handle_alloc_error(layout),
+        Ok(()) => { /* yay */ }
+    }
+}
+
+// We need to guarantee the following:
+// * We don't ever allocate `> isize::MAX` byte-size objects.
+// * We don't overflow `usize::MAX` and actually allocate too little.
+//
+// On 64-bit we just need to check for overflow since trying to allocate
+// `> isize::MAX` bytes will surely fail. On 32-bit and 16-bit we need to add
+// an extra guard for this in case we're running on a platform which can use
+// all 4GB in user-space, e.g., PAE or x32.
+
+#[inline]
+fn alloc_guard(alloc_size: usize) -> Result<(), TryReserveError> {
+    if usize::BITS < 64 && alloc_size > isize::MAX as usize {
+        Err(CapacityOverflow.into())
+    } else {
+        Ok(())
+    }
+}
+
+// One central function responsible for reporting capacity overflows. This'll
+// ensure that the code generation related to these panics is minimal as there's
+// only one location which panics rather than a bunch throughout the module.
+#[cfg(not(no_global_oom_handling))]
+fn capacity_overflow() -> ! {
+    panic!("capacity overflow");
+}
diff --git a/rust/alloc/slice.rs b/rust/alloc/slice.rs
new file mode 100644
index 000000000000..e444e97fa145
--- /dev/null
+++ b/rust/alloc/slice.rs
@@ -0,0 +1,1204 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+//! A dynamically-sized view into a contiguous sequence, `[T]`.
+//!
+//! *[See also the slice primitive type](slice).*
+//!
+//! Slices are a view into a block of memory represented as a pointer and a
+//! length.
+//!
+//! ```
+//! // slicing a Vec
+//! let vec = vec![1, 2, 3];
+//! let int_slice = &vec[..];
+//! // coercing an array to a slice
+//! let str_slice: &[&str] = &["one", "two", "three"];
+//! ```
+//!
+//! Slices are either mutable or shared. The shared slice type is `&[T]`,
+//! while the mutable slice type is `&mut [T]`, where `T` represents the element
+//! type. For example, you can mutate the block of memory that a mutable slice
+//! points to:
+//!
+//! ```
+//! let x = &mut [1, 2, 3];
+//! x[1] = 7;
+//! assert_eq!(x, &[1, 7, 3]);
+//! ```
+//!
+//! Here are some of the things this module contains:
+//!
+//! ## Structs
+//!
+//! There are several structs that are useful for slices, such as [`Iter`], which
+//! represents iteration over a slice.
+//!
+//! ## Trait Implementations
+//!
+//! There are several implementations of common traits for slices. Some examples
+//! include:
+//!
+//! * [`Clone`]
+//! * [`Eq`], [`Ord`] - for slices whose element type are [`Eq`] or [`Ord`].
+//! * [`Hash`] - for slices whose element type is [`Hash`].
+//!
+//! ## Iteration
+//!
+//! The slices implement `IntoIterator`. The iterator yields references to the
+//! slice elements.
+//!
+//! ```
+//! let numbers = &[0, 1, 2];
+//! for n in numbers {
+//!     println!("{n} is a number!");
+//! }
+//! ```
+//!
+//! The mutable slice yields mutable references to the elements:
+//!
+//! ```
+//! let mut scores = [7, 8, 9];
+//! for score in &mut scores[..] {
+//!     *score += 1;
+//! }
+//! ```
+//!
+//! This iterator yields mutable references to the slice's elements, so while
+//! the element type of the slice is `i32`, the element type of the iterator is
+//! `&mut i32`.
+//!
+//! * [`.iter`] and [`.iter_mut`] are the explicit methods to return the default
+//!   iterators.
+//! * Further methods that return iterators are [`.split`], [`.splitn`],
+//!   [`.chunks`], [`.windows`] and more.
+//!
+//! [`Hash`]: core::hash::Hash
+//! [`.iter`]: slice::iter
+//! [`.iter_mut`]: slice::iter_mut
+//! [`.split`]: slice::split
+//! [`.splitn`]: slice::splitn
+//! [`.chunks`]: slice::chunks
+//! [`.windows`]: slice::windows
+#![stable(feature = "rust1", since = "1.0.0")]
+// Many of the usings in this module are only used in the test configuration.
+// It's cleaner to just turn off the unused_imports warning than to fix them.
+#![cfg_attr(test, allow(unused_imports, dead_code))]
+
+use core::borrow::{Borrow, BorrowMut};
+#[cfg(not(no_global_oom_handling))]
+use core::cmp::Ordering::{self, Less};
+#[cfg(not(no_global_oom_handling))]
+use core::mem;
+#[cfg(not(no_global_oom_handling))]
+use core::mem::size_of;
+#[cfg(not(no_global_oom_handling))]
+use core::ptr;
+
+use crate::alloc::Allocator;
+#[cfg(not(no_global_oom_handling))]
+use crate::alloc::Global;
+#[cfg(not(no_global_oom_handling))]
+use crate::borrow::ToOwned;
+use crate::boxed::Box;
+use crate::vec::Vec;
+
+#[unstable(feature = "slice_range", issue = "76393")]
+pub use core::slice::range;
+#[unstable(feature = "array_chunks", issue = "74985")]
+pub use core::slice::ArrayChunks;
+#[unstable(feature = "array_chunks", issue = "74985")]
+pub use core::slice::ArrayChunksMut;
+#[unstable(feature = "array_windows", issue = "75027")]
+pub use core::slice::ArrayWindows;
+#[stable(feature = "inherent_ascii_escape", since = "1.60.0")]
+pub use core::slice::EscapeAscii;
+#[stable(feature = "slice_get_slice", since = "1.28.0")]
+pub use core::slice::SliceIndex;
+#[stable(feature = "from_ref", since = "1.28.0")]
+pub use core::slice::{from_mut, from_ref};
+#[stable(feature = "rust1", since = "1.0.0")]
+pub use core::slice::{from_raw_parts, from_raw_parts_mut};
+#[stable(feature = "rust1", since = "1.0.0")]
+pub use core::slice::{Chunks, Windows};
+#[stable(feature = "chunks_exact", since = "1.31.0")]
+pub use core::slice::{ChunksExact, ChunksExactMut};
+#[stable(feature = "rust1", since = "1.0.0")]
+pub use core::slice::{ChunksMut, Split, SplitMut};
+#[unstable(feature = "slice_group_by", issue = "80552")]
+pub use core::slice::{GroupBy, GroupByMut};
+#[stable(feature = "rust1", since = "1.0.0")]
+pub use core::slice::{Iter, IterMut};
+#[stable(feature = "rchunks", since = "1.31.0")]
+pub use core::slice::{RChunks, RChunksExact, RChunksExactMut, RChunksMut};
+#[stable(feature = "slice_rsplit", since = "1.27.0")]
+pub use core::slice::{RSplit, RSplitMut};
+#[stable(feature = "rust1", since = "1.0.0")]
+pub use core::slice::{RSplitN, RSplitNMut, SplitN, SplitNMut};
+#[stable(feature = "split_inclusive", since = "1.51.0")]
+pub use core::slice::{SplitInclusive, SplitInclusiveMut};
+
+////////////////////////////////////////////////////////////////////////////////
+// Basic slice extension methods
+////////////////////////////////////////////////////////////////////////////////
+
+// HACK(japaric) needed for the implementation of `vec!` macro during testing
+// N.B., see the `hack` module in this file for more details.
+#[cfg(test)]
+pub use hack::into_vec;
+
+// HACK(japaric) needed for the implementation of `Vec::clone` during testing
+// N.B., see the `hack` module in this file for more details.
+#[cfg(test)]
+pub use hack::to_vec;
+
+// HACK(japaric): With cfg(test) `impl [T]` is not available, these three
+// functions are actually methods that are in `impl [T]` but not in
+// `core::slice::SliceExt` - we need to supply these functions for the
+// `test_permutations` test
+pub(crate) mod hack {
+    use core::alloc::Allocator;
+
+    use crate::boxed::Box;
+    use crate::vec::Vec;
+
+    // We shouldn't add inline attribute to this since this is used in
+    // `vec!` macro mostly and causes perf regression. See #71204 for
+    // discussion and perf results.
+    pub fn into_vec<T, A: Allocator>(b: Box<[T], A>) -> Vec<T, A> {
+        unsafe {
+            let len = b.len();
+            let (b, alloc) = Box::into_raw_with_allocator(b);
+            Vec::from_raw_parts_in(b as *mut T, len, len, alloc)
+        }
+    }
+
+    #[cfg(not(no_global_oom_handling))]
+    #[inline]
+    pub fn to_vec<T: ConvertVec, A: Allocator>(s: &[T], alloc: A) -> Vec<T, A> {
+        T::to_vec(s, alloc)
+    }
+
+    #[cfg(not(no_global_oom_handling))]
+    pub trait ConvertVec {
+        fn to_vec<A: Allocator>(s: &[Self], alloc: A) -> Vec<Self, A>
+        where
+            Self: Sized;
+    }
+
+    #[cfg(not(no_global_oom_handling))]
+    impl<T: Clone> ConvertVec for T {
+        #[inline]
+        default fn to_vec<A: Allocator>(s: &[Self], alloc: A) -> Vec<Self, A> {
+            struct DropGuard<'a, T, A: Allocator> {
+                vec: &'a mut Vec<T, A>,
+                num_init: usize,
+            }
+            impl<'a, T, A: Allocator> Drop for DropGuard<'a, T, A> {
+                #[inline]
+                fn drop(&mut self) {
+                    // SAFETY:
+                    // items were marked initialized in the loop below
+                    unsafe {
+                        self.vec.set_len(self.num_init);
+                    }
+                }
+            }
+            let mut vec = Vec::with_capacity_in(s.len(), alloc);
+            let mut guard = DropGuard { vec: &mut vec, num_init: 0 };
+            let slots = guard.vec.spare_capacity_mut();
+            // .take(slots.len()) is necessary for LLVM to remove bounds checks
+            // and has better codegen than zip.
+            for (i, b) in s.iter().enumerate().take(slots.len()) {
+                guard.num_init = i;
+                slots[i].write(b.clone());
+            }
+            core::mem::forget(guard);
+            // SAFETY:
+            // the vec was allocated and initialized above to at least this length.
+            unsafe {
+                vec.set_len(s.len());
+            }
+            vec
+        }
+    }
+
+    #[cfg(not(no_global_oom_handling))]
+    impl<T: Copy> ConvertVec for T {
+        #[inline]
+        fn to_vec<A: Allocator>(s: &[Self], alloc: A) -> Vec<Self, A> {
+            let mut v = Vec::with_capacity_in(s.len(), alloc);
+            // SAFETY:
+            // allocated above with the capacity of `s`, and initialize to `s.len()` in
+            // ptr::copy_to_non_overlapping below.
+            unsafe {
+                s.as_ptr().copy_to_nonoverlapping(v.as_mut_ptr(), s.len());
+                v.set_len(s.len());
+            }
+            v
+        }
+    }
+}
+
+#[cfg(not(test))]
+impl<T> [T] {
+    /// Sorts the slice.
+    ///
+    /// This sort is stable (i.e., does not reorder equal elements) and *O*(*n* \* log(*n*)) worst-case.
+    ///
+    /// When applicable, unstable sorting is preferred because it is generally faster than stable
+    /// sorting and it doesn't allocate auxiliary memory.
+    /// See [`sort_unstable`](slice::sort_unstable).
+    ///
+    /// # Current implementation
+    ///
+    /// The current algorithm is an adaptive, iterative merge sort inspired by
+    /// [timsort](https://en.wikipedia.org/wiki/Timsort).
+    /// It is designed to be very fast in cases where the slice is nearly sorted, or consists of
+    /// two or more sorted sequences concatenated one after another.
+    ///
+    /// Also, it allocates temporary storage half the size of `self`, but for short slices a
+    /// non-allocating insertion sort is used instead.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = [-5, 4, 1, -3, 2];
+    ///
+    /// v.sort();
+    /// assert!(v == [-5, -3, 1, 2, 4]);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[rustc_allow_incoherent_impl]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    #[inline]
+    pub fn sort(&mut self)
+    where
+        T: Ord,
+    {
+        merge_sort(self, |a, b| a.lt(b));
+    }
+
+    /// Sorts the slice with a comparator function.
+    ///
+    /// This sort is stable (i.e., does not reorder equal elements) and *O*(*n* \* log(*n*)) worst-case.
+    ///
+    /// The comparator function must define a total ordering for the elements in the slice. If
+    /// the ordering is not total, the order of the elements is unspecified. An order is a
+    /// total order if it is (for all `a`, `b` and `c`):
+    ///
+    /// * total and antisymmetric: exactly one of `a < b`, `a == b` or `a > b` is true, and
+    /// * transitive, `a < b` and `b < c` implies `a < c`. The same must hold for both `==` and `>`.
+    ///
+    /// For example, while [`f64`] doesn't implement [`Ord`] because `NaN != NaN`, we can use
+    /// `partial_cmp` as our sort function when we know the slice doesn't contain a `NaN`.
+    ///
+    /// ```
+    /// let mut floats = [5f64, 4.0, 1.0, 3.0, 2.0];
+    /// floats.sort_by(|a, b| a.partial_cmp(b).unwrap());
+    /// assert_eq!(floats, [1.0, 2.0, 3.0, 4.0, 5.0]);
+    /// ```
+    ///
+    /// When applicable, unstable sorting is preferred because it is generally faster than stable
+    /// sorting and it doesn't allocate auxiliary memory.
+    /// See [`sort_unstable_by`](slice::sort_unstable_by).
+    ///
+    /// # Current implementation
+    ///
+    /// The current algorithm is an adaptive, iterative merge sort inspired by
+    /// [timsort](https://en.wikipedia.org/wiki/Timsort).
+    /// It is designed to be very fast in cases where the slice is nearly sorted, or consists of
+    /// two or more sorted sequences concatenated one after another.
+    ///
+    /// Also, it allocates temporary storage half the size of `self`, but for short slices a
+    /// non-allocating insertion sort is used instead.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = [5, 4, 1, 3, 2];
+    /// v.sort_by(|a, b| a.cmp(b));
+    /// assert!(v == [1, 2, 3, 4, 5]);
+    ///
+    /// // reverse sorting
+    /// v.sort_by(|a, b| b.cmp(a));
+    /// assert!(v == [5, 4, 3, 2, 1]);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[rustc_allow_incoherent_impl]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    #[inline]
+    pub fn sort_by<F>(&mut self, mut compare: F)
+    where
+        F: FnMut(&T, &T) -> Ordering,
+    {
+        merge_sort(self, |a, b| compare(a, b) == Less);
+    }
+
+    /// Sorts the slice with a key extraction function.
+    ///
+    /// This sort is stable (i.e., does not reorder equal elements) and *O*(*m* \* *n* \* log(*n*))
+    /// worst-case, where the key function is *O*(*m*).
+    ///
+    /// For expensive key functions (e.g. functions that are not simple property accesses or
+    /// basic operations), [`sort_by_cached_key`](slice::sort_by_cached_key) is likely to be
+    /// significantly faster, as it does not recompute element keys.
+    ///
+    /// When applicable, unstable sorting is preferred because it is generally faster than stable
+    /// sorting and it doesn't allocate auxiliary memory.
+    /// See [`sort_unstable_by_key`](slice::sort_unstable_by_key).
+    ///
+    /// # Current implementation
+    ///
+    /// The current algorithm is an adaptive, iterative merge sort inspired by
+    /// [timsort](https://en.wikipedia.org/wiki/Timsort).
+    /// It is designed to be very fast in cases where the slice is nearly sorted, or consists of
+    /// two or more sorted sequences concatenated one after another.
+    ///
+    /// Also, it allocates temporary storage half the size of `self`, but for short slices a
+    /// non-allocating insertion sort is used instead.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = [-5i32, 4, 1, -3, 2];
+    ///
+    /// v.sort_by_key(|k| k.abs());
+    /// assert!(v == [1, 2, -3, 4, -5]);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[rustc_allow_incoherent_impl]
+    #[stable(feature = "slice_sort_by_key", since = "1.7.0")]
+    #[inline]
+    pub fn sort_by_key<K, F>(&mut self, mut f: F)
+    where
+        F: FnMut(&T) -> K,
+        K: Ord,
+    {
+        merge_sort(self, |a, b| f(a).lt(&f(b)));
+    }
+
+    /// Sorts the slice with a key extraction function.
+    ///
+    /// During sorting, the key function is called at most once per element, by using
+    /// temporary storage to remember the results of key evaluation.
+    /// The order of calls to the key function is unspecified and may change in future versions
+    /// of the standard library.
+    ///
+    /// This sort is stable (i.e., does not reorder equal elements) and *O*(*m* \* *n* + *n* \* log(*n*))
+    /// worst-case, where the key function is *O*(*m*).
+    ///
+    /// For simple key functions (e.g., functions that are property accesses or
+    /// basic operations), [`sort_by_key`](slice::sort_by_key) is likely to be
+    /// faster.
+    ///
+    /// # Current implementation
+    ///
+    /// The current algorithm is based on [pattern-defeating quicksort][pdqsort] by Orson Peters,
+    /// which combines the fast average case of randomized quicksort with the fast worst case of
+    /// heapsort, while achieving linear time on slices with certain patterns. It uses some
+    /// randomization to avoid degenerate cases, but with a fixed seed to always provide
+    /// deterministic behavior.
+    ///
+    /// In the worst case, the algorithm allocates temporary storage in a `Vec<(K, usize)>` the
+    /// length of the slice.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = [-5i32, 4, 32, -3, 2];
+    ///
+    /// v.sort_by_cached_key(|k| k.to_string());
+    /// assert!(v == [-3, -5, 2, 32, 4]);
+    /// ```
+    ///
+    /// [pdqsort]: https://github.com/orlp/pdqsort
+    #[cfg(not(no_global_oom_handling))]
+    #[rustc_allow_incoherent_impl]
+    #[stable(feature = "slice_sort_by_cached_key", since = "1.34.0")]
+    #[inline]
+    pub fn sort_by_cached_key<K, F>(&mut self, f: F)
+    where
+        F: FnMut(&T) -> K,
+        K: Ord,
+    {
+        // Helper macro for indexing our vector by the smallest possible type, to reduce allocation.
+        macro_rules! sort_by_key {
+            ($t:ty, $slice:ident, $f:ident) => {{
+                let mut indices: Vec<_> =
+                    $slice.iter().map($f).enumerate().map(|(i, k)| (k, i as $t)).collect();
+                // The elements of `indices` are unique, as they are indexed, so any sort will be
+                // stable with respect to the original slice. We use `sort_unstable` here because
+                // it requires less memory allocation.
+                indices.sort_unstable();
+                for i in 0..$slice.len() {
+                    let mut index = indices[i].1;
+                    while (index as usize) < i {
+                        index = indices[index as usize].1;
+                    }
+                    indices[i].1 = index;
+                    $slice.swap(i, index as usize);
+                }
+            }};
+        }
+
+        let sz_u8 = mem::size_of::<(K, u8)>();
+        let sz_u16 = mem::size_of::<(K, u16)>();
+        let sz_u32 = mem::size_of::<(K, u32)>();
+        let sz_usize = mem::size_of::<(K, usize)>();
+
+        let len = self.len();
+        if len < 2 {
+            return;
+        }
+        if sz_u8 < sz_u16 && len <= (u8::MAX as usize) {
+            return sort_by_key!(u8, self, f);
+        }
+        if sz_u16 < sz_u32 && len <= (u16::MAX as usize) {
+            return sort_by_key!(u16, self, f);
+        }
+        if sz_u32 < sz_usize && len <= (u32::MAX as usize) {
+            return sort_by_key!(u32, self, f);
+        }
+        sort_by_key!(usize, self, f)
+    }
+
+    /// Copies `self` into a new `Vec`.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let s = [10, 40, 30];
+    /// let x = s.to_vec();
+    /// // Here, `s` and `x` can be modified independently.
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[rustc_allow_incoherent_impl]
+    #[rustc_conversion_suggestion]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    #[inline]
+    pub fn to_vec(&self) -> Vec<T>
+    where
+        T: Clone,
+    {
+        self.to_vec_in(Global)
+    }
+
+    /// Copies `self` into a new `Vec` with an allocator.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api)]
+    ///
+    /// use std::alloc::System;
+    ///
+    /// let s = [10, 40, 30];
+    /// let x = s.to_vec_in(System);
+    /// // Here, `s` and `x` can be modified independently.
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[rustc_allow_incoherent_impl]
+    #[inline]
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    pub fn to_vec_in<A: Allocator>(&self, alloc: A) -> Vec<T, A>
+    where
+        T: Clone,
+    {
+        // N.B., see the `hack` module in this file for more details.
+        hack::to_vec(self, alloc)
+    }
+
+    /// Converts `self` into a vector without clones or allocation.
+    ///
+    /// The resulting vector can be converted back into a box via
+    /// `Vec<T>`'s `into_boxed_slice` method.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let s: Box<[i32]> = Box::new([10, 40, 30]);
+    /// let x = s.into_vec();
+    /// // `s` cannot be used anymore because it has been converted into `x`.
+    ///
+    /// assert_eq!(x, vec![10, 40, 30]);
+    /// ```
+    #[rustc_allow_incoherent_impl]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    #[inline]
+    pub fn into_vec<A: Allocator>(self: Box<Self, A>) -> Vec<T, A> {
+        // N.B., see the `hack` module in this file for more details.
+        hack::into_vec(self)
+    }
+
+    /// Creates a vector by repeating a slice `n` times.
+    ///
+    /// # Panics
+    ///
+    /// This function will panic if the capacity would overflow.
+    ///
+    /// # Examples
+    ///
+    /// Basic usage:
+    ///
+    /// ```
+    /// assert_eq!([1, 2].repeat(3), vec![1, 2, 1, 2, 1, 2]);
+    /// ```
+    ///
+    /// A panic upon overflow:
+    ///
+    /// ```should_panic
+    /// // this will panic at runtime
+    /// b"0123456789abcdef".repeat(usize::MAX);
+    /// ```
+    #[rustc_allow_incoherent_impl]
+    #[cfg(not(no_global_oom_handling))]
+    #[stable(feature = "repeat_generic_slice", since = "1.40.0")]
+    pub fn repeat(&self, n: usize) -> Vec<T>
+    where
+        T: Copy,
+    {
+        if n == 0 {
+            return Vec::new();
+        }
+
+        // If `n` is larger than zero, it can be split as
+        // `n = 2^expn + rem (2^expn > rem, expn >= 0, rem >= 0)`.
+        // `2^expn` is the number represented by the leftmost '1' bit of `n`,
+        // and `rem` is the remaining part of `n`.
+
+        // Using `Vec` to access `set_len()`.
+        let capacity = self.len().checked_mul(n).expect("capacity overflow");
+        let mut buf = Vec::with_capacity(capacity);
+
+        // `2^expn` repetition is done by doubling `buf` `expn`-times.
+        buf.extend(self);
+        {
+            let mut m = n >> 1;
+            // If `m > 0`, there are remaining bits up to the leftmost '1'.
+            while m > 0 {
+                // `buf.extend(buf)`:
+                unsafe {
+                    ptr::copy_nonoverlapping(
+                        buf.as_ptr(),
+                        (buf.as_mut_ptr() as *mut T).add(buf.len()),
+                        buf.len(),
+                    );
+                    // `buf` has capacity of `self.len() * n`.
+                    let buf_len = buf.len();
+                    buf.set_len(buf_len * 2);
+                }
+
+                m >>= 1;
+            }
+        }
+
+        // `rem` (`= n - 2^expn`) repetition is done by copying
+        // first `rem` repetitions from `buf` itself.
+        let rem_len = capacity - buf.len(); // `self.len() * rem`
+        if rem_len > 0 {
+            // `buf.extend(buf[0 .. rem_len])`:
+            unsafe {
+                // This is non-overlapping since `2^expn > rem`.
+                ptr::copy_nonoverlapping(
+                    buf.as_ptr(),
+                    (buf.as_mut_ptr() as *mut T).add(buf.len()),
+                    rem_len,
+                );
+                // `buf.len() + rem_len` equals to `buf.capacity()` (`= self.len() * n`).
+                buf.set_len(capacity);
+            }
+        }
+        buf
+    }
+
+    /// Flattens a slice of `T` into a single value `Self::Output`.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// assert_eq!(["hello", "world"].concat(), "helloworld");
+    /// assert_eq!([[1, 2], [3, 4]].concat(), [1, 2, 3, 4]);
+    /// ```
+    #[rustc_allow_incoherent_impl]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn concat<Item: ?Sized>(&self) -> <Self as Concat<Item>>::Output
+    where
+        Self: Concat<Item>,
+    {
+        Concat::concat(self)
+    }
+
+    /// Flattens a slice of `T` into a single value `Self::Output`, placing a
+    /// given separator between each.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// assert_eq!(["hello", "world"].join(" "), "hello world");
+    /// assert_eq!([[1, 2], [3, 4]].join(&0), [1, 2, 0, 3, 4]);
+    /// assert_eq!([[1, 2], [3, 4]].join(&[0, 0][..]), [1, 2, 0, 0, 3, 4]);
+    /// ```
+    #[rustc_allow_incoherent_impl]
+    #[stable(feature = "rename_connect_to_join", since = "1.3.0")]
+    pub fn join<Separator>(&self, sep: Separator) -> <Self as Join<Separator>>::Output
+    where
+        Self: Join<Separator>,
+    {
+        Join::join(self, sep)
+    }
+
+    /// Flattens a slice of `T` into a single value `Self::Output`, placing a
+    /// given separator between each.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// # #![allow(deprecated)]
+    /// assert_eq!(["hello", "world"].connect(" "), "hello world");
+    /// assert_eq!([[1, 2], [3, 4]].connect(&0), [1, 2, 0, 3, 4]);
+    /// ```
+    #[rustc_allow_incoherent_impl]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    #[deprecated(since = "1.3.0", note = "renamed to join")]
+    pub fn connect<Separator>(&self, sep: Separator) -> <Self as Join<Separator>>::Output
+    where
+        Self: Join<Separator>,
+    {
+        Join::join(self, sep)
+    }
+}
+
+#[cfg(not(test))]
+impl [u8] {
+    /// Returns a vector containing a copy of this slice where each byte
+    /// is mapped to its ASCII upper case equivalent.
+    ///
+    /// ASCII letters 'a' to 'z' are mapped to 'A' to 'Z',
+    /// but non-ASCII letters are unchanged.
+    ///
+    /// To uppercase the value in-place, use [`make_ascii_uppercase`].
+    ///
+    /// [`make_ascii_uppercase`]: slice::make_ascii_uppercase
+    #[cfg(not(no_global_oom_handling))]
+    #[rustc_allow_incoherent_impl]
+    #[must_use = "this returns the uppercase bytes as a new Vec, \
+                  without modifying the original"]
+    #[stable(feature = "ascii_methods_on_intrinsics", since = "1.23.0")]
+    #[inline]
+    pub fn to_ascii_uppercase(&self) -> Vec<u8> {
+        let mut me = self.to_vec();
+        me.make_ascii_uppercase();
+        me
+    }
+
+    /// Returns a vector containing a copy of this slice where each byte
+    /// is mapped to its ASCII lower case equivalent.
+    ///
+    /// ASCII letters 'A' to 'Z' are mapped to 'a' to 'z',
+    /// but non-ASCII letters are unchanged.
+    ///
+    /// To lowercase the value in-place, use [`make_ascii_lowercase`].
+    ///
+    /// [`make_ascii_lowercase`]: slice::make_ascii_lowercase
+    #[cfg(not(no_global_oom_handling))]
+    #[rustc_allow_incoherent_impl]
+    #[must_use = "this returns the lowercase bytes as a new Vec, \
+                  without modifying the original"]
+    #[stable(feature = "ascii_methods_on_intrinsics", since = "1.23.0")]
+    #[inline]
+    pub fn to_ascii_lowercase(&self) -> Vec<u8> {
+        let mut me = self.to_vec();
+        me.make_ascii_lowercase();
+        me
+    }
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// Extension traits for slices over specific kinds of data
+////////////////////////////////////////////////////////////////////////////////
+
+/// Helper trait for [`[T]::concat`](slice::concat).
+///
+/// Note: the `Item` type parameter is not used in this trait,
+/// but it allows impls to be more generic.
+/// Without it, we get this error:
+///
+/// ```error
+/// error[E0207]: the type parameter `T` is not constrained by the impl trait, self type, or predica
+///    --> src/liballoc/slice.rs:608:6
+///     |
+/// 608 | impl<T: Clone, V: Borrow<[T]>> Concat for [V] {
+///     |      ^ unconstrained type parameter
+/// ```
+///
+/// This is because there could exist `V` types with multiple `Borrow<[_]>` impls,
+/// such that multiple `T` types would apply:
+///
+/// ```
+/// # #[allow(dead_code)]
+/// pub struct Foo(Vec<u32>, Vec<String>);
+///
+/// impl std::borrow::Borrow<[u32]> for Foo {
+///     fn borrow(&self) -> &[u32] { &self.0 }
+/// }
+///
+/// impl std::borrow::Borrow<[String]> for Foo {
+///     fn borrow(&self) -> &[String] { &self.1 }
+/// }
+/// ```
+#[unstable(feature = "slice_concat_trait", issue = "27747")]
+pub trait Concat<Item: ?Sized> {
+    #[unstable(feature = "slice_concat_trait", issue = "27747")]
+    /// The resulting type after concatenation
+    type Output;
+
+    /// Implementation of [`[T]::concat`](slice::concat)
+    #[unstable(feature = "slice_concat_trait", issue = "27747")]
+    fn concat(slice: &Self) -> Self::Output;
+}
+
+/// Helper trait for [`[T]::join`](slice::join)
+#[unstable(feature = "slice_concat_trait", issue = "27747")]
+pub trait Join<Separator> {
+    #[unstable(feature = "slice_concat_trait", issue = "27747")]
+    /// The resulting type after concatenation
+    type Output;
+
+    /// Implementation of [`[T]::join`](slice::join)
+    #[unstable(feature = "slice_concat_trait", issue = "27747")]
+    fn join(slice: &Self, sep: Separator) -> Self::Output;
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[unstable(feature = "slice_concat_ext", issue = "27747")]
+impl<T: Clone, V: Borrow<[T]>> Concat<T> for [V] {
+    type Output = Vec<T>;
+
+    fn concat(slice: &Self) -> Vec<T> {
+        let size = slice.iter().map(|slice| slice.borrow().len()).sum();
+        let mut result = Vec::with_capacity(size);
+        for v in slice {
+            result.extend_from_slice(v.borrow())
+        }
+        result
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[unstable(feature = "slice_concat_ext", issue = "27747")]
+impl<T: Clone, V: Borrow<[T]>> Join<&T> for [V] {
+    type Output = Vec<T>;
+
+    fn join(slice: &Self, sep: &T) -> Vec<T> {
+        let mut iter = slice.iter();
+        let first = match iter.next() {
+            Some(first) => first,
+            None => return vec![],
+        };
+        let size = slice.iter().map(|v| v.borrow().len()).sum::<usize>() + slice.len() - 1;
+        let mut result = Vec::with_capacity(size);
+        result.extend_from_slice(first.borrow());
+
+        for v in iter {
+            result.push(sep.clone());
+            result.extend_from_slice(v.borrow())
+        }
+        result
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[unstable(feature = "slice_concat_ext", issue = "27747")]
+impl<T: Clone, V: Borrow<[T]>> Join<&[T]> for [V] {
+    type Output = Vec<T>;
+
+    fn join(slice: &Self, sep: &[T]) -> Vec<T> {
+        let mut iter = slice.iter();
+        let first = match iter.next() {
+            Some(first) => first,
+            None => return vec![],
+        };
+        let size =
+            slice.iter().map(|v| v.borrow().len()).sum::<usize>() + sep.len() * (slice.len() - 1);
+        let mut result = Vec::with_capacity(size);
+        result.extend_from_slice(first.borrow());
+
+        for v in iter {
+            result.extend_from_slice(sep);
+            result.extend_from_slice(v.borrow())
+        }
+        result
+    }
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// Standard trait implementations for slices
+////////////////////////////////////////////////////////////////////////////////
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T> Borrow<[T]> for Vec<T> {
+    fn borrow(&self) -> &[T] {
+        &self[..]
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T> BorrowMut<[T]> for Vec<T> {
+    fn borrow_mut(&mut self) -> &mut [T] {
+        &mut self[..]
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: Clone> ToOwned for [T] {
+    type Owned = Vec<T>;
+    #[cfg(not(test))]
+    fn to_owned(&self) -> Vec<T> {
+        self.to_vec()
+    }
+
+    #[cfg(test)]
+    fn to_owned(&self) -> Vec<T> {
+        hack::to_vec(self, Global)
+    }
+
+    fn clone_into(&self, target: &mut Vec<T>) {
+        // drop anything in target that will not be overwritten
+        target.truncate(self.len());
+
+        // target.len <= self.len due to the truncate above, so the
+        // slices here are always in-bounds.
+        let (init, tail) = self.split_at(target.len());
+
+        // reuse the contained values' allocations/resources.
+        target.clone_from_slice(init);
+        target.extend_from_slice(tail);
+    }
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// Sorting
+////////////////////////////////////////////////////////////////////////////////
+
+/// Inserts `v[0]` into pre-sorted sequence `v[1..]` so that whole `v[..]` becomes sorted.
+///
+/// This is the integral subroutine of insertion sort.
+#[cfg(not(no_global_oom_handling))]
+fn insert_head<T, F>(v: &mut [T], is_less: &mut F)
+where
+    F: FnMut(&T, &T) -> bool,
+{
+    if v.len() >= 2 && is_less(&v[1], &v[0]) {
+        unsafe {
+            // There are three ways to implement insertion here:
+            //
+            // 1. Swap adjacent elements until the first one gets to its final destination.
+            //    However, this way we copy data around more than is necessary. If elements are big
+            //    structures (costly to copy), this method will be slow.
+            //
+            // 2. Iterate until the right place for the first element is found. Then shift the
+            //    elements succeeding it to make room for it and finally place it into the
+            //    remaining hole. This is a good method.
+            //
+            // 3. Copy the first element into a temporary variable. Iterate until the right place
+            //    for it is found. As we go along, copy every traversed element into the slot
+            //    preceding it. Finally, copy data from the temporary variable into the remaining
+            //    hole. This method is very good. Benchmarks demonstrated slightly better
+            //    performance than with the 2nd method.
+            //
+            // All methods were benchmarked, and the 3rd showed best results. So we chose that one.
+            let tmp = mem::ManuallyDrop::new(ptr::read(&v[0]));
+
+            // Intermediate state of the insertion process is always tracked by `hole`, which
+            // serves two purposes:
+            // 1. Protects integrity of `v` from panics in `is_less`.
+            // 2. Fills the remaining hole in `v` in the end.
+            //
+            // Panic safety:
+            //
+            // If `is_less` panics at any point during the process, `hole` will get dropped and
+            // fill the hole in `v` with `tmp`, thus ensuring that `v` still holds every object it
+            // initially held exactly once.
+            let mut hole = InsertionHole { src: &*tmp, dest: &mut v[1] };
+            ptr::copy_nonoverlapping(&v[1], &mut v[0], 1);
+
+            for i in 2..v.len() {
+                if !is_less(&v[i], &*tmp) {
+                    break;
+                }
+                ptr::copy_nonoverlapping(&v[i], &mut v[i - 1], 1);
+                hole.dest = &mut v[i];
+            }
+            // `hole` gets dropped and thus copies `tmp` into the remaining hole in `v`.
+        }
+    }
+
+    // When dropped, copies from `src` into `dest`.
+    struct InsertionHole<T> {
+        src: *const T,
+        dest: *mut T,
+    }
+
+    impl<T> Drop for InsertionHole<T> {
+        fn drop(&mut self) {
+            unsafe {
+                ptr::copy_nonoverlapping(self.src, self.dest, 1);
+            }
+        }
+    }
+}
+
+/// Merges non-decreasing runs `v[..mid]` and `v[mid..]` using `buf` as temporary storage, and
+/// stores the result into `v[..]`.
+///
+/// # Safety
+///
+/// The two slices must be non-empty and `mid` must be in bounds. Buffer `buf` must be long enough
+/// to hold a copy of the shorter slice. Also, `T` must not be a zero-sized type.
+#[cfg(not(no_global_oom_handling))]
+unsafe fn merge<T, F>(v: &mut [T], mid: usize, buf: *mut T, is_less: &mut F)
+where
+    F: FnMut(&T, &T) -> bool,
+{
+    let len = v.len();
+    let v = v.as_mut_ptr();
+    let (v_mid, v_end) = unsafe { (v.add(mid), v.add(len)) };
+
+    // The merge process first copies the shorter run into `buf`. Then it traces the newly copied
+    // run and the longer run forwards (or backwards), comparing their next unconsumed elements and
+    // copying the lesser (or greater) one into `v`.
+    //
+    // As soon as the shorter run is fully consumed, the process is done. If the longer run gets
+    // consumed first, then we must copy whatever is left of the shorter run into the remaining
+    // hole in `v`.
+    //
+    // Intermediate state of the process is always tracked by `hole`, which serves two purposes:
+    // 1. Protects integrity of `v` from panics in `is_less`.
+    // 2. Fills the remaining hole in `v` if the longer run gets consumed first.
+    //
+    // Panic safety:
+    //
+    // If `is_less` panics at any point during the process, `hole` will get dropped and fill the
+    // hole in `v` with the unconsumed range in `buf`, thus ensuring that `v` still holds every
+    // object it initially held exactly once.
+    let mut hole;
+
+    if mid <= len - mid {
+        // The left run is shorter.
+        unsafe {
+            ptr::copy_nonoverlapping(v, buf, mid);
+            hole = MergeHole { start: buf, end: buf.add(mid), dest: v };
+        }
+
+        // Initially, these pointers point to the beginnings of their arrays.
+        let left = &mut hole.start;
+        let mut right = v_mid;
+        let out = &mut hole.dest;
+
+        while *left < hole.end && right < v_end {
+            // Consume the lesser side.
+            // If equal, prefer the left run to maintain stability.
+            unsafe {
+                let to_copy = if is_less(&*right, &**left) {
+                    get_and_increment(&mut right)
+                } else {
+                    get_and_increment(left)
+                };
+                ptr::copy_nonoverlapping(to_copy, get_and_increment(out), 1);
+            }
+        }
+    } else {
+        // The right run is shorter.
+        unsafe {
+            ptr::copy_nonoverlapping(v_mid, buf, len - mid);
+            hole = MergeHole { start: buf, end: buf.add(len - mid), dest: v_mid };
+        }
+
+        // Initially, these pointers point past the ends of their arrays.
+        let left = &mut hole.dest;
+        let right = &mut hole.end;
+        let mut out = v_end;
+
+        while v < *left && buf < *right {
+            // Consume the greater side.
+            // If equal, prefer the right run to maintain stability.
+            unsafe {
+                let to_copy = if is_less(&*right.offset(-1), &*left.offset(-1)) {
+                    decrement_and_get(left)
+                } else {
+                    decrement_and_get(right)
+                };
+                ptr::copy_nonoverlapping(to_copy, decrement_and_get(&mut out), 1);
+            }
+        }
+    }
+    // Finally, `hole` gets dropped. If the shorter run was not fully consumed, whatever remains of
+    // it will now be copied into the hole in `v`.
+
+    unsafe fn get_and_increment<T>(ptr: &mut *mut T) -> *mut T {
+        let old = *ptr;
+        *ptr = unsafe { ptr.offset(1) };
+        old
+    }
+
+    unsafe fn decrement_and_get<T>(ptr: &mut *mut T) -> *mut T {
+        *ptr = unsafe { ptr.offset(-1) };
+        *ptr
+    }
+
+    // When dropped, copies the range `start..end` into `dest..`.
+    struct MergeHole<T> {
+        start: *mut T,
+        end: *mut T,
+        dest: *mut T,
+    }
+
+    impl<T> Drop for MergeHole<T> {
+        fn drop(&mut self) {
+            // `T` is not a zero-sized type, and these are pointers into a slice's elements.
+            unsafe {
+                let len = self.end.sub_ptr(self.start);
+                ptr::copy_nonoverlapping(self.start, self.dest, len);
+            }
+        }
+    }
+}
+
+/// This merge sort borrows some (but not all) ideas from TimSort, which is described in detail
+/// [here](https://github.com/python/cpython/blob/main/Objects/listsort.txt).
+///
+/// The algorithm identifies strictly descending and non-descending subsequences, which are called
+/// natural runs. There is a stack of pending runs yet to be merged. Each newly found run is pushed
+/// onto the stack, and then some pairs of adjacent runs are merged until these two invariants are
+/// satisfied:
+///
+/// 1. for every `i` in `1..runs.len()`: `runs[i - 1].len > runs[i].len`
+/// 2. for every `i` in `2..runs.len()`: `runs[i - 2].len > runs[i - 1].len + runs[i].len`
+///
+/// The invariants ensure that the total running time is *O*(*n* \* log(*n*)) worst-case.
+#[cfg(not(no_global_oom_handling))]
+fn merge_sort<T, F>(v: &mut [T], mut is_less: F)
+where
+    F: FnMut(&T, &T) -> bool,
+{
+    // Slices of up to this length get sorted using insertion sort.
+    const MAX_INSERTION: usize = 20;
+    // Very short runs are extended using insertion sort to span at least this many elements.
+    const MIN_RUN: usize = 10;
+
+    // Sorting has no meaningful behavior on zero-sized types.
+    if size_of::<T>() == 0 {
+        return;
+    }
+
+    let len = v.len();
+
+    // Short arrays get sorted in-place via insertion sort to avoid allocations.
+    if len <= MAX_INSERTION {
+        if len >= 2 {
+            for i in (0..len - 1).rev() {
+                insert_head(&mut v[i..], &mut is_less);
+            }
+        }
+        return;
+    }
+
+    // Allocate a buffer to use as scratch memory. We keep the length 0 so we can keep in it
+    // shallow copies of the contents of `v` without risking the dtors running on copies if
+    // `is_less` panics. When merging two sorted runs, this buffer holds a copy of the shorter run,
+    // which will always have length at most `len / 2`.
+    let mut buf = Vec::with_capacity(len / 2);
+
+    // In order to identify natural runs in `v`, we traverse it backwards. That might seem like a
+    // strange decision, but consider the fact that merges more often go in the opposite direction
+    // (forwards). According to benchmarks, merging forwards is slightly faster than merging
+    // backwards. To conclude, identifying runs by traversing backwards improves performance.
+    let mut runs = vec![];
+    let mut end = len;
+    while end > 0 {
+        // Find the next natural run, and reverse it if it's strictly descending.
+        let mut start = end - 1;
+        if start > 0 {
+            start -= 1;
+            unsafe {
+                if is_less(v.get_unchecked(start + 1), v.get_unchecked(start)) {
+                    while start > 0 && is_less(v.get_unchecked(start), v.get_unchecked(start - 1)) {
+                        start -= 1;
+                    }
+                    v[start..end].reverse();
+                } else {
+                    while start > 0 && !is_less(v.get_unchecked(start), v.get_unchecked(start - 1))
+                    {
+                        start -= 1;
+                    }
+                }
+            }
+        }
+
+        // Insert some more elements into the run if it's too short. Insertion sort is faster than
+        // merge sort on short sequences, so this significantly improves performance.
+        while start > 0 && end - start < MIN_RUN {
+            start -= 1;
+            insert_head(&mut v[start..end], &mut is_less);
+        }
+
+        // Push this run onto the stack.
+        runs.push(Run { start, len: end - start });
+        end = start;
+
+        // Merge some pairs of adjacent runs to satisfy the invariants.
+        while let Some(r) = collapse(&runs) {
+            let left = runs[r + 1];
+            let right = runs[r];
+            unsafe {
+                merge(
+                    &mut v[left.start..right.start + right.len],
+                    left.len,
+                    buf.as_mut_ptr(),
+                    &mut is_less,
+                );
+            }
+            runs[r] = Run { start: left.start, len: left.len + right.len };
+            runs.remove(r + 1);
+        }
+    }
+
+    // Finally, exactly one run must remain in the stack.
+    debug_assert!(runs.len() == 1 && runs[0].start == 0 && runs[0].len == len);
+
+    // Examines the stack of runs and identifies the next pair of runs to merge. More specifically,
+    // if `Some(r)` is returned, that means `runs[r]` and `runs[r + 1]` must be merged next. If the
+    // algorithm should continue building a new run instead, `None` is returned.
+    //
+    // TimSort is infamous for its buggy implementations, as described here:
+    // http://envisage-project.eu/timsort-specification-and-verification/
+    //
+    // The gist of the story is: we must enforce the invariants on the top four runs on the stack.
+    // Enforcing them on just top three is not sufficient to ensure that the invariants will still
+    // hold for *all* runs in the stack.
+    //
+    // This function correctly checks invariants for the top four runs. Additionally, if the top
+    // run starts at index 0, it will always demand a merge operation until the stack is fully
+    // collapsed, in order to complete the sort.
+    #[inline]
+    fn collapse(runs: &[Run]) -> Option<usize> {
+        let n = runs.len();
+        if n >= 2
+            && (runs[n - 1].start == 0
+                || runs[n - 2].len <= runs[n - 1].len
+                || (n >= 3 && runs[n - 3].len <= runs[n - 2].len + runs[n - 1].len)
+                || (n >= 4 && runs[n - 4].len <= runs[n - 3].len + runs[n - 2].len))
+        {
+            if n >= 3 && runs[n - 3].len < runs[n - 1].len { Some(n - 3) } else { Some(n - 2) }
+        } else {
+            None
+        }
+    }
+
+    #[derive(Clone, Copy)]
+    struct Run {
+        start: usize,
+        len: usize,
+    }
+}
diff --git a/rust/alloc/vec/drain.rs b/rust/alloc/vec/drain.rs
new file mode 100644
index 000000000000..b6a5f98e4fcd
--- /dev/null
+++ b/rust/alloc/vec/drain.rs
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+use crate::alloc::{Allocator, Global};
+use core::fmt;
+use core::iter::{FusedIterator, TrustedLen};
+use core::mem;
+use core::ptr::{self, NonNull};
+use core::slice::{self};
+
+use super::Vec;
+
+/// A draining iterator for `Vec<T>`.
+///
+/// This `struct` is created by [`Vec::drain`].
+/// See its documentation for more.
+///
+/// # Example
+///
+/// ```
+/// let mut v = vec![0, 1, 2];
+/// let iter: std::vec::Drain<_> = v.drain(..);
+/// ```
+#[stable(feature = "drain", since = "1.6.0")]
+pub struct Drain<
+    'a,
+    T: 'a,
+    #[unstable(feature = "allocator_api", issue = "32838")] A: Allocator + 'a = Global,
+> {
+    /// Index of tail to preserve
+    pub(super) tail_start: usize,
+    /// Length of tail
+    pub(super) tail_len: usize,
+    /// Current remaining range to remove
+    pub(super) iter: slice::Iter<'a, T>,
+    pub(super) vec: NonNull<Vec<T, A>>,
+}
+
+#[stable(feature = "collection_debug", since = "1.17.0")]
+impl<T: fmt::Debug, A: Allocator> fmt::Debug for Drain<'_, T, A> {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        f.debug_tuple("Drain").field(&self.iter.as_slice()).finish()
+    }
+}
+
+impl<'a, T, A: Allocator> Drain<'a, T, A> {
+    /// Returns the remaining items of this iterator as a slice.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec!['a', 'b', 'c'];
+    /// let mut drain = vec.drain(..);
+    /// assert_eq!(drain.as_slice(), &['a', 'b', 'c']);
+    /// let _ = drain.next().unwrap();
+    /// assert_eq!(drain.as_slice(), &['b', 'c']);
+    /// ```
+    #[must_use]
+    #[stable(feature = "vec_drain_as_slice", since = "1.46.0")]
+    pub fn as_slice(&self) -> &[T] {
+        self.iter.as_slice()
+    }
+
+    /// Returns a reference to the underlying allocator.
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    #[must_use]
+    #[inline]
+    pub fn allocator(&self) -> &A {
+        unsafe { self.vec.as_ref().allocator() }
+    }
+}
+
+#[stable(feature = "vec_drain_as_slice", since = "1.46.0")]
+impl<'a, T, A: Allocator> AsRef<[T]> for Drain<'a, T, A> {
+    fn as_ref(&self) -> &[T] {
+        self.as_slice()
+    }
+}
+
+#[stable(feature = "drain", since = "1.6.0")]
+unsafe impl<T: Sync, A: Sync + Allocator> Sync for Drain<'_, T, A> {}
+#[stable(feature = "drain", since = "1.6.0")]
+unsafe impl<T: Send, A: Send + Allocator> Send for Drain<'_, T, A> {}
+
+#[stable(feature = "drain", since = "1.6.0")]
+impl<T, A: Allocator> Iterator for Drain<'_, T, A> {
+    type Item = T;
+
+    #[inline]
+    fn next(&mut self) -> Option<T> {
+        self.iter.next().map(|elt| unsafe { ptr::read(elt as *const _) })
+    }
+
+    fn size_hint(&self) -> (usize, Option<usize>) {
+        self.iter.size_hint()
+    }
+}
+
+#[stable(feature = "drain", since = "1.6.0")]
+impl<T, A: Allocator> DoubleEndedIterator for Drain<'_, T, A> {
+    #[inline]
+    fn next_back(&mut self) -> Option<T> {
+        self.iter.next_back().map(|elt| unsafe { ptr::read(elt as *const _) })
+    }
+}
+
+#[stable(feature = "drain", since = "1.6.0")]
+impl<T, A: Allocator> Drop for Drain<'_, T, A> {
+    fn drop(&mut self) {
+        /// Moves back the un-`Drain`ed elements to restore the original `Vec`.
+        struct DropGuard<'r, 'a, T, A: Allocator>(&'r mut Drain<'a, T, A>);
+
+        impl<'r, 'a, T, A: Allocator> Drop for DropGuard<'r, 'a, T, A> {
+            fn drop(&mut self) {
+                if self.0.tail_len > 0 {
+                    unsafe {
+                        let source_vec = self.0.vec.as_mut();
+                        // memmove back untouched tail, update to new length
+                        let start = source_vec.len();
+                        let tail = self.0.tail_start;
+                        if tail != start {
+                            let src = source_vec.as_ptr().add(tail);
+                            let dst = source_vec.as_mut_ptr().add(start);
+                            ptr::copy(src, dst, self.0.tail_len);
+                        }
+                        source_vec.set_len(start + self.0.tail_len);
+                    }
+                }
+            }
+        }
+
+        let iter = mem::replace(&mut self.iter, (&mut []).iter());
+        let drop_len = iter.len();
+
+        let mut vec = self.vec;
+
+        if mem::size_of::<T>() == 0 {
+            // ZSTs have no identity, so we don't need to move them around, we only need to drop the correct amount.
+            // this can be achieved by manipulating the Vec length instead of moving values out from `iter`.
+            unsafe {
+                let vec = vec.as_mut();
+                let old_len = vec.len();
+                vec.set_len(old_len + drop_len + self.tail_len);
+                vec.truncate(old_len + self.tail_len);
+            }
+
+            return;
+        }
+
+        // ensure elements are moved back into their appropriate places, even when drop_in_place panics
+        let _guard = DropGuard(self);
+
+        if drop_len == 0 {
+            return;
+        }
+
+        // as_slice() must only be called when iter.len() is > 0 because
+        // vec::Splice modifies vec::Drain fields and may grow the vec which would invalidate
+        // the iterator's internal pointers. Creating a reference to deallocated memory
+        // is invalid even when it is zero-length
+        let drop_ptr = iter.as_slice().as_ptr();
+
+        unsafe {
+            // drop_ptr comes from a slice::Iter which only gives us a &[T] but for drop_in_place
+            // a pointer with mutable provenance is necessary. Therefore we must reconstruct
+            // it from the original vec but also avoid creating a &mut to the front since that could
+            // invalidate raw pointers to it which some unsafe code might rely on.
+            let vec_ptr = vec.as_mut().as_mut_ptr();
+            let drop_offset = drop_ptr.sub_ptr(vec_ptr);
+            let to_drop = ptr::slice_from_raw_parts_mut(vec_ptr.add(drop_offset), drop_len);
+            ptr::drop_in_place(to_drop);
+        }
+    }
+}
+
+#[stable(feature = "drain", since = "1.6.0")]
+impl<T, A: Allocator> ExactSizeIterator for Drain<'_, T, A> {
+    fn is_empty(&self) -> bool {
+        self.iter.is_empty()
+    }
+}
+
+#[unstable(feature = "trusted_len", issue = "37572")]
+unsafe impl<T, A: Allocator> TrustedLen for Drain<'_, T, A> {}
+
+#[stable(feature = "fused", since = "1.26.0")]
+impl<T, A: Allocator> FusedIterator for Drain<'_, T, A> {}
diff --git a/rust/alloc/vec/drain_filter.rs b/rust/alloc/vec/drain_filter.rs
new file mode 100644
index 000000000000..b04fce041622
--- /dev/null
+++ b/rust/alloc/vec/drain_filter.rs
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+use crate::alloc::{Allocator, Global};
+use core::ptr::{self};
+use core::slice::{self};
+
+use super::Vec;
+
+/// An iterator which uses a closure to determine if an element should be removed.
+///
+/// This struct is created by [`Vec::drain_filter`].
+/// See its documentation for more.
+///
+/// # Example
+///
+/// ```
+/// #![feature(drain_filter)]
+///
+/// let mut v = vec![0, 1, 2];
+/// let iter: std::vec::DrainFilter<_, _> = v.drain_filter(|x| *x % 2 == 0);
+/// ```
+#[unstable(feature = "drain_filter", reason = "recently added", issue = "43244")]
+#[derive(Debug)]
+pub struct DrainFilter<
+    'a,
+    T,
+    F,
+    #[unstable(feature = "allocator_api", issue = "32838")] A: Allocator = Global,
+> where
+    F: FnMut(&mut T) -> bool,
+{
+    pub(super) vec: &'a mut Vec<T, A>,
+    /// The index of the item that will be inspected by the next call to `next`.
+    pub(super) idx: usize,
+    /// The number of items that have been drained (removed) thus far.
+    pub(super) del: usize,
+    /// The original length of `vec` prior to draining.
+    pub(super) old_len: usize,
+    /// The filter test predicate.
+    pub(super) pred: F,
+    /// A flag that indicates a panic has occurred in the filter test predicate.
+    /// This is used as a hint in the drop implementation to prevent consumption
+    /// of the remainder of the `DrainFilter`. Any unprocessed items will be
+    /// backshifted in the `vec`, but no further items will be dropped or
+    /// tested by the filter predicate.
+    pub(super) panic_flag: bool,
+}
+
+impl<T, F, A: Allocator> DrainFilter<'_, T, F, A>
+where
+    F: FnMut(&mut T) -> bool,
+{
+    /// Returns a reference to the underlying allocator.
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    #[inline]
+    pub fn allocator(&self) -> &A {
+        self.vec.allocator()
+    }
+}
+
+#[unstable(feature = "drain_filter", reason = "recently added", issue = "43244")]
+impl<T, F, A: Allocator> Iterator for DrainFilter<'_, T, F, A>
+where
+    F: FnMut(&mut T) -> bool,
+{
+    type Item = T;
+
+    fn next(&mut self) -> Option<T> {
+        unsafe {
+            while self.idx < self.old_len {
+                let i = self.idx;
+                let v = slice::from_raw_parts_mut(self.vec.as_mut_ptr(), self.old_len);
+                self.panic_flag = true;
+                let drained = (self.pred)(&mut v[i]);
+                self.panic_flag = false;
+                // Update the index *after* the predicate is called. If the index
+                // is updated prior and the predicate panics, the element at this
+                // index would be leaked.
+                self.idx += 1;
+                if drained {
+                    self.del += 1;
+                    return Some(ptr::read(&v[i]));
+                } else if self.del > 0 {
+                    let del = self.del;
+                    let src: *const T = &v[i];
+                    let dst: *mut T = &mut v[i - del];
+                    ptr::copy_nonoverlapping(src, dst, 1);
+                }
+            }
+            None
+        }
+    }
+
+    fn size_hint(&self) -> (usize, Option<usize>) {
+        (0, Some(self.old_len - self.idx))
+    }
+}
+
+#[unstable(feature = "drain_filter", reason = "recently added", issue = "43244")]
+impl<T, F, A: Allocator> Drop for DrainFilter<'_, T, F, A>
+where
+    F: FnMut(&mut T) -> bool,
+{
+    fn drop(&mut self) {
+        struct BackshiftOnDrop<'a, 'b, T, F, A: Allocator>
+        where
+            F: FnMut(&mut T) -> bool,
+        {
+            drain: &'b mut DrainFilter<'a, T, F, A>,
+        }
+
+        impl<'a, 'b, T, F, A: Allocator> Drop for BackshiftOnDrop<'a, 'b, T, F, A>
+        where
+            F: FnMut(&mut T) -> bool,
+        {
+            fn drop(&mut self) {
+                unsafe {
+                    if self.drain.idx < self.drain.old_len && self.drain.del > 0 {
+                        // This is a pretty messed up state, and there isn't really an
+                        // obviously right thing to do. We don't want to keep trying
+                        // to execute `pred`, so we just backshift all the unprocessed
+                        // elements and tell the vec that they still exist. The backshift
+                        // is required to prevent a double-drop of the last successfully
+                        // drained item prior to a panic in the predicate.
+                        let ptr = self.drain.vec.as_mut_ptr();
+                        let src = ptr.add(self.drain.idx);
+                        let dst = src.sub(self.drain.del);
+                        let tail_len = self.drain.old_len - self.drain.idx;
+                        src.copy_to(dst, tail_len);
+                    }
+                    self.drain.vec.set_len(self.drain.old_len - self.drain.del);
+                }
+            }
+        }
+
+        let backshift = BackshiftOnDrop { drain: self };
+
+        // Attempt to consume any remaining elements if the filter predicate
+        // has not yet panicked. We'll backshift any remaining elements
+        // whether we've already panicked or if the consumption here panics.
+        if !backshift.drain.panic_flag {
+            backshift.drain.for_each(drop);
+        }
+    }
+}
diff --git a/rust/alloc/vec/into_iter.rs b/rust/alloc/vec/into_iter.rs
new file mode 100644
index 000000000000..f7a50e76691e
--- /dev/null
+++ b/rust/alloc/vec/into_iter.rs
@@ -0,0 +1,366 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+#[cfg(not(no_global_oom_handling))]
+use super::AsVecIntoIter;
+use crate::alloc::{Allocator, Global};
+use crate::raw_vec::RawVec;
+use core::fmt;
+use core::intrinsics::arith_offset;
+use core::iter::{
+    FusedIterator, InPlaceIterable, SourceIter, TrustedLen, TrustedRandomAccessNoCoerce,
+};
+use core::marker::PhantomData;
+use core::mem::{self, ManuallyDrop};
+#[cfg(not(no_global_oom_handling))]
+use core::ops::Deref;
+use core::ptr::{self, NonNull};
+use core::slice::{self};
+
+/// An iterator that moves out of a vector.
+///
+/// This `struct` is created by the `into_iter` method on [`Vec`](super::Vec)
+/// (provided by the [`IntoIterator`] trait).
+///
+/// # Example
+///
+/// ```
+/// let v = vec![0, 1, 2];
+/// let iter: std::vec::IntoIter<_> = v.into_iter();
+/// ```
+#[stable(feature = "rust1", since = "1.0.0")]
+#[rustc_insignificant_dtor]
+pub struct IntoIter<
+    T,
+    #[unstable(feature = "allocator_api", issue = "32838")] A: Allocator = Global,
+> {
+    pub(super) buf: NonNull<T>,
+    pub(super) phantom: PhantomData<T>,
+    pub(super) cap: usize,
+    // the drop impl reconstructs a RawVec from buf, cap and alloc
+    // to avoid dropping the allocator twice we need to wrap it into ManuallyDrop
+    pub(super) alloc: ManuallyDrop<A>,
+    pub(super) ptr: *const T,
+    pub(super) end: *const T,
+}
+
+#[stable(feature = "vec_intoiter_debug", since = "1.13.0")]
+impl<T: fmt::Debug, A: Allocator> fmt::Debug for IntoIter<T, A> {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        f.debug_tuple("IntoIter").field(&self.as_slice()).finish()
+    }
+}
+
+impl<T, A: Allocator> IntoIter<T, A> {
+    /// Returns the remaining items of this iterator as a slice.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let vec = vec!['a', 'b', 'c'];
+    /// let mut into_iter = vec.into_iter();
+    /// assert_eq!(into_iter.as_slice(), &['a', 'b', 'c']);
+    /// let _ = into_iter.next().unwrap();
+    /// assert_eq!(into_iter.as_slice(), &['b', 'c']);
+    /// ```
+    #[stable(feature = "vec_into_iter_as_slice", since = "1.15.0")]
+    pub fn as_slice(&self) -> &[T] {
+        unsafe { slice::from_raw_parts(self.ptr, self.len()) }
+    }
+
+    /// Returns the remaining items of this iterator as a mutable slice.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let vec = vec!['a', 'b', 'c'];
+    /// let mut into_iter = vec.into_iter();
+    /// assert_eq!(into_iter.as_slice(), &['a', 'b', 'c']);
+    /// into_iter.as_mut_slice()[2] = 'z';
+    /// assert_eq!(into_iter.next().unwrap(), 'a');
+    /// assert_eq!(into_iter.next().unwrap(), 'b');
+    /// assert_eq!(into_iter.next().unwrap(), 'z');
+    /// ```
+    #[stable(feature = "vec_into_iter_as_slice", since = "1.15.0")]
+    pub fn as_mut_slice(&mut self) -> &mut [T] {
+        unsafe { &mut *self.as_raw_mut_slice() }
+    }
+
+    /// Returns a reference to the underlying allocator.
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    #[inline]
+    pub fn allocator(&self) -> &A {
+        &self.alloc
+    }
+
+    fn as_raw_mut_slice(&mut self) -> *mut [T] {
+        ptr::slice_from_raw_parts_mut(self.ptr as *mut T, self.len())
+    }
+
+    /// Drops remaining elements and relinquishes the backing allocation.
+    ///
+    /// This is roughly equivalent to the following, but more efficient
+    ///
+    /// ```
+    /// # let mut into_iter = Vec::<u8>::with_capacity(10).into_iter();
+    /// (&mut into_iter).for_each(core::mem::drop);
+    /// unsafe { core::ptr::write(&mut into_iter, Vec::new().into_iter()); }
+    /// ```
+    ///
+    /// This method is used by in-place iteration, refer to the vec::in_place_collect
+    /// documentation for an overview.
+    #[cfg(not(no_global_oom_handling))]
+    pub(super) fn forget_allocation_drop_remaining(&mut self) {
+        let remaining = self.as_raw_mut_slice();
+
+        // overwrite the individual fields instead of creating a new
+        // struct and then overwriting &mut self.
+        // this creates less assembly
+        self.cap = 0;
+        self.buf = unsafe { NonNull::new_unchecked(RawVec::NEW.ptr()) };
+        self.ptr = self.buf.as_ptr();
+        self.end = self.buf.as_ptr();
+
+        unsafe {
+            ptr::drop_in_place(remaining);
+        }
+    }
+
+    /// Forgets to Drop the remaining elements while still allowing the backing allocation to be freed.
+    #[allow(dead_code)]
+    pub(crate) fn forget_remaining_elements(&mut self) {
+        self.ptr = self.end;
+    }
+}
+
+#[stable(feature = "vec_intoiter_as_ref", since = "1.46.0")]
+impl<T, A: Allocator> AsRef<[T]> for IntoIter<T, A> {
+    fn as_ref(&self) -> &[T] {
+        self.as_slice()
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+unsafe impl<T: Send, A: Allocator + Send> Send for IntoIter<T, A> {}
+#[stable(feature = "rust1", since = "1.0.0")]
+unsafe impl<T: Sync, A: Allocator + Sync> Sync for IntoIter<T, A> {}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T, A: Allocator> Iterator for IntoIter<T, A> {
+    type Item = T;
+
+    #[inline]
+    fn next(&mut self) -> Option<T> {
+        if self.ptr as *const _ == self.end {
+            None
+        } else if mem::size_of::<T>() == 0 {
+            // purposefully don't use 'ptr.offset' because for
+            // vectors with 0-size elements this would return the
+            // same pointer.
+            self.ptr = unsafe { arith_offset(self.ptr as *const i8, 1) as *mut T };
+
+            // Make up a value of this ZST.
+            Some(unsafe { mem::zeroed() })
+        } else {
+            let old = self.ptr;
+            self.ptr = unsafe { self.ptr.offset(1) };
+
+            Some(unsafe { ptr::read(old) })
+        }
+    }
+
+    #[inline]
+    fn size_hint(&self) -> (usize, Option<usize>) {
+        let exact = if mem::size_of::<T>() == 0 {
+            self.end.addr().wrapping_sub(self.ptr.addr())
+        } else {
+            unsafe { self.end.sub_ptr(self.ptr) }
+        };
+        (exact, Some(exact))
+    }
+
+    #[inline]
+    fn advance_by(&mut self, n: usize) -> Result<(), usize> {
+        let step_size = self.len().min(n);
+        let to_drop = ptr::slice_from_raw_parts_mut(self.ptr as *mut T, step_size);
+        if mem::size_of::<T>() == 0 {
+            // SAFETY: due to unchecked casts of unsigned amounts to signed offsets the wraparound
+            // effectively results in unsigned pointers representing positions 0..usize::MAX,
+            // which is valid for ZSTs.
+            self.ptr = unsafe { arith_offset(self.ptr as *const i8, step_size as isize) as *mut T }
+        } else {
+            // SAFETY: the min() above ensures that step_size is in bounds
+            self.ptr = unsafe { self.ptr.add(step_size) };
+        }
+        // SAFETY: the min() above ensures that step_size is in bounds
+        unsafe {
+            ptr::drop_in_place(to_drop);
+        }
+        if step_size < n {
+            return Err(step_size);
+        }
+        Ok(())
+    }
+
+    #[inline]
+    fn count(self) -> usize {
+        self.len()
+    }
+
+    unsafe fn __iterator_get_unchecked(&mut self, i: usize) -> Self::Item
+    where
+        Self: TrustedRandomAccessNoCoerce,
+    {
+        // SAFETY: the caller must guarantee that `i` is in bounds of the
+        // `Vec<T>`, so `i` cannot overflow an `isize`, and the `self.ptr.add(i)`
+        // is guaranteed to pointer to an element of the `Vec<T>` and
+        // thus guaranteed to be valid to dereference.
+        //
+        // Also note the implementation of `Self: TrustedRandomAccess` requires
+        // that `T: Copy` so reading elements from the buffer doesn't invalidate
+        // them for `Drop`.
+        unsafe {
+            if mem::size_of::<T>() == 0 { mem::zeroed() } else { ptr::read(self.ptr.add(i)) }
+        }
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T, A: Allocator> DoubleEndedIterator for IntoIter<T, A> {
+    #[inline]
+    fn next_back(&mut self) -> Option<T> {
+        if self.end == self.ptr {
+            None
+        } else if mem::size_of::<T>() == 0 {
+            // See above for why 'ptr.offset' isn't used
+            self.end = unsafe { arith_offset(self.end as *const i8, -1) as *mut T };
+
+            // Make up a value of this ZST.
+            Some(unsafe { mem::zeroed() })
+        } else {
+            self.end = unsafe { self.end.offset(-1) };
+
+            Some(unsafe { ptr::read(self.end) })
+        }
+    }
+
+    #[inline]
+    fn advance_back_by(&mut self, n: usize) -> Result<(), usize> {
+        let step_size = self.len().min(n);
+        if mem::size_of::<T>() == 0 {
+            // SAFETY: same as for advance_by()
+            self.end = unsafe {
+                arith_offset(self.end as *const i8, step_size.wrapping_neg() as isize) as *mut T
+            }
+        } else {
+            // SAFETY: same as for advance_by()
+            self.end = unsafe { self.end.offset(step_size.wrapping_neg() as isize) };
+        }
+        let to_drop = ptr::slice_from_raw_parts_mut(self.end as *mut T, step_size);
+        // SAFETY: same as for advance_by()
+        unsafe {
+            ptr::drop_in_place(to_drop);
+        }
+        if step_size < n {
+            return Err(step_size);
+        }
+        Ok(())
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T, A: Allocator> ExactSizeIterator for IntoIter<T, A> {
+    fn is_empty(&self) -> bool {
+        self.ptr == self.end
+    }
+}
+
+#[stable(feature = "fused", since = "1.26.0")]
+impl<T, A: Allocator> FusedIterator for IntoIter<T, A> {}
+
+#[unstable(feature = "trusted_len", issue = "37572")]
+unsafe impl<T, A: Allocator> TrustedLen for IntoIter<T, A> {}
+
+#[doc(hidden)]
+#[unstable(issue = "none", feature = "std_internals")]
+#[rustc_unsafe_specialization_marker]
+pub trait NonDrop {}
+
+// T: Copy as approximation for !Drop since get_unchecked does not advance self.ptr
+// and thus we can't implement drop-handling
+#[unstable(issue = "none", feature = "std_internals")]
+impl<T: Copy> NonDrop for T {}
+
+#[doc(hidden)]
+#[unstable(issue = "none", feature = "std_internals")]
+// TrustedRandomAccess (without NoCoerce) must not be implemented because
+// subtypes/supertypes of `T` might not be `NonDrop`
+unsafe impl<T, A: Allocator> TrustedRandomAccessNoCoerce for IntoIter<T, A>
+where
+    T: NonDrop,
+{
+    const MAY_HAVE_SIDE_EFFECT: bool = false;
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "vec_into_iter_clone", since = "1.8.0")]
+impl<T: Clone, A: Allocator + Clone> Clone for IntoIter<T, A> {
+    #[cfg(not(test))]
+    fn clone(&self) -> Self {
+        self.as_slice().to_vec_in(self.alloc.deref().clone()).into_iter()
+    }
+    #[cfg(test)]
+    fn clone(&self) -> Self {
+        crate::slice::to_vec(self.as_slice(), self.alloc.deref().clone()).into_iter()
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+unsafe impl<#[may_dangle] T, A: Allocator> Drop for IntoIter<T, A> {
+    fn drop(&mut self) {
+        struct DropGuard<'a, T, A: Allocator>(&'a mut IntoIter<T, A>);
+
+        impl<T, A: Allocator> Drop for DropGuard<'_, T, A> {
+            fn drop(&mut self) {
+                unsafe {
+                    // `IntoIter::alloc` is not used anymore after this and will be dropped by RawVec
+                    let alloc = ManuallyDrop::take(&mut self.0.alloc);
+                    // RawVec handles deallocation
+                    let _ = RawVec::from_raw_parts_in(self.0.buf.as_ptr(), self.0.cap, alloc);
+                }
+            }
+        }
+
+        let guard = DropGuard(self);
+        // destroy the remaining elements
+        unsafe {
+            ptr::drop_in_place(guard.0.as_raw_mut_slice());
+        }
+        // now `guard` will be dropped and do the rest
+    }
+}
+
+// In addition to the SAFETY invariants of the following three unsafe traits
+// also refer to the vec::in_place_collect module documentation to get an overview
+#[unstable(issue = "none", feature = "inplace_iteration")]
+#[doc(hidden)]
+unsafe impl<T, A: Allocator> InPlaceIterable for IntoIter<T, A> {}
+
+#[unstable(issue = "none", feature = "inplace_iteration")]
+#[doc(hidden)]
+unsafe impl<T, A: Allocator> SourceIter for IntoIter<T, A> {
+    type Source = Self;
+
+    #[inline]
+    unsafe fn as_inner(&mut self) -> &mut Self::Source {
+        self
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+unsafe impl<T> AsVecIntoIter for IntoIter<T> {
+    type Item = T;
+
+    fn as_into_iter(&mut self) -> &mut IntoIter<Self::Item> {
+        self
+    }
+}
diff --git a/rust/alloc/vec/is_zero.rs b/rust/alloc/vec/is_zero.rs
new file mode 100644
index 000000000000..377f3d172777
--- /dev/null
+++ b/rust/alloc/vec/is_zero.rs
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+use crate::boxed::Box;
+
+#[rustc_specialization_trait]
+pub(super) unsafe trait IsZero {
+    /// Whether this value's representation is all zeros
+    fn is_zero(&self) -> bool;
+}
+
+macro_rules! impl_is_zero {
+    ($t:ty, $is_zero:expr) => {
+        unsafe impl IsZero for $t {
+            #[inline]
+            fn is_zero(&self) -> bool {
+                $is_zero(*self)
+            }
+        }
+    };
+}
+
+impl_is_zero!(i16, |x| x == 0);
+impl_is_zero!(i32, |x| x == 0);
+impl_is_zero!(i64, |x| x == 0);
+impl_is_zero!(i128, |x| x == 0);
+impl_is_zero!(isize, |x| x == 0);
+
+impl_is_zero!(u16, |x| x == 0);
+impl_is_zero!(u32, |x| x == 0);
+impl_is_zero!(u64, |x| x == 0);
+impl_is_zero!(u128, |x| x == 0);
+impl_is_zero!(usize, |x| x == 0);
+
+impl_is_zero!(bool, |x| x == false);
+impl_is_zero!(char, |x| x == '\0');
+
+impl_is_zero!(f32, |x: f32| x.to_bits() == 0);
+impl_is_zero!(f64, |x: f64| x.to_bits() == 0);
+
+unsafe impl<T> IsZero for *const T {
+    #[inline]
+    fn is_zero(&self) -> bool {
+        (*self).is_null()
+    }
+}
+
+unsafe impl<T> IsZero for *mut T {
+    #[inline]
+    fn is_zero(&self) -> bool {
+        (*self).is_null()
+    }
+}
+
+unsafe impl<T: IsZero, const N: usize> IsZero for [T; N] {
+    #[inline]
+    fn is_zero(&self) -> bool {
+        // Because this is generated as a runtime check, it's not obvious that
+        // it's worth doing if the array is really long.  The threshold here
+        // is largely arbitrary, but was picked because as of 2022-05-01 LLVM
+        // can const-fold the check in `vec![[0; 32]; n]` but not in
+        // `vec![[0; 64]; n]`: https://godbolt.org/z/WTzjzfs5b
+        // Feel free to tweak if you have better evidence.
+
+        N <= 32 && self.iter().all(IsZero::is_zero)
+    }
+}
+
+// `Option<&T>` and `Option<Box<T>>` are guaranteed to represent `None` as null.
+// For fat pointers, the bytes that would be the pointer metadata in the `Some`
+// variant are padding in the `None` variant, so ignoring them and
+// zero-initializing instead is ok.
+// `Option<&mut T>` never implements `Clone`, so there's no need for an impl of
+// `SpecFromElem`.
+
+unsafe impl<T: ?Sized> IsZero for Option<&T> {
+    #[inline]
+    fn is_zero(&self) -> bool {
+        self.is_none()
+    }
+}
+
+unsafe impl<T: ?Sized> IsZero for Option<Box<T>> {
+    #[inline]
+    fn is_zero(&self) -> bool {
+        self.is_none()
+    }
+}
+
+// `Option<num::NonZeroU32>` and similar have a representation guarantee that
+// they're the same size as the corresponding `u32` type, as well as a guarantee
+// that transmuting between `NonZeroU32` and `Option<num::NonZeroU32>` works.
+// While the documentation officially makes it UB to transmute from `None`,
+// we're the standard library so we can make extra inferences, and we know that
+// the only niche available to represent `None` is the one that's all zeros.
+
+macro_rules! impl_is_zero_option_of_nonzero {
+    ($($t:ident,)+) => {$(
+        unsafe impl IsZero for Option<core::num::$t> {
+            #[inline]
+            fn is_zero(&self) -> bool {
+                self.is_none()
+            }
+        }
+    )+};
+}
+
+impl_is_zero_option_of_nonzero!(
+    NonZeroU8,
+    NonZeroU16,
+    NonZeroU32,
+    NonZeroU64,
+    NonZeroU128,
+    NonZeroI8,
+    NonZeroI16,
+    NonZeroI32,
+    NonZeroI64,
+    NonZeroI128,
+    NonZeroUsize,
+    NonZeroIsize,
+);
diff --git a/rust/alloc/vec/mod.rs b/rust/alloc/vec/mod.rs
new file mode 100644
index 000000000000..540787804cc2
--- /dev/null
+++ b/rust/alloc/vec/mod.rs
@@ -0,0 +1,3140 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+//! A contiguous growable array type with heap-allocated contents, written
+//! `Vec<T>`.
+//!
+//! Vectors have *O*(1) indexing, amortized *O*(1) push (to the end) and
+//! *O*(1) pop (from the end).
+//!
+//! Vectors ensure they never allocate more than `isize::MAX` bytes.
+//!
+//! # Examples
+//!
+//! You can explicitly create a [`Vec`] with [`Vec::new`]:
+//!
+//! ```
+//! let v: Vec<i32> = Vec::new();
+//! ```
+//!
+//! ...or by using the [`vec!`] macro:
+//!
+//! ```
+//! let v: Vec<i32> = vec![];
+//!
+//! let v = vec![1, 2, 3, 4, 5];
+//!
+//! let v = vec![0; 10]; // ten zeroes
+//! ```
+//!
+//! You can [`push`] values onto the end of a vector (which will grow the vector
+//! as needed):
+//!
+//! ```
+//! let mut v = vec![1, 2];
+//!
+//! v.push(3);
+//! ```
+//!
+//! Popping values works in much the same way:
+//!
+//! ```
+//! let mut v = vec![1, 2];
+//!
+//! let two = v.pop();
+//! ```
+//!
+//! Vectors also support indexing (through the [`Index`] and [`IndexMut`] traits):
+//!
+//! ```
+//! let mut v = vec![1, 2, 3];
+//! let three = v[2];
+//! v[1] = v[1] + 5;
+//! ```
+//!
+//! [`push`]: Vec::push
+
+#![stable(feature = "rust1", since = "1.0.0")]
+
+#[cfg(not(no_global_oom_handling))]
+use core::cmp;
+use core::cmp::Ordering;
+use core::convert::TryFrom;
+use core::fmt;
+use core::hash::{Hash, Hasher};
+use core::intrinsics::{arith_offset, assume};
+use core::iter;
+#[cfg(not(no_global_oom_handling))]
+use core::iter::FromIterator;
+use core::marker::PhantomData;
+use core::mem::{self, ManuallyDrop, MaybeUninit};
+use core::ops::{self, Index, IndexMut, Range, RangeBounds};
+use core::ptr::{self, NonNull};
+use core::slice::{self, SliceIndex};
+
+use crate::alloc::{Allocator, Global};
+use crate::borrow::{Cow, ToOwned};
+use crate::boxed::Box;
+use crate::collections::TryReserveError;
+use crate::raw_vec::RawVec;
+
+#[unstable(feature = "drain_filter", reason = "recently added", issue = "43244")]
+pub use self::drain_filter::DrainFilter;
+
+mod drain_filter;
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "vec_splice", since = "1.21.0")]
+pub use self::splice::Splice;
+
+#[cfg(not(no_global_oom_handling))]
+mod splice;
+
+#[stable(feature = "drain", since = "1.6.0")]
+pub use self::drain::Drain;
+
+mod drain;
+
+#[cfg(not(no_global_oom_handling))]
+mod cow;
+
+#[cfg(not(no_global_oom_handling))]
+pub(crate) use self::in_place_collect::AsVecIntoIter;
+#[stable(feature = "rust1", since = "1.0.0")]
+pub use self::into_iter::IntoIter;
+
+mod into_iter;
+
+#[cfg(not(no_global_oom_handling))]
+use self::is_zero::IsZero;
+
+mod is_zero;
+
+#[cfg(not(no_global_oom_handling))]
+mod in_place_collect;
+
+mod partial_eq;
+
+#[cfg(not(no_global_oom_handling))]
+use self::spec_from_elem::SpecFromElem;
+
+#[cfg(not(no_global_oom_handling))]
+mod spec_from_elem;
+
+#[cfg(not(no_global_oom_handling))]
+use self::set_len_on_drop::SetLenOnDrop;
+
+#[cfg(not(no_global_oom_handling))]
+mod set_len_on_drop;
+
+#[cfg(not(no_global_oom_handling))]
+use self::in_place_drop::InPlaceDrop;
+
+#[cfg(not(no_global_oom_handling))]
+mod in_place_drop;
+
+#[cfg(not(no_global_oom_handling))]
+use self::spec_from_iter_nested::SpecFromIterNested;
+
+#[cfg(not(no_global_oom_handling))]
+mod spec_from_iter_nested;
+
+#[cfg(not(no_global_oom_handling))]
+use self::spec_from_iter::SpecFromIter;
+
+#[cfg(not(no_global_oom_handling))]
+mod spec_from_iter;
+
+#[cfg(not(no_global_oom_handling))]
+use self::spec_extend::SpecExtend;
+
+#[cfg(not(no_global_oom_handling))]
+mod spec_extend;
+
+/// A contiguous growable array type, written as `Vec<T>`, short for 'vector'.
+///
+/// # Examples
+///
+/// ```
+/// let mut vec = Vec::new();
+/// vec.push(1);
+/// vec.push(2);
+///
+/// assert_eq!(vec.len(), 2);
+/// assert_eq!(vec[0], 1);
+///
+/// assert_eq!(vec.pop(), Some(2));
+/// assert_eq!(vec.len(), 1);
+///
+/// vec[0] = 7;
+/// assert_eq!(vec[0], 7);
+///
+/// vec.extend([1, 2, 3].iter().copied());
+///
+/// for x in &vec {
+///     println!("{x}");
+/// }
+/// assert_eq!(vec, [7, 1, 2, 3]);
+/// ```
+///
+/// The [`vec!`] macro is provided for convenient initialization:
+///
+/// ```
+/// let mut vec1 = vec![1, 2, 3];
+/// vec1.push(4);
+/// let vec2 = Vec::from([1, 2, 3, 4]);
+/// assert_eq!(vec1, vec2);
+/// ```
+///
+/// It can also initialize each element of a `Vec<T>` with a given value.
+/// This may be more efficient than performing allocation and initialization
+/// in separate steps, especially when initializing a vector of zeros:
+///
+/// ```
+/// let vec = vec![0; 5];
+/// assert_eq!(vec, [0, 0, 0, 0, 0]);
+///
+/// // The following is equivalent, but potentially slower:
+/// let mut vec = Vec::with_capacity(5);
+/// vec.resize(5, 0);
+/// assert_eq!(vec, [0, 0, 0, 0, 0]);
+/// ```
+///
+/// For more information, see
+/// [Capacity and Reallocation](#capacity-and-reallocation).
+///
+/// Use a `Vec<T>` as an efficient stack:
+///
+/// ```
+/// let mut stack = Vec::new();
+///
+/// stack.push(1);
+/// stack.push(2);
+/// stack.push(3);
+///
+/// while let Some(top) = stack.pop() {
+///     // Prints 3, 2, 1
+///     println!("{top}");
+/// }
+/// ```
+///
+/// # Indexing
+///
+/// The `Vec` type allows to access values by index, because it implements the
+/// [`Index`] trait. An example will be more explicit:
+///
+/// ```
+/// let v = vec![0, 2, 4, 6];
+/// println!("{}", v[1]); // it will display '2'
+/// ```
+///
+/// However be careful: if you try to access an index which isn't in the `Vec`,
+/// your software will panic! You cannot do this:
+///
+/// ```should_panic
+/// let v = vec![0, 2, 4, 6];
+/// println!("{}", v[6]); // it will panic!
+/// ```
+///
+/// Use [`get`] and [`get_mut`] if you want to check whether the index is in
+/// the `Vec`.
+///
+/// # Slicing
+///
+/// A `Vec` can be mutable. On the other hand, slices are read-only objects.
+/// To get a [slice][prim@slice], use [`&`]. Example:
+///
+/// ```
+/// fn read_slice(slice: &[usize]) {
+///     // ...
+/// }
+///
+/// let v = vec![0, 1];
+/// read_slice(&v);
+///
+/// // ... and that's all!
+/// // you can also do it like this:
+/// let u: &[usize] = &v;
+/// // or like this:
+/// let u: &[_] = &v;
+/// ```
+///
+/// In Rust, it's more common to pass slices as arguments rather than vectors
+/// when you just want to provide read access. The same goes for [`String`] and
+/// [`&str`].
+///
+/// # Capacity and reallocation
+///
+/// The capacity of a vector is the amount of space allocated for any future
+/// elements that will be added onto the vector. This is not to be confused with
+/// the *length* of a vector, which specifies the number of actual elements
+/// within the vector. If a vector's length exceeds its capacity, its capacity
+/// will automatically be increased, but its elements will have to be
+/// reallocated.
+///
+/// For example, a vector with capacity 10 and length 0 would be an empty vector
+/// with space for 10 more elements. Pushing 10 or fewer elements onto the
+/// vector will not change its capacity or cause reallocation to occur. However,
+/// if the vector's length is increased to 11, it will have to reallocate, which
+/// can be slow. For this reason, it is recommended to use [`Vec::with_capacity`]
+/// whenever possible to specify how big the vector is expected to get.
+///
+/// # Guarantees
+///
+/// Due to its incredibly fundamental nature, `Vec` makes a lot of guarantees
+/// about its design. This ensures that it's as low-overhead as possible in
+/// the general case, and can be correctly manipulated in primitive ways
+/// by unsafe code. Note that these guarantees refer to an unqualified `Vec<T>`.
+/// If additional type parameters are added (e.g., to support custom allocators),
+/// overriding their defaults may change the behavior.
+///
+/// Most fundamentally, `Vec` is and always will be a (pointer, capacity, length)
+/// triplet. No more, no less. The order of these fields is completely
+/// unspecified, and you should use the appropriate methods to modify these.
+/// The pointer will never be null, so this type is null-pointer-optimized.
+///
+/// However, the pointer might not actually point to allocated memory. In particular,
+/// if you construct a `Vec` with capacity 0 via [`Vec::new`], [`vec![]`][`vec!`],
+/// [`Vec::with_capacity(0)`][`Vec::with_capacity`], or by calling [`shrink_to_fit`]
+/// on an empty Vec, it will not allocate memory. Similarly, if you store zero-sized
+/// types inside a `Vec`, it will not allocate space for them. *Note that in this case
+/// the `Vec` might not report a [`capacity`] of 0*. `Vec` will allocate if and only
+/// if <code>[mem::size_of::\<T>]\() * [capacity]\() > 0</code>. In general, `Vec`'s allocation
+/// details are very subtle --- if you intend to allocate memory using a `Vec`
+/// and use it for something else (either to pass to unsafe code, or to build your
+/// own memory-backed collection), be sure to deallocate this memory by using
+/// `from_raw_parts` to recover the `Vec` and then dropping it.
+///
+/// If a `Vec` *has* allocated memory, then the memory it points to is on the heap
+/// (as defined by the allocator Rust is configured to use by default), and its
+/// pointer points to [`len`] initialized, contiguous elements in order (what
+/// you would see if you coerced it to a slice), followed by <code>[capacity] - [len]</code>
+/// logically uninitialized, contiguous elements.
+///
+/// A vector containing the elements `'a'` and `'b'` with capacity 4 can be
+/// visualized as below. The top part is the `Vec` struct, it contains a
+/// pointer to the head of the allocation in the heap, length and capacity.
+/// The bottom part is the allocation on the heap, a contiguous memory block.
+///
+/// ```text
+///             ptr      len  capacity
+///        +--------+--------+--------+
+///        | 0x0123 |      2 |      4 |
+///        +--------+--------+--------+
+///             |
+///             v
+/// Heap   +--------+--------+--------+--------+
+///        |    'a' |    'b' | uninit | uninit |
+///        +--------+--------+--------+--------+
+/// ```
+///
+/// - **uninit** represents memory that is not initialized, see [`MaybeUninit`].
+/// - Note: the ABI is not stable and `Vec` makes no guarantees about its memory
+///   layout (including the order of fields).
+///
+/// `Vec` will never perform a "small optimization" where elements are actually
+/// stored on the stack for two reasons:
+///
+/// * It would make it more difficult for unsafe code to correctly manipulate
+///   a `Vec`. The contents of a `Vec` wouldn't have a stable address if it were
+///   only moved, and it would be more difficult to determine if a `Vec` had
+///   actually allocated memory.
+///
+/// * It would penalize the general case, incurring an additional branch
+///   on every access.
+///
+/// `Vec` will never automatically shrink itself, even if completely empty. This
+/// ensures no unnecessary allocations or deallocations occur. Emptying a `Vec`
+/// and then filling it back up to the same [`len`] should incur no calls to
+/// the allocator. If you wish to free up unused memory, use
+/// [`shrink_to_fit`] or [`shrink_to`].
+///
+/// [`push`] and [`insert`] will never (re)allocate if the reported capacity is
+/// sufficient. [`push`] and [`insert`] *will* (re)allocate if
+/// <code>[len] == [capacity]</code>. That is, the reported capacity is completely
+/// accurate, and can be relied on. It can even be used to manually free the memory
+/// allocated by a `Vec` if desired. Bulk insertion methods *may* reallocate, even
+/// when not necessary.
+///
+/// `Vec` does not guarantee any particular growth strategy when reallocating
+/// when full, nor when [`reserve`] is called. The current strategy is basic
+/// and it may prove desirable to use a non-constant growth factor. Whatever
+/// strategy is used will of course guarantee *O*(1) amortized [`push`].
+///
+/// `vec![x; n]`, `vec![a, b, c, d]`, and
+/// [`Vec::with_capacity(n)`][`Vec::with_capacity`], will all produce a `Vec`
+/// with exactly the requested capacity. If <code>[len] == [capacity]</code>,
+/// (as is the case for the [`vec!`] macro), then a `Vec<T>` can be converted to
+/// and from a [`Box<[T]>`][owned slice] without reallocating or moving the elements.
+///
+/// `Vec` will not specifically overwrite any data that is removed from it,
+/// but also won't specifically preserve it. Its uninitialized memory is
+/// scratch space that it may use however it wants. It will generally just do
+/// whatever is most efficient or otherwise easy to implement. Do not rely on
+/// removed data to be erased for security purposes. Even if you drop a `Vec`, its
+/// buffer may simply be reused by another allocation. Even if you zero a `Vec`'s memory
+/// first, that might not actually happen because the optimizer does not consider
+/// this a side-effect that must be preserved. There is one case which we will
+/// not break, however: using `unsafe` code to write to the excess capacity,
+/// and then increasing the length to match, is always valid.
+///
+/// Currently, `Vec` does not guarantee the order in which elements are dropped.
+/// The order has changed in the past and may change again.
+///
+/// [`get`]: ../../std/vec/struct.Vec.html#method.get
+/// [`get_mut`]: ../../std/vec/struct.Vec.html#method.get_mut
+/// [`String`]: crate::string::String
+/// [`&str`]: type@str
+/// [`shrink_to_fit`]: Vec::shrink_to_fit
+/// [`shrink_to`]: Vec::shrink_to
+/// [capacity]: Vec::capacity
+/// [`capacity`]: Vec::capacity
+/// [mem::size_of::\<T>]: core::mem::size_of
+/// [len]: Vec::len
+/// [`len`]: Vec::len
+/// [`push`]: Vec::push
+/// [`insert`]: Vec::insert
+/// [`reserve`]: Vec::reserve
+/// [`MaybeUninit`]: core::mem::MaybeUninit
+/// [owned slice]: Box
+#[stable(feature = "rust1", since = "1.0.0")]
+#[cfg_attr(not(test), rustc_diagnostic_item = "Vec")]
+#[rustc_insignificant_dtor]
+pub struct Vec<T, #[unstable(feature = "allocator_api", issue = "32838")] A: Allocator = Global> {
+    buf: RawVec<T, A>,
+    len: usize,
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// Inherent methods
+////////////////////////////////////////////////////////////////////////////////
+
+impl<T> Vec<T> {
+    /// Constructs a new, empty `Vec<T>`.
+    ///
+    /// The vector will not allocate until elements are pushed onto it.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// # #![allow(unused_mut)]
+    /// let mut vec: Vec<i32> = Vec::new();
+    /// ```
+    #[inline]
+    #[rustc_const_stable(feature = "const_vec_new", since = "1.39.0")]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    #[must_use]
+    pub const fn new() -> Self {
+        Vec { buf: RawVec::NEW, len: 0 }
+    }
+
+    /// Constructs a new, empty `Vec<T>` with the specified capacity.
+    ///
+    /// The vector will be able to hold exactly `capacity` elements without
+    /// reallocating. If `capacity` is 0, the vector will not allocate.
+    ///
+    /// It is important to note that although the returned vector has the
+    /// *capacity* specified, the vector will have a zero *length*. For an
+    /// explanation of the difference between length and capacity, see
+    /// *[Capacity and reallocation]*.
+    ///
+    /// [Capacity and reallocation]: #capacity-and-reallocation
+    ///
+    /// # Panics
+    ///
+    /// Panics if the new capacity exceeds `isize::MAX` bytes.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = Vec::with_capacity(10);
+    ///
+    /// // The vector contains no items, even though it has capacity for more
+    /// assert_eq!(vec.len(), 0);
+    /// assert_eq!(vec.capacity(), 10);
+    ///
+    /// // These are all done without reallocating...
+    /// for i in 0..10 {
+    ///     vec.push(i);
+    /// }
+    /// assert_eq!(vec.len(), 10);
+    /// assert_eq!(vec.capacity(), 10);
+    ///
+    /// // ...but this may make the vector reallocate
+    /// vec.push(11);
+    /// assert_eq!(vec.len(), 11);
+    /// assert!(vec.capacity() >= 11);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[inline]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    #[must_use]
+    pub fn with_capacity(capacity: usize) -> Self {
+        Self::with_capacity_in(capacity, Global)
+    }
+
+    /// Creates a `Vec<T>` directly from the raw components of another vector.
+    ///
+    /// # Safety
+    ///
+    /// This is highly unsafe, due to the number of invariants that aren't
+    /// checked:
+    ///
+    /// * `ptr` needs to have been previously allocated via [`String`]/`Vec<T>`
+    ///   (at least, it's highly likely to be incorrect if it wasn't).
+    /// * `T` needs to have the same alignment as what `ptr` was allocated with.
+    ///   (`T` having a less strict alignment is not sufficient, the alignment really
+    ///   needs to be equal to satisfy the [`dealloc`] requirement that memory must be
+    ///   allocated and deallocated with the same layout.)
+    /// * The size of `T` times the `capacity` (ie. the allocated size in bytes) needs
+    ///   to be the same size as the pointer was allocated with. (Because similar to
+    ///   alignment, [`dealloc`] must be called with the same layout `size`.)
+    /// * `length` needs to be less than or equal to `capacity`.
+    ///
+    /// Violating these may cause problems like corrupting the allocator's
+    /// internal data structures. For example it is normally **not** safe
+    /// to build a `Vec<u8>` from a pointer to a C `char` array with length
+    /// `size_t`, doing so is only safe if the array was initially allocated by
+    /// a `Vec` or `String`.
+    /// It's also not safe to build one from a `Vec<u16>` and its length, because
+    /// the allocator cares about the alignment, and these two types have different
+    /// alignments. The buffer was allocated with alignment 2 (for `u16`), but after
+    /// turning it into a `Vec<u8>` it'll be deallocated with alignment 1. To avoid
+    /// these issues, it is often preferable to do casting/transmuting using
+    /// [`slice::from_raw_parts`] instead.
+    ///
+    /// The ownership of `ptr` is effectively transferred to the
+    /// `Vec<T>` which may then deallocate, reallocate or change the
+    /// contents of memory pointed to by the pointer at will. Ensure
+    /// that nothing else uses the pointer after calling this
+    /// function.
+    ///
+    /// [`String`]: crate::string::String
+    /// [`dealloc`]: crate::alloc::GlobalAlloc::dealloc
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use std::ptr;
+    /// use std::mem;
+    ///
+    /// let v = vec![1, 2, 3];
+    ///
+    // FIXME Update this when vec_into_raw_parts is stabilized
+    /// // Prevent running `v`'s destructor so we are in complete control
+    /// // of the allocation.
+    /// let mut v = mem::ManuallyDrop::new(v);
+    ///
+    /// // Pull out the various important pieces of information about `v`
+    /// let p = v.as_mut_ptr();
+    /// let len = v.len();
+    /// let cap = v.capacity();
+    ///
+    /// unsafe {
+    ///     // Overwrite memory with 4, 5, 6
+    ///     for i in 0..len as isize {
+    ///         ptr::write(p.offset(i), 4 + i);
+    ///     }
+    ///
+    ///     // Put everything back together into a Vec
+    ///     let rebuilt = Vec::from_raw_parts(p, len, cap);
+    ///     assert_eq!(rebuilt, [4, 5, 6]);
+    /// }
+    /// ```
+    #[inline]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub unsafe fn from_raw_parts(ptr: *mut T, length: usize, capacity: usize) -> Self {
+        unsafe { Self::from_raw_parts_in(ptr, length, capacity, Global) }
+    }
+}
+
+impl<T, A: Allocator> Vec<T, A> {
+    /// Constructs a new, empty `Vec<T, A>`.
+    ///
+    /// The vector will not allocate until elements are pushed onto it.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api)]
+    ///
+    /// use std::alloc::System;
+    ///
+    /// # #[allow(unused_mut)]
+    /// let mut vec: Vec<i32, _> = Vec::new_in(System);
+    /// ```
+    #[inline]
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    pub const fn new_in(alloc: A) -> Self {
+        Vec { buf: RawVec::new_in(alloc), len: 0 }
+    }
+
+    /// Constructs a new, empty `Vec<T, A>` with the specified capacity with the provided
+    /// allocator.
+    ///
+    /// The vector will be able to hold exactly `capacity` elements without
+    /// reallocating. If `capacity` is 0, the vector will not allocate.
+    ///
+    /// It is important to note that although the returned vector has the
+    /// *capacity* specified, the vector will have a zero *length*. For an
+    /// explanation of the difference between length and capacity, see
+    /// *[Capacity and reallocation]*.
+    ///
+    /// [Capacity and reallocation]: #capacity-and-reallocation
+    ///
+    /// # Panics
+    ///
+    /// Panics if the new capacity exceeds `isize::MAX` bytes.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api)]
+    ///
+    /// use std::alloc::System;
+    ///
+    /// let mut vec = Vec::with_capacity_in(10, System);
+    ///
+    /// // The vector contains no items, even though it has capacity for more
+    /// assert_eq!(vec.len(), 0);
+    /// assert_eq!(vec.capacity(), 10);
+    ///
+    /// // These are all done without reallocating...
+    /// for i in 0..10 {
+    ///     vec.push(i);
+    /// }
+    /// assert_eq!(vec.len(), 10);
+    /// assert_eq!(vec.capacity(), 10);
+    ///
+    /// // ...but this may make the vector reallocate
+    /// vec.push(11);
+    /// assert_eq!(vec.len(), 11);
+    /// assert!(vec.capacity() >= 11);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[inline]
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    pub fn with_capacity_in(capacity: usize, alloc: A) -> Self {
+        Vec { buf: RawVec::with_capacity_in(capacity, alloc), len: 0 }
+    }
+
+    /// Creates a `Vec<T, A>` directly from the raw components of another vector.
+    ///
+    /// # Safety
+    ///
+    /// This is highly unsafe, due to the number of invariants that aren't
+    /// checked:
+    ///
+    /// * `ptr` needs to have been previously allocated via [`String`]/`Vec<T>`
+    ///   (at least, it's highly likely to be incorrect if it wasn't).
+    /// * `T` needs to have the same size and alignment as what `ptr` was allocated with.
+    ///   (`T` having a less strict alignment is not sufficient, the alignment really
+    ///   needs to be equal to satisfy the [`dealloc`] requirement that memory must be
+    ///   allocated and deallocated with the same layout.)
+    /// * `length` needs to be less than or equal to `capacity`.
+    /// * `capacity` needs to be the capacity that the pointer was allocated with.
+    ///
+    /// Violating these may cause problems like corrupting the allocator's
+    /// internal data structures. For example it is **not** safe
+    /// to build a `Vec<u8>` from a pointer to a C `char` array with length `size_t`.
+    /// It's also not safe to build one from a `Vec<u16>` and its length, because
+    /// the allocator cares about the alignment, and these two types have different
+    /// alignments. The buffer was allocated with alignment 2 (for `u16`), but after
+    /// turning it into a `Vec<u8>` it'll be deallocated with alignment 1.
+    ///
+    /// The ownership of `ptr` is effectively transferred to the
+    /// `Vec<T>` which may then deallocate, reallocate or change the
+    /// contents of memory pointed to by the pointer at will. Ensure
+    /// that nothing else uses the pointer after calling this
+    /// function.
+    ///
+    /// [`String`]: crate::string::String
+    /// [`dealloc`]: crate::alloc::GlobalAlloc::dealloc
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api)]
+    ///
+    /// use std::alloc::System;
+    ///
+    /// use std::ptr;
+    /// use std::mem;
+    ///
+    /// let mut v = Vec::with_capacity_in(3, System);
+    /// v.push(1);
+    /// v.push(2);
+    /// v.push(3);
+    ///
+    // FIXME Update this when vec_into_raw_parts is stabilized
+    /// // Prevent running `v`'s destructor so we are in complete control
+    /// // of the allocation.
+    /// let mut v = mem::ManuallyDrop::new(v);
+    ///
+    /// // Pull out the various important pieces of information about `v`
+    /// let p = v.as_mut_ptr();
+    /// let len = v.len();
+    /// let cap = v.capacity();
+    /// let alloc = v.allocator();
+    ///
+    /// unsafe {
+    ///     // Overwrite memory with 4, 5, 6
+    ///     for i in 0..len as isize {
+    ///         ptr::write(p.offset(i), 4 + i);
+    ///     }
+    ///
+    ///     // Put everything back together into a Vec
+    ///     let rebuilt = Vec::from_raw_parts_in(p, len, cap, alloc.clone());
+    ///     assert_eq!(rebuilt, [4, 5, 6]);
+    /// }
+    /// ```
+    #[inline]
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    pub unsafe fn from_raw_parts_in(ptr: *mut T, length: usize, capacity: usize, alloc: A) -> Self {
+        unsafe { Vec { buf: RawVec::from_raw_parts_in(ptr, capacity, alloc), len: length } }
+    }
+
+    /// Decomposes a `Vec<T>` into its raw components.
+    ///
+    /// Returns the raw pointer to the underlying data, the length of
+    /// the vector (in elements), and the allocated capacity of the
+    /// data (in elements). These are the same arguments in the same
+    /// order as the arguments to [`from_raw_parts`].
+    ///
+    /// After calling this function, the caller is responsible for the
+    /// memory previously managed by the `Vec`. The only way to do
+    /// this is to convert the raw pointer, length, and capacity back
+    /// into a `Vec` with the [`from_raw_parts`] function, allowing
+    /// the destructor to perform the cleanup.
+    ///
+    /// [`from_raw_parts`]: Vec::from_raw_parts
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(vec_into_raw_parts)]
+    /// let v: Vec<i32> = vec![-1, 0, 1];
+    ///
+    /// let (ptr, len, cap) = v.into_raw_parts();
+    ///
+    /// let rebuilt = unsafe {
+    ///     // We can now make changes to the components, such as
+    ///     // transmuting the raw pointer to a compatible type.
+    ///     let ptr = ptr as *mut u32;
+    ///
+    ///     Vec::from_raw_parts(ptr, len, cap)
+    /// };
+    /// assert_eq!(rebuilt, [4294967295, 0, 1]);
+    /// ```
+    #[unstable(feature = "vec_into_raw_parts", reason = "new API", issue = "65816")]
+    pub fn into_raw_parts(self) -> (*mut T, usize, usize) {
+        let mut me = ManuallyDrop::new(self);
+        (me.as_mut_ptr(), me.len(), me.capacity())
+    }
+
+    /// Decomposes a `Vec<T>` into its raw components.
+    ///
+    /// Returns the raw pointer to the underlying data, the length of the vector (in elements),
+    /// the allocated capacity of the data (in elements), and the allocator. These are the same
+    /// arguments in the same order as the arguments to [`from_raw_parts_in`].
+    ///
+    /// After calling this function, the caller is responsible for the
+    /// memory previously managed by the `Vec`. The only way to do
+    /// this is to convert the raw pointer, length, and capacity back
+    /// into a `Vec` with the [`from_raw_parts_in`] function, allowing
+    /// the destructor to perform the cleanup.
+    ///
+    /// [`from_raw_parts_in`]: Vec::from_raw_parts_in
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(allocator_api, vec_into_raw_parts)]
+    ///
+    /// use std::alloc::System;
+    ///
+    /// let mut v: Vec<i32, System> = Vec::new_in(System);
+    /// v.push(-1);
+    /// v.push(0);
+    /// v.push(1);
+    ///
+    /// let (ptr, len, cap, alloc) = v.into_raw_parts_with_alloc();
+    ///
+    /// let rebuilt = unsafe {
+    ///     // We can now make changes to the components, such as
+    ///     // transmuting the raw pointer to a compatible type.
+    ///     let ptr = ptr as *mut u32;
+    ///
+    ///     Vec::from_raw_parts_in(ptr, len, cap, alloc)
+    /// };
+    /// assert_eq!(rebuilt, [4294967295, 0, 1]);
+    /// ```
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    // #[unstable(feature = "vec_into_raw_parts", reason = "new API", issue = "65816")]
+    pub fn into_raw_parts_with_alloc(self) -> (*mut T, usize, usize, A) {
+        let mut me = ManuallyDrop::new(self);
+        let len = me.len();
+        let capacity = me.capacity();
+        let ptr = me.as_mut_ptr();
+        let alloc = unsafe { ptr::read(me.allocator()) };
+        (ptr, len, capacity, alloc)
+    }
+
+    /// Returns the number of elements the vector can hold without
+    /// reallocating.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let vec: Vec<i32> = Vec::with_capacity(10);
+    /// assert_eq!(vec.capacity(), 10);
+    /// ```
+    #[inline]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn capacity(&self) -> usize {
+        self.buf.capacity()
+    }
+
+    /// Reserves capacity for at least `additional` more elements to be inserted
+    /// in the given `Vec<T>`. The collection may reserve more space to avoid
+    /// frequent reallocations. After calling `reserve`, capacity will be
+    /// greater than or equal to `self.len() + additional`. Does nothing if
+    /// capacity is already sufficient.
+    ///
+    /// # Panics
+    ///
+    /// Panics if the new capacity exceeds `isize::MAX` bytes.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec![1];
+    /// vec.reserve(10);
+    /// assert!(vec.capacity() >= 11);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn reserve(&mut self, additional: usize) {
+        self.buf.reserve(self.len, additional);
+    }
+
+    /// Reserves the minimum capacity for exactly `additional` more elements to
+    /// be inserted in the given `Vec<T>`. After calling `reserve_exact`,
+    /// capacity will be greater than or equal to `self.len() + additional`.
+    /// Does nothing if the capacity is already sufficient.
+    ///
+    /// Note that the allocator may give the collection more space than it
+    /// requests. Therefore, capacity can not be relied upon to be precisely
+    /// minimal. Prefer [`reserve`] if future insertions are expected.
+    ///
+    /// [`reserve`]: Vec::reserve
+    ///
+    /// # Panics
+    ///
+    /// Panics if the new capacity exceeds `isize::MAX` bytes.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec![1];
+    /// vec.reserve_exact(10);
+    /// assert!(vec.capacity() >= 11);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn reserve_exact(&mut self, additional: usize) {
+        self.buf.reserve_exact(self.len, additional);
+    }
+
+    /// Tries to reserve capacity for at least `additional` more elements to be inserted
+    /// in the given `Vec<T>`. The collection may reserve more space to avoid
+    /// frequent reallocations. After calling `try_reserve`, capacity will be
+    /// greater than or equal to `self.len() + additional`. Does nothing if
+    /// capacity is already sufficient.
+    ///
+    /// # Errors
+    ///
+    /// If the capacity overflows, or the allocator reports a failure, then an error
+    /// is returned.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use std::collections::TryReserveError;
+    ///
+    /// fn process_data(data: &[u32]) -> Result<Vec<u32>, TryReserveError> {
+    ///     let mut output = Vec::new();
+    ///
+    ///     // Pre-reserve the memory, exiting if we can't
+    ///     output.try_reserve(data.len())?;
+    ///
+    ///     // Now we know this can't OOM in the middle of our complex work
+    ///     output.extend(data.iter().map(|&val| {
+    ///         val * 2 + 5 // very complicated
+    ///     }));
+    ///
+    ///     Ok(output)
+    /// }
+    /// # process_data(&[1, 2, 3]).expect("why is the test harness OOMing on 12 bytes?");
+    /// ```
+    #[stable(feature = "try_reserve", since = "1.57.0")]
+    pub fn try_reserve(&mut self, additional: usize) -> Result<(), TryReserveError> {
+        self.buf.try_reserve(self.len, additional)
+    }
+
+    /// Tries to reserve the minimum capacity for exactly `additional`
+    /// elements to be inserted in the given `Vec<T>`. After calling
+    /// `try_reserve_exact`, capacity will be greater than or equal to
+    /// `self.len() + additional` if it returns `Ok(())`.
+    /// Does nothing if the capacity is already sufficient.
+    ///
+    /// Note that the allocator may give the collection more space than it
+    /// requests. Therefore, capacity can not be relied upon to be precisely
+    /// minimal. Prefer [`try_reserve`] if future insertions are expected.
+    ///
+    /// [`try_reserve`]: Vec::try_reserve
+    ///
+    /// # Errors
+    ///
+    /// If the capacity overflows, or the allocator reports a failure, then an error
+    /// is returned.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use std::collections::TryReserveError;
+    ///
+    /// fn process_data(data: &[u32]) -> Result<Vec<u32>, TryReserveError> {
+    ///     let mut output = Vec::new();
+    ///
+    ///     // Pre-reserve the memory, exiting if we can't
+    ///     output.try_reserve_exact(data.len())?;
+    ///
+    ///     // Now we know this can't OOM in the middle of our complex work
+    ///     output.extend(data.iter().map(|&val| {
+    ///         val * 2 + 5 // very complicated
+    ///     }));
+    ///
+    ///     Ok(output)
+    /// }
+    /// # process_data(&[1, 2, 3]).expect("why is the test harness OOMing on 12 bytes?");
+    /// ```
+    #[stable(feature = "try_reserve", since = "1.57.0")]
+    pub fn try_reserve_exact(&mut self, additional: usize) -> Result<(), TryReserveError> {
+        self.buf.try_reserve_exact(self.len, additional)
+    }
+
+    /// Shrinks the capacity of the vector as much as possible.
+    ///
+    /// It will drop down as close as possible to the length but the allocator
+    /// may still inform the vector that there is space for a few more elements.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = Vec::with_capacity(10);
+    /// vec.extend([1, 2, 3]);
+    /// assert_eq!(vec.capacity(), 10);
+    /// vec.shrink_to_fit();
+    /// assert!(vec.capacity() >= 3);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn shrink_to_fit(&mut self) {
+        // The capacity is never less than the length, and there's nothing to do when
+        // they are equal, so we can avoid the panic case in `RawVec::shrink_to_fit`
+        // by only calling it with a greater capacity.
+        if self.capacity() > self.len {
+            self.buf.shrink_to_fit(self.len);
+        }
+    }
+
+    /// Shrinks the capacity of the vector with a lower bound.
+    ///
+    /// The capacity will remain at least as large as both the length
+    /// and the supplied value.
+    ///
+    /// If the current capacity is less than the lower limit, this is a no-op.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = Vec::with_capacity(10);
+    /// vec.extend([1, 2, 3]);
+    /// assert_eq!(vec.capacity(), 10);
+    /// vec.shrink_to(4);
+    /// assert!(vec.capacity() >= 4);
+    /// vec.shrink_to(0);
+    /// assert!(vec.capacity() >= 3);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[stable(feature = "shrink_to", since = "1.56.0")]
+    pub fn shrink_to(&mut self, min_capacity: usize) {
+        if self.capacity() > min_capacity {
+            self.buf.shrink_to_fit(cmp::max(self.len, min_capacity));
+        }
+    }
+
+    /// Converts the vector into [`Box<[T]>`][owned slice].
+    ///
+    /// Note that this will drop any excess capacity.
+    ///
+    /// [owned slice]: Box
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let v = vec![1, 2, 3];
+    ///
+    /// let slice = v.into_boxed_slice();
+    /// ```
+    ///
+    /// Any excess capacity is removed:
+    ///
+    /// ```
+    /// let mut vec = Vec::with_capacity(10);
+    /// vec.extend([1, 2, 3]);
+    ///
+    /// assert_eq!(vec.capacity(), 10);
+    /// let slice = vec.into_boxed_slice();
+    /// assert_eq!(slice.into_vec().capacity(), 3);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn into_boxed_slice(mut self) -> Box<[T], A> {
+        unsafe {
+            self.shrink_to_fit();
+            let me = ManuallyDrop::new(self);
+            let buf = ptr::read(&me.buf);
+            let len = me.len();
+            buf.into_box(len).assume_init()
+        }
+    }
+
+    /// Shortens the vector, keeping the first `len` elements and dropping
+    /// the rest.
+    ///
+    /// If `len` is greater than the vector's current length, this has no
+    /// effect.
+    ///
+    /// The [`drain`] method can emulate `truncate`, but causes the excess
+    /// elements to be returned instead of dropped.
+    ///
+    /// Note that this method has no effect on the allocated capacity
+    /// of the vector.
+    ///
+    /// # Examples
+    ///
+    /// Truncating a five element vector to two elements:
+    ///
+    /// ```
+    /// let mut vec = vec![1, 2, 3, 4, 5];
+    /// vec.truncate(2);
+    /// assert_eq!(vec, [1, 2]);
+    /// ```
+    ///
+    /// No truncation occurs when `len` is greater than the vector's current
+    /// length:
+    ///
+    /// ```
+    /// let mut vec = vec![1, 2, 3];
+    /// vec.truncate(8);
+    /// assert_eq!(vec, [1, 2, 3]);
+    /// ```
+    ///
+    /// Truncating when `len == 0` is equivalent to calling the [`clear`]
+    /// method.
+    ///
+    /// ```
+    /// let mut vec = vec![1, 2, 3];
+    /// vec.truncate(0);
+    /// assert_eq!(vec, []);
+    /// ```
+    ///
+    /// [`clear`]: Vec::clear
+    /// [`drain`]: Vec::drain
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn truncate(&mut self, len: usize) {
+        // This is safe because:
+        //
+        // * the slice passed to `drop_in_place` is valid; the `len > self.len`
+        //   case avoids creating an invalid slice, and
+        // * the `len` of the vector is shrunk before calling `drop_in_place`,
+        //   such that no value will be dropped twice in case `drop_in_place`
+        //   were to panic once (if it panics twice, the program aborts).
+        unsafe {
+            // Note: It's intentional that this is `>` and not `>=`.
+            //       Changing it to `>=` has negative performance
+            //       implications in some cases. See #78884 for more.
+            if len > self.len {
+                return;
+            }
+            let remaining_len = self.len - len;
+            let s = ptr::slice_from_raw_parts_mut(self.as_mut_ptr().add(len), remaining_len);
+            self.len = len;
+            ptr::drop_in_place(s);
+        }
+    }
+
+    /// Extracts a slice containing the entire vector.
+    ///
+    /// Equivalent to `&s[..]`.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use std::io::{self, Write};
+    /// let buffer = vec![1, 2, 3, 5, 8];
+    /// io::sink().write(buffer.as_slice()).unwrap();
+    /// ```
+    #[inline]
+    #[stable(feature = "vec_as_slice", since = "1.7.0")]
+    pub fn as_slice(&self) -> &[T] {
+        self
+    }
+
+    /// Extracts a mutable slice of the entire vector.
+    ///
+    /// Equivalent to `&mut s[..]`.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use std::io::{self, Read};
+    /// let mut buffer = vec![0; 3];
+    /// io::repeat(0b101).read_exact(buffer.as_mut_slice()).unwrap();
+    /// ```
+    #[inline]
+    #[stable(feature = "vec_as_slice", since = "1.7.0")]
+    pub fn as_mut_slice(&mut self) -> &mut [T] {
+        self
+    }
+
+    /// Returns a raw pointer to the vector's buffer.
+    ///
+    /// The caller must ensure that the vector outlives the pointer this
+    /// function returns, or else it will end up pointing to garbage.
+    /// Modifying the vector may cause its buffer to be reallocated,
+    /// which would also make any pointers to it invalid.
+    ///
+    /// The caller must also ensure that the memory the pointer (non-transitively) points to
+    /// is never written to (except inside an `UnsafeCell`) using this pointer or any pointer
+    /// derived from it. If you need to mutate the contents of the slice, use [`as_mut_ptr`].
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let x = vec![1, 2, 4];
+    /// let x_ptr = x.as_ptr();
+    ///
+    /// unsafe {
+    ///     for i in 0..x.len() {
+    ///         assert_eq!(*x_ptr.add(i), 1 << i);
+    ///     }
+    /// }
+    /// ```
+    ///
+    /// [`as_mut_ptr`]: Vec::as_mut_ptr
+    #[stable(feature = "vec_as_ptr", since = "1.37.0")]
+    #[inline]
+    pub fn as_ptr(&self) -> *const T {
+        // We shadow the slice method of the same name to avoid going through
+        // `deref`, which creates an intermediate reference.
+        let ptr = self.buf.ptr();
+        unsafe {
+            assume(!ptr.is_null());
+        }
+        ptr
+    }
+
+    /// Returns an unsafe mutable pointer to the vector's buffer.
+    ///
+    /// The caller must ensure that the vector outlives the pointer this
+    /// function returns, or else it will end up pointing to garbage.
+    /// Modifying the vector may cause its buffer to be reallocated,
+    /// which would also make any pointers to it invalid.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// // Allocate vector big enough for 4 elements.
+    /// let size = 4;
+    /// let mut x: Vec<i32> = Vec::with_capacity(size);
+    /// let x_ptr = x.as_mut_ptr();
+    ///
+    /// // Initialize elements via raw pointer writes, then set length.
+    /// unsafe {
+    ///     for i in 0..size {
+    ///         *x_ptr.add(i) = i as i32;
+    ///     }
+    ///     x.set_len(size);
+    /// }
+    /// assert_eq!(&*x, &[0, 1, 2, 3]);
+    /// ```
+    #[stable(feature = "vec_as_ptr", since = "1.37.0")]
+    #[inline]
+    pub fn as_mut_ptr(&mut self) -> *mut T {
+        // We shadow the slice method of the same name to avoid going through
+        // `deref_mut`, which creates an intermediate reference.
+        let ptr = self.buf.ptr();
+        unsafe {
+            assume(!ptr.is_null());
+        }
+        ptr
+    }
+
+    /// Returns a reference to the underlying allocator.
+    #[unstable(feature = "allocator_api", issue = "32838")]
+    #[inline]
+    pub fn allocator(&self) -> &A {
+        self.buf.allocator()
+    }
+
+    /// Forces the length of the vector to `new_len`.
+    ///
+    /// This is a low-level operation that maintains none of the normal
+    /// invariants of the type. Normally changing the length of a vector
+    /// is done using one of the safe operations instead, such as
+    /// [`truncate`], [`resize`], [`extend`], or [`clear`].
+    ///
+    /// [`truncate`]: Vec::truncate
+    /// [`resize`]: Vec::resize
+    /// [`extend`]: Extend::extend
+    /// [`clear`]: Vec::clear
+    ///
+    /// # Safety
+    ///
+    /// - `new_len` must be less than or equal to [`capacity()`].
+    /// - The elements at `old_len..new_len` must be initialized.
+    ///
+    /// [`capacity()`]: Vec::capacity
+    ///
+    /// # Examples
+    ///
+    /// This method can be useful for situations in which the vector
+    /// is serving as a buffer for other code, particularly over FFI:
+    ///
+    /// ```no_run
+    /// # #![allow(dead_code)]
+    /// # // This is just a minimal skeleton for the doc example;
+    /// # // don't use this as a starting point for a real library.
+    /// # pub struct StreamWrapper { strm: *mut std::ffi::c_void }
+    /// # const Z_OK: i32 = 0;
+    /// # extern "C" {
+    /// #     fn deflateGetDictionary(
+    /// #         strm: *mut std::ffi::c_void,
+    /// #         dictionary: *mut u8,
+    /// #         dictLength: *mut usize,
+    /// #     ) -> i32;
+    /// # }
+    /// # impl StreamWrapper {
+    /// pub fn get_dictionary(&self) -> Option<Vec<u8>> {
+    ///     // Per the FFI method's docs, "32768 bytes is always enough".
+    ///     let mut dict = Vec::with_capacity(32_768);
+    ///     let mut dict_length = 0;
+    ///     // SAFETY: When `deflateGetDictionary` returns `Z_OK`, it holds that:
+    ///     // 1. `dict_length` elements were initialized.
+    ///     // 2. `dict_length` <= the capacity (32_768)
+    ///     // which makes `set_len` safe to call.
+    ///     unsafe {
+    ///         // Make the FFI call...
+    ///         let r = deflateGetDictionary(self.strm, dict.as_mut_ptr(), &mut dict_length);
+    ///         if r == Z_OK {
+    ///             // ...and update the length to what was initialized.
+    ///             dict.set_len(dict_length);
+    ///             Some(dict)
+    ///         } else {
+    ///             None
+    ///         }
+    ///     }
+    /// }
+    /// # }
+    /// ```
+    ///
+    /// While the following example is sound, there is a memory leak since
+    /// the inner vectors were not freed prior to the `set_len` call:
+    ///
+    /// ```
+    /// let mut vec = vec![vec![1, 0, 0],
+    ///                    vec![0, 1, 0],
+    ///                    vec![0, 0, 1]];
+    /// // SAFETY:
+    /// // 1. `old_len..0` is empty so no elements need to be initialized.
+    /// // 2. `0 <= capacity` always holds whatever `capacity` is.
+    /// unsafe {
+    ///     vec.set_len(0);
+    /// }
+    /// ```
+    ///
+    /// Normally, here, one would use [`clear`] instead to correctly drop
+    /// the contents and thus not leak memory.
+    #[inline]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub unsafe fn set_len(&mut self, new_len: usize) {
+        debug_assert!(new_len <= self.capacity());
+
+        self.len = new_len;
+    }
+
+    /// Removes an element from the vector and returns it.
+    ///
+    /// The removed element is replaced by the last element of the vector.
+    ///
+    /// This does not preserve ordering, but is *O*(1).
+    /// If you need to preserve the element order, use [`remove`] instead.
+    ///
+    /// [`remove`]: Vec::remove
+    ///
+    /// # Panics
+    ///
+    /// Panics if `index` is out of bounds.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = vec!["foo", "bar", "baz", "qux"];
+    ///
+    /// assert_eq!(v.swap_remove(1), "bar");
+    /// assert_eq!(v, ["foo", "qux", "baz"]);
+    ///
+    /// assert_eq!(v.swap_remove(0), "foo");
+    /// assert_eq!(v, ["baz", "qux"]);
+    /// ```
+    #[inline]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn swap_remove(&mut self, index: usize) -> T {
+        #[cold]
+        #[inline(never)]
+        fn assert_failed(index: usize, len: usize) -> ! {
+            panic!("swap_remove index (is {index}) should be < len (is {len})");
+        }
+
+        let len = self.len();
+        if index >= len {
+            assert_failed(index, len);
+        }
+        unsafe {
+            // We replace self[index] with the last element. Note that if the
+            // bounds check above succeeds there must be a last element (which
+            // can be self[index] itself).
+            let value = ptr::read(self.as_ptr().add(index));
+            let base_ptr = self.as_mut_ptr();
+            ptr::copy(base_ptr.add(len - 1), base_ptr.add(index), 1);
+            self.set_len(len - 1);
+            value
+        }
+    }
+
+    /// Inserts an element at position `index` within the vector, shifting all
+    /// elements after it to the right.
+    ///
+    /// # Panics
+    ///
+    /// Panics if `index > len`.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec![1, 2, 3];
+    /// vec.insert(1, 4);
+    /// assert_eq!(vec, [1, 4, 2, 3]);
+    /// vec.insert(4, 5);
+    /// assert_eq!(vec, [1, 4, 2, 3, 5]);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn insert(&mut self, index: usize, element: T) {
+        #[cold]
+        #[inline(never)]
+        fn assert_failed(index: usize, len: usize) -> ! {
+            panic!("insertion index (is {index}) should be <= len (is {len})");
+        }
+
+        let len = self.len();
+        if index > len {
+            assert_failed(index, len);
+        }
+
+        // space for the new element
+        if len == self.buf.capacity() {
+            self.reserve(1);
+        }
+
+        unsafe {
+            // infallible
+            // The spot to put the new value
+            {
+                let p = self.as_mut_ptr().add(index);
+                // Shift everything over to make space. (Duplicating the
+                // `index`th element into two consecutive places.)
+                ptr::copy(p, p.offset(1), len - index);
+                // Write it in, overwriting the first copy of the `index`th
+                // element.
+                ptr::write(p, element);
+            }
+            self.set_len(len + 1);
+        }
+    }
+
+    /// Removes and returns the element at position `index` within the vector,
+    /// shifting all elements after it to the left.
+    ///
+    /// Note: Because this shifts over the remaining elements, it has a
+    /// worst-case performance of *O*(*n*). If you don't need the order of elements
+    /// to be preserved, use [`swap_remove`] instead. If you'd like to remove
+    /// elements from the beginning of the `Vec`, consider using
+    /// [`VecDeque::pop_front`] instead.
+    ///
+    /// [`swap_remove`]: Vec::swap_remove
+    /// [`VecDeque::pop_front`]: crate::collections::VecDeque::pop_front
+    ///
+    /// # Panics
+    ///
+    /// Panics if `index` is out of bounds.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = vec![1, 2, 3];
+    /// assert_eq!(v.remove(1), 2);
+    /// assert_eq!(v, [1, 3]);
+    /// ```
+    #[stable(feature = "rust1", since = "1.0.0")]
+    #[track_caller]
+    pub fn remove(&mut self, index: usize) -> T {
+        #[cold]
+        #[inline(never)]
+        #[track_caller]
+        fn assert_failed(index: usize, len: usize) -> ! {
+            panic!("removal index (is {index}) should be < len (is {len})");
+        }
+
+        let len = self.len();
+        if index >= len {
+            assert_failed(index, len);
+        }
+        unsafe {
+            // infallible
+            let ret;
+            {
+                // the place we are taking from.
+                let ptr = self.as_mut_ptr().add(index);
+                // copy it out, unsafely having a copy of the value on
+                // the stack and in the vector at the same time.
+                ret = ptr::read(ptr);
+
+                // Shift everything down to fill in that spot.
+                ptr::copy(ptr.offset(1), ptr, len - index - 1);
+            }
+            self.set_len(len - 1);
+            ret
+        }
+    }
+
+    /// Retains only the elements specified by the predicate.
+    ///
+    /// In other words, remove all elements `e` for which `f(&e)` returns `false`.
+    /// This method operates in place, visiting each element exactly once in the
+    /// original order, and preserves the order of the retained elements.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec![1, 2, 3, 4];
+    /// vec.retain(|&x| x % 2 == 0);
+    /// assert_eq!(vec, [2, 4]);
+    /// ```
+    ///
+    /// Because the elements are visited exactly once in the original order,
+    /// external state may be used to decide which elements to keep.
+    ///
+    /// ```
+    /// let mut vec = vec![1, 2, 3, 4, 5];
+    /// let keep = [false, true, true, false, true];
+    /// let mut iter = keep.iter();
+    /// vec.retain(|_| *iter.next().unwrap());
+    /// assert_eq!(vec, [2, 3, 5]);
+    /// ```
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn retain<F>(&mut self, mut f: F)
+    where
+        F: FnMut(&T) -> bool,
+    {
+        self.retain_mut(|elem| f(elem));
+    }
+
+    /// Retains only the elements specified by the predicate, passing a mutable reference to it.
+    ///
+    /// In other words, remove all elements `e` such that `f(&mut e)` returns `false`.
+    /// This method operates in place, visiting each element exactly once in the
+    /// original order, and preserves the order of the retained elements.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec![1, 2, 3, 4];
+    /// vec.retain_mut(|x| if *x > 3 {
+    ///     false
+    /// } else {
+    ///     *x += 1;
+    ///     true
+    /// });
+    /// assert_eq!(vec, [2, 3, 4]);
+    /// ```
+    #[stable(feature = "vec_retain_mut", since = "1.61.0")]
+    pub fn retain_mut<F>(&mut self, mut f: F)
+    where
+        F: FnMut(&mut T) -> bool,
+    {
+        let original_len = self.len();
+        // Avoid double drop if the drop guard is not executed,
+        // since we may make some holes during the process.
+        unsafe { self.set_len(0) };
+
+        // Vec: [Kept, Kept, Hole, Hole, Hole, Hole, Unchecked, Unchecked]
+        //      |<-              processed len   ->| ^- next to check
+        //                  |<-  deleted cnt     ->|
+        //      |<-              original_len                          ->|
+        // Kept: Elements which predicate returns true on.
+        // Hole: Moved or dropped element slot.
+        // Unchecked: Unchecked valid elements.
+        //
+        // This drop guard will be invoked when predicate or `drop` of element panicked.
+        // It shifts unchecked elements to cover holes and `set_len` to the correct length.
+        // In cases when predicate and `drop` never panick, it will be optimized out.
+        struct BackshiftOnDrop<'a, T, A: Allocator> {
+            v: &'a mut Vec<T, A>,
+            processed_len: usize,
+            deleted_cnt: usize,
+            original_len: usize,
+        }
+
+        impl<T, A: Allocator> Drop for BackshiftOnDrop<'_, T, A> {
+            fn drop(&mut self) {
+                if self.deleted_cnt > 0 {
+                    // SAFETY: Trailing unchecked items must be valid since we never touch them.
+                    unsafe {
+                        ptr::copy(
+                            self.v.as_ptr().add(self.processed_len),
+                            self.v.as_mut_ptr().add(self.processed_len - self.deleted_cnt),
+                            self.original_len - self.processed_len,
+                        );
+                    }
+                }
+                // SAFETY: After filling holes, all items are in contiguous memory.
+                unsafe {
+                    self.v.set_len(self.original_len - self.deleted_cnt);
+                }
+            }
+        }
+
+        let mut g = BackshiftOnDrop { v: self, processed_len: 0, deleted_cnt: 0, original_len };
+
+        fn process_loop<F, T, A: Allocator, const DELETED: bool>(
+            original_len: usize,
+            f: &mut F,
+            g: &mut BackshiftOnDrop<'_, T, A>,
+        ) where
+            F: FnMut(&mut T) -> bool,
+        {
+            while g.processed_len != original_len {
+                // SAFETY: Unchecked element must be valid.
+                let cur = unsafe { &mut *g.v.as_mut_ptr().add(g.processed_len) };
+                if !f(cur) {
+                    // Advance early to avoid double drop if `drop_in_place` panicked.
+                    g.processed_len += 1;
+                    g.deleted_cnt += 1;
+                    // SAFETY: We never touch this element again after dropped.
+                    unsafe { ptr::drop_in_place(cur) };
+                    // We already advanced the counter.
+                    if DELETED {
+                        continue;
+                    } else {
+                        break;
+                    }
+                }
+                if DELETED {
+                    // SAFETY: `deleted_cnt` > 0, so the hole slot must not overlap with current element.
+                    // We use copy for move, and never touch this element again.
+                    unsafe {
+                        let hole_slot = g.v.as_mut_ptr().add(g.processed_len - g.deleted_cnt);
+                        ptr::copy_nonoverlapping(cur, hole_slot, 1);
+                    }
+                }
+                g.processed_len += 1;
+            }
+        }
+
+        // Stage 1: Nothing was deleted.
+        process_loop::<F, T, A, false>(original_len, &mut f, &mut g);
+
+        // Stage 2: Some elements were deleted.
+        process_loop::<F, T, A, true>(original_len, &mut f, &mut g);
+
+        // All item are processed. This can be optimized to `set_len` by LLVM.
+        drop(g);
+    }
+
+    /// Removes all but the first of consecutive elements in the vector that resolve to the same
+    /// key.
+    ///
+    /// If the vector is sorted, this removes all duplicates.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec![10, 20, 21, 30, 20];
+    ///
+    /// vec.dedup_by_key(|i| *i / 10);
+    ///
+    /// assert_eq!(vec, [10, 20, 30, 20]);
+    /// ```
+    #[stable(feature = "dedup_by", since = "1.16.0")]
+    #[inline]
+    pub fn dedup_by_key<F, K>(&mut self, mut key: F)
+    where
+        F: FnMut(&mut T) -> K,
+        K: PartialEq,
+    {
+        self.dedup_by(|a, b| key(a) == key(b))
+    }
+
+    /// Removes all but the first of consecutive elements in the vector satisfying a given equality
+    /// relation.
+    ///
+    /// The `same_bucket` function is passed references to two elements from the vector and
+    /// must determine if the elements compare equal. The elements are passed in opposite order
+    /// from their order in the slice, so if `same_bucket(a, b)` returns `true`, `a` is removed.
+    ///
+    /// If the vector is sorted, this removes all duplicates.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec!["foo", "bar", "Bar", "baz", "bar"];
+    ///
+    /// vec.dedup_by(|a, b| a.eq_ignore_ascii_case(b));
+    ///
+    /// assert_eq!(vec, ["foo", "bar", "baz", "bar"]);
+    /// ```
+    #[stable(feature = "dedup_by", since = "1.16.0")]
+    pub fn dedup_by<F>(&mut self, mut same_bucket: F)
+    where
+        F: FnMut(&mut T, &mut T) -> bool,
+    {
+        let len = self.len();
+        if len <= 1 {
+            return;
+        }
+
+        /* INVARIANT: vec.len() > read >= write > write-1 >= 0 */
+        struct FillGapOnDrop<'a, T, A: core::alloc::Allocator> {
+            /* Offset of the element we want to check if it is duplicate */
+            read: usize,
+
+            /* Offset of the place where we want to place the non-duplicate
+             * when we find it. */
+            write: usize,
+
+            /* The Vec that would need correction if `same_bucket` panicked */
+            vec: &'a mut Vec<T, A>,
+        }
+
+        impl<'a, T, A: core::alloc::Allocator> Drop for FillGapOnDrop<'a, T, A> {
+            fn drop(&mut self) {
+                /* This code gets executed when `same_bucket` panics */
+
+                /* SAFETY: invariant guarantees that `read - write`
+                 * and `len - read` never overflow and that the copy is always
+                 * in-bounds. */
+                unsafe {
+                    let ptr = self.vec.as_mut_ptr();
+                    let len = self.vec.len();
+
+                    /* How many items were left when `same_bucket` panicked.
+                     * Basically vec[read..].len() */
+                    let items_left = len.wrapping_sub(self.read);
+
+                    /* Pointer to first item in vec[write..write+items_left] slice */
+                    let dropped_ptr = ptr.add(self.write);
+                    /* Pointer to first item in vec[read..] slice */
+                    let valid_ptr = ptr.add(self.read);
+
+                    /* Copy `vec[read..]` to `vec[write..write+items_left]`.
+                     * The slices can overlap, so `copy_nonoverlapping` cannot be used */
+                    ptr::copy(valid_ptr, dropped_ptr, items_left);
+
+                    /* How many items have been already dropped
+                     * Basically vec[read..write].len() */
+                    let dropped = self.read.wrapping_sub(self.write);
+
+                    self.vec.set_len(len - dropped);
+                }
+            }
+        }
+
+        let mut gap = FillGapOnDrop { read: 1, write: 1, vec: self };
+        let ptr = gap.vec.as_mut_ptr();
+
+        /* Drop items while going through Vec, it should be more efficient than
+         * doing slice partition_dedup + truncate */
+
+        /* SAFETY: Because of the invariant, read_ptr, prev_ptr and write_ptr
+         * are always in-bounds and read_ptr never aliases prev_ptr */
+        unsafe {
+            while gap.read < len {
+                let read_ptr = ptr.add(gap.read);
+                let prev_ptr = ptr.add(gap.write.wrapping_sub(1));
+
+                if same_bucket(&mut *read_ptr, &mut *prev_ptr) {
+                    // Increase `gap.read` now since the drop may panic.
+                    gap.read += 1;
+                    /* We have found duplicate, drop it in-place */
+                    ptr::drop_in_place(read_ptr);
+                } else {
+                    let write_ptr = ptr.add(gap.write);
+
+                    /* Because `read_ptr` can be equal to `write_ptr`, we either
+                     * have to use `copy` or conditional `copy_nonoverlapping`.
+                     * Looks like the first option is faster. */
+                    ptr::copy(read_ptr, write_ptr, 1);
+
+                    /* We have filled that place, so go further */
+                    gap.write += 1;
+                    gap.read += 1;
+                }
+            }
+
+            /* Technically we could let `gap` clean up with its Drop, but
+             * when `same_bucket` is guaranteed to not panic, this bloats a little
+             * the codegen, so we just do it manually */
+            gap.vec.set_len(gap.write);
+            mem::forget(gap);
+        }
+    }
+
+    /// Appends an element to the back of a collection.
+    ///
+    /// # Panics
+    ///
+    /// Panics if the new capacity exceeds `isize::MAX` bytes.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec![1, 2];
+    /// vec.push(3);
+    /// assert_eq!(vec, [1, 2, 3]);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[inline]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn push(&mut self, value: T) {
+        // This will panic or abort if we would allocate > isize::MAX bytes
+        // or if the length increment would overflow for zero-sized types.
+        if self.len == self.buf.capacity() {
+            self.buf.reserve_for_push(self.len);
+        }
+        unsafe {
+            let end = self.as_mut_ptr().add(self.len);
+            ptr::write(end, value);
+            self.len += 1;
+        }
+    }
+
+    /// Tries to append an element to the back of a collection.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec![1, 2];
+    /// vec.try_push(3).unwrap();
+    /// assert_eq!(vec, [1, 2, 3]);
+    /// ```
+    #[inline]
+    #[stable(feature = "kernel", since = "1.0.0")]
+    pub fn try_push(&mut self, value: T) -> Result<(), TryReserveError> {
+        if self.len == self.buf.capacity() {
+            self.buf.try_reserve_for_push(self.len)?;
+        }
+        unsafe {
+            let end = self.as_mut_ptr().add(self.len);
+            ptr::write(end, value);
+            self.len += 1;
+        }
+        Ok(())
+    }
+
+    /// Removes the last element from a vector and returns it, or [`None`] if it
+    /// is empty.
+    ///
+    /// If you'd like to pop the first element, consider using
+    /// [`VecDeque::pop_front`] instead.
+    ///
+    /// [`VecDeque::pop_front`]: crate::collections::VecDeque::pop_front
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec![1, 2, 3];
+    /// assert_eq!(vec.pop(), Some(3));
+    /// assert_eq!(vec, [1, 2]);
+    /// ```
+    #[inline]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn pop(&mut self) -> Option<T> {
+        if self.len == 0 {
+            None
+        } else {
+            unsafe {
+                self.len -= 1;
+                Some(ptr::read(self.as_ptr().add(self.len())))
+            }
+        }
+    }
+
+    /// Moves all the elements of `other` into `self`, leaving `other` empty.
+    ///
+    /// # Panics
+    ///
+    /// Panics if the number of elements in the vector overflows a `usize`.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec![1, 2, 3];
+    /// let mut vec2 = vec![4, 5, 6];
+    /// vec.append(&mut vec2);
+    /// assert_eq!(vec, [1, 2, 3, 4, 5, 6]);
+    /// assert_eq!(vec2, []);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[inline]
+    #[stable(feature = "append", since = "1.4.0")]
+    pub fn append(&mut self, other: &mut Self) {
+        unsafe {
+            self.append_elements(other.as_slice() as _);
+            other.set_len(0);
+        }
+    }
+
+    /// Appends elements to `self` from other buffer.
+    #[cfg(not(no_global_oom_handling))]
+    #[inline]
+    unsafe fn append_elements(&mut self, other: *const [T]) {
+        let count = unsafe { (*other).len() };
+        self.reserve(count);
+        let len = self.len();
+        unsafe { ptr::copy_nonoverlapping(other as *const T, self.as_mut_ptr().add(len), count) };
+        self.len += count;
+    }
+
+    /// Removes the specified range from the vector in bulk, returning all
+    /// removed elements as an iterator. If the iterator is dropped before
+    /// being fully consumed, it drops the remaining removed elements.
+    ///
+    /// The returned iterator keeps a mutable borrow on the vector to optimize
+    /// its implementation.
+    ///
+    /// # Panics
+    ///
+    /// Panics if the starting point is greater than the end point or if
+    /// the end point is greater than the length of the vector.
+    ///
+    /// # Leaking
+    ///
+    /// If the returned iterator goes out of scope without being dropped (due to
+    /// [`mem::forget`], for example), the vector may have lost and leaked
+    /// elements arbitrarily, including elements outside the range.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = vec![1, 2, 3];
+    /// let u: Vec<_> = v.drain(1..).collect();
+    /// assert_eq!(v, &[1]);
+    /// assert_eq!(u, &[2, 3]);
+    ///
+    /// // A full range clears the vector, like `clear()` does
+    /// v.drain(..);
+    /// assert_eq!(v, &[]);
+    /// ```
+    #[stable(feature = "drain", since = "1.6.0")]
+    pub fn drain<R>(&mut self, range: R) -> Drain<'_, T, A>
+    where
+        R: RangeBounds<usize>,
+    {
+        // Memory safety
+        //
+        // When the Drain is first created, it shortens the length of
+        // the source vector to make sure no uninitialized or moved-from elements
+        // are accessible at all if the Drain's destructor never gets to run.
+        //
+        // Drain will ptr::read out the values to remove.
+        // When finished, remaining tail of the vec is copied back to cover
+        // the hole, and the vector length is restored to the new length.
+        //
+        let len = self.len();
+        let Range { start, end } = slice::range(range, ..len);
+
+        unsafe {
+            // set self.vec length's to start, to be safe in case Drain is leaked
+            self.set_len(start);
+            // Use the borrow in the IterMut to indicate borrowing behavior of the
+            // whole Drain iterator (like &mut T).
+            let range_slice = slice::from_raw_parts_mut(self.as_mut_ptr().add(start), end - start);
+            Drain {
+                tail_start: end,
+                tail_len: len - end,
+                iter: range_slice.iter(),
+                vec: NonNull::from(self),
+            }
+        }
+    }
+
+    /// Clears the vector, removing all values.
+    ///
+    /// Note that this method has no effect on the allocated capacity
+    /// of the vector.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = vec![1, 2, 3];
+    ///
+    /// v.clear();
+    ///
+    /// assert!(v.is_empty());
+    /// ```
+    #[inline]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn clear(&mut self) {
+        let elems: *mut [T] = self.as_mut_slice();
+
+        // SAFETY:
+        // - `elems` comes directly from `as_mut_slice` and is therefore valid.
+        // - Setting `self.len` before calling `drop_in_place` means that,
+        //   if an element's `Drop` impl panics, the vector's `Drop` impl will
+        //   do nothing (leaking the rest of the elements) instead of dropping
+        //   some twice.
+        unsafe {
+            self.len = 0;
+            ptr::drop_in_place(elems);
+        }
+    }
+
+    /// Returns the number of elements in the vector, also referred to
+    /// as its 'length'.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let a = vec![1, 2, 3];
+    /// assert_eq!(a.len(), 3);
+    /// ```
+    #[inline]
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn len(&self) -> usize {
+        self.len
+    }
+
+    /// Returns `true` if the vector contains no elements.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = Vec::new();
+    /// assert!(v.is_empty());
+    ///
+    /// v.push(1);
+    /// assert!(!v.is_empty());
+    /// ```
+    #[stable(feature = "rust1", since = "1.0.0")]
+    pub fn is_empty(&self) -> bool {
+        self.len() == 0
+    }
+
+    /// Splits the collection into two at the given index.
+    ///
+    /// Returns a newly allocated vector containing the elements in the range
+    /// `[at, len)`. After the call, the original vector will be left containing
+    /// the elements `[0, at)` with its previous capacity unchanged.
+    ///
+    /// # Panics
+    ///
+    /// Panics if `at > len`.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec![1, 2, 3];
+    /// let vec2 = vec.split_off(1);
+    /// assert_eq!(vec, [1]);
+    /// assert_eq!(vec2, [2, 3]);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[inline]
+    #[must_use = "use `.truncate()` if you don't need the other half"]
+    #[stable(feature = "split_off", since = "1.4.0")]
+    pub fn split_off(&mut self, at: usize) -> Self
+    where
+        A: Clone,
+    {
+        #[cold]
+        #[inline(never)]
+        fn assert_failed(at: usize, len: usize) -> ! {
+            panic!("`at` split index (is {at}) should be <= len (is {len})");
+        }
+
+        if at > self.len() {
+            assert_failed(at, self.len());
+        }
+
+        if at == 0 {
+            // the new vector can take over the original buffer and avoid the copy
+            return mem::replace(
+                self,
+                Vec::with_capacity_in(self.capacity(), self.allocator().clone()),
+            );
+        }
+
+        let other_len = self.len - at;
+        let mut other = Vec::with_capacity_in(other_len, self.allocator().clone());
+
+        // Unsafely `set_len` and copy items to `other`.
+        unsafe {
+            self.set_len(at);
+            other.set_len(other_len);
+
+            ptr::copy_nonoverlapping(self.as_ptr().add(at), other.as_mut_ptr(), other.len());
+        }
+        other
+    }
+
+    /// Resizes the `Vec` in-place so that `len` is equal to `new_len`.
+    ///
+    /// If `new_len` is greater than `len`, the `Vec` is extended by the
+    /// difference, with each additional slot filled with the result of
+    /// calling the closure `f`. The return values from `f` will end up
+    /// in the `Vec` in the order they have been generated.
+    ///
+    /// If `new_len` is less than `len`, the `Vec` is simply truncated.
+    ///
+    /// This method uses a closure to create new values on every push. If
+    /// you'd rather [`Clone`] a given value, use [`Vec::resize`]. If you
+    /// want to use the [`Default`] trait to generate values, you can
+    /// pass [`Default::default`] as the second argument.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec![1, 2, 3];
+    /// vec.resize_with(5, Default::default);
+    /// assert_eq!(vec, [1, 2, 3, 0, 0]);
+    ///
+    /// let mut vec = vec![];
+    /// let mut p = 1;
+    /// vec.resize_with(4, || { p *= 2; p });
+    /// assert_eq!(vec, [2, 4, 8, 16]);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[stable(feature = "vec_resize_with", since = "1.33.0")]
+    pub fn resize_with<F>(&mut self, new_len: usize, f: F)
+    where
+        F: FnMut() -> T,
+    {
+        let len = self.len();
+        if new_len > len {
+            self.extend_with(new_len - len, ExtendFunc(f));
+        } else {
+            self.truncate(new_len);
+        }
+    }
+
+    /// Consumes and leaks the `Vec`, returning a mutable reference to the contents,
+    /// `&'a mut [T]`. Note that the type `T` must outlive the chosen lifetime
+    /// `'a`. If the type has only static references, or none at all, then this
+    /// may be chosen to be `'static`.
+    ///
+    /// As of Rust 1.57, this method does not reallocate or shrink the `Vec`,
+    /// so the leaked allocation may include unused capacity that is not part
+    /// of the returned slice.
+    ///
+    /// This function is mainly useful for data that lives for the remainder of
+    /// the program's life. Dropping the returned reference will cause a memory
+    /// leak.
+    ///
+    /// # Examples
+    ///
+    /// Simple usage:
+    ///
+    /// ```
+    /// let x = vec![1, 2, 3];
+    /// let static_ref: &'static mut [usize] = x.leak();
+    /// static_ref[0] += 1;
+    /// assert_eq!(static_ref, &[2, 2, 3]);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[stable(feature = "vec_leak", since = "1.47.0")]
+    #[inline]
+    pub fn leak<'a>(self) -> &'a mut [T]
+    where
+        A: 'a,
+    {
+        let mut me = ManuallyDrop::new(self);
+        unsafe { slice::from_raw_parts_mut(me.as_mut_ptr(), me.len) }
+    }
+
+    /// Returns the remaining spare capacity of the vector as a slice of
+    /// `MaybeUninit<T>`.
+    ///
+    /// The returned slice can be used to fill the vector with data (e.g. by
+    /// reading from a file) before marking the data as initialized using the
+    /// [`set_len`] method.
+    ///
+    /// [`set_len`]: Vec::set_len
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// // Allocate vector big enough for 10 elements.
+    /// let mut v = Vec::with_capacity(10);
+    ///
+    /// // Fill in the first 3 elements.
+    /// let uninit = v.spare_capacity_mut();
+    /// uninit[0].write(0);
+    /// uninit[1].write(1);
+    /// uninit[2].write(2);
+    ///
+    /// // Mark the first 3 elements of the vector as being initialized.
+    /// unsafe {
+    ///     v.set_len(3);
+    /// }
+    ///
+    /// assert_eq!(&v, &[0, 1, 2]);
+    /// ```
+    #[stable(feature = "vec_spare_capacity", since = "1.60.0")]
+    #[inline]
+    pub fn spare_capacity_mut(&mut self) -> &mut [MaybeUninit<T>] {
+        // Note:
+        // This method is not implemented in terms of `split_at_spare_mut`,
+        // to prevent invalidation of pointers to the buffer.
+        unsafe {
+            slice::from_raw_parts_mut(
+                self.as_mut_ptr().add(self.len) as *mut MaybeUninit<T>,
+                self.buf.capacity() - self.len,
+            )
+        }
+    }
+
+    /// Returns vector content as a slice of `T`, along with the remaining spare
+    /// capacity of the vector as a slice of `MaybeUninit<T>`.
+    ///
+    /// The returned spare capacity slice can be used to fill the vector with data
+    /// (e.g. by reading from a file) before marking the data as initialized using
+    /// the [`set_len`] method.
+    ///
+    /// [`set_len`]: Vec::set_len
+    ///
+    /// Note that this is a low-level API, which should be used with care for
+    /// optimization purposes. If you need to append data to a `Vec`
+    /// you can use [`push`], [`extend`], [`extend_from_slice`],
+    /// [`extend_from_within`], [`insert`], [`append`], [`resize`] or
+    /// [`resize_with`], depending on your exact needs.
+    ///
+    /// [`push`]: Vec::push
+    /// [`extend`]: Vec::extend
+    /// [`extend_from_slice`]: Vec::extend_from_slice
+    /// [`extend_from_within`]: Vec::extend_from_within
+    /// [`insert`]: Vec::insert
+    /// [`append`]: Vec::append
+    /// [`resize`]: Vec::resize
+    /// [`resize_with`]: Vec::resize_with
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(vec_split_at_spare)]
+    ///
+    /// let mut v = vec![1, 1, 2];
+    ///
+    /// // Reserve additional space big enough for 10 elements.
+    /// v.reserve(10);
+    ///
+    /// let (init, uninit) = v.split_at_spare_mut();
+    /// let sum = init.iter().copied().sum::<u32>();
+    ///
+    /// // Fill in the next 4 elements.
+    /// uninit[0].write(sum);
+    /// uninit[1].write(sum * 2);
+    /// uninit[2].write(sum * 3);
+    /// uninit[3].write(sum * 4);
+    ///
+    /// // Mark the 4 elements of the vector as being initialized.
+    /// unsafe {
+    ///     let len = v.len();
+    ///     v.set_len(len + 4);
+    /// }
+    ///
+    /// assert_eq!(&v, &[1, 1, 2, 4, 8, 12, 16]);
+    /// ```
+    #[unstable(feature = "vec_split_at_spare", issue = "81944")]
+    #[inline]
+    pub fn split_at_spare_mut(&mut self) -> (&mut [T], &mut [MaybeUninit<T>]) {
+        // SAFETY:
+        // - len is ignored and so never changed
+        let (init, spare, _) = unsafe { self.split_at_spare_mut_with_len() };
+        (init, spare)
+    }
+
+    /// Safety: changing returned .2 (&mut usize) is considered the same as calling `.set_len(_)`.
+    ///
+    /// This method provides unique access to all vec parts at once in `extend_from_within`.
+    unsafe fn split_at_spare_mut_with_len(
+        &mut self,
+    ) -> (&mut [T], &mut [MaybeUninit<T>], &mut usize) {
+        let ptr = self.as_mut_ptr();
+        // SAFETY:
+        // - `ptr` is guaranteed to be valid for `self.len` elements
+        // - but the allocation extends out to `self.buf.capacity()` elements, possibly
+        // uninitialized
+        let spare_ptr = unsafe { ptr.add(self.len) };
+        let spare_ptr = spare_ptr.cast::<MaybeUninit<T>>();
+        let spare_len = self.buf.capacity() - self.len;
+
+        // SAFETY:
+        // - `ptr` is guaranteed to be valid for `self.len` elements
+        // - `spare_ptr` is pointing one element past the buffer, so it doesn't overlap with `initialized`
+        unsafe {
+            let initialized = slice::from_raw_parts_mut(ptr, self.len);
+            let spare = slice::from_raw_parts_mut(spare_ptr, spare_len);
+
+            (initialized, spare, &mut self.len)
+        }
+    }
+}
+
+impl<T: Clone, A: Allocator> Vec<T, A> {
+    /// Resizes the `Vec` in-place so that `len` is equal to `new_len`.
+    ///
+    /// If `new_len` is greater than `len`, the `Vec` is extended by the
+    /// difference, with each additional slot filled with `value`.
+    /// If `new_len` is less than `len`, the `Vec` is simply truncated.
+    ///
+    /// This method requires `T` to implement [`Clone`],
+    /// in order to be able to clone the passed value.
+    /// If you need more flexibility (or want to rely on [`Default`] instead of
+    /// [`Clone`]), use [`Vec::resize_with`].
+    /// If you only need to resize to a smaller size, use [`Vec::truncate`].
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec!["hello"];
+    /// vec.resize(3, "world");
+    /// assert_eq!(vec, ["hello", "world", "world"]);
+    ///
+    /// let mut vec = vec![1, 2, 3, 4];
+    /// vec.resize(2, 0);
+    /// assert_eq!(vec, [1, 2]);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[stable(feature = "vec_resize", since = "1.5.0")]
+    pub fn resize(&mut self, new_len: usize, value: T) {
+        let len = self.len();
+
+        if new_len > len {
+            self.extend_with(new_len - len, ExtendElement(value))
+        } else {
+            self.truncate(new_len);
+        }
+    }
+
+    /// Clones and appends all elements in a slice to the `Vec`.
+    ///
+    /// Iterates over the slice `other`, clones each element, and then appends
+    /// it to this `Vec`. The `other` slice is traversed in-order.
+    ///
+    /// Note that this function is same as [`extend`] except that it is
+    /// specialized to work with slices instead. If and when Rust gets
+    /// specialization this function will likely be deprecated (but still
+    /// available).
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec![1];
+    /// vec.extend_from_slice(&[2, 3, 4]);
+    /// assert_eq!(vec, [1, 2, 3, 4]);
+    /// ```
+    ///
+    /// [`extend`]: Vec::extend
+    #[cfg(not(no_global_oom_handling))]
+    #[stable(feature = "vec_extend_from_slice", since = "1.6.0")]
+    pub fn extend_from_slice(&mut self, other: &[T]) {
+        self.spec_extend(other.iter())
+    }
+
+    /// Copies elements from `src` range to the end of the vector.
+    ///
+    /// # Panics
+    ///
+    /// Panics if the starting point is greater than the end point or if
+    /// the end point is greater than the length of the vector.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec![0, 1, 2, 3, 4];
+    ///
+    /// vec.extend_from_within(2..);
+    /// assert_eq!(vec, [0, 1, 2, 3, 4, 2, 3, 4]);
+    ///
+    /// vec.extend_from_within(..2);
+    /// assert_eq!(vec, [0, 1, 2, 3, 4, 2, 3, 4, 0, 1]);
+    ///
+    /// vec.extend_from_within(4..8);
+    /// assert_eq!(vec, [0, 1, 2, 3, 4, 2, 3, 4, 0, 1, 4, 2, 3, 4]);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[stable(feature = "vec_extend_from_within", since = "1.53.0")]
+    pub fn extend_from_within<R>(&mut self, src: R)
+    where
+        R: RangeBounds<usize>,
+    {
+        let range = slice::range(src, ..self.len());
+        self.reserve(range.len());
+
+        // SAFETY:
+        // - `slice::range` guarantees  that the given range is valid for indexing self
+        unsafe {
+            self.spec_extend_from_within(range);
+        }
+    }
+}
+
+impl<T, A: Allocator, const N: usize> Vec<[T; N], A> {
+    /// Takes a `Vec<[T; N]>` and flattens it into a `Vec<T>`.
+    ///
+    /// # Panics
+    ///
+    /// Panics if the length of the resulting vector would overflow a `usize`.
+    ///
+    /// This is only possible when flattening a vector of arrays of zero-sized
+    /// types, and thus tends to be irrelevant in practice. If
+    /// `size_of::<T>() > 0`, this will never panic.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(slice_flatten)]
+    ///
+    /// let mut vec = vec![[1, 2, 3], [4, 5, 6], [7, 8, 9]];
+    /// assert_eq!(vec.pop(), Some([7, 8, 9]));
+    ///
+    /// let mut flattened = vec.into_flattened();
+    /// assert_eq!(flattened.pop(), Some(6));
+    /// ```
+    #[unstable(feature = "slice_flatten", issue = "95629")]
+    pub fn into_flattened(self) -> Vec<T, A> {
+        let (ptr, len, cap, alloc) = self.into_raw_parts_with_alloc();
+        let (new_len, new_cap) = if mem::size_of::<T>() == 0 {
+            (len.checked_mul(N).expect("vec len overflow"), usize::MAX)
+        } else {
+            // SAFETY:
+            // - `cap * N` cannot overflow because the allocation is already in
+            // the address space.
+            // - Each `[T; N]` has `N` valid elements, so there are `len * N`
+            // valid elements in the allocation.
+            unsafe { (len.unchecked_mul(N), cap.unchecked_mul(N)) }
+        };
+        // SAFETY:
+        // - `ptr` was allocated by `self`
+        // - `ptr` is well-aligned because `[T; N]` has the same alignment as `T`.
+        // - `new_cap` refers to the same sized allocation as `cap` because
+        // `new_cap * size_of::<T>()` == `cap * size_of::<[T; N]>()`
+        // - `len` <= `cap`, so `len * N` <= `cap * N`.
+        unsafe { Vec::<T, A>::from_raw_parts_in(ptr.cast(), new_len, new_cap, alloc) }
+    }
+}
+
+// This code generalizes `extend_with_{element,default}`.
+trait ExtendWith<T> {
+    fn next(&mut self) -> T;
+    fn last(self) -> T;
+}
+
+struct ExtendElement<T>(T);
+impl<T: Clone> ExtendWith<T> for ExtendElement<T> {
+    fn next(&mut self) -> T {
+        self.0.clone()
+    }
+    fn last(self) -> T {
+        self.0
+    }
+}
+
+struct ExtendFunc<F>(F);
+impl<T, F: FnMut() -> T> ExtendWith<T> for ExtendFunc<F> {
+    fn next(&mut self) -> T {
+        (self.0)()
+    }
+    fn last(mut self) -> T {
+        (self.0)()
+    }
+}
+
+impl<T, A: Allocator> Vec<T, A> {
+    #[cfg(not(no_global_oom_handling))]
+    /// Extend the vector by `n` values, using the given generator.
+    fn extend_with<E: ExtendWith<T>>(&mut self, n: usize, mut value: E) {
+        self.reserve(n);
+
+        unsafe {
+            let mut ptr = self.as_mut_ptr().add(self.len());
+            // Use SetLenOnDrop to work around bug where compiler
+            // might not realize the store through `ptr` through self.set_len()
+            // don't alias.
+            let mut local_len = SetLenOnDrop::new(&mut self.len);
+
+            // Write all elements except the last one
+            for _ in 1..n {
+                ptr::write(ptr, value.next());
+                ptr = ptr.offset(1);
+                // Increment the length in every step in case next() panics
+                local_len.increment_len(1);
+            }
+
+            if n > 0 {
+                // We can write the last element directly without cloning needlessly
+                ptr::write(ptr, value.last());
+                local_len.increment_len(1);
+            }
+
+            // len set by scope guard
+        }
+    }
+}
+
+impl<T: PartialEq, A: Allocator> Vec<T, A> {
+    /// Removes consecutive repeated elements in the vector according to the
+    /// [`PartialEq`] trait implementation.
+    ///
+    /// If the vector is sorted, this removes all duplicates.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut vec = vec![1, 2, 2, 3, 2];
+    ///
+    /// vec.dedup();
+    ///
+    /// assert_eq!(vec, [1, 2, 3, 2]);
+    /// ```
+    #[stable(feature = "rust1", since = "1.0.0")]
+    #[inline]
+    pub fn dedup(&mut self) {
+        self.dedup_by(|a, b| a == b)
+    }
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// Internal methods and functions
+////////////////////////////////////////////////////////////////////////////////
+
+#[doc(hidden)]
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+pub fn from_elem<T: Clone>(elem: T, n: usize) -> Vec<T> {
+    <T as SpecFromElem>::from_elem(elem, n, Global)
+}
+
+#[doc(hidden)]
+#[cfg(not(no_global_oom_handling))]
+#[unstable(feature = "allocator_api", issue = "32838")]
+pub fn from_elem_in<T: Clone, A: Allocator>(elem: T, n: usize, alloc: A) -> Vec<T, A> {
+    <T as SpecFromElem>::from_elem(elem, n, alloc)
+}
+
+trait ExtendFromWithinSpec {
+    /// # Safety
+    ///
+    /// - `src` needs to be valid index
+    /// - `self.capacity() - self.len()` must be `>= src.len()`
+    unsafe fn spec_extend_from_within(&mut self, src: Range<usize>);
+}
+
+impl<T: Clone, A: Allocator> ExtendFromWithinSpec for Vec<T, A> {
+    default unsafe fn spec_extend_from_within(&mut self, src: Range<usize>) {
+        // SAFETY:
+        // - len is increased only after initializing elements
+        let (this, spare, len) = unsafe { self.split_at_spare_mut_with_len() };
+
+        // SAFETY:
+        // - caller guaratees that src is a valid index
+        let to_clone = unsafe { this.get_unchecked(src) };
+
+        iter::zip(to_clone, spare)
+            .map(|(src, dst)| dst.write(src.clone()))
+            // Note:
+            // - Element was just initialized with `MaybeUninit::write`, so it's ok to increase len
+            // - len is increased after each element to prevent leaks (see issue #82533)
+            .for_each(|_| *len += 1);
+    }
+}
+
+impl<T: Copy, A: Allocator> ExtendFromWithinSpec for Vec<T, A> {
+    unsafe fn spec_extend_from_within(&mut self, src: Range<usize>) {
+        let count = src.len();
+        {
+            let (init, spare) = self.split_at_spare_mut();
+
+            // SAFETY:
+            // - caller guaratees that `src` is a valid index
+            let source = unsafe { init.get_unchecked(src) };
+
+            // SAFETY:
+            // - Both pointers are created from unique slice references (`&mut [_]`)
+            //   so they are valid and do not overlap.
+            // - Elements are :Copy so it's OK to to copy them, without doing
+            //   anything with the original values
+            // - `count` is equal to the len of `source`, so source is valid for
+            //   `count` reads
+            // - `.reserve(count)` guarantees that `spare.len() >= count` so spare
+            //   is valid for `count` writes
+            unsafe { ptr::copy_nonoverlapping(source.as_ptr(), spare.as_mut_ptr() as _, count) };
+        }
+
+        // SAFETY:
+        // - The elements were just initialized by `copy_nonoverlapping`
+        self.len += count;
+    }
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// Common trait implementations for Vec
+////////////////////////////////////////////////////////////////////////////////
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T, A: Allocator> ops::Deref for Vec<T, A> {
+    type Target = [T];
+
+    fn deref(&self) -> &[T] {
+        unsafe { slice::from_raw_parts(self.as_ptr(), self.len) }
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T, A: Allocator> ops::DerefMut for Vec<T, A> {
+    fn deref_mut(&mut self) -> &mut [T] {
+        unsafe { slice::from_raw_parts_mut(self.as_mut_ptr(), self.len) }
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+trait SpecCloneFrom {
+    fn clone_from(this: &mut Self, other: &Self);
+}
+
+#[cfg(not(no_global_oom_handling))]
+impl<T: Clone, A: Allocator> SpecCloneFrom for Vec<T, A> {
+    default fn clone_from(this: &mut Self, other: &Self) {
+        // drop anything that will not be overwritten
+        this.truncate(other.len());
+
+        // self.len <= other.len due to the truncate above, so the
+        // slices here are always in-bounds.
+        let (init, tail) = other.split_at(this.len());
+
+        // reuse the contained values' allocations/resources.
+        this.clone_from_slice(init);
+        this.extend_from_slice(tail);
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+impl<T: Copy, A: Allocator> SpecCloneFrom for Vec<T, A> {
+    fn clone_from(this: &mut Self, other: &Self) {
+        this.clear();
+        this.extend_from_slice(other);
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: Clone, A: Allocator + Clone> Clone for Vec<T, A> {
+    #[cfg(not(test))]
+    fn clone(&self) -> Self {
+        let alloc = self.allocator().clone();
+        <[T]>::to_vec_in(&**self, alloc)
+    }
+
+    // HACK(japaric): with cfg(test) the inherent `[T]::to_vec` method, which is
+    // required for this method definition, is not available. Instead use the
+    // `slice::to_vec`  function which is only available with cfg(test)
+    // NB see the slice::hack module in slice.rs for more information
+    #[cfg(test)]
+    fn clone(&self) -> Self {
+        let alloc = self.allocator().clone();
+        crate::slice::to_vec(&**self, alloc)
+    }
+
+    fn clone_from(&mut self, other: &Self) {
+        SpecCloneFrom::clone_from(self, other)
+    }
+}
+
+/// The hash of a vector is the same as that of the corresponding slice,
+/// as required by the `core::borrow::Borrow` implementation.
+///
+/// ```
+/// #![feature(build_hasher_simple_hash_one)]
+/// use std::hash::BuildHasher;
+///
+/// let b = std::collections::hash_map::RandomState::new();
+/// let v: Vec<u8> = vec![0xa8, 0x3c, 0x09];
+/// let s: &[u8] = &[0xa8, 0x3c, 0x09];
+/// assert_eq!(b.hash_one(v), b.hash_one(s));
+/// ```
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: Hash, A: Allocator> Hash for Vec<T, A> {
+    #[inline]
+    fn hash<H: Hasher>(&self, state: &mut H) {
+        Hash::hash(&**self, state)
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+#[rustc_on_unimplemented(
+    message = "vector indices are of type `usize` or ranges of `usize`",
+    label = "vector indices are of type `usize` or ranges of `usize`"
+)]
+impl<T, I: SliceIndex<[T]>, A: Allocator> Index<I> for Vec<T, A> {
+    type Output = I::Output;
+
+    #[inline]
+    fn index(&self, index: I) -> &Self::Output {
+        Index::index(&**self, index)
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+#[rustc_on_unimplemented(
+    message = "vector indices are of type `usize` or ranges of `usize`",
+    label = "vector indices are of type `usize` or ranges of `usize`"
+)]
+impl<T, I: SliceIndex<[T]>, A: Allocator> IndexMut<I> for Vec<T, A> {
+    #[inline]
+    fn index_mut(&mut self, index: I) -> &mut Self::Output {
+        IndexMut::index_mut(&mut **self, index)
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T> FromIterator<T> for Vec<T> {
+    #[inline]
+    fn from_iter<I: IntoIterator<Item = T>>(iter: I) -> Vec<T> {
+        <Self as SpecFromIter<T, I::IntoIter>>::from_iter(iter.into_iter())
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T, A: Allocator> IntoIterator for Vec<T, A> {
+    type Item = T;
+    type IntoIter = IntoIter<T, A>;
+
+    /// Creates a consuming iterator, that is, one that moves each value out of
+    /// the vector (from start to end). The vector cannot be used after calling
+    /// this.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let v = vec!["a".to_string(), "b".to_string()];
+    /// for s in v.into_iter() {
+    ///     // s has type String, not &String
+    ///     println!("{s}");
+    /// }
+    /// ```
+    #[inline]
+    fn into_iter(self) -> IntoIter<T, A> {
+        unsafe {
+            let mut me = ManuallyDrop::new(self);
+            let alloc = ManuallyDrop::new(ptr::read(me.allocator()));
+            let begin = me.as_mut_ptr();
+            let end = if mem::size_of::<T>() == 0 {
+                arith_offset(begin as *const i8, me.len() as isize) as *const T
+            } else {
+                begin.add(me.len()) as *const T
+            };
+            let cap = me.buf.capacity();
+            IntoIter {
+                buf: NonNull::new_unchecked(begin),
+                phantom: PhantomData,
+                cap,
+                alloc,
+                ptr: begin,
+                end,
+            }
+        }
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<'a, T, A: Allocator> IntoIterator for &'a Vec<T, A> {
+    type Item = &'a T;
+    type IntoIter = slice::Iter<'a, T>;
+
+    fn into_iter(self) -> slice::Iter<'a, T> {
+        self.iter()
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<'a, T, A: Allocator> IntoIterator for &'a mut Vec<T, A> {
+    type Item = &'a mut T;
+    type IntoIter = slice::IterMut<'a, T>;
+
+    fn into_iter(self) -> slice::IterMut<'a, T> {
+        self.iter_mut()
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T, A: Allocator> Extend<T> for Vec<T, A> {
+    #[inline]
+    fn extend<I: IntoIterator<Item = T>>(&mut self, iter: I) {
+        <Self as SpecExtend<T, I::IntoIter>>::spec_extend(self, iter.into_iter())
+    }
+
+    #[inline]
+    fn extend_one(&mut self, item: T) {
+        self.push(item);
+    }
+
+    #[inline]
+    fn extend_reserve(&mut self, additional: usize) {
+        self.reserve(additional);
+    }
+}
+
+impl<T, A: Allocator> Vec<T, A> {
+    // leaf method to which various SpecFrom/SpecExtend implementations delegate when
+    // they have no further optimizations to apply
+    #[cfg(not(no_global_oom_handling))]
+    fn extend_desugared<I: Iterator<Item = T>>(&mut self, mut iterator: I) {
+        // This is the case for a general iterator.
+        //
+        // This function should be the moral equivalent of:
+        //
+        //      for item in iterator {
+        //          self.push(item);
+        //      }
+        while let Some(element) = iterator.next() {
+            let len = self.len();
+            if len == self.capacity() {
+                let (lower, _) = iterator.size_hint();
+                self.reserve(lower.saturating_add(1));
+            }
+            unsafe {
+                ptr::write(self.as_mut_ptr().add(len), element);
+                // Since next() executes user code which can panic we have to bump the length
+                // after each step.
+                // NB can't overflow since we would have had to alloc the address space
+                self.set_len(len + 1);
+            }
+        }
+    }
+
+    /// Creates a splicing iterator that replaces the specified range in the vector
+    /// with the given `replace_with` iterator and yields the removed items.
+    /// `replace_with` does not need to be the same length as `range`.
+    ///
+    /// `range` is removed even if the iterator is not consumed until the end.
+    ///
+    /// It is unspecified how many elements are removed from the vector
+    /// if the `Splice` value is leaked.
+    ///
+    /// The input iterator `replace_with` is only consumed when the `Splice` value is dropped.
+    ///
+    /// This is optimal if:
+    ///
+    /// * The tail (elements in the vector after `range`) is empty,
+    /// * or `replace_with` yields fewer or equal elements than `range`’s length
+    /// * or the lower bound of its `size_hint()` is exact.
+    ///
+    /// Otherwise, a temporary vector is allocated and the tail is moved twice.
+    ///
+    /// # Panics
+    ///
+    /// Panics if the starting point is greater than the end point or if
+    /// the end point is greater than the length of the vector.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let mut v = vec![1, 2, 3, 4];
+    /// let new = [7, 8, 9];
+    /// let u: Vec<_> = v.splice(1..3, new).collect();
+    /// assert_eq!(v, &[1, 7, 8, 9, 4]);
+    /// assert_eq!(u, &[2, 3]);
+    /// ```
+    #[cfg(not(no_global_oom_handling))]
+    #[inline]
+    #[stable(feature = "vec_splice", since = "1.21.0")]
+    pub fn splice<R, I>(&mut self, range: R, replace_with: I) -> Splice<'_, I::IntoIter, A>
+    where
+        R: RangeBounds<usize>,
+        I: IntoIterator<Item = T>,
+    {
+        Splice { drain: self.drain(range), replace_with: replace_with.into_iter() }
+    }
+
+    /// Creates an iterator which uses a closure to determine if an element should be removed.
+    ///
+    /// If the closure returns true, then the element is removed and yielded.
+    /// If the closure returns false, the element will remain in the vector and will not be yielded
+    /// by the iterator.
+    ///
+    /// Using this method is equivalent to the following code:
+    ///
+    /// ```
+    /// # let some_predicate = |x: &mut i32| { *x == 2 || *x == 3 || *x == 6 };
+    /// # let mut vec = vec![1, 2, 3, 4, 5, 6];
+    /// let mut i = 0;
+    /// while i < vec.len() {
+    ///     if some_predicate(&mut vec[i]) {
+    ///         let val = vec.remove(i);
+    ///         // your code here
+    ///     } else {
+    ///         i += 1;
+    ///     }
+    /// }
+    ///
+    /// # assert_eq!(vec, vec![1, 4, 5]);
+    /// ```
+    ///
+    /// But `drain_filter` is easier to use. `drain_filter` is also more efficient,
+    /// because it can backshift the elements of the array in bulk.
+    ///
+    /// Note that `drain_filter` also lets you mutate every element in the filter closure,
+    /// regardless of whether you choose to keep or remove it.
+    ///
+    /// # Examples
+    ///
+    /// Splitting an array into evens and odds, reusing the original allocation:
+    ///
+    /// ```
+    /// #![feature(drain_filter)]
+    /// let mut numbers = vec![1, 2, 3, 4, 5, 6, 8, 9, 11, 13, 14, 15];
+    ///
+    /// let evens = numbers.drain_filter(|x| *x % 2 == 0).collect::<Vec<_>>();
+    /// let odds = numbers;
+    ///
+    /// assert_eq!(evens, vec![2, 4, 6, 8, 14]);
+    /// assert_eq!(odds, vec![1, 3, 5, 9, 11, 13, 15]);
+    /// ```
+    #[unstable(feature = "drain_filter", reason = "recently added", issue = "43244")]
+    pub fn drain_filter<F>(&mut self, filter: F) -> DrainFilter<'_, T, F, A>
+    where
+        F: FnMut(&mut T) -> bool,
+    {
+        let old_len = self.len();
+
+        // Guard against us getting leaked (leak amplification)
+        unsafe {
+            self.set_len(0);
+        }
+
+        DrainFilter { vec: self, idx: 0, del: 0, old_len, pred: filter, panic_flag: false }
+    }
+}
+
+/// Extend implementation that copies elements out of references before pushing them onto the Vec.
+///
+/// This implementation is specialized for slice iterators, where it uses [`copy_from_slice`] to
+/// append the entire slice at once.
+///
+/// [`copy_from_slice`]: slice::copy_from_slice
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "extend_ref", since = "1.2.0")]
+impl<'a, T: Copy + 'a, A: Allocator + 'a> Extend<&'a T> for Vec<T, A> {
+    fn extend<I: IntoIterator<Item = &'a T>>(&mut self, iter: I) {
+        self.spec_extend(iter.into_iter())
+    }
+
+    #[inline]
+    fn extend_one(&mut self, &item: &'a T) {
+        self.push(item);
+    }
+
+    #[inline]
+    fn extend_reserve(&mut self, additional: usize) {
+        self.reserve(additional);
+    }
+}
+
+/// Implements comparison of vectors, [lexicographically](core::cmp::Ord#lexicographical-comparison).
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: PartialOrd, A: Allocator> PartialOrd for Vec<T, A> {
+    #[inline]
+    fn partial_cmp(&self, other: &Self) -> Option<Ordering> {
+        PartialOrd::partial_cmp(&**self, &**other)
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: Eq, A: Allocator> Eq for Vec<T, A> {}
+
+/// Implements ordering of vectors, [lexicographically](core::cmp::Ord#lexicographical-comparison).
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: Ord, A: Allocator> Ord for Vec<T, A> {
+    #[inline]
+    fn cmp(&self, other: &Self) -> Ordering {
+        Ord::cmp(&**self, &**other)
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+unsafe impl<#[may_dangle] T, A: Allocator> Drop for Vec<T, A> {
+    fn drop(&mut self) {
+        unsafe {
+            // use drop for [T]
+            // use a raw slice to refer to the elements of the vector as weakest necessary type;
+            // could avoid questions of validity in certain cases
+            ptr::drop_in_place(ptr::slice_from_raw_parts_mut(self.as_mut_ptr(), self.len))
+        }
+        // RawVec handles deallocation
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+#[rustc_const_unstable(feature = "const_default_impls", issue = "87864")]
+impl<T> const Default for Vec<T> {
+    /// Creates an empty `Vec<T>`.
+    fn default() -> Vec<T> {
+        Vec::new()
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: fmt::Debug, A: Allocator> fmt::Debug for Vec<T, A> {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        fmt::Debug::fmt(&**self, f)
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T, A: Allocator> AsRef<Vec<T, A>> for Vec<T, A> {
+    fn as_ref(&self) -> &Vec<T, A> {
+        self
+    }
+}
+
+#[stable(feature = "vec_as_mut", since = "1.5.0")]
+impl<T, A: Allocator> AsMut<Vec<T, A>> for Vec<T, A> {
+    fn as_mut(&mut self) -> &mut Vec<T, A> {
+        self
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T, A: Allocator> AsRef<[T]> for Vec<T, A> {
+    fn as_ref(&self) -> &[T] {
+        self
+    }
+}
+
+#[stable(feature = "vec_as_mut", since = "1.5.0")]
+impl<T, A: Allocator> AsMut<[T]> for Vec<T, A> {
+    fn as_mut(&mut self) -> &mut [T] {
+        self
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+impl<T: Clone> From<&[T]> for Vec<T> {
+    /// Allocate a `Vec<T>` and fill it by cloning `s`'s items.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// assert_eq!(Vec::from(&[1, 2, 3][..]), vec![1, 2, 3]);
+    /// ```
+    #[cfg(not(test))]
+    fn from(s: &[T]) -> Vec<T> {
+        s.to_vec()
+    }
+    #[cfg(test)]
+    fn from(s: &[T]) -> Vec<T> {
+        crate::slice::to_vec(s, Global)
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "vec_from_mut", since = "1.19.0")]
+impl<T: Clone> From<&mut [T]> for Vec<T> {
+    /// Allocate a `Vec<T>` and fill it by cloning `s`'s items.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// assert_eq!(Vec::from(&mut [1, 2, 3][..]), vec![1, 2, 3]);
+    /// ```
+    #[cfg(not(test))]
+    fn from(s: &mut [T]) -> Vec<T> {
+        s.to_vec()
+    }
+    #[cfg(test)]
+    fn from(s: &mut [T]) -> Vec<T> {
+        crate::slice::to_vec(s, Global)
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "vec_from_array", since = "1.44.0")]
+impl<T, const N: usize> From<[T; N]> for Vec<T> {
+    /// Allocate a `Vec<T>` and move `s`'s items into it.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// assert_eq!(Vec::from([1, 2, 3]), vec![1, 2, 3]);
+    /// ```
+    #[cfg(not(test))]
+    fn from(s: [T; N]) -> Vec<T> {
+        <[T]>::into_vec(box s)
+    }
+
+    #[cfg(test)]
+    fn from(s: [T; N]) -> Vec<T> {
+        crate::slice::into_vec(box s)
+    }
+}
+
+#[stable(feature = "vec_from_cow_slice", since = "1.14.0")]
+impl<'a, T> From<Cow<'a, [T]>> for Vec<T>
+where
+    [T]: ToOwned<Owned = Vec<T>>,
+{
+    /// Convert a clone-on-write slice into a vector.
+    ///
+    /// If `s` already owns a `Vec<T>`, it will be returned directly.
+    /// If `s` is borrowing a slice, a new `Vec<T>` will be allocated and
+    /// filled by cloning `s`'s items into it.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// # use std::borrow::Cow;
+    /// let o: Cow<[i32]> = Cow::Owned(vec![1, 2, 3]);
+    /// let b: Cow<[i32]> = Cow::Borrowed(&[1, 2, 3]);
+    /// assert_eq!(Vec::from(o), Vec::from(b));
+    /// ```
+    fn from(s: Cow<'a, [T]>) -> Vec<T> {
+        s.into_owned()
+    }
+}
+
+// note: test pulls in libstd, which causes errors here
+#[cfg(not(test))]
+#[stable(feature = "vec_from_box", since = "1.18.0")]
+impl<T, A: Allocator> From<Box<[T], A>> for Vec<T, A> {
+    /// Convert a boxed slice into a vector by transferring ownership of
+    /// the existing heap allocation.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// let b: Box<[i32]> = vec![1, 2, 3].into_boxed_slice();
+    /// assert_eq!(Vec::from(b), vec![1, 2, 3]);
+    /// ```
+    fn from(s: Box<[T], A>) -> Self {
+        s.into_vec()
+    }
+}
+
+// note: test pulls in libstd, which causes errors here
+#[cfg(not(no_global_oom_handling))]
+#[cfg(not(test))]
+#[stable(feature = "box_from_vec", since = "1.20.0")]
+impl<T, A: Allocator> From<Vec<T, A>> for Box<[T], A> {
+    /// Convert a vector into a boxed slice.
+    ///
+    /// If `v` has excess capacity, its items will be moved into a
+    /// newly-allocated buffer with exactly the right capacity.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// assert_eq!(Box::from(vec![1, 2, 3]), vec![1, 2, 3].into_boxed_slice());
+    /// ```
+    fn from(v: Vec<T, A>) -> Self {
+        v.into_boxed_slice()
+    }
+}
+
+#[cfg(not(no_global_oom_handling))]
+#[stable(feature = "rust1", since = "1.0.0")]
+impl From<&str> for Vec<u8> {
+    /// Allocate a `Vec<u8>` and fill it with a UTF-8 string.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// assert_eq!(Vec::from("123"), vec![b'1', b'2', b'3']);
+    /// ```
+    fn from(s: &str) -> Vec<u8> {
+        From::from(s.as_bytes())
+    }
+}
+
+#[stable(feature = "array_try_from_vec", since = "1.48.0")]
+impl<T, A: Allocator, const N: usize> TryFrom<Vec<T, A>> for [T; N] {
+    type Error = Vec<T, A>;
+
+    /// Gets the entire contents of the `Vec<T>` as an array,
+    /// if its size exactly matches that of the requested array.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// assert_eq!(vec![1, 2, 3].try_into(), Ok([1, 2, 3]));
+    /// assert_eq!(<Vec<i32>>::new().try_into(), Ok([]));
+    /// ```
+    ///
+    /// If the length doesn't match, the input comes back in `Err`:
+    /// ```
+    /// let r: Result<[i32; 4], _> = (0..10).collect::<Vec<_>>().try_into();
+    /// assert_eq!(r, Err(vec![0, 1, 2, 3, 4, 5, 6, 7, 8, 9]));
+    /// ```
+    ///
+    /// If you're fine with just getting a prefix of the `Vec<T>`,
+    /// you can call [`.truncate(N)`](Vec::truncate) first.
+    /// ```
+    /// let mut v = String::from("hello world").into_bytes();
+    /// v.sort();
+    /// v.truncate(2);
+    /// let [a, b]: [_; 2] = v.try_into().unwrap();
+    /// assert_eq!(a, b' ');
+    /// assert_eq!(b, b'd');
+    /// ```
+    fn try_from(mut vec: Vec<T, A>) -> Result<[T; N], Vec<T, A>> {
+        if vec.len() != N {
+            return Err(vec);
+        }
+
+        // SAFETY: `.set_len(0)` is always sound.
+        unsafe { vec.set_len(0) };
+
+        // SAFETY: A `Vec`'s pointer is always aligned properly, and
+        // the alignment the array needs is the same as the items.
+        // We checked earlier that we have sufficient items.
+        // The items will not double-drop as the `set_len`
+        // tells the `Vec` not to also drop them.
+        let array = unsafe { ptr::read(vec.as_ptr() as *const [T; N]) };
+        Ok(array)
+    }
+}
diff --git a/rust/alloc/vec/partial_eq.rs b/rust/alloc/vec/partial_eq.rs
new file mode 100644
index 000000000000..10ad4e492287
--- /dev/null
+++ b/rust/alloc/vec/partial_eq.rs
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+use crate::alloc::Allocator;
+#[cfg(not(no_global_oom_handling))]
+use crate::borrow::Cow;
+
+use super::Vec;
+
+macro_rules! __impl_slice_eq1 {
+    ([$($vars:tt)*] $lhs:ty, $rhs:ty $(where $ty:ty: $bound:ident)?, #[$stability:meta]) => {
+        #[$stability]
+        impl<T, U, $($vars)*> PartialEq<$rhs> for $lhs
+        where
+            T: PartialEq<U>,
+            $($ty: $bound)?
+        {
+            #[inline]
+            fn eq(&self, other: &$rhs) -> bool { self[..] == other[..] }
+            #[inline]
+            fn ne(&self, other: &$rhs) -> bool { self[..] != other[..] }
+        }
+    }
+}
+
+__impl_slice_eq1! { [A1: Allocator, A2: Allocator] Vec<T, A1>, Vec<U, A2>, #[stable(feature = "rust1", since = "1.0.0")] }
+__impl_slice_eq1! { [A: Allocator] Vec<T, A>, &[U], #[stable(feature = "rust1", since = "1.0.0")] }
+__impl_slice_eq1! { [A: Allocator] Vec<T, A>, &mut [U], #[stable(feature = "rust1", since = "1.0.0")] }
+__impl_slice_eq1! { [A: Allocator] &[T], Vec<U, A>, #[stable(feature = "partialeq_vec_for_ref_slice", since = "1.46.0")] }
+__impl_slice_eq1! { [A: Allocator] &mut [T], Vec<U, A>, #[stable(feature = "partialeq_vec_for_ref_slice", since = "1.46.0")] }
+__impl_slice_eq1! { [A: Allocator] Vec<T, A>, [U], #[stable(feature = "partialeq_vec_for_slice", since = "1.48.0")]  }
+__impl_slice_eq1! { [A: Allocator] [T], Vec<U, A>, #[stable(feature = "partialeq_vec_for_slice", since = "1.48.0")]  }
+#[cfg(not(no_global_oom_handling))]
+__impl_slice_eq1! { [A: Allocator] Cow<'_, [T]>, Vec<U, A> where T: Clone, #[stable(feature = "rust1", since = "1.0.0")] }
+#[cfg(not(no_global_oom_handling))]
+__impl_slice_eq1! { [] Cow<'_, [T]>, &[U] where T: Clone, #[stable(feature = "rust1", since = "1.0.0")] }
+#[cfg(not(no_global_oom_handling))]
+__impl_slice_eq1! { [] Cow<'_, [T]>, &mut [U] where T: Clone, #[stable(feature = "rust1", since = "1.0.0")] }
+__impl_slice_eq1! { [A: Allocator, const N: usize] Vec<T, A>, [U; N], #[stable(feature = "rust1", since = "1.0.0")] }
+__impl_slice_eq1! { [A: Allocator, const N: usize] Vec<T, A>, &[U; N], #[stable(feature = "rust1", since = "1.0.0")] }
+
+// NOTE: some less important impls are omitted to reduce code bloat
+// FIXME(Centril): Reconsider this?
+//__impl_slice_eq1! { [const N: usize] Vec<A>, &mut [B; N], }
+//__impl_slice_eq1! { [const N: usize] [A; N], Vec<B>, }
+//__impl_slice_eq1! { [const N: usize] &[A; N], Vec<B>, }
+//__impl_slice_eq1! { [const N: usize] &mut [A; N], Vec<B>, }
+//__impl_slice_eq1! { [const N: usize] Cow<'a, [A]>, [B; N], }
+//__impl_slice_eq1! { [const N: usize] Cow<'a, [A]>, &[B; N], }
+//__impl_slice_eq1! { [const N: usize] Cow<'a, [A]>, &mut [B; N], }
diff --git a/rust/bindgen_parameters b/rust/bindgen_parameters
new file mode 100644
index 000000000000..be4963bf7203
--- /dev/null
+++ b/rust/bindgen_parameters
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0
+
+--opaque-type xregs_state
+--opaque-type desc_struct
+--opaque-type arch_lbr_state
+--opaque-type local_apic
+
+# Packed type cannot transitively contain a `#[repr(align)]` type.
+--opaque-type x86_msi_data
+--opaque-type x86_msi_addr_lo
+
+# `try` is a reserved keyword since Rust 2018; solved in `bindgen` v0.59.2,
+# commit 2aed6b021680 ("context: Escape the try keyword properly").
+--opaque-type kunit_try_catch
+
+# If SMP is disabled, `arch_spinlock_t` is defined as a ZST which triggers a Rust
+# warning. We don't need to peek into it anyway.
+--opaque-type spinlock
+
+# `seccomp`'s comment gets understood as a doctest
+--no-doc-comments
diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
new file mode 100644
index 000000000000..c48bc284214a
--- /dev/null
+++ b/rust/bindings/bindings_helper.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Header that contains the code (mostly headers) for which Rust bindings
+ * will be automatically generated by `bindgen`.
+ *
+ * Sorted alphabetically.
+ */
+
+#include <linux/slab.h>
+
+/* `bindgen` gets confused at certain things. */
+const gfp_t BINDINGS_GFP_KERNEL = GFP_KERNEL;
+const gfp_t BINDINGS___GFP_ZERO = __GFP_ZERO;
diff --git a/rust/bindings/lib.rs b/rust/bindings/lib.rs
new file mode 100644
index 000000000000..6c50ee62c56b
--- /dev/null
+++ b/rust/bindings/lib.rs
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Bindings.
+//!
+//! Imports the generated bindings by `bindgen`.
+//!
+//! This crate may not be directly used. If you need a kernel C API that is
+//! not ported or wrapped in the `kernel` crate, then do so first instead of
+//! using this crate.
+
+#![no_std]
+#![feature(core_ffi_c)]
+// See <https://github.com/rust-lang/rust-bindgen/issues/1651>.
+#![cfg_attr(test, allow(deref_nullptr))]
+#![cfg_attr(test, allow(unaligned_references))]
+#![cfg_attr(test, allow(unsafe_op_in_unsafe_fn))]
+#![allow(
+    clippy::all,
+    missing_docs,
+    non_camel_case_types,
+    non_upper_case_globals,
+    non_snake_case,
+    improper_ctypes,
+    unreachable_pub,
+    unsafe_op_in_unsafe_fn
+)]
+
+mod bindings_raw {
+    // Use glob import here to expose all helpers.
+    // Symbols defined within the module will take precedence to the glob import.
+    pub use super::bindings_helper::*;
+    include!(concat!(
+        env!("OBJTREE"),
+        "/rust/bindings/bindings_generated.rs"
+    ));
+}
+
+// When both a directly exposed symbol and a helper exists for the same function,
+// the directly exposed symbol is preferred and the helper becomes dead code, so
+// ignore the warning here.
+#[allow(dead_code)]
+mod bindings_helper {
+    // Import the generated bindings for types.
+    include!(concat!(
+        env!("OBJTREE"),
+        "/rust/bindings/bindings_helpers_generated.rs"
+    ));
+}
+
+pub use bindings_raw::*;
+
+pub const GFP_KERNEL: gfp_t = BINDINGS_GFP_KERNEL;
+pub const __GFP_ZERO: gfp_t = BINDINGS___GFP_ZERO;
diff --git a/rust/compiler_builtins.rs b/rust/compiler_builtins.rs
new file mode 100644
index 000000000000..f8f39a3e6855
--- /dev/null
+++ b/rust/compiler_builtins.rs
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Our own `compiler_builtins`.
+//!
+//! Rust provides [`compiler_builtins`] as a port of LLVM's [`compiler-rt`].
+//! Since we do not need the vast majority of them, we avoid the dependency
+//! by providing this file.
+//!
+//! At the moment, some builtins are required that should not be. For instance,
+//! [`core`] has 128-bit integers functionality which we should not be compiling
+//! in. We will work with upstream [`core`] to provide feature flags to disable
+//! the parts we do not need. For the moment, we define them to [`panic!`] at
+//! runtime for simplicity to catch mistakes, instead of performing surgery
+//! on `core.o`.
+//!
+//! In any case, all these symbols are weakened to ensure we do not override
+//! those that may be provided by the rest of the kernel.
+//!
+//! [`compiler_builtins`]: https://github.com/rust-lang/compiler-builtins
+//! [`compiler-rt`]: https://compiler-rt.llvm.org/
+
+#![feature(compiler_builtins)]
+#![compiler_builtins]
+#![no_builtins]
+#![no_std]
+
+macro_rules! define_panicking_intrinsics(
+    ($reason: tt, { $($ident: ident, )* }) => {
+        $(
+            #[doc(hidden)]
+            #[no_mangle]
+            pub extern "C" fn $ident() {
+                panic!($reason);
+            }
+        )*
+    }
+);
+
+define_panicking_intrinsics!("`f32` should not be used", {
+    __eqsf2,
+    __gesf2,
+    __lesf2,
+    __nesf2,
+    __unordsf2,
+});
+
+define_panicking_intrinsics!("`f64` should not be used", {
+    __unorddf2,
+});
+
+define_panicking_intrinsics!("`i128` should not be used", {
+    __ashrti3,
+    __muloti4,
+    __multi3,
+});
+
+define_panicking_intrinsics!("`u128` should not be used", {
+    __ashlti3,
+    __lshrti3,
+    __udivmodti4,
+    __udivti3,
+    __umodti3,
+});
diff --git a/rust/exports.c b/rust/exports.c
new file mode 100644
index 000000000000..bb7cc64cecd0
--- /dev/null
+++ b/rust/exports.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A hack to export Rust symbols for loadable modules without having to redo
+ * the entire `include/linux/export.h` logic in Rust.
+ *
+ * This requires the Rust's new/future `v0` mangling scheme because the default
+ * one ("legacy") uses invalid characters for C identifiers (thus we cannot use
+ * the `EXPORT_SYMBOL_*` macros).
+ *
+ * All symbols are exported as GPL-only to guarantee no GPL-only feature is
+ * accidentally exposed.
+ */
+
+#include <linux/module.h>
+
+#define EXPORT_SYMBOL_RUST_GPL(sym) extern int sym; EXPORT_SYMBOL_GPL(sym)
+
+#include "exports_core_generated.h"
+#include "exports_alloc_generated.h"
+#include "exports_bindings_generated.h"
+#include "exports_kernel_generated.h"
diff --git a/rust/helpers.c b/rust/helpers.c
new file mode 100644
index 000000000000..b4f15eee2ffd
--- /dev/null
+++ b/rust/helpers.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Non-trivial C macros cannot be used in Rust. Similarly, inlined C functions
+ * cannot be called either. This file explicitly creates functions ("helpers")
+ * that wrap those so that they can be called from Rust.
+ *
+ * Even though Rust kernel modules should never use directly the bindings, some
+ * of these helpers need to be exported because Rust generics and inlined
+ * functions may not get their code generated in the crate where they are
+ * defined. Other helpers, called from non-inline functions, may not be
+ * exported, in principle. However, in general, the Rust compiler does not
+ * guarantee codegen will be performed for a non-inline function either.
+ * Therefore, this file exports all the helpers. In the future, this may be
+ * revisited to reduce the number of exports after the compiler is informed
+ * about the places codegen is required.
+ *
+ * All symbols are exported as GPL-only to guarantee no GPL-only feature is
+ * accidentally exposed.
+ */
+
+#include <linux/bug.h>
+#include <linux/build_bug.h>
+
+__noreturn void rust_helper_BUG(void)
+{
+	BUG();
+}
+EXPORT_SYMBOL_GPL(rust_helper_BUG);
+
+/*
+ * We use `bindgen`'s `--size_t-is-usize` option to bind the C `size_t` type
+ * as the Rust `usize` type, so we can use it in contexts where Rust
+ * expects a `usize` like slice (array) indices. `usize` is defined to be
+ * the same as C's `uintptr_t` type (can hold any pointer) but not
+ * necessarily the same as `size_t` (can hold the size of any single
+ * object). Most modern platforms use the same concrete integer type for
+ * both of them, but in case we find ourselves on a platform where
+ * that's not true, fail early instead of risking ABI or
+ * integer-overflow issues.
+ *
+ * If your platform fails this assertion, it means that you are in
+ * danger of integer-overflow bugs (even if you attempt to remove
+ * `--size_t-is-usize`). It may be easiest to change the kernel ABI on
+ * your platform such that `size_t` matches `uintptr_t` (i.e., to increase
+ * `size_t`, because `uintptr_t` has to be at least as big as `size_t`).
+ */
+static_assert(
+	sizeof(size_t) == sizeof(uintptr_t) &&
+	__alignof__(size_t) == __alignof__(uintptr_t),
+	"Rust code expects C `size_t` to match Rust `usize`"
+);
diff --git a/rust/kernel/allocator.rs b/rust/kernel/allocator.rs
new file mode 100644
index 000000000000..397a3dd57a9b
--- /dev/null
+++ b/rust/kernel/allocator.rs
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Allocator support.
+
+use core::alloc::{GlobalAlloc, Layout};
+use core::ptr;
+
+use crate::bindings;
+
+struct KernelAllocator;
+
+unsafe impl GlobalAlloc for KernelAllocator {
+    unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
+        // `krealloc()` is used instead of `kmalloc()` because the latter is
+        // an inline function and cannot be bound to as a result.
+        unsafe { bindings::krealloc(ptr::null(), layout.size(), bindings::GFP_KERNEL) as *mut u8 }
+    }
+
+    unsafe fn dealloc(&self, ptr: *mut u8, _layout: Layout) {
+        unsafe {
+            bindings::kfree(ptr as *const core::ffi::c_void);
+        }
+    }
+}
+
+#[global_allocator]
+static ALLOCATOR: KernelAllocator = KernelAllocator;
+
+// `rustc` only generates these for some crate types. Even then, we would need
+// to extract the object file that has them from the archive. For the moment,
+// let's generate them ourselves instead.
+//
+// Note that `#[no_mangle]` implies exported too, nowadays.
+#[no_mangle]
+fn __rust_alloc(size: usize, _align: usize) -> *mut u8 {
+    unsafe { bindings::krealloc(core::ptr::null(), size, bindings::GFP_KERNEL) as *mut u8 }
+}
+
+#[no_mangle]
+fn __rust_dealloc(ptr: *mut u8, _size: usize, _align: usize) {
+    unsafe { bindings::kfree(ptr as *const core::ffi::c_void) };
+}
+
+#[no_mangle]
+fn __rust_realloc(ptr: *mut u8, _old_size: usize, _align: usize, new_size: usize) -> *mut u8 {
+    unsafe {
+        bindings::krealloc(
+            ptr as *const core::ffi::c_void,
+            new_size,
+            bindings::GFP_KERNEL,
+        ) as *mut u8
+    }
+}
+
+#[no_mangle]
+fn __rust_alloc_zeroed(size: usize, _align: usize) -> *mut u8 {
+    unsafe {
+        bindings::krealloc(
+            core::ptr::null(),
+            size,
+            bindings::GFP_KERNEL | bindings::__GFP_ZERO,
+        ) as *mut u8
+    }
+}
diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs
new file mode 100644
index 000000000000..466b2a8fe569
--- /dev/null
+++ b/rust/kernel/error.rs
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Kernel errors.
+//!
+//! C header: [`include/uapi/asm-generic/errno-base.h`](../../../include/uapi/asm-generic/errno-base.h)
+
+use alloc::collections::TryReserveError;
+
+/// Contains the C-compatible error codes.
+pub mod code {
+    /// Out of memory.
+    pub const ENOMEM: super::Error = super::Error(-(crate::bindings::ENOMEM as i32));
+}
+
+/// Generic integer kernel error.
+///
+/// The kernel defines a set of integer generic error codes based on C and
+/// POSIX ones. These codes may have a more specific meaning in some contexts.
+///
+/// # Invariants
+///
+/// The value is a valid `errno` (i.e. `>= -MAX_ERRNO && < 0`).
+#[derive(Clone, Copy, PartialEq, Eq)]
+pub struct Error(core::ffi::c_int);
+
+impl Error {
+    /// Returns the kernel error code.
+    pub fn to_kernel_errno(self) -> core::ffi::c_int {
+        self.0
+    }
+}
+
+impl From<TryReserveError> for Error {
+    fn from(_: TryReserveError) -> Error {
+        code::ENOMEM
+    }
+}
+
+/// A [`Result`] with an [`Error`] error type.
+///
+/// To be used as the return type for functions that may fail.
+///
+/// # Error codes in C and Rust
+///
+/// In C, it is common that functions indicate success or failure through
+/// their return value; modifying or returning extra data through non-`const`
+/// pointer parameters. In particular, in the kernel, functions that may fail
+/// typically return an `int` that represents a generic error code. We model
+/// those as [`Error`].
+///
+/// In Rust, it is idiomatic to model functions that may fail as returning
+/// a [`Result`]. Since in the kernel many functions return an error code,
+/// [`Result`] is a type alias for a [`core::result::Result`] that uses
+/// [`Error`] as its error type.
+///
+/// Note that even if a function does not return anything when it succeeds,
+/// it should still be modeled as returning a `Result` rather than
+/// just an [`Error`].
+pub type Result<T = ()> = core::result::Result<T, Error>;
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
new file mode 100644
index 000000000000..abd46261d385
--- /dev/null
+++ b/rust/kernel/lib.rs
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! The `kernel` crate.
+//!
+//! This crate contains the kernel APIs that have been ported or wrapped for
+//! usage by Rust code in the kernel and is shared by all of them.
+//!
+//! In other words, all the rest of the Rust code in the kernel (e.g. kernel
+//! modules written in Rust) depends on [`core`], [`alloc`] and this crate.
+//!
+//! If you need a kernel C API that is not ported or wrapped yet here, then
+//! do so first instead of bypassing this crate.
+
+#![no_std]
+#![feature(core_ffi_c)]
+
+// Ensure conditional compilation based on the kernel configuration works;
+// otherwise we may silently break things like initcall handling.
+#[cfg(not(CONFIG_RUST))]
+compile_error!("Missing kernel configuration for conditional compilation");
+
+#[cfg(not(test))]
+#[cfg(not(testlib))]
+mod allocator;
+pub mod error;
+pub mod prelude;
+pub mod print;
+pub mod str;
+
+#[doc(hidden)]
+pub use bindings;
+pub use macros;
+
+/// Prefix to appear before log messages printed from within the `kernel` crate.
+const __LOG_PREFIX: &[u8] = b"rust_kernel\0";
+
+/// The top level entrypoint to implementing a kernel module.
+///
+/// For any teardown or cleanup operations, your type may implement [`Drop`].
+pub trait Module: Sized + Sync {
+    /// Called at module initialization time.
+    ///
+    /// Use this method to perform whatever setup or registration your module
+    /// should do.
+    ///
+    /// Equivalent to the `module_init` macro in the C API.
+    fn init(module: &'static ThisModule) -> error::Result<Self>;
+}
+
+/// Equivalent to `THIS_MODULE` in the C API.
+///
+/// C header: `include/linux/export.h`
+pub struct ThisModule(*mut bindings::module);
+
+// SAFETY: `THIS_MODULE` may be used from all threads within a module.
+unsafe impl Sync for ThisModule {}
+
+impl ThisModule {
+    /// Creates a [`ThisModule`] given the `THIS_MODULE` pointer.
+    ///
+    /// # Safety
+    ///
+    /// The pointer must be equal to the right `THIS_MODULE`.
+    pub const unsafe fn from_ptr(ptr: *mut bindings::module) -> ThisModule {
+        ThisModule(ptr)
+    }
+}
+
+#[cfg(not(any(testlib, test)))]
+#[panic_handler]
+fn panic(info: &core::panic::PanicInfo<'_>) -> ! {
+    pr_emerg!("{}\n", info);
+    // SAFETY: FFI call.
+    unsafe { bindings::BUG() };
+    // Bindgen currently does not recognize `__noreturn` so `BUG` returns `()`
+    // instead of `!`. See <https://github.com/rust-lang/rust-bindgen/issues/2094>.
+    loop {}
+}
diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs
new file mode 100644
index 000000000000..495e22250726
--- /dev/null
+++ b/rust/kernel/prelude.rs
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! The `kernel` prelude.
+//!
+//! These are the most common items used by Rust code in the kernel,
+//! intended to be imported by all Rust code, for convenience.
+//!
+//! # Examples
+//!
+//! ```
+//! use kernel::prelude::*;
+//! ```
+
+pub use super::{
+    error::{Error, Result},
+    pr_emerg, pr_info, ThisModule,
+};
+pub use alloc::{boxed::Box, vec::Vec};
+pub use core::pin::Pin;
+pub use macros::module;
diff --git a/rust/kernel/print.rs b/rust/kernel/print.rs
new file mode 100644
index 000000000000..55db5a1ba752
--- /dev/null
+++ b/rust/kernel/print.rs
@@ -0,0 +1,198 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Printing facilities.
+//!
+//! C header: [`include/linux/printk.h`](../../../../include/linux/printk.h)
+//!
+//! Reference: <https://www.kernel.org/doc/html/latest/core-api/printk-basics.html>
+
+use core::{
+    ffi::{c_char, c_void},
+    fmt,
+};
+
+use crate::str::RawFormatter;
+
+#[cfg(CONFIG_PRINTK)]
+use crate::bindings;
+
+// Called from `vsprintf` with format specifier `%pA`.
+#[no_mangle]
+unsafe fn rust_fmt_argument(buf: *mut c_char, end: *mut c_char, ptr: *const c_void) -> *mut c_char {
+    use fmt::Write;
+    // SAFETY: The C contract guarantees that `buf` is valid if it's less than `end`.
+    let mut w = unsafe { RawFormatter::from_ptrs(buf.cast(), end.cast()) };
+    let _ = w.write_fmt(unsafe { *(ptr as *const fmt::Arguments<'_>) });
+    w.pos().cast()
+}
+
+/// Format strings.
+///
+/// Public but hidden since it should only be used from public macros.
+#[doc(hidden)]
+pub mod format_strings {
+    use crate::bindings;
+
+    /// The length we copy from the `KERN_*` kernel prefixes.
+    const LENGTH_PREFIX: usize = 2;
+
+    /// The length of the fixed format strings.
+    pub const LENGTH: usize = 10;
+
+    /// Generates a fixed format string for the kernel's [`_printk`].
+    ///
+    /// The format string is always the same for a given level, i.e. for a
+    /// given `prefix`, which are the kernel's `KERN_*` constants.
+    ///
+    /// [`_printk`]: ../../../../include/linux/printk.h
+    const fn generate(is_cont: bool, prefix: &[u8; 3]) -> [u8; LENGTH] {
+        // Ensure the `KERN_*` macros are what we expect.
+        assert!(prefix[0] == b'\x01');
+        if is_cont {
+            assert!(prefix[1] == b'c');
+        } else {
+            assert!(prefix[1] >= b'0' && prefix[1] <= b'7');
+        }
+        assert!(prefix[2] == b'\x00');
+
+        let suffix: &[u8; LENGTH - LENGTH_PREFIX] = if is_cont {
+            b"%pA\0\0\0\0\0"
+        } else {
+            b"%s: %pA\0"
+        };
+
+        [
+            prefix[0], prefix[1], suffix[0], suffix[1], suffix[2], suffix[3], suffix[4], suffix[5],
+            suffix[6], suffix[7],
+        ]
+    }
+
+    // Generate the format strings at compile-time.
+    //
+    // This avoids the compiler generating the contents on the fly in the stack.
+    //
+    // Furthermore, `static` instead of `const` is used to share the strings
+    // for all the kernel.
+    pub static EMERG: [u8; LENGTH] = generate(false, bindings::KERN_EMERG);
+    pub static INFO: [u8; LENGTH] = generate(false, bindings::KERN_INFO);
+}
+
+/// Prints a message via the kernel's [`_printk`].
+///
+/// Public but hidden since it should only be used from public macros.
+///
+/// # Safety
+///
+/// The format string must be one of the ones in [`format_strings`], and
+/// the module name must be null-terminated.
+///
+/// [`_printk`]: ../../../../include/linux/_printk.h
+#[doc(hidden)]
+#[cfg_attr(not(CONFIG_PRINTK), allow(unused_variables))]
+pub unsafe fn call_printk(
+    format_string: &[u8; format_strings::LENGTH],
+    module_name: &[u8],
+    args: fmt::Arguments<'_>,
+) {
+    // `_printk` does not seem to fail in any path.
+    #[cfg(CONFIG_PRINTK)]
+    unsafe {
+        bindings::_printk(
+            format_string.as_ptr() as _,
+            module_name.as_ptr(),
+            &args as *const _ as *const c_void,
+        );
+    }
+}
+
+/// Performs formatting and forwards the string to [`call_printk`].
+///
+/// Public but hidden since it should only be used from public macros.
+#[doc(hidden)]
+#[cfg(not(testlib))]
+#[macro_export]
+#[allow(clippy::crate_in_macro_def)]
+macro_rules! print_macro (
+    // The non-continuation cases (most of them, e.g. `INFO`).
+    ($format_string:path, $($arg:tt)+) => (
+        // SAFETY: This hidden macro should only be called by the documented
+        // printing macros which ensure the format string is one of the fixed
+        // ones. All `__LOG_PREFIX`s are null-terminated as they are generated
+        // by the `module!` proc macro or fixed values defined in a kernel
+        // crate.
+        unsafe {
+            $crate::print::call_printk(
+                &$format_string,
+                crate::__LOG_PREFIX,
+                format_args!($($arg)+),
+            );
+        }
+    );
+);
+
+/// Stub for doctests
+#[cfg(testlib)]
+#[macro_export]
+macro_rules! print_macro (
+    ($format_string:path, $e:expr, $($arg:tt)+) => (
+        ()
+    );
+);
+
+// We could use a macro to generate these macros. However, doing so ends
+// up being a bit ugly: it requires the dollar token trick to escape `$` as
+// well as playing with the `doc` attribute. Furthermore, they cannot be easily
+// imported in the prelude due to [1]. So, for the moment, we just write them
+// manually, like in the C side; while keeping most of the logic in another
+// macro, i.e. [`print_macro`].
+//
+// [1]: https://github.com/rust-lang/rust/issues/52234
+
+/// Prints an emergency-level message (level 0).
+///
+/// Use this level if the system is unusable.
+///
+/// Equivalent to the kernel's [`pr_emerg`] macro.
+///
+/// Mimics the interface of [`std::print!`]. See [`core::fmt`] and
+/// `alloc::format!` for information about the formatting syntax.
+///
+/// [`pr_emerg`]: https://www.kernel.org/doc/html/latest/core-api/printk-basics.html#c.pr_emerg
+/// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+///
+/// # Examples
+///
+/// ```
+/// pr_emerg!("hello {}\n", "there");
+/// ```
+#[macro_export]
+macro_rules! pr_emerg (
+    ($($arg:tt)*) => (
+        $crate::print_macro!($crate::print::format_strings::EMERG, $($arg)*)
+    )
+);
+
+/// Prints an info-level message (level 6).
+///
+/// Use this level for informational messages.
+///
+/// Equivalent to the kernel's [`pr_info`] macro.
+///
+/// Mimics the interface of [`std::print!`]. See [`core::fmt`] and
+/// `alloc::format!` for information about the formatting syntax.
+///
+/// [`pr_info`]: https://www.kernel.org/doc/html/latest/core-api/printk-basics.html#c.pr_info
+/// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html
+///
+/// # Examples
+///
+/// ```
+/// pr_info!("hello {}\n", "there");
+/// ```
+#[macro_export]
+#[doc(alias = "print")]
+macro_rules! pr_info (
+    ($($arg:tt)*) => (
+        $crate::print_macro!($crate::print::format_strings::INFO, $($arg)*)
+    )
+);
diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
new file mode 100644
index 000000000000..e45ff220ae50
--- /dev/null
+++ b/rust/kernel/str.rs
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! String representations.
+
+use core::fmt;
+
+/// Allows formatting of [`fmt::Arguments`] into a raw buffer.
+///
+/// It does not fail if callers write past the end of the buffer so that they can calculate the
+/// size required to fit everything.
+///
+/// # Invariants
+///
+/// The memory region between `pos` (inclusive) and `end` (exclusive) is valid for writes if `pos`
+/// is less than `end`.
+pub(crate) struct RawFormatter {
+    // Use `usize` to use `saturating_*` functions.
+    #[allow(dead_code)]
+    beg: usize,
+    pos: usize,
+    end: usize,
+}
+
+impl RawFormatter {
+    /// Creates a new instance of [`RawFormatter`] with the given buffer pointers.
+    ///
+    /// # Safety
+    ///
+    /// If `pos` is less than `end`, then the region between `pos` (inclusive) and `end`
+    /// (exclusive) must be valid for writes for the lifetime of the returned [`RawFormatter`].
+    pub(crate) unsafe fn from_ptrs(pos: *mut u8, end: *mut u8) -> Self {
+        // INVARIANT: The safety requierments guarantee the type invariants.
+        Self {
+            beg: pos as _,
+            pos: pos as _,
+            end: end as _,
+        }
+    }
+
+    /// Returns the current insert position.
+    ///
+    /// N.B. It may point to invalid memory.
+    pub(crate) fn pos(&self) -> *mut u8 {
+        self.pos as _
+    }
+}
+
+impl fmt::Write for RawFormatter {
+    fn write_str(&mut self, s: &str) -> fmt::Result {
+        // `pos` value after writing `len` bytes. This does not have to be bounded by `end`, but we
+        // don't want it to wrap around to 0.
+        let pos_new = self.pos.saturating_add(s.len());
+
+        // Amount that we can copy. `saturating_sub` ensures we get 0 if `pos` goes past `end`.
+        let len_to_copy = core::cmp::min(pos_new, self.end).saturating_sub(self.pos);
+
+        if len_to_copy > 0 {
+            // SAFETY: If `len_to_copy` is non-zero, then we know `pos` has not gone past `end`
+            // yet, so it is valid for write per the type invariants.
+            unsafe {
+                core::ptr::copy_nonoverlapping(
+                    s.as_bytes().as_ptr(),
+                    self.pos as *mut u8,
+                    len_to_copy,
+                )
+            };
+        }
+
+        self.pos = pos_new;
+        Ok(())
+    }
+}
diff --git a/rust/macros/helpers.rs b/rust/macros/helpers.rs
new file mode 100644
index 000000000000..cdc7dc6135d2
--- /dev/null
+++ b/rust/macros/helpers.rs
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+
+use proc_macro::{token_stream, TokenTree};
+
+pub(crate) fn try_ident(it: &mut token_stream::IntoIter) -> Option<String> {
+    if let Some(TokenTree::Ident(ident)) = it.next() {
+        Some(ident.to_string())
+    } else {
+        None
+    }
+}
+
+pub(crate) fn try_literal(it: &mut token_stream::IntoIter) -> Option<String> {
+    if let Some(TokenTree::Literal(literal)) = it.next() {
+        Some(literal.to_string())
+    } else {
+        None
+    }
+}
+
+pub(crate) fn try_byte_string(it: &mut token_stream::IntoIter) -> Option<String> {
+    try_literal(it).and_then(|byte_string| {
+        if byte_string.starts_with("b\"") && byte_string.ends_with('\"') {
+            Some(byte_string[2..byte_string.len() - 1].to_string())
+        } else {
+            None
+        }
+    })
+}
+
+pub(crate) fn expect_ident(it: &mut token_stream::IntoIter) -> String {
+    try_ident(it).expect("Expected Ident")
+}
+
+pub(crate) fn expect_punct(it: &mut token_stream::IntoIter) -> char {
+    if let TokenTree::Punct(punct) = it.next().expect("Reached end of token stream for Punct") {
+        punct.as_char()
+    } else {
+        panic!("Expected Punct");
+    }
+}
+
+pub(crate) fn expect_byte_string(it: &mut token_stream::IntoIter) -> String {
+    try_byte_string(it).expect("Expected byte string")
+}
+
+pub(crate) fn expect_end(it: &mut token_stream::IntoIter) {
+    if it.next().is_some() {
+        panic!("Expected end");
+    }
+}
diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs
new file mode 100644
index 000000000000..91764bfb1f89
--- /dev/null
+++ b/rust/macros/lib.rs
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Crate for all kernel procedural macros.
+
+mod helpers;
+mod module;
+
+use proc_macro::TokenStream;
+
+/// Declares a kernel module.
+///
+/// The `type` argument should be a type which implements the [`Module`]
+/// trait. Also accepts various forms of kernel metadata.
+///
+/// C header: [`include/linux/moduleparam.h`](../../../include/linux/moduleparam.h)
+///
+/// [`Module`]: ../kernel/trait.Module.html
+///
+/// # Examples
+///
+/// ```ignore
+/// use kernel::prelude::*;
+///
+/// module!{
+///     type: MyModule,
+///     name: b"my_kernel_module",
+///     author: b"Rust for Linux Contributors",
+///     description: b"My very own kernel module!",
+///     license: b"GPL",
+///     params: {
+///        my_i32: i32 {
+///            default: 42,
+///            permissions: 0o000,
+///            description: b"Example of i32",
+///        },
+///        writeable_i32: i32 {
+///            default: 42,
+///            permissions: 0o644,
+///            description: b"Example of i32",
+///        },
+///    },
+/// }
+///
+/// struct MyModule;
+///
+/// impl kernel::Module for MyModule {
+///     fn init() -> Result<Self> {
+///         // If the parameter is writeable, then the kparam lock must be
+///         // taken to read the parameter:
+///         {
+///             let lock = THIS_MODULE.kernel_param_lock();
+///             pr_info!("i32 param is:  {}\n", writeable_i32.read(&lock));
+///         }
+///         // If the parameter is read only, it can be read without locking
+///         // the kernel parameters:
+///         pr_info!("i32 param is:  {}\n", my_i32.read());
+///         Ok(Self)
+///     }
+/// }
+/// ```
+///
+/// # Supported argument types
+///   - `type`: type which implements the [`Module`] trait (required).
+///   - `name`: byte array of the name of the kernel module (required).
+///   - `author`: byte array of the author of the kernel module.
+///   - `description`: byte array of the description of the kernel module.
+///   - `license`: byte array of the license of the kernel module (required).
+///   - `alias`: byte array of alias name of the kernel module.
+#[proc_macro]
+pub fn module(ts: TokenStream) -> TokenStream {
+    module::module(ts)
+}
diff --git a/rust/macros/module.rs b/rust/macros/module.rs
new file mode 100644
index 000000000000..186a5b8be23c
--- /dev/null
+++ b/rust/macros/module.rs
@@ -0,0 +1,282 @@
+// SPDX-License-Identifier: GPL-2.0
+
+use crate::helpers::*;
+use proc_macro::{token_stream, Literal, TokenStream, TokenTree};
+use std::fmt::Write;
+
+struct ModInfoBuilder<'a> {
+    module: &'a str,
+    counter: usize,
+    buffer: String,
+}
+
+impl<'a> ModInfoBuilder<'a> {
+    fn new(module: &'a str) -> Self {
+        ModInfoBuilder {
+            module,
+            counter: 0,
+            buffer: String::new(),
+        }
+    }
+
+    fn emit_base(&mut self, field: &str, content: &str, builtin: bool) {
+        let string = if builtin {
+            // Built-in modules prefix their modinfo strings by `module.`.
+            format!(
+                "{module}.{field}={content}\0",
+                module = self.module,
+                field = field,
+                content = content
+            )
+        } else {
+            // Loadable modules' modinfo strings go as-is.
+            format!("{field}={content}\0", field = field, content = content)
+        };
+
+        write!(
+            &mut self.buffer,
+            "
+                {cfg}
+                #[doc(hidden)]
+                #[link_section = \".modinfo\"]
+                #[used]
+                pub static __{module}_{counter}: [u8; {length}] = *{string};
+            ",
+            cfg = if builtin {
+                "#[cfg(not(MODULE))]"
+            } else {
+                "#[cfg(MODULE)]"
+            },
+            module = self.module.to_uppercase(),
+            counter = self.counter,
+            length = string.len(),
+            string = Literal::byte_string(string.as_bytes()),
+        )
+        .unwrap();
+
+        self.counter += 1;
+    }
+
+    fn emit_only_builtin(&mut self, field: &str, content: &str) {
+        self.emit_base(field, content, true)
+    }
+
+    fn emit_only_loadable(&mut self, field: &str, content: &str) {
+        self.emit_base(field, content, false)
+    }
+
+    fn emit(&mut self, field: &str, content: &str) {
+        self.emit_only_builtin(field, content);
+        self.emit_only_loadable(field, content);
+    }
+}
+
+#[derive(Debug, Default)]
+struct ModuleInfo {
+    type_: String,
+    license: String,
+    name: String,
+    author: Option<String>,
+    description: Option<String>,
+    alias: Option<String>,
+}
+
+impl ModuleInfo {
+    fn parse(it: &mut token_stream::IntoIter) -> Self {
+        let mut info = ModuleInfo::default();
+
+        const EXPECTED_KEYS: &[&str] =
+            &["type", "name", "author", "description", "license", "alias"];
+        const REQUIRED_KEYS: &[&str] = &["type", "name", "license"];
+        let mut seen_keys = Vec::new();
+
+        loop {
+            let key = match it.next() {
+                Some(TokenTree::Ident(ident)) => ident.to_string(),
+                Some(_) => panic!("Expected Ident or end"),
+                None => break,
+            };
+
+            if seen_keys.contains(&key) {
+                panic!(
+                    "Duplicated key \"{}\". Keys can only be specified once.",
+                    key
+                );
+            }
+
+            assert_eq!(expect_punct(it), ':');
+
+            match key.as_str() {
+                "type" => info.type_ = expect_ident(it),
+                "name" => info.name = expect_byte_string(it),
+                "author" => info.author = Some(expect_byte_string(it)),
+                "description" => info.description = Some(expect_byte_string(it)),
+                "license" => info.license = expect_byte_string(it),
+                "alias" => info.alias = Some(expect_byte_string(it)),
+                _ => panic!(
+                    "Unknown key \"{}\". Valid keys are: {:?}.",
+                    key, EXPECTED_KEYS
+                ),
+            }
+
+            assert_eq!(expect_punct(it), ',');
+
+            seen_keys.push(key);
+        }
+
+        expect_end(it);
+
+        for key in REQUIRED_KEYS {
+            if !seen_keys.iter().any(|e| e == key) {
+                panic!("Missing required key \"{}\".", key);
+            }
+        }
+
+        let mut ordered_keys: Vec<&str> = Vec::new();
+        for key in EXPECTED_KEYS {
+            if seen_keys.iter().any(|e| e == key) {
+                ordered_keys.push(key);
+            }
+        }
+
+        if seen_keys != ordered_keys {
+            panic!(
+                "Keys are not ordered as expected. Order them like: {:?}.",
+                ordered_keys
+            );
+        }
+
+        info
+    }
+}
+
+pub(crate) fn module(ts: TokenStream) -> TokenStream {
+    let mut it = ts.into_iter();
+
+    let info = ModuleInfo::parse(&mut it);
+
+    let mut modinfo = ModInfoBuilder::new(info.name.as_ref());
+    if let Some(author) = info.author {
+        modinfo.emit("author", &author);
+    }
+    if let Some(description) = info.description {
+        modinfo.emit("description", &description);
+    }
+    modinfo.emit("license", &info.license);
+    if let Some(alias) = info.alias {
+        modinfo.emit("alias", &alias);
+    }
+
+    // Built-in modules also export the `file` modinfo string.
+    let file =
+        std::env::var("RUST_MODFILE").expect("Unable to fetch RUST_MODFILE environmental variable");
+    modinfo.emit_only_builtin("file", &file);
+
+    format!(
+        "
+            /// The module name.
+            ///
+            /// Used by the printing macros, e.g. [`info!`].
+            const __LOG_PREFIX: &[u8] = b\"{name}\\0\";
+
+            /// The \"Rust loadable module\" mark, for `scripts/is_rust_module.sh`.
+            //
+            // This may be best done another way later on, e.g. as a new modinfo
+            // key or a new section. For the moment, keep it simple.
+            #[cfg(MODULE)]
+            #[doc(hidden)]
+            #[used]
+            static __IS_RUST_MODULE: () = ();
+
+            static mut __MOD: Option<{type_}> = None;
+
+            // SAFETY: `__this_module` is constructed by the kernel at load time and will not be
+            // freed until the module is unloaded.
+            #[cfg(MODULE)]
+            static THIS_MODULE: kernel::ThisModule = unsafe {{
+                kernel::ThisModule::from_ptr(&kernel::bindings::__this_module as *const _ as *mut _)
+            }};
+            #[cfg(not(MODULE))]
+            static THIS_MODULE: kernel::ThisModule = unsafe {{
+                kernel::ThisModule::from_ptr(core::ptr::null_mut())
+            }};
+
+            // Loadable modules need to export the `{{init,cleanup}}_module` identifiers.
+            #[cfg(MODULE)]
+            #[doc(hidden)]
+            #[no_mangle]
+            pub extern \"C\" fn init_module() -> core::ffi::c_int {{
+                __init()
+            }}
+
+            #[cfg(MODULE)]
+            #[doc(hidden)]
+            #[no_mangle]
+            pub extern \"C\" fn cleanup_module() {{
+                __exit()
+            }}
+
+            // Built-in modules are initialized through an initcall pointer
+            // and the identifiers need to be unique.
+            #[cfg(not(MODULE))]
+            #[cfg(not(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS))]
+            #[doc(hidden)]
+            #[link_section = \"{initcall_section}\"]
+            #[used]
+            pub static __{name}_initcall: extern \"C\" fn() -> core::ffi::c_int = __{name}_init;
+
+            #[cfg(not(MODULE))]
+            #[cfg(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)]
+            core::arch::global_asm!(
+                r#\".section \"{initcall_section}\", \"a\"
+                __{name}_initcall:
+                    .long   __{name}_init - .
+                    .previous
+                \"#
+            );
+
+            #[cfg(not(MODULE))]
+            #[doc(hidden)]
+            #[no_mangle]
+            pub extern \"C\" fn __{name}_init() -> core::ffi::c_int {{
+                __init()
+            }}
+
+            #[cfg(not(MODULE))]
+            #[doc(hidden)]
+            #[no_mangle]
+            pub extern \"C\" fn __{name}_exit() {{
+                __exit()
+            }}
+
+            fn __init() -> core::ffi::c_int {{
+                match <{type_} as kernel::Module>::init(&THIS_MODULE) {{
+                    Ok(m) => {{
+                        unsafe {{
+                            __MOD = Some(m);
+                        }}
+                        return 0;
+                    }}
+                    Err(e) => {{
+                        return e.to_kernel_errno();
+                    }}
+                }}
+            }}
+
+            fn __exit() {{
+                unsafe {{
+                    // Invokes `drop()` on `__MOD`, which should be used for cleanup.
+                    __MOD = None;
+                }}
+            }}
+
+            {modinfo}
+        ",
+        type_ = info.type_,
+        name = info.name,
+        modinfo = modinfo.buffer,
+        initcall_section = ".initcall6.init"
+    )
+    .parse()
+    .expect("Error parsing formatted string into token stream.")
+}
diff --git a/samples/Kconfig b/samples/Kconfig
index 470ee3baf2e1..0d81c00289ee 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -263,6 +263,8 @@ config SAMPLE_CORESIGHT_SYSCFG
 	  This demonstrates how a user may create their own CoreSight
 	  configurations and easily load them into the system at runtime.
 
+source "samples/rust/Kconfig"
+
 endif # SAMPLES
 
 config HAVE_SAMPLE_FTRACE_DIRECT
diff --git a/samples/Makefile b/samples/Makefile
index 701e912ab5af..9832ef3f8fcb 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -35,3 +35,4 @@ subdir-$(CONFIG_SAMPLE_WATCH_QUEUE)	+= watch_queue
 obj-$(CONFIG_DEBUG_KMEMLEAK_TEST)	+= kmemleak/
 obj-$(CONFIG_SAMPLE_CORESIGHT_SYSCFG)	+= coresight/
 obj-$(CONFIG_SAMPLE_FPROBE)		+= fprobe/
+obj-$(CONFIG_SAMPLES_RUST)		+= rust/
diff --git a/samples/rust/Kconfig b/samples/rust/Kconfig
new file mode 100644
index 000000000000..841e0906e943
--- /dev/null
+++ b/samples/rust/Kconfig
@@ -0,0 +1,30 @@
+# SPDX-License-Identifier: GPL-2.0
+
+menuconfig SAMPLES_RUST
+	bool "Rust samples"
+	depends on RUST
+	help
+	  You can build sample Rust kernel code here.
+
+	  If unsure, say N.
+
+if SAMPLES_RUST
+
+config SAMPLE_RUST_MINIMAL
+	tristate "Minimal"
+	help
+	  This option builds the Rust minimal module sample.
+
+	  To compile this as a module, choose M here:
+	  the module will be called rust_minimal.
+
+	  If unsure, say N.
+
+config SAMPLE_RUST_HOSTPROGS
+	bool "Host programs"
+	help
+	  This option builds the Rust host program samples.
+
+	  If unsure, say N.
+
+endif # SAMPLES_RUST
diff --git a/samples/rust/Makefile b/samples/rust/Makefile
new file mode 100644
index 000000000000..1daba5f8658a
--- /dev/null
+++ b/samples/rust/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_SAMPLE_RUST_MINIMAL)		+= rust_minimal.o
+
+subdir-$(CONFIG_SAMPLE_RUST_HOSTPROGS)		+= hostprogs
diff --git a/samples/rust/hostprogs/.gitignore b/samples/rust/hostprogs/.gitignore
new file mode 100644
index 000000000000..a6c173da5048
--- /dev/null
+++ b/samples/rust/hostprogs/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+single
diff --git a/samples/rust/hostprogs/Makefile b/samples/rust/hostprogs/Makefile
new file mode 100644
index 000000000000..8ddcbd7416db
--- /dev/null
+++ b/samples/rust/hostprogs/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
+hostprogs-always-y := single
+
+single-rust := y
diff --git a/samples/rust/hostprogs/a.rs b/samples/rust/hostprogs/a.rs
new file mode 100644
index 000000000000..f7a4a3d0f4e0
--- /dev/null
+++ b/samples/rust/hostprogs/a.rs
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Rust single host program sample: module `a`.
+
+pub(crate) fn f(x: i32) {
+    println!("The number is {}.", x);
+}
diff --git a/samples/rust/hostprogs/b.rs b/samples/rust/hostprogs/b.rs
new file mode 100644
index 000000000000..c1675890648f
--- /dev/null
+++ b/samples/rust/hostprogs/b.rs
@@ -0,0 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Rust single host program sample: module `b`.
+
+pub(crate) const CONSTANT: i32 = 42;
diff --git a/samples/rust/hostprogs/single.rs b/samples/rust/hostprogs/single.rs
new file mode 100644
index 000000000000..8c48a119339a
--- /dev/null
+++ b/samples/rust/hostprogs/single.rs
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Rust single host program sample.
+
+mod a;
+mod b;
+
+fn main() {
+    println!("Hello world!");
+
+    a::f(b::CONSTANT);
+}
diff --git a/samples/rust/rust_minimal.rs b/samples/rust/rust_minimal.rs
new file mode 100644
index 000000000000..54ad17685742
--- /dev/null
+++ b/samples/rust/rust_minimal.rs
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Rust minimal sample.
+
+use kernel::prelude::*;
+
+module! {
+    type: RustMinimal,
+    name: b"rust_minimal",
+    author: b"Rust for Linux Contributors",
+    description: b"Rust minimal sample",
+    license: b"GPL",
+}
+
+struct RustMinimal {
+    numbers: Vec<i32>,
+}
+
+impl kernel::Module for RustMinimal {
+    fn init(_module: &'static ThisModule) -> Result<Self> {
+        pr_info!("Rust minimal sample (init)\n");
+        pr_info!("Am I built-in? {}\n", !cfg!(MODULE));
+
+        let mut numbers = Vec::new();
+        numbers.try_push(72)?;
+        numbers.try_push(108)?;
+        numbers.try_push(200)?;
+
+        Ok(RustMinimal { numbers })
+    }
+}
+
+impl Drop for RustMinimal {
+    fn drop(&mut self) {
+        pr_info!("My numbers are {:?}\n", self.numbers);
+        pr_info!("Rust minimal sample (exit)\n");
+    }
+}
diff --git a/scripts/.gitignore b/scripts/.gitignore
index eed308bef604..b7aec8eb1bd4 100644
--- a/scripts/.gitignore
+++ b/scripts/.gitignore
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 /asn1_compiler
 /bin2c
+/generate_rust_target
 /insert-sys-cert
 /kallsyms
 /module.lds
diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include
index a0ccceb22cf8..274125307ebd 100644
--- a/scripts/Kconfig.include
+++ b/scripts/Kconfig.include
@@ -36,12 +36,12 @@ ld-option = $(success,$(LD) -v $(1))
 as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -c -x assembler -o /dev/null -)
 
 # check if $(CC) and $(LD) exist
-$(error-if,$(failure,command -v $(CC)),compiler '$(CC)' not found)
+$(error-if,$(failure,command -v $(CC)),C compiler '$(CC)' not found)
 $(error-if,$(failure,command -v $(LD)),linker '$(LD)' not found)
 
-# Get the compiler name, version, and error out if it is not supported.
+# Get the C compiler name, version, and error out if it is not supported.
 cc-info := $(shell,$(srctree)/scripts/cc-version.sh $(CC))
-$(error-if,$(success,test -z "$(cc-info)"),Sorry$(comma) this compiler is not supported.)
+$(error-if,$(success,test -z "$(cc-info)"),Sorry$(comma) this C compiler is not supported.)
 cc-name := $(shell,set -- $(cc-info) && echo $1)
 cc-version := $(shell,set -- $(cc-info) && echo $2)
 
diff --git a/scripts/Makefile b/scripts/Makefile
index f084f08ed176..1575af84d557 100644
--- a/scripts/Makefile
+++ b/scripts/Makefile
@@ -10,6 +10,9 @@ hostprogs-always-$(CONFIG_BUILDTIME_TABLE_SORT)		+= sorttable
 hostprogs-always-$(CONFIG_ASN1)				+= asn1_compiler
 hostprogs-always-$(CONFIG_MODULE_SIG_FORMAT)		+= sign-file
 hostprogs-always-$(CONFIG_SYSTEM_EXTRA_CERTIFICATE)	+= insert-sys-cert
+hostprogs-always-$(CONFIG_RUST)				+= generate_rust_target
+
+generate_rust_target-rust := y
 
 HOSTCFLAGS_sorttable.o = -I$(srctree)/tools/include
 HOSTLDLIBS_sorttable = -lpthread
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 784f46d41959..27be77c0d6d8 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -26,6 +26,7 @@ EXTRA_CPPFLAGS :=
 EXTRA_LDFLAGS  :=
 asflags-y  :=
 ccflags-y  :=
+rustflags-y :=
 cppflags-y :=
 ldflags-y  :=
 
@@ -271,6 +272,65 @@ quiet_cmd_cc_lst_c = MKLST   $@
 $(obj)/%.lst: $(src)/%.c FORCE
 	$(call if_changed_dep,cc_lst_c)
 
+# Compile Rust sources (.rs)
+# ---------------------------------------------------------------------------
+
+rust_allowed_features := core_ffi_c
+
+rust_common_cmd = \
+	RUST_MODFILE=$(modfile) $(RUSTC_OR_CLIPPY) $(rust_flags) \
+	-Zallow-features=$(rust_allowed_features) \
+	-Zcrate-attr=no_std \
+	-Zcrate-attr='feature($(rust_allowed_features))' \
+	--extern alloc --extern kernel \
+	--crate-type rlib --out-dir $(obj) -L $(objtree)/rust/ \
+	--crate-name $(basename $(notdir $@))
+
+rust_handle_depfile = \
+	mv $(obj)/$(basename $(notdir $@)).d $(depfile); \
+	sed -i '/^\#/d' $(depfile)
+
+# `--emit=obj`, `--emit=asm` and `--emit=llvm-ir` imply a single codegen unit
+# will be used. We explicitly request `-Ccodegen-units=1` in any case, and
+# the compiler shows a warning if it is not 1. However, if we ever stop
+# requesting it explicitly and we start using some other `--emit` that does not
+# imply it (and for which codegen is performed), then we would be out of sync,
+# i.e. the outputs we would get for the different single targets (e.g. `.ll`)
+# would not match each other.
+
+quiet_cmd_rustc_o_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@
+      cmd_rustc_o_rs = \
+	$(rust_common_cmd) --emit=dep-info,obj $<; \
+	$(rust_handle_depfile)
+
+$(obj)/%.o: $(src)/%.rs FORCE
+	$(call if_changed_dep,rustc_o_rs)
+
+quiet_cmd_rustc_rsi_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@
+      cmd_rustc_rsi_rs = \
+	$(rust_common_cmd) --emit=dep-info -Zunpretty=expanded $< >$@; \
+	command -v $(RUSTFMT) >/dev/null && $(RUSTFMT) $@; \
+	$(rust_handle_depfile)
+
+$(obj)/%.rsi: $(src)/%.rs FORCE
+	$(call if_changed_dep,rustc_rsi_rs)
+
+quiet_cmd_rustc_s_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@
+      cmd_rustc_s_rs = \
+	$(rust_common_cmd) --emit=dep-info,asm $<; \
+	$(rust_handle_depfile)
+
+$(obj)/%.s: $(src)/%.rs FORCE
+	$(call if_changed_dep,rustc_s_rs)
+
+quiet_cmd_rustc_ll_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@
+      cmd_rustc_ll_rs = \
+	$(rust_common_cmd) --emit=dep-info,llvm-ir $<; \
+	$(rust_handle_depfile)
+
+$(obj)/%.ll: $(src)/%.rs FORCE
+	$(call if_changed_dep,rustc_ll_rs)
+
 # Compile assembler sources (.S)
 # ---------------------------------------------------------------------------
 
diff --git a/scripts/Makefile.debug b/scripts/Makefile.debug
index 9f39b0130551..332c486f705f 100644
--- a/scripts/Makefile.debug
+++ b/scripts/Makefile.debug
@@ -1,26 +1,30 @@
 DEBUG_CFLAGS	:=
+DEBUG_RUSTFLAGS	:=
+
+debug-flags-y	:= -g
 
 ifdef CONFIG_DEBUG_INFO_SPLIT
 DEBUG_CFLAGS	+= -gsplit-dwarf
-else
-DEBUG_CFLAGS	+= -g
-endif
-
-ifndef CONFIG_AS_IS_LLVM
-KBUILD_AFLAGS	+= -Wa,-gdwarf-2
 endif
 
-ifndef CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT
-dwarf-version-$(CONFIG_DEBUG_INFO_DWARF4) := 4
-dwarf-version-$(CONFIG_DEBUG_INFO_DWARF5) := 5
-DEBUG_CFLAGS	+= -gdwarf-$(dwarf-version-y)
+debug-flags-$(CONFIG_DEBUG_INFO_DWARF4)	+= -gdwarf-4
+debug-flags-$(CONFIG_DEBUG_INFO_DWARF5)	+= -gdwarf-5
+ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_AS_IS_GNU),yy)
+# Clang does not pass -g or -gdwarf-* option down to GAS.
+# Add -Wa, prefix to explicitly specify the flags.
+KBUILD_AFLAGS	+= $(addprefix -Wa$(comma), $(debug-flags-y))
 endif
+DEBUG_CFLAGS	+= $(debug-flags-y)
+KBUILD_AFLAGS	+= $(debug-flags-y)
 
 ifdef CONFIG_DEBUG_INFO_REDUCED
 DEBUG_CFLAGS	+= -fno-var-tracking
+DEBUG_RUSTFLAGS	+= -Cdebuginfo=1
 ifdef CONFIG_CC_IS_GCC
 DEBUG_CFLAGS	+= -femit-struct-debug-baseonly
 endif
+else
+DEBUG_RUSTFLAGS	+= -Cdebuginfo=2
 endif
 
 ifdef CONFIG_DEBUG_INFO_COMPRESSED
@@ -29,5 +33,8 @@ KBUILD_AFLAGS	+= -gz=zlib
 KBUILD_LDFLAGS	+= --compress-debug-sections=zlib
 endif
 
-KBUILD_CFLAGS += $(DEBUG_CFLAGS)
+KBUILD_CFLAGS	+= $(DEBUG_CFLAGS)
 export DEBUG_CFLAGS
+
+KBUILD_RUSTFLAGS += $(DEBUG_RUSTFLAGS)
+export DEBUG_RUSTFLAGS
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index f5f0d6f09053..52bd7df84fd6 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -47,12 +47,24 @@ else
 
 ifdef CONFIG_CC_IS_CLANG
 KBUILD_CFLAGS += -Wno-initializer-overrides
+# Clang before clang-16 would warn on default argument promotions.
+ifeq ($(shell [ $(CONFIG_CLANG_VERSION) -lt 160000 ] && echo y),y)
+# Disable -Wformat
 KBUILD_CFLAGS += -Wno-format
+# Then re-enable flags that were part of the -Wformat group that aren't
+# problematic.
+KBUILD_CFLAGS += -Wformat-extra-args -Wformat-invalid-specifier
+KBUILD_CFLAGS += -Wformat-zero-length -Wnonnull
+# Requires clang-12+.
+ifeq ($(shell [ $(CONFIG_CLANG_VERSION) -ge 120000 ] && echo y),y)
+KBUILD_CFLAGS += -Wformat-insufficient-args
+endif
+endif
 KBUILD_CFLAGS += -Wno-sign-compare
-KBUILD_CFLAGS += -Wno-format-zero-length
 KBUILD_CFLAGS += $(call cc-disable-warning, pointer-to-enum-cast)
 KBUILD_CFLAGS += -Wno-tautological-constant-out-of-range-compare
 KBUILD_CFLAGS += $(call cc-disable-warning, unaligned-access)
+KBUILD_CFLAGS += $(call cc-disable-warning, cast-function-type-strict)
 endif
 
 endif
diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins
index 692d64a70542..e4deaf5fa571 100644
--- a/scripts/Makefile.gcc-plugins
+++ b/scripts/Makefile.gcc-plugins
@@ -4,7 +4,7 @@ gcc-plugin-$(CONFIG_GCC_PLUGIN_LATENT_ENTROPY)	+= latent_entropy_plugin.so
 gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_LATENT_ENTROPY)		\
 		+= -DLATENT_ENTROPY_PLUGIN
 ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
-    DISABLE_LATENT_ENTROPY_PLUGIN += -fplugin-arg-latent_entropy_plugin-disable
+    DISABLE_LATENT_ENTROPY_PLUGIN += -fplugin-arg-latent_entropy_plugin-disable -ULATENT_ENTROPY_PLUGIN
 endif
 export DISABLE_LATENT_ENTROPY_PLUGIN
 
diff --git a/scripts/Makefile.host b/scripts/Makefile.host
index 278b4d6ac945..da133780b751 100644
--- a/scripts/Makefile.host
+++ b/scripts/Makefile.host
@@ -22,6 +22,8 @@ $(obj)/%.tab.c $(obj)/%.tab.h: $(src)/%.y FORCE
 # to preprocess a data file.
 #
 # Both C and C++ are supported, but preferred language is C for such utilities.
+# Rust is also supported, but it may only be used in scenarios where a Rust
+# toolchain is required to be available (e.g. when  `CONFIG_RUST` is enabled).
 #
 # Sample syntax (see Documentation/kbuild/makefiles.rst for reference)
 # hostprogs := bin2hex
@@ -37,15 +39,20 @@ $(obj)/%.tab.c $(obj)/%.tab.h: $(src)/%.y FORCE
 # qconf-objs      := menu.o
 # Will compile qconf as a C++ program, and menu as a C program.
 # They are linked as C++ code to the executable qconf
+#
+# hostprogs   := target
+# target-rust := y
+# Will compile `target` as a Rust program, using `target.rs` as the crate root.
+# The crate may consist of several source files.
 
 # C code
 # Executables compiled from a single .c file
 host-csingle	:= $(foreach m,$(hostprogs), \
-			$(if $($(m)-objs)$($(m)-cxxobjs),,$(m)))
+			$(if $($(m)-objs)$($(m)-cxxobjs)$($(m)-rust),,$(m)))
 
 # C executables linked based on several .o files
 host-cmulti	:= $(foreach m,$(hostprogs),\
-		   $(if $($(m)-cxxobjs),,$(if $($(m)-objs),$(m))))
+		   $(if $($(m)-cxxobjs)$($(m)-rust),,$(if $($(m)-objs),$(m))))
 
 # Object (.o) files compiled from .c files
 host-cobjs	:= $(sort $(foreach m,$(hostprogs),$($(m)-objs)))
@@ -58,11 +65,17 @@ host-cxxmulti	:= $(foreach m,$(hostprogs),$(if $($(m)-cxxobjs),$(m)))
 # C++ Object (.o) files compiled from .cc files
 host-cxxobjs	:= $(sort $(foreach m,$(host-cxxmulti),$($(m)-cxxobjs)))
 
+# Rust code
+# Executables compiled from a single Rust crate (which may consist of
+# one or more .rs files)
+host-rust	:= $(foreach m,$(hostprogs),$(if $($(m)-rust),$(m)))
+
 host-csingle	:= $(addprefix $(obj)/,$(host-csingle))
 host-cmulti	:= $(addprefix $(obj)/,$(host-cmulti))
 host-cobjs	:= $(addprefix $(obj)/,$(host-cobjs))
 host-cxxmulti	:= $(addprefix $(obj)/,$(host-cxxmulti))
 host-cxxobjs	:= $(addprefix $(obj)/,$(host-cxxobjs))
+host-rust	:= $(addprefix $(obj)/,$(host-rust))
 
 #####
 # Handle options to gcc. Support building with separate output directory
@@ -71,6 +84,8 @@ _hostc_flags   = $(KBUILD_HOSTCFLAGS)   $(HOST_EXTRACFLAGS)   \
                  $(HOSTCFLAGS_$(target-stem).o)
 _hostcxx_flags = $(KBUILD_HOSTCXXFLAGS) $(HOST_EXTRACXXFLAGS) \
                  $(HOSTCXXFLAGS_$(target-stem).o)
+_hostrust_flags = $(KBUILD_HOSTRUSTFLAGS) $(HOST_EXTRARUSTFLAGS) \
+                  $(HOSTRUSTFLAGS_$(target-stem))
 
 # $(objtree)/$(obj) for including generated headers from checkin source files
 ifeq ($(KBUILD_EXTMOD),)
@@ -82,6 +97,7 @@ endif
 
 hostc_flags    = -Wp,-MMD,$(depfile) $(_hostc_flags)
 hostcxx_flags  = -Wp,-MMD,$(depfile) $(_hostcxx_flags)
+hostrust_flags = $(_hostrust_flags)
 
 #####
 # Compile programs on the host
@@ -128,5 +144,17 @@ quiet_cmd_host-cxxobjs	= HOSTCXX $@
 $(host-cxxobjs): $(obj)/%.o: $(src)/%.cc FORCE
 	$(call if_changed_dep,host-cxxobjs)
 
+# Create executable from a single Rust crate (which may consist of
+# one or more `.rs` files)
+# host-rust -> Executable
+quiet_cmd_host-rust	= HOSTRUSTC $@
+      cmd_host-rust	= \
+	$(HOSTRUSTC) $(hostrust_flags) --emit=dep-info,link \
+		--out-dir=$(obj)/ $<; \
+	mv $(obj)/$(target-stem).d $(depfile); \
+	sed -i '/^\#/d' $(depfile)
+$(host-rust): $(obj)/%: $(src)/%.rs FORCE
+	$(call if_changed_dep,host-rust)
+
 targets += $(host-csingle) $(host-cmulti) $(host-cobjs) \
-	   $(host-cxxmulti) $(host-cxxobjs)
+	   $(host-cxxmulti) $(host-cxxobjs) $(host-rust)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 3fb6a99e78c4..c88b98b5dc44 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -8,6 +8,7 @@ ldflags-y  += $(EXTRA_LDFLAGS)
 # flags that take effect in current and sub directories
 KBUILD_AFLAGS += $(subdir-asflags-y)
 KBUILD_CFLAGS += $(subdir-ccflags-y)
+KBUILD_RUSTFLAGS += $(subdir-rustflags-y)
 
 # Figure out what we need to build from the various variables
 # ===========================================================================
@@ -128,6 +129,10 @@ _c_flags       = $(filter-out $(CFLAGS_REMOVE_$(target-stem).o), \
                      $(filter-out $(ccflags-remove-y), \
                          $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(ccflags-y)) \
                      $(CFLAGS_$(target-stem).o))
+_rust_flags    = $(filter-out $(RUSTFLAGS_REMOVE_$(target-stem).o), \
+                     $(filter-out $(rustflags-remove-y), \
+                         $(KBUILD_RUSTFLAGS) $(rustflags-y)) \
+                     $(RUSTFLAGS_$(target-stem).o))
 _a_flags       = $(filter-out $(AFLAGS_REMOVE_$(target-stem).o), \
                      $(filter-out $(asflags-remove-y), \
                          $(KBUILD_CPPFLAGS) $(KBUILD_AFLAGS) $(asflags-y)) \
@@ -202,6 +207,11 @@ modkern_cflags =                                          \
 		$(KBUILD_CFLAGS_MODULE) $(CFLAGS_MODULE), \
 		$(KBUILD_CFLAGS_KERNEL) $(CFLAGS_KERNEL) $(modfile_flags))
 
+modkern_rustflags =                                              \
+	$(if $(part-of-module),                                   \
+		$(KBUILD_RUSTFLAGS_MODULE) $(RUSTFLAGS_MODULE), \
+		$(KBUILD_RUSTFLAGS_KERNEL) $(RUSTFLAGS_KERNEL))
+
 modkern_aflags = $(if $(part-of-module),				\
 			$(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE),	\
 			$(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL))
@@ -211,6 +221,8 @@ c_flags        = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE)     \
 		 $(_c_flags) $(modkern_cflags)                           \
 		 $(basename_flags) $(modname_flags)
 
+rust_flags     = $(_rust_flags) $(modkern_rustflags) @$(objtree)/include/generated/rustc_cfg
+
 a_flags        = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE)     \
 		 $(_a_flags) $(modkern_aflags)
 
diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
index 35100e981f4a..9a1fa6aa30fe 100644
--- a/scripts/Makefile.modfinal
+++ b/scripts/Makefile.modfinal
@@ -39,11 +39,13 @@ quiet_cmd_ld_ko_o = LD [M]  $@
 
 quiet_cmd_btf_ko = BTF [M] $@
       cmd_btf_ko = 							\
-	if [ -f vmlinux ]; then						\
+	if [ ! -f vmlinux ]; then					\
+		printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \
+	elif [ -n "$(CONFIG_RUST)" ] && $(srctree)/scripts/is_rust_module.sh $@; then 		\
+		printf "Skipping BTF generation for %s because it's a Rust module\n" $@ 1>&2; \
+	else								\
 		LLVM_OBJCOPY="$(OBJCOPY)" $(PAHOLE) -J $(PAHOLE_FLAGS) --btf_base vmlinux $@; \
 		$(RESOLVE_BTFIDS) -b vmlinux $@; 			\
-	else								\
-		printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \
 	fi;
 
 # Same as newer-prereqs, but allows to exclude specified extra dependencies
diff --git a/scripts/cc-version.sh b/scripts/cc-version.sh
index f1952c522466..2401c86fcf53 100755
--- a/scripts/cc-version.sh
+++ b/scripts/cc-version.sh
@@ -1,13 +1,13 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 #
-# Print the compiler name and its version in a 5 or 6-digit form.
+# Print the C compiler name and its version in a 5 or 6-digit form.
 # Also, perform the minimum version check.
 
 set -e
 
-# Print the compiler name and some version components.
-get_compiler_info()
+# Print the C compiler name and some version components.
+get_c_compiler_info()
 {
 	cat <<- EOF | "$@" -E -P -x c - 2>/dev/null
 	#if defined(__clang__)
@@ -32,7 +32,7 @@ get_canonical_version()
 
 # $@ instead of $1 because multiple words might be given, e.g. CC="ccache gcc".
 orig_args="$@"
-set -- $(get_compiler_info "$@")
+set -- $(get_c_compiler_info "$@")
 
 name=$1
 
@@ -52,7 +52,7 @@ ICC)
 	min_version=$($min_tool_version icc)
 	;;
 *)
-	echo "$orig_args: unknown compiler" >&2
+	echo "$orig_args: unknown C compiler" >&2
 	exit 1
 	;;
 esac
@@ -62,7 +62,7 @@ min_cversion=$(get_canonical_version $min_version)
 
 if [ "$cversion" -lt "$min_cversion" ]; then
 	echo >&2 "***"
-	echo >&2 "*** Compiler is too old."
+	echo >&2 "*** C compiler is too old."
 	echo >&2 "***   Your $name version:    $version"
 	echo >&2 "***   Minimum $name version: $min_version"
 	echo >&2 "***"
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 79e759aac543..c8a616a9d034 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -3616,7 +3616,7 @@ sub process {
 				my $comment = "";
 				if ($realfile =~ /\.(h|s|S)$/) {
 					$comment = '/*';
-				} elsif ($realfile =~ /\.(c|dts|dtsi)$/) {
+				} elsif ($realfile =~ /\.(c|rs|dts|dtsi)$/) {
 					$comment = '//';
 				} elsif (($checklicenseline == 2) || $realfile =~ /\.(sh|pl|py|awk|tc|yaml)$/) {
 					$comment = '#';
@@ -3664,7 +3664,7 @@ sub process {
 		}
 
 # check we are in a valid source file if not then ignore this hunk
-		next if ($realfile !~ /\.(h|c|s|S|sh|dtsi|dts)$/);
+		next if ($realfile !~ /\.(h|c|rs|s|S|sh|dtsi|dts)$/);
 
 # check for using SPDX-License-Identifier on the wrong line number
 		if ($realline != $checklicenseline &&
@@ -3751,7 +3751,7 @@ sub process {
 		if ($realfile =~ /\.S$/ &&
 		    $line =~ /^\+\s*(?:[A-Z]+_)?SYM_[A-Z]+_(?:START|END)(?:_[A-Z_]+)?\s*\(\s*\.L/) {
 			WARN("AVOID_L_PREFIX",
-			     "Avoid using '.L' prefixed local symbol names for denoting a range of code via 'SYM_*_START/END' annotations; see Documentation/asm-annotations.rst\n" . $herecurr);
+			     "Avoid using '.L' prefixed local symbol names for denoting a range of code via 'SYM_*_START/END' annotations; see Documentation/core-api/asm-annotations.rst\n" . $herecurr);
 		}
 
 # check we are in a valid source file C or perl if not then ignore this hunk
@@ -4695,12 +4695,12 @@ sub process {
 			}
 		}
 
-# avoid BUG() or BUG_ON()
-		if ($line =~ /\b(?:BUG|BUG_ON)\b/) {
+# do not use BUG() or variants
+		if ($line =~ /\b(?!AA_|BUILD_|DCCP_|IDA_|KVM_|RWLOCK_|snd_|SPIN_)(?:[a-zA-Z_]*_)?BUG(?:_ON)?(?:_[A-Z_]+)?\s*\(/) {
 			my $msg_level = \&WARN;
 			$msg_level = \&CHK if ($file);
 			&{$msg_level}("AVOID_BUG",
-				      "Avoid crashing the kernel - try using WARN_ON & recovery code rather than BUG() or BUG_ON()\n" . $herecurr);
+				      "Do not crash the kernel unless it is absolutely unavoidable--use WARN_ON_ONCE() plus recovery code (if feasible) instead of BUG() or variants\n" . $herecurr);
 		}
 
 # avoid LINUX_VERSION_CODE
@@ -6783,15 +6783,19 @@ sub process {
 				}
 				if ($bad_specifier ne "") {
 					my $stat_real = get_stat_real($linenr, $lc);
+					my $msg_level = \&WARN;
 					my $ext_type = "Invalid";
 					my $use = "";
 					if ($bad_specifier =~ /p[Ff]/) {
 						$use = " - use %pS instead";
 						$use =~ s/pS/ps/ if ($bad_specifier =~ /pf/);
+					} elsif ($bad_specifier =~ /pA/) {
+						$use =  " - '%pA' is only intended to be used from Rust code";
+						$msg_level = \&ERROR;
 					}
 
-					WARN("VSPRINTF_POINTER_EXTENSION",
-					     "$ext_type vsprintf pointer extension '$bad_specifier'$use\n" . "$here\n$stat_real\n");
+					&{$msg_level}("VSPRINTF_POINTER_EXTENSION",
+						      "$ext_type vsprintf pointer extension '$bad_specifier'$use\n" . "$here\n$stat_real\n");
 				}
 			}
 		}
diff --git a/scripts/clang-tools/run-clang-tools.py b/scripts/clang-tools/run-clang-tools.py
index f754415af398..bb78c9bde55c 100755
--- a/scripts/clang-tools/run-clang-tools.py
+++ b/scripts/clang-tools/run-clang-tools.py
@@ -12,7 +12,6 @@ compile_commands.json.
 import argparse
 import json
 import multiprocessing
-import os
 import subprocess
 import sys
 
@@ -51,6 +50,7 @@ def run_analysis(entry):
         checks += "linuxkernel-*"
     else:
         checks += "clang-analyzer-*"
+        checks += ",-clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling"
     p = subprocess.run(["clang-tidy", "-p", args.path, checks, entry["file"]],
                        stdout=subprocess.PIPE,
                        stderr=subprocess.STDOUT,
diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh
index 7075e26ab2c4..564c5632e1a2 100755
--- a/scripts/decode_stacktrace.sh
+++ b/scripts/decode_stacktrace.sh
@@ -8,6 +8,14 @@ usage() {
 	echo "	$0 -r <release> | <vmlinux> [<base path>|auto] [<modules path>]"
 }
 
+# Try to find a Rust demangler
+if type llvm-cxxfilt >/dev/null 2>&1 ; then
+	cppfilt=llvm-cxxfilt
+elif type c++filt >/dev/null 2>&1 ; then
+	cppfilt=c++filt
+	cppfilt_opts=-i
+fi
+
 if [[ $1 == "-r" ]] ; then
 	vmlinux=""
 	basepath="auto"
@@ -180,6 +188,12 @@ parse_symbol() {
 	# In the case of inlines, move everything to same line
 	code=${code//$'\n'/' '}
 
+	# Demangle if the name looks like a Rust symbol and if
+	# we got a Rust demangler
+	if [[ $name =~ ^_R && $cppfilt != "" ]] ; then
+		name=$("$cppfilt" "$cppfilt_opts" "$name")
+	fi
+
 	# Replace old address with pretty line numbers
 	symbol="$segment$name ($code)"
 }
diff --git a/scripts/dummy-tools/gcc b/scripts/dummy-tools/gcc
index 7db825843435..1db1889f6d81 100755
--- a/scripts/dummy-tools/gcc
+++ b/scripts/dummy-tools/gcc
@@ -59,7 +59,7 @@ fi
 if arg_contain -E "$@"; then
 	# For scripts/cc-version.sh; This emulates GCC 20.0.0
 	if arg_contain - "$@"; then
-		sed -n '/^GCC/{s/__GNUC__/20/; s/__GNUC_MINOR__/0/; s/__GNUC_PATCHLEVEL__/0/; p;}'
+		sed -n '/^GCC/{s/__GNUC__/20/; s/__GNUC_MINOR__/0/; s/__GNUC_PATCHLEVEL__/0/; p;}; s/__LONG_DOUBLE_128__/1/ p'
 		exit 0
 	else
 		echo "no input files" >&2
diff --git a/scripts/extract-ikconfig b/scripts/extract-ikconfig
index 3b42f255e2ba..8df33e7d6daa 100755
--- a/scripts/extract-ikconfig
+++ b/scripts/extract-ikconfig
@@ -62,6 +62,7 @@ try_decompress 'BZh'          xy    bunzip2
 try_decompress '\135\0\0\0'   xxx   unlzma
 try_decompress '\211\114\132' xy    'lzop -d'
 try_decompress '\002\041\114\030' xyy 'lz4 -d -l'
+try_decompress '\050\265\057\375' xxx unzstd
 
 # Bail out:
 echo "$me: Cannot find kernel config." >&2
diff --git a/scripts/gcc-goto.sh b/scripts/gcc-goto.sh
deleted file mode 100755
index 8b980fb2270a..000000000000
--- a/scripts/gcc-goto.sh
+++ /dev/null
@@ -1,22 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-# Test for gcc 'asm goto' support
-# Copyright (C) 2010, Jason Baron <jbaron@redhat.com>
-
-cat << "END" | $@ -x c - -fno-PIE -c -o /dev/null
-int main(void)
-{
-#if defined(__arm__) || defined(__aarch64__)
-	/*
-	 * Not related to asm goto, but used by jump label
-	 * and broken on some ARM GCC versions (see GCC Bug 48637).
-	 */
-	static struct { int dummy; int state; } tp;
-	asm (".long %c0" :: "i" (&tp.state));
-#endif
-
-entry:
-	asm goto ("" :::: entry);
-	return 0;
-}
-END
diff --git a/scripts/gcc-ld b/scripts/gcc-ld
deleted file mode 100755
index 997b818c3962..000000000000
--- a/scripts/gcc-ld
+++ /dev/null
@@ -1,30 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-# run gcc with ld options
-# used as a wrapper to execute link time optimizations
-# yes virginia, this is not pretty
-
-ARGS="-nostdlib"
-
-while [ "$1" != "" ] ; do
-	case "$1" in
-	-save-temps|-m32|-m64) N="$1" ;;
-	-r) N="$1" ;;
-	-[Wg]*) N="$1" ;;
-	-[olv]|-[Ofd]*|-nostdlib) N="$1" ;;
-	--end-group|--start-group)
-		 N="-Wl,$1" ;;
-	-[RTFGhIezcbyYu]*|\
---script|--defsym|-init|-Map|--oformat|-rpath|\
--rpath-link|--sort-section|--section-start|-Tbss|-Tdata|-Ttext|\
---version-script|--dynamic-list|--version-exports-symbol|--wrap|-m)
-		A="$1" ; shift ; N="-Wl,$A,$1" ;;
-	-[m]*) N="$1" ;;
-	-*) N="-Wl,$1" ;;
-	*)  N="$1" ;;
-	esac
-	ARGS="$ARGS $N"
-	shift
-done
-
-exec $CC $ARGS
diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py
new file mode 100755
index 000000000000..75bb611bd751
--- /dev/null
+++ b/scripts/generate_rust_analyzer.py
@@ -0,0 +1,135 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+"""generate_rust_analyzer - Generates the `rust-project.json` file for `rust-analyzer`.
+"""
+
+import argparse
+import json
+import logging
+import pathlib
+import sys
+
+def generate_crates(srctree, objtree, sysroot_src):
+    # Generate the configuration list.
+    cfg = []
+    with open(objtree / "include" / "generated" / "rustc_cfg") as fd:
+        for line in fd:
+            line = line.replace("--cfg=", "")
+            line = line.replace("\n", "")
+            cfg.append(line)
+
+    # Now fill the crates list -- dependencies need to come first.
+    #
+    # Avoid O(n^2) iterations by keeping a map of indexes.
+    crates = []
+    crates_indexes = {}
+
+    def append_crate(display_name, root_module, deps, cfg=[], is_workspace_member=True, is_proc_macro=False):
+        crates_indexes[display_name] = len(crates)
+        crates.append({
+            "display_name": display_name,
+            "root_module": str(root_module),
+            "is_workspace_member": is_workspace_member,
+            "is_proc_macro": is_proc_macro,
+            "deps": [{"crate": crates_indexes[dep], "name": dep} for dep in deps],
+            "cfg": cfg,
+            "edition": "2021",
+            "env": {
+                "RUST_MODFILE": "This is only for rust-analyzer"
+            }
+        })
+
+    # First, the ones in `rust/` since they are a bit special.
+    append_crate(
+        "core",
+        sysroot_src / "core" / "src" / "lib.rs",
+        [],
+        is_workspace_member=False,
+    )
+
+    append_crate(
+        "compiler_builtins",
+        srctree / "rust" / "compiler_builtins.rs",
+        [],
+    )
+
+    append_crate(
+        "alloc",
+        srctree / "rust" / "alloc" / "lib.rs",
+        ["core", "compiler_builtins"],
+    )
+
+    append_crate(
+        "macros",
+        srctree / "rust" / "macros" / "lib.rs",
+        [],
+        is_proc_macro=True,
+    )
+    crates[-1]["proc_macro_dylib_path"] = "rust/libmacros.so"
+
+    append_crate(
+        "bindings",
+        srctree / "rust"/ "bindings" / "lib.rs",
+        ["core"],
+        cfg=cfg,
+    )
+    crates[-1]["env"]["OBJTREE"] = str(objtree.resolve(True))
+
+    append_crate(
+        "kernel",
+        srctree / "rust" / "kernel" / "lib.rs",
+        ["core", "alloc", "macros", "bindings"],
+        cfg=cfg,
+    )
+    crates[-1]["source"] = {
+        "include_dirs": [
+            str(srctree / "rust" / "kernel"),
+            str(objtree / "rust")
+        ],
+        "exclude_dirs": [],
+    }
+
+    # Then, the rest outside of `rust/`.
+    #
+    # We explicitly mention the top-level folders we want to cover.
+    for folder in ("samples", "drivers"):
+        for path in (srctree / folder).rglob("*.rs"):
+            logging.info("Checking %s", path)
+            name = path.name.replace(".rs", "")
+
+            # Skip those that are not crate roots.
+            if f"{name}.o" not in open(path.parent / "Makefile").read():
+                continue
+
+            logging.info("Adding %s", name)
+            append_crate(
+                name,
+                path,
+                ["core", "alloc", "kernel"],
+                cfg=cfg,
+            )
+
+    return crates
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--verbose', '-v', action='store_true')
+    parser.add_argument("srctree", type=pathlib.Path)
+    parser.add_argument("objtree", type=pathlib.Path)
+    parser.add_argument("sysroot_src", type=pathlib.Path)
+    args = parser.parse_args()
+
+    logging.basicConfig(
+        format="[%(asctime)s] [%(levelname)s] %(message)s",
+        level=logging.INFO if args.verbose else logging.WARNING
+    )
+
+    rust_project = {
+        "crates": generate_crates(args.srctree, args.objtree, args.sysroot_src),
+        "sysroot_src": str(args.sysroot_src),
+    }
+
+    json.dump(rust_project, sys.stdout, sort_keys=True, indent=4)
+
+if __name__ == "__main__":
+    main()
diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs
new file mode 100644
index 000000000000..3c6cbe2b278d
--- /dev/null
+++ b/scripts/generate_rust_target.rs
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! The custom target specification file generator for `rustc`.
+//!
+//! To configure a target from scratch, a JSON-encoded file has to be passed
+//! to `rustc` (introduced in [RFC 131]). These options and the file itself are
+//! unstable. Eventually, `rustc` should provide a way to do this in a stable
+//! manner. For instance, via command-line arguments. Therefore, this file
+//! should avoid using keys which can be set via `-C` or `-Z` options.
+//!
+//! [RFC 131]: https://rust-lang.github.io/rfcs/0131-target-specification.html
+
+use std::{
+    collections::HashMap,
+    fmt::{Display, Formatter, Result},
+    io::BufRead,
+};
+
+enum Value {
+    Boolean(bool),
+    Number(i32),
+    String(String),
+    Object(Object),
+}
+
+type Object = Vec<(String, Value)>;
+
+/// Minimal "almost JSON" generator (e.g. no `null`s, no arrays, no escaping),
+/// enough for this purpose.
+impl Display for Value {
+    fn fmt(&self, formatter: &mut Formatter<'_>) -> Result {
+        match self {
+            Value::Boolean(boolean) => write!(formatter, "{}", boolean),
+            Value::Number(number) => write!(formatter, "{}", number),
+            Value::String(string) => write!(formatter, "\"{}\"", string),
+            Value::Object(object) => {
+                formatter.write_str("{")?;
+                if let [ref rest @ .., ref last] = object[..] {
+                    for (key, value) in rest {
+                        write!(formatter, "\"{}\": {},", key, value)?;
+                    }
+                    write!(formatter, "\"{}\": {}", last.0, last.1)?;
+                }
+                formatter.write_str("}")
+            }
+        }
+    }
+}
+
+struct TargetSpec(Object);
+
+impl TargetSpec {
+    fn new() -> TargetSpec {
+        TargetSpec(Vec::new())
+    }
+}
+
+trait Push<T> {
+    fn push(&mut self, key: &str, value: T);
+}
+
+impl Push<bool> for TargetSpec {
+    fn push(&mut self, key: &str, value: bool) {
+        self.0.push((key.to_string(), Value::Boolean(value)));
+    }
+}
+
+impl Push<i32> for TargetSpec {
+    fn push(&mut self, key: &str, value: i32) {
+        self.0.push((key.to_string(), Value::Number(value)));
+    }
+}
+
+impl Push<String> for TargetSpec {
+    fn push(&mut self, key: &str, value: String) {
+        self.0.push((key.to_string(), Value::String(value)));
+    }
+}
+
+impl Push<&str> for TargetSpec {
+    fn push(&mut self, key: &str, value: &str) {
+        self.push(key, value.to_string());
+    }
+}
+
+impl Push<Object> for TargetSpec {
+    fn push(&mut self, key: &str, value: Object) {
+        self.0.push((key.to_string(), Value::Object(value)));
+    }
+}
+
+impl Display for TargetSpec {
+    fn fmt(&self, formatter: &mut Formatter<'_>) -> Result {
+        // We add some newlines for clarity.
+        formatter.write_str("{\n")?;
+        if let [ref rest @ .., ref last] = self.0[..] {
+            for (key, value) in rest {
+                write!(formatter, "    \"{}\": {},\n", key, value)?;
+            }
+            write!(formatter, "    \"{}\": {}\n", last.0, last.1)?;
+        }
+        formatter.write_str("}")
+    }
+}
+
+struct KernelConfig(HashMap<String, String>);
+
+impl KernelConfig {
+    /// Parses `include/config/auto.conf` from `stdin`.
+    fn from_stdin() -> KernelConfig {
+        let mut result = HashMap::new();
+
+        let stdin = std::io::stdin();
+        let mut handle = stdin.lock();
+        let mut line = String::new();
+
+        loop {
+            line.clear();
+
+            if handle.read_line(&mut line).unwrap() == 0 {
+                break;
+            }
+
+            if line.starts_with('#') {
+                continue;
+            }
+
+            let (key, value) = line.split_once('=').expect("Missing `=` in line.");
+            result.insert(key.to_string(), value.trim_end_matches('\n').to_string());
+        }
+
+        KernelConfig(result)
+    }
+
+    /// Does the option exist in the configuration (any value)?
+    ///
+    /// The argument must be passed without the `CONFIG_` prefix.
+    /// This avoids repetition and it also avoids `fixdep` making us
+    /// depend on it.
+    fn has(&self, option: &str) -> bool {
+        let option = "CONFIG_".to_owned() + option;
+        self.0.contains_key(&option)
+    }
+}
+
+fn main() {
+    let cfg = KernelConfig::from_stdin();
+    let mut ts = TargetSpec::new();
+
+    // `llvm-target`s are taken from `scripts/Makefile.clang`.
+    if cfg.has("X86_64") {
+        ts.push("arch", "x86_64");
+        ts.push(
+            "data-layout",
+            "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128",
+        );
+        let mut features = "-3dnow,-3dnowa,-mmx,+soft-float".to_string();
+        if cfg.has("RETPOLINE") {
+            features += ",+retpoline-external-thunk";
+        }
+        ts.push("features", features);
+        ts.push("llvm-target", "x86_64-linux-gnu");
+        ts.push("target-pointer-width", "64");
+    } else {
+        panic!("Unsupported architecture");
+    }
+
+    ts.push("emit-debug-gdb-scripts", false);
+    ts.push("frame-pointer", "may-omit");
+    ts.push(
+        "stack-probes",
+        vec![("kind".to_string(), Value::String("none".to_string()))],
+    );
+
+    // Everything else is LE, whether `CPU_LITTLE_ENDIAN` is declared or not
+    // (e.g. x86). It is also `rustc`'s default.
+    if cfg.has("CPU_BIG_ENDIAN") {
+        ts.push("target-endian", "big");
+    }
+
+    println!("{}", ts);
+}
diff --git a/scripts/is_rust_module.sh b/scripts/is_rust_module.sh
new file mode 100755
index 000000000000..28b3831a7593
--- /dev/null
+++ b/scripts/is_rust_module.sh
@@ -0,0 +1,16 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# is_rust_module.sh module.ko
+#
+# Returns `0` if `module.ko` is a Rust module, `1` otherwise.
+
+set -e
+
+# Using the `16_` prefix ensures other symbols with the same substring
+# are not picked up (even if it would be unlikely). The last part is
+# used just in case LLVM decides to use the `.` suffix.
+#
+# In the future, checking for the `.comment` section may be another
+# option, see https://github.com/rust-lang/rust/pull/97550.
+${NM} "$*" | grep -qE '^[0-9a-fA-F]+ r _R[^[:space:]]+16___IS_RUST_MODULE[^[:space:]]*$'
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index f18e6dfc68c5..ff5e7810e437 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -27,7 +27,23 @@
 
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
 
-#define KSYM_NAME_LEN		128
+#define _stringify_1(x)	#x
+#define _stringify(x)	_stringify_1(x)
+
+#define KSYM_NAME_LEN		512
+
+/*
+ * A substantially bigger size than the current maximum.
+ *
+ * It cannot be defined as an expression because it gets stringified
+ * for the fscanf() format string. Therefore, a _Static_assert() is
+ * used instead to maintain the relationship with KSYM_NAME_LEN.
+ */
+#define KSYM_NAME_LEN_BUFFER	2048
+_Static_assert(
+	KSYM_NAME_LEN_BUFFER == KSYM_NAME_LEN * 4,
+	"Please keep KSYM_NAME_LEN_BUFFER in sync with KSYM_NAME_LEN"
+);
 
 struct sym_entry {
 	unsigned long long addr;
@@ -119,6 +135,7 @@ static bool is_ignored_symbol(const char *name, char type)
 		"__ThumbV7PILongThunk_",
 		"__LA25Thunk_",		/* mips lld */
 		"__microLA25Thunk_",
+		"__kcfi_typeid_",	/* CFI type identifiers */
 		NULL
 	};
 
@@ -198,15 +215,15 @@ static void check_symbol_range(const char *sym, unsigned long long addr,
 
 static struct sym_entry *read_symbol(FILE *in)
 {
-	char name[500], type;
+	char name[KSYM_NAME_LEN_BUFFER+1], type;
 	unsigned long long addr;
 	unsigned int len;
 	struct sym_entry *sym;
 	int rc;
 
-	rc = fscanf(in, "%llx %c %499s\n", &addr, &type, name);
+	rc = fscanf(in, "%llx %c %" _stringify(KSYM_NAME_LEN_BUFFER) "s\n", &addr, &type, name);
 	if (rc != 3) {
-		if (rc != EOF && fgets(name, 500, in) == NULL)
+		if (rc != EOF && fgets(name, ARRAY_SIZE(name), in) == NULL)
 			fprintf(stderr, "Read error or end of file.\n");
 		return NULL;
 	}
@@ -471,12 +488,35 @@ static void write_src(void)
 		if ((i & 0xFF) == 0)
 			markers[i >> 8] = off;
 
-		printf("\t.byte 0x%02x", table[i]->len);
+		/* There cannot be any symbol of length zero. */
+		if (table[i]->len == 0) {
+			fprintf(stderr, "kallsyms failure: "
+				"unexpected zero symbol length\n");
+			exit(EXIT_FAILURE);
+		}
+
+		/* Only lengths that fit in up-to-two-byte ULEB128 are supported. */
+		if (table[i]->len > 0x3FFF) {
+			fprintf(stderr, "kallsyms failure: "
+				"unexpected huge symbol length\n");
+			exit(EXIT_FAILURE);
+		}
+
+		/* Encode length with ULEB128. */
+		if (table[i]->len <= 0x7F) {
+			/* Most symbols use a single byte for the length. */
+			printf("\t.byte 0x%02x", table[i]->len);
+			off += table[i]->len + 1;
+		} else {
+			/* "Big" symbols use two bytes. */
+			printf("\t.byte 0x%02x, 0x%02x",
+				(table[i]->len & 0x7F) | 0x80,
+				(table[i]->len >> 7) & 0x7F);
+			off += table[i]->len + 2;
+		}
 		for (k = 0; k < table[i]->len; k++)
 			printf(", 0x%02x", table[i]->sym[k]);
 		printf("\n");
-
-		off += table[i]->len + 1;
 	}
 	printf("\n");
 
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index c4340c90e172..b7c9f1dd5e42 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -216,6 +216,13 @@ static const char *conf_get_autoheader_name(void)
 	return name ? name : "include/generated/autoconf.h";
 }
 
+static const char *conf_get_rustccfg_name(void)
+{
+	char *name = getenv("KCONFIG_RUSTCCFG");
+
+	return name ? name : "include/generated/rustc_cfg";
+}
+
 static int conf_set_sym_val(struct symbol *sym, int def, int def_flags, char *p)
 {
 	char *p2;
@@ -605,6 +612,9 @@ static const struct comment_style comment_style_c = {
 
 static void conf_write_heading(FILE *fp, const struct comment_style *cs)
 {
+	if (!cs)
+		return;
+
 	fprintf(fp, "%s\n", cs->prefix);
 
 	fprintf(fp, "%s Automatically generated file; DO NOT EDIT.\n",
@@ -745,6 +755,65 @@ static void print_symbol_for_c(FILE *fp, struct symbol *sym)
 	free(escaped);
 }
 
+static void print_symbol_for_rustccfg(FILE *fp, struct symbol *sym)
+{
+	const char *val;
+	const char *val_prefix = "";
+	char *val_prefixed = NULL;
+	size_t val_prefixed_len;
+	char *escaped = NULL;
+
+	if (sym->type == S_UNKNOWN)
+		return;
+
+	val = sym_get_string_value(sym);
+
+	switch (sym->type) {
+	case S_BOOLEAN:
+	case S_TRISTATE:
+		/*
+		 * We do not care about disabled ones, i.e. no need for
+		 * what otherwise are "comments" in other printers.
+		 */
+		if (*val == 'n')
+			return;
+
+		/*
+		 * To have similar functionality to the C macro `IS_ENABLED()`
+		 * we provide an empty `--cfg CONFIG_X` here in both `y`
+		 * and `m` cases.
+		 *
+		 * Then, the common `fprintf()` below will also give us
+		 * a `--cfg CONFIG_X="y"` or `--cfg CONFIG_X="m"`, which can
+		 * be used as the equivalent of `IS_BUILTIN()`/`IS_MODULE()`.
+		 */
+		fprintf(fp, "--cfg=%s%s\n", CONFIG_, sym->name);
+		break;
+	case S_HEX:
+		if (val[0] != '0' || (val[1] != 'x' && val[1] != 'X'))
+			val_prefix = "0x";
+		break;
+	default:
+		break;
+	}
+
+	if (strlen(val_prefix) > 0) {
+		val_prefixed_len = strlen(val) + strlen(val_prefix) + 1;
+		val_prefixed = xmalloc(val_prefixed_len);
+		snprintf(val_prefixed, val_prefixed_len, "%s%s", val_prefix, val);
+		val = val_prefixed;
+	}
+
+	/* All values get escaped: the `--cfg` option only takes strings */
+	escaped = escape_string_value(val);
+	val = escaped;
+
+	fprintf(fp, "--cfg=%s%s=%s\n", CONFIG_, sym->name, val);
+
+	free(escaped);
+	free(val_prefixed);
+}
+
 /*
  * Write out a minimal config.
  * All values that has default values are skipped as this is redundant.
@@ -1132,6 +1201,12 @@ int conf_write_autoconf(int overwrite)
 	if (ret)
 		return ret;
 
+	ret = __conf_write_autoconf(conf_get_rustccfg_name(),
+				    print_symbol_for_rustccfg,
+				    NULL);
+	if (ret)
+		return ret;
+
 	/*
 	 * Create include/config/auto.conf. This must be the last step because
 	 * Kbuild has a dependency on auto.conf and this marks the successful
diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h
index fa8c010aa683..c396aa104090 100644
--- a/scripts/kconfig/lkc.h
+++ b/scripts/kconfig/lkc.h
@@ -98,7 +98,6 @@ bool menu_is_empty(struct menu *menu);
 bool menu_is_visible(struct menu *menu);
 bool menu_has_prompt(struct menu *menu);
 const char *menu_get_prompt(struct menu *menu);
-struct menu *menu_get_root_menu(struct menu *menu);
 struct menu *menu_get_parent_menu(struct menu *menu);
 bool menu_has_help(struct menu *menu);
 const char *menu_get_help(struct menu *menu);
diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c
index 3d6f7cba8846..62b6313f51c8 100644
--- a/scripts/kconfig/menu.c
+++ b/scripts/kconfig/menu.c
@@ -661,11 +661,6 @@ const char *menu_get_prompt(struct menu *menu)
 	return NULL;
 }
 
-struct menu *menu_get_root_menu(struct menu *menu)
-{
-	return &rootmenu;
-}
-
 struct menu *menu_get_parent_menu(struct menu *menu)
 {
 	enum prop_type type;
diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh
index 250925aab101..b6593eac5003 100755
--- a/scripts/min-tool-version.sh
+++ b/scripts/min-tool-version.sh
@@ -30,6 +30,12 @@ llvm)
 		echo 11.0.0
 	fi
 	;;
+rustc)
+	echo 1.62.0
+	;;
+bindgen)
+	echo 0.56.0
+	;;
 *)
 	echo "$1: unknown tool" >&2
 	exit 1
diff --git a/scripts/mksysmap b/scripts/mksysmap
index 9aa23d15862a..ad8bbc52267d 100755
--- a/scripts/mksysmap
+++ b/scripts/mksysmap
@@ -41,4 +41,4 @@
 # so we just ignore them to let readprofile continue to work.
 # (At least sparc64 has __crc_ in the middle).
 
-$NM -n $1 | grep -v '\( [aNUw] \)\|\(__crc_\)\|\( \$[adt]\)\|\( \.L\)' > $2
+$NM -n $1 | grep -v '\( [aNUw] \)\|\(__crc_\)\|\( \$[adt]\)\|\( \.L\)\|\( L0\)' > $2
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 55e32af2e53f..2c80da0220c3 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -2021,13 +2021,11 @@ static void add_exported_symbols(struct buffer *buf, struct module *mod)
 	/* record CRCs for exported symbols */
 	buf_printf(buf, "\n");
 	list_for_each_entry(sym, &mod->exported_symbols, list) {
-		if (!sym->crc_valid) {
+		if (!sym->crc_valid)
 			warn("EXPORT symbol \"%s\" [%s%s] version generation failed, symbol will not be versioned.\n"
 			     "Is \"%s\" prototyped in <asm/asm-prototypes.h>?\n",
 			     sym->name, mod->name, mod->is_vmlinux ? "" : ".ko",
 			     sym->name);
-			continue;
-		}
 
 		buf_printf(buf, "SYMBOL_CRC(%s, 0x%08x, \"%s\");\n",
 			   sym->name, sym->crc, sym->is_gpl_only ? "_gpl" : "");
diff --git a/scripts/module.lds.S b/scripts/module.lds.S
index 3a3aa2354ed8..da4bddd26171 100644
--- a/scripts/module.lds.S
+++ b/scripts/module.lds.S
@@ -3,20 +3,10 @@
  * Archs are free to supply their own linker scripts.  ld will
  * combine them automatically.
  */
-#ifdef CONFIG_CFI_CLANG
-# include <asm/page.h>
-# define ALIGN_CFI 		ALIGN(PAGE_SIZE)
-# define SANITIZER_DISCARDS	*(.eh_frame)
-#else
-# define ALIGN_CFI
-# define SANITIZER_DISCARDS
-#endif
-
 SECTIONS {
 	/DISCARD/ : {
 		*(.discard)
 		*(.discard.*)
-		SANITIZER_DISCARDS
 	}
 
 	__ksymtab		0 : { *(SORT(___ksymtab+*)) }
@@ -33,6 +23,10 @@ SECTIONS {
 
 	__patchable_function_entries : { *(__patchable_function_entries) }
 
+#ifdef CONFIG_ARCH_USES_CFI_TRAPS
+	__kcfi_traps 		: { KEEP(*(.kcfi_traps)) }
+#endif
+
 #ifdef CONFIG_LTO_CLANG
 	/*
 	 * With CONFIG_LTO_CLANG, LLD always enables -fdata-sections and
@@ -53,15 +47,6 @@ SECTIONS {
 		*(.rodata .rodata.[0-9a-zA-Z_]*)
 		*(.rodata..L*)
 	}
-
-	/*
-	 * With CONFIG_CFI_CLANG, we assume __cfi_check is at the beginning
-	 * of the .text section, and is aligned to PAGE_SIZE.
-	 */
-	.text : ALIGN_CFI {
-		*(.text.__cfi_check)
-		*(.text .text.[0-9a-zA-Z_]* .text..L.cfi*)
-	}
 #endif
 }
 
diff --git a/scripts/rust_is_available.sh b/scripts/rust_is_available.sh
new file mode 100755
index 000000000000..aebbf1913970
--- /dev/null
+++ b/scripts/rust_is_available.sh
@@ -0,0 +1,160 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Tests whether a suitable Rust toolchain is available.
+#
+# Pass `-v` for human output and more checks (as warnings).
+
+set -e
+
+min_tool_version=$(dirname $0)/min-tool-version.sh
+
+# Convert the version string x.y.z to a canonical up-to-7-digits form.
+#
+# Note that this function uses one more digit (compared to other
+# instances in other version scripts) to give a bit more space to
+# `rustc` since it will reach 1.100.0 in late 2026.
+get_canonical_version()
+{
+	IFS=.
+	set -- $1
+	echo $((100000 * $1 + 100 * $2 + $3))
+}
+
+# Check that the Rust compiler exists.
+if ! command -v "$RUSTC" >/dev/null; then
+	if [ "$1" = -v ]; then
+		echo >&2 "***"
+		echo >&2 "*** Rust compiler '$RUSTC' could not be found."
+		echo >&2 "***"
+	fi
+	exit 1
+fi
+
+# Check that the Rust bindings generator exists.
+if ! command -v "$BINDGEN" >/dev/null; then
+	if [ "$1" = -v ]; then
+		echo >&2 "***"
+		echo >&2 "*** Rust bindings generator '$BINDGEN' could not be found."
+		echo >&2 "***"
+	fi
+	exit 1
+fi
+
+# Check that the Rust compiler version is suitable.
+#
+# Non-stable and distributions' versions may have a version suffix, e.g. `-dev`.
+rust_compiler_version=$( \
+	LC_ALL=C "$RUSTC" --version 2>/dev/null \
+		| head -n 1 \
+		| grep -oE '[0-9]+\.[0-9]+\.[0-9]+' \
+)
+rust_compiler_min_version=$($min_tool_version rustc)
+rust_compiler_cversion=$(get_canonical_version $rust_compiler_version)
+rust_compiler_min_cversion=$(get_canonical_version $rust_compiler_min_version)
+if [ "$rust_compiler_cversion" -lt "$rust_compiler_min_cversion" ]; then
+	if [ "$1" = -v ]; then
+		echo >&2 "***"
+		echo >&2 "*** Rust compiler '$RUSTC' is too old."
+		echo >&2 "***   Your version:    $rust_compiler_version"
+		echo >&2 "***   Minimum version: $rust_compiler_min_version"
+		echo >&2 "***"
+	fi
+	exit 1
+fi
+if [ "$1" = -v ] && [ "$rust_compiler_cversion" -gt "$rust_compiler_min_cversion" ]; then
+	echo >&2 "***"
+	echo >&2 "*** Rust compiler '$RUSTC' is too new. This may or may not work."
+	echo >&2 "***   Your version:     $rust_compiler_version"
+	echo >&2 "***   Expected version: $rust_compiler_min_version"
+	echo >&2 "***"
+fi
+
+# Check that the Rust bindings generator is suitable.
+#
+# Non-stable and distributions' versions may have a version suffix, e.g. `-dev`.
+rust_bindings_generator_version=$( \
+	LC_ALL=C "$BINDGEN" --version 2>/dev/null \
+		| head -n 1 \
+		| grep -oE '[0-9]+\.[0-9]+\.[0-9]+' \
+)
+rust_bindings_generator_min_version=$($min_tool_version bindgen)
+rust_bindings_generator_cversion=$(get_canonical_version $rust_bindings_generator_version)
+rust_bindings_generator_min_cversion=$(get_canonical_version $rust_bindings_generator_min_version)
+if [ "$rust_bindings_generator_cversion" -lt "$rust_bindings_generator_min_cversion" ]; then
+	if [ "$1" = -v ]; then
+		echo >&2 "***"
+		echo >&2 "*** Rust bindings generator '$BINDGEN' is too old."
+		echo >&2 "***   Your version:    $rust_bindings_generator_version"
+		echo >&2 "***   Minimum version: $rust_bindings_generator_min_version"
+		echo >&2 "***"
+	fi
+	exit 1
+fi
+if [ "$1" = -v ] && [ "$rust_bindings_generator_cversion" -gt "$rust_bindings_generator_min_cversion" ]; then
+	echo >&2 "***"
+	echo >&2 "*** Rust bindings generator '$BINDGEN' is too new. This may or may not work."
+	echo >&2 "***   Your version:     $rust_bindings_generator_version"
+	echo >&2 "***   Expected version: $rust_bindings_generator_min_version"
+	echo >&2 "***"
+fi
+
+# Check that the `libclang` used by the Rust bindings generator is suitable.
+bindgen_libclang_version=$( \
+	LC_ALL=C "$BINDGEN" $(dirname $0)/rust_is_available_bindgen_libclang.h 2>&1 >/dev/null \
+		| grep -F 'clang version ' \
+		| grep -oE '[0-9]+\.[0-9]+\.[0-9]+' \
+		| head -n 1 \
+)
+bindgen_libclang_min_version=$($min_tool_version llvm)
+bindgen_libclang_cversion=$(get_canonical_version $bindgen_libclang_version)
+bindgen_libclang_min_cversion=$(get_canonical_version $bindgen_libclang_min_version)
+if [ "$bindgen_libclang_cversion" -lt "$bindgen_libclang_min_cversion" ]; then
+	if [ "$1" = -v ]; then
+		echo >&2 "***"
+		echo >&2 "*** libclang (used by the Rust bindings generator '$BINDGEN') is too old."
+		echo >&2 "***   Your version:    $bindgen_libclang_version"
+		echo >&2 "***   Minimum version: $bindgen_libclang_min_version"
+		echo >&2 "***"
+	fi
+	exit 1
+fi
+
+# If the C compiler is Clang, then we can also check whether its version
+# matches the `libclang` version used by the Rust bindings generator.
+#
+# In the future, we might be able to perform a full version check, see
+# https://github.com/rust-lang/rust-bindgen/issues/2138.
+if [ "$1" = -v ]; then
+	cc_name=$($(dirname $0)/cc-version.sh "$CC" | cut -f1 -d' ')
+	if [ "$cc_name" = Clang ]; then
+		clang_version=$( \
+			LC_ALL=C "$CC" --version 2>/dev/null \
+				| sed -nE '1s:.*version ([0-9]+\.[0-9]+\.[0-9]+).*:\1:p'
+		)
+		if [ "$clang_version" != "$bindgen_libclang_version" ]; then
+			echo >&2 "***"
+			echo >&2 "*** libclang (used by the Rust bindings generator '$BINDGEN')"
+			echo >&2 "*** version does not match Clang's. This may be a problem."
+			echo >&2 "***   libclang version: $bindgen_libclang_version"
+			echo >&2 "***   Clang version:    $clang_version"
+			echo >&2 "***"
+		fi
+	fi
+fi
+
+# Check that the source code for the `core` standard library exists.
+#
+# `$KRUSTFLAGS` is passed in case the user added `--sysroot`.
+rustc_sysroot=$("$RUSTC" $KRUSTFLAGS --print sysroot)
+rustc_src=${RUST_LIB_SRC:-"$rustc_sysroot/lib/rustlib/src/rust/library"}
+rustc_src_core="$rustc_src/core/src/lib.rs"
+if [ ! -e "$rustc_src_core" ]; then
+	if [ "$1" = -v ]; then
+		echo >&2 "***"
+		echo >&2 "*** Source code for the 'core' standard library could not be found"
+		echo >&2 "*** at '$rustc_src_core'."
+		echo >&2 "***"
+	fi
+	exit 1
+fi
diff --git a/scripts/rust_is_available_bindgen_libclang.h b/scripts/rust_is_available_bindgen_libclang.h
new file mode 100644
index 000000000000..0ef6db10d674
--- /dev/null
+++ b/scripts/rust_is_available_bindgen_libclang.h
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#pragma message("clang version " __clang_version__)
diff --git a/scripts/selinux/install_policy.sh b/scripts/selinux/install_policy.sh
index 2dccf141241d..24086793b0d8 100755
--- a/scripts/selinux/install_policy.sh
+++ b/scripts/selinux/install_policy.sh
@@ -31,8 +31,7 @@ fi
 if selinuxenabled; then
     echo "SELinux is already enabled"
     echo "This prevents safely relabeling all files."
-    echo "Boot with selinux=0 on the kernel command-line or"
-    echo "SELINUX=disabled in /etc/selinux/config."
+    echo "Boot with selinux=0 on the kernel command-line."
     exit 1
 fi
 
@@ -78,7 +77,7 @@ cd /etc/selinux/dummy/contexts/files
 $SF -F file_contexts /
 
 mounts=`cat /proc/$$/mounts | \
-	egrep "ext[234]|jfs|xfs|reiserfs|jffs2|gfs2|btrfs|f2fs|ocfs2" | \
+	grep -E "ext[234]|jfs|xfs|reiserfs|jffs2|gfs2|btrfs|f2fs|ocfs2" | \
 	awk '{ print $2 '}`
 $SF -F file_contexts $mounts
 
diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening
index bd2aabb2c60f..995bc42003e6 100644
--- a/security/Kconfig.hardening
+++ b/security/Kconfig.hardening
@@ -22,11 +22,17 @@ menu "Memory initialization"
 config CC_HAS_AUTO_VAR_INIT_PATTERN
 	def_bool $(cc-option,-ftrivial-auto-var-init=pattern)
 
-config CC_HAS_AUTO_VAR_INIT_ZERO
-	# GCC ignores the -enable flag, so we can test for the feature with
-	# a single invocation using the flag, but drop it as appropriate in
-	# the Makefile, depending on the presence of Clang.
+config CC_HAS_AUTO_VAR_INIT_ZERO_BARE
+	def_bool $(cc-option,-ftrivial-auto-var-init=zero)
+
+config CC_HAS_AUTO_VAR_INIT_ZERO_ENABLER
+	# Clang 16 and later warn about using the -enable flag, but it
+	# is required before then.
 	def_bool $(cc-option,-ftrivial-auto-var-init=zero -enable-trivial-auto-var-init-zero-knowing-it-will-be-removed-from-clang)
+	depends on !CC_HAS_AUTO_VAR_INIT_ZERO_BARE
+
+config CC_HAS_AUTO_VAR_INIT_ZERO
+	def_bool CC_HAS_AUTO_VAR_INIT_ZERO_BARE || CC_HAS_AUTO_VAR_INIT_ZERO_ENABLER
 
 choice
 	prompt "Initialize kernel stack variables at function entry"
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index 2e6fb6e2ffd2..23d484e05e6f 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -457,10 +457,21 @@ static int evm_xattr_acl_change(struct user_namespace *mnt_userns,
 	int rc;
 
 	/*
-	 * user_ns is not relevant here, ACL_USER/ACL_GROUP don't have impact
-	 * on the inode mode (see posix_acl_equiv_mode()).
+	 * An earlier comment here mentioned that the idmappings for
+	 * ACL_{GROUP,USER} don't matter since EVM is only interested in the
+	 * mode stored as part of POSIX ACLs. Nonetheless, if it must translate
+	 * from the uapi POSIX ACL representation to the VFS internal POSIX ACL
+	 * representation it should do so correctly. There's no guarantee that
+	 * we won't change POSIX ACLs in a way that ACL_{GROUP,USER} matters
+	 * for the mode at some point and it's difficult to keep track of all
+	 * the LSM and integrity modules and what they do to POSIX ACLs.
+	 *
+	 * Frankly, EVM shouldn't try to interpret the uapi struct for POSIX
+	 * ACLs it received. It requires knowledge that only the VFS is
+	 * guaranteed to have.
 	 */
-	acl = posix_acl_from_xattr(&init_user_ns, xattr_value, xattr_value_len);
+	acl = vfs_set_acl_prepare(mnt_userns, i_user_ns(inode),
+				  xattr_value, xattr_value_len);
 	if (IS_ERR_OR_NULL(acl))
 		return 1;
 
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index bde74fcecee3..3e0fbbd99534 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -750,22 +750,26 @@ int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name,
 	const struct evm_ima_xattr_data *xvalue = xattr_value;
 	int digsig = 0;
 	int result;
+	int err;
 
 	result = ima_protect_xattr(dentry, xattr_name, xattr_value,
 				   xattr_value_len);
 	if (result == 1) {
 		if (!xattr_value_len || (xvalue->type >= IMA_XATTR_LAST))
 			return -EINVAL;
+
+		err = validate_hash_algo(dentry, xvalue, xattr_value_len);
+		if (err)
+			return err;
+
 		digsig = (xvalue->type == EVM_IMA_XATTR_DIGSIG);
 	} else if (!strcmp(xattr_name, XATTR_NAME_EVM) && xattr_value_len > 0) {
 		digsig = (xvalue->type == EVM_XATTR_PORTABLE_DIGSIG);
 	}
 	if (result == 1 || evm_revalidate_status(xattr_name)) {
-		result = validate_hash_algo(dentry, xvalue, xattr_value_len);
-		if (result)
-			return result;
-
 		ima_reset_appraise_flags(d_backing_inode(dentry), digsig);
+		if (result == 1)
+			result = 0;
 	}
 	return result;
 }
diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c
index 093894a640dc..b78753d27d8e 100644
--- a/security/integrity/platform_certs/load_uefi.c
+++ b/security/integrity/platform_certs/load_uefi.c
@@ -31,7 +31,7 @@ static const struct dmi_system_id uefi_skip_cert[] = {
 	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookAir8,1") },
 	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookAir8,2") },
 	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookAir9,1") },
-	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacMini8,1") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "Macmini8,1") },
 	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacPro7,1") },
 	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "iMac20,1") },
 	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "iMac20,2") },
diff --git a/security/landlock/fs.c b/security/landlock/fs.c
index ec5a6247cd3e..a9dbd99d9ee7 100644
--- a/security/landlock/fs.c
+++ b/security/landlock/fs.c
@@ -150,6 +150,16 @@ retry:
 /* clang-format on */
 
 /*
+ * All access rights that are denied by default whether they are handled or not
+ * by a ruleset/layer.  This must be ORed with all ruleset->fs_access_masks[]
+ * entries when we need to get the absolute handled access masks.
+ */
+/* clang-format off */
+#define ACCESS_INITIALLY_DENIED ( \
+	LANDLOCK_ACCESS_FS_REFER)
+/* clang-format on */
+
+/*
  * @path: Should have been checked by get_path_from_fd().
  */
 int landlock_append_fs_rule(struct landlock_ruleset *const ruleset,
@@ -167,7 +177,9 @@ int landlock_append_fs_rule(struct landlock_ruleset *const ruleset,
 		return -EINVAL;
 
 	/* Transforms relative access rights to absolute ones. */
-	access_rights |= LANDLOCK_MASK_ACCESS_FS & ~ruleset->fs_access_masks[0];
+	access_rights |=
+		LANDLOCK_MASK_ACCESS_FS &
+		~(ruleset->fs_access_masks[0] | ACCESS_INITIALLY_DENIED);
 	object = get_inode_object(d_backing_inode(path->dentry));
 	if (IS_ERR(object))
 		return PTR_ERR(object);
@@ -277,23 +289,12 @@ static inline bool is_nouser_or_private(const struct dentry *dentry)
 static inline access_mask_t
 get_handled_accesses(const struct landlock_ruleset *const domain)
 {
-	access_mask_t access_dom = 0;
-	unsigned long access_bit;
-
-	for (access_bit = 0; access_bit < LANDLOCK_NUM_ACCESS_FS;
-	     access_bit++) {
-		size_t layer_level;
+	access_mask_t access_dom = ACCESS_INITIALLY_DENIED;
+	size_t layer_level;
 
-		for (layer_level = 0; layer_level < domain->num_layers;
-		     layer_level++) {
-			if (domain->fs_access_masks[layer_level] &
-			    BIT_ULL(access_bit)) {
-				access_dom |= BIT_ULL(access_bit);
-				break;
-			}
-		}
-	}
-	return access_dom;
+	for (layer_level = 0; layer_level < domain->num_layers; layer_level++)
+		access_dom |= domain->fs_access_masks[layer_level];
+	return access_dom & LANDLOCK_MASK_ACCESS_FS;
 }
 
 static inline access_mask_t
@@ -316,8 +317,13 @@ init_layer_masks(const struct landlock_ruleset *const domain,
 
 		for_each_set_bit(access_bit, &access_req,
 				 ARRAY_SIZE(*layer_masks)) {
-			if (domain->fs_access_masks[layer_level] &
-			    BIT_ULL(access_bit)) {
+			/*
+			 * Artificially handles all initially denied by default
+			 * access rights.
+			 */
+			if (BIT_ULL(access_bit) &
+			    (domain->fs_access_masks[layer_level] |
+			     ACCESS_INITIALLY_DENIED)) {
 				(*layer_masks)[access_bit] |=
 					BIT_ULL(layer_level);
 				handled_accesses |= BIT_ULL(access_bit);
@@ -857,10 +863,6 @@ static int current_check_refer_path(struct dentry *const old_dentry,
 					      NULL, NULL);
 	}
 
-	/* Backward compatibility: no reparenting support. */
-	if (!(get_handled_accesses(dom) & LANDLOCK_ACCESS_FS_REFER))
-		return -EXDEV;
-
 	access_request_parent1 |= LANDLOCK_ACCESS_FS_REFER;
 	access_request_parent2 |= LANDLOCK_ACCESS_FS_REFER;
 
diff --git a/security/loadpin/Kconfig b/security/loadpin/Kconfig
index 70e7985b2561..6724eaba3d36 100644
--- a/security/loadpin/Kconfig
+++ b/security/loadpin/Kconfig
@@ -33,4 +33,9 @@ config SECURITY_LOADPIN_VERITY
 	  on the LoadPin securityfs entry 'dm-verity'. The ioctl
 	  expects a file descriptor of a file with verity digests as
 	  parameter. The file must be located on the pinned root and
-	  contain a comma separated list of digests.
+	  start with the line:
+
+	  # LOADPIN_TRUSTED_VERITY_ROOT_DIGESTS
+
+	  This is followed by the verity digests, with one digest per
+	  line.
diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c
index 6ab5f2bbf41f..de41621f4998 100644
--- a/security/loadpin/loadpin.c
+++ b/security/loadpin/loadpin.c
@@ -21,6 +21,8 @@
 #include <linux/dm-verity-loadpin.h>
 #include <uapi/linux/loadpin.h>
 
+#define VERITY_DIGEST_FILE_HEADER "# LOADPIN_TRUSTED_VERITY_ROOT_DIGESTS"
+
 static void report_load(const char *origin, struct file *file, char *operation)
 {
 	char *cmdline, *pathname;
@@ -292,9 +294,21 @@ static int read_trusted_verity_root_digests(unsigned int fd)
 
 	p = strim(data);
 	while ((d = strsep(&p, "\n")) != NULL) {
-		int len = strlen(d);
+		int len;
 		struct dm_verity_loadpin_trusted_root_digest *trd;
 
+		if (d == data) {
+			/* first line, validate header */
+			if (strcmp(d, VERITY_DIGEST_FILE_HEADER)) {
+				rc = -EPROTO;
+				goto err;
+			}
+
+			continue;
+		}
+
+		len = strlen(d);
+
 		if (len % 2) {
 			rc = -EPROTO;
 			goto err;
@@ -356,13 +370,11 @@ static long dm_verity_ioctl(struct file *filp, unsigned int cmd, unsigned long a
 {
 	void __user *uarg = (void __user *)arg;
 	unsigned int fd;
-	int rc;
 
 	switch (cmd) {
 	case LOADPIN_IOC_SET_TRUSTED_VERITY_DIGESTS:
-		rc = copy_from_user(&fd, uarg, sizeof(fd));
-		if (rc)
-			return rc;
+		if (copy_from_user(&fd, uarg, sizeof(fd)))
+			return -EFAULT;
 
 		return read_trusted_verity_root_digests(fd);
 
diff --git a/security/lockdown/lockdown.c b/security/lockdown/lockdown.c
index 87cbdc64d272..a79b985e917e 100644
--- a/security/lockdown/lockdown.c
+++ b/security/lockdown/lockdown.c
@@ -63,7 +63,7 @@ static int lockdown_is_locked_down(enum lockdown_reason what)
 
 	if (kernel_locked_down >= what) {
 		if (lockdown_reasons[what])
-			pr_notice("Lockdown: %s: %s is restricted; see man kernel_lockdown.7\n",
+			pr_notice_ratelimited("Lockdown: %s: %s is restricted; see man kernel_lockdown.7\n",
 				  current->comm, lockdown_reasons[what]);
 		return -EPERM;
 	}
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 78a278f28e49..75cc3f8d2a42 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -44,9 +44,6 @@ int ipv4_skb_to_auditdata(struct sk_buff *skb,
 	struct iphdr *ih;
 
 	ih = ip_hdr(skb);
-	if (ih == NULL)
-		return -EINVAL;
-
 	ad->u.net->v4info.saddr = ih->saddr;
 	ad->u.net->v4info.daddr = ih->daddr;
 
@@ -59,8 +56,6 @@ int ipv4_skb_to_auditdata(struct sk_buff *skb,
 	switch (ih->protocol) {
 	case IPPROTO_TCP: {
 		struct tcphdr *th = tcp_hdr(skb);
-		if (th == NULL)
-			break;
 
 		ad->u.net->sport = th->source;
 		ad->u.net->dport = th->dest;
@@ -68,8 +63,6 @@ int ipv4_skb_to_auditdata(struct sk_buff *skb,
 	}
 	case IPPROTO_UDP: {
 		struct udphdr *uh = udp_hdr(skb);
-		if (uh == NULL)
-			break;
 
 		ad->u.net->sport = uh->source;
 		ad->u.net->dport = uh->dest;
@@ -77,8 +70,6 @@ int ipv4_skb_to_auditdata(struct sk_buff *skb,
 	}
 	case IPPROTO_DCCP: {
 		struct dccp_hdr *dh = dccp_hdr(skb);
-		if (dh == NULL)
-			break;
 
 		ad->u.net->sport = dh->dccph_sport;
 		ad->u.net->dport = dh->dccph_dport;
@@ -86,8 +77,7 @@ int ipv4_skb_to_auditdata(struct sk_buff *skb,
 	}
 	case IPPROTO_SCTP: {
 		struct sctphdr *sh = sctp_hdr(skb);
-		if (sh == NULL)
-			break;
+
 		ad->u.net->sport = sh->source;
 		ad->u.net->dport = sh->dest;
 		break;
@@ -115,8 +105,6 @@ int ipv6_skb_to_auditdata(struct sk_buff *skb,
 	__be16 frag_off;
 
 	ip6 = ipv6_hdr(skb);
-	if (ip6 == NULL)
-		return -EINVAL;
 	ad->u.net->v6info.saddr = ip6->saddr;
 	ad->u.net->v6info.daddr = ip6->daddr;
 	/* IPv6 can have several extension header before the Transport header
diff --git a/security/security.c b/security/security.c
index 14d30fec8a00..9696dd64095e 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1909,6 +1909,11 @@ void security_task_to_inode(struct task_struct *p, struct inode *inode)
 	call_void_hook(task_to_inode, p, inode);
 }
 
+int security_create_user_ns(const struct cred *cred)
+{
+	return call_int_hook(userns_create, 0, cred);
+}
+
 int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag)
 {
 	return call_int_hook(ipc_permission, 0, ipcp, flag);
@@ -2660,4 +2665,8 @@ int security_uring_sqpoll(void)
 {
 	return call_int_hook(uring_sqpoll, 0);
 }
+int security_uring_cmd(struct io_uring_cmd *ioucmd)
+{
+	return call_int_hook(uring_cmd, 0, ioucmd);
+}
 #endif /* CONFIG_IO_URING */
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 79573504783b..f8b05f14284b 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -91,6 +91,7 @@
 #include <uapi/linux/mount.h>
 #include <linux/fsnotify.h>
 #include <linux/fanotify.h>
+#include <linux/io_uring.h>
 
 #include "avc.h"
 #include "objsec.h"
@@ -4221,6 +4222,14 @@ static void selinux_task_to_inode(struct task_struct *p,
 	spin_unlock(&isec->lock);
 }
 
+static int selinux_userns_create(const struct cred *cred)
+{
+	u32 sid = current_sid();
+
+	return avc_has_perm(&selinux_state, sid, sid, SECCLASS_USER_NAMESPACE,
+						USER_NAMESPACE__CREATE, NULL);
+}
+
 /* Returns error only if unable to parse addresses */
 static int selinux_parse_skb_ipv4(struct sk_buff *skb,
 			struct common_audit_data *ad, u8 *proto)
@@ -5986,7 +5995,6 @@ static int selinux_msg_queue_alloc_security(struct kern_ipc_perm *msq)
 	struct ipc_security_struct *isec;
 	struct common_audit_data ad;
 	u32 sid = current_sid();
-	int rc;
 
 	isec = selinux_ipc(msq);
 	ipc_init_security(isec, SECCLASS_MSGQ);
@@ -5994,10 +6002,9 @@ static int selinux_msg_queue_alloc_security(struct kern_ipc_perm *msq)
 	ad.type = LSM_AUDIT_DATA_IPC;
 	ad.u.ipc_id = msq->key;
 
-	rc = avc_has_perm(&selinux_state,
-			  sid, isec->sid, SECCLASS_MSGQ,
-			  MSGQ__CREATE, &ad);
-	return rc;
+	return avc_has_perm(&selinux_state,
+			    sid, isec->sid, SECCLASS_MSGQ,
+			    MSGQ__CREATE, &ad);
 }
 
 static int selinux_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg)
@@ -6125,7 +6132,6 @@ static int selinux_shm_alloc_security(struct kern_ipc_perm *shp)
 	struct ipc_security_struct *isec;
 	struct common_audit_data ad;
 	u32 sid = current_sid();
-	int rc;
 
 	isec = selinux_ipc(shp);
 	ipc_init_security(isec, SECCLASS_SHM);
@@ -6133,10 +6139,9 @@ static int selinux_shm_alloc_security(struct kern_ipc_perm *shp)
 	ad.type = LSM_AUDIT_DATA_IPC;
 	ad.u.ipc_id = shp->key;
 
-	rc = avc_has_perm(&selinux_state,
-			  sid, isec->sid, SECCLASS_SHM,
-			  SHM__CREATE, &ad);
-	return rc;
+	return avc_has_perm(&selinux_state,
+			    sid, isec->sid, SECCLASS_SHM,
+			    SHM__CREATE, &ad);
 }
 
 static int selinux_shm_associate(struct kern_ipc_perm *shp, int shmflg)
@@ -6210,7 +6215,6 @@ static int selinux_sem_alloc_security(struct kern_ipc_perm *sma)
 	struct ipc_security_struct *isec;
 	struct common_audit_data ad;
 	u32 sid = current_sid();
-	int rc;
 
 	isec = selinux_ipc(sma);
 	ipc_init_security(isec, SECCLASS_SEM);
@@ -6218,10 +6222,9 @@ static int selinux_sem_alloc_security(struct kern_ipc_perm *sma)
 	ad.type = LSM_AUDIT_DATA_IPC;
 	ad.u.ipc_id = sma->key;
 
-	rc = avc_has_perm(&selinux_state,
-			  sid, isec->sid, SECCLASS_SEM,
-			  SEM__CREATE, &ad);
-	return rc;
+	return avc_has_perm(&selinux_state,
+			    sid, isec->sid, SECCLASS_SEM,
+			    SEM__CREATE, &ad);
 }
 
 static int selinux_sem_associate(struct kern_ipc_perm *sma, int semflg)
@@ -6987,6 +6990,28 @@ static int selinux_uring_sqpoll(void)
 	return avc_has_perm(&selinux_state, sid, sid,
 			    SECCLASS_IO_URING, IO_URING__SQPOLL, NULL);
 }
+
+/**
+ * selinux_uring_cmd - check if IORING_OP_URING_CMD is allowed
+ * @ioucmd: the io_uring command structure
+ *
+ * Check to see if the current domain is allowed to execute an
+ * IORING_OP_URING_CMD against the device/file specified in @ioucmd.
+ *
+ */
+static int selinux_uring_cmd(struct io_uring_cmd *ioucmd)
+{
+	struct file *file = ioucmd->file;
+	struct inode *inode = file_inode(file);
+	struct inode_security_struct *isec = selinux_inode(inode);
+	struct common_audit_data ad;
+
+	ad.type = LSM_AUDIT_DATA_FILE;
+	ad.u.file = file;
+
+	return avc_has_perm(&selinux_state, current_sid(), isec->sid,
+			    SECCLASS_IO_URING, IO_URING__CMD, &ad);
+}
 #endif /* CONFIG_IO_URING */
 
 /*
@@ -7111,6 +7136,7 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = {
 	LSM_HOOK_INIT(task_movememory, selinux_task_movememory),
 	LSM_HOOK_INIT(task_kill, selinux_task_kill),
 	LSM_HOOK_INIT(task_to_inode, selinux_task_to_inode),
+	LSM_HOOK_INIT(userns_create, selinux_userns_create),
 
 	LSM_HOOK_INIT(ipc_permission, selinux_ipc_permission),
 	LSM_HOOK_INIT(ipc_getsecid, selinux_ipc_getsecid),
@@ -7231,6 +7257,7 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = {
 #ifdef CONFIG_IO_URING
 	LSM_HOOK_INIT(uring_override_creds, selinux_uring_override_creds),
 	LSM_HOOK_INIT(uring_sqpoll, selinux_uring_sqpoll),
+	LSM_HOOK_INIT(uring_cmd, selinux_uring_cmd),
 #endif
 
 	/*
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index ff757ae5f253..a3c380775d41 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -253,7 +253,9 @@ const struct security_class_mapping secclass_map[] = {
 	{ "anon_inode",
 	  { COMMON_FILE_PERMS, NULL } },
 	{ "io_uring",
-	  { "override_creds", "sqpoll", NULL } },
+	  { "override_creds", "sqpoll", "cmd", NULL } },
+	{ "user_namespace",
+	  { "create", NULL } },
 	{ NULL }
   };
 
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 8fcdd494af27..a00d19139436 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -71,7 +71,7 @@ struct selinux_fs_info {
 	struct dentry *bool_dir;
 	unsigned int bool_num;
 	char **bool_pending_names;
-	unsigned int *bool_pending_values;
+	int *bool_pending_values;
 	struct dentry *class_dir;
 	unsigned long last_class_ino;
 	bool policy_opened;
@@ -356,7 +356,7 @@ static const struct file_operations sel_policyvers_ops = {
 /* declaration for sel_write_load */
 static int sel_make_bools(struct selinux_policy *newpolicy, struct dentry *bool_dir,
 			  unsigned int *bool_num, char ***bool_pending_names,
-			  unsigned int **bool_pending_values);
+			  int **bool_pending_values);
 static int sel_make_classes(struct selinux_policy *newpolicy,
 			    struct dentry *class_dir,
 			    unsigned long *last_class_ino);
@@ -527,7 +527,7 @@ static const struct file_operations sel_policy_ops = {
 };
 
 static void sel_remove_old_bool_data(unsigned int bool_num, char **bool_names,
-				unsigned int *bool_values)
+				     int *bool_values)
 {
 	u32 i;
 
@@ -545,7 +545,7 @@ static int sel_make_policy_nodes(struct selinux_fs_info *fsi,
 	struct dentry *tmp_parent, *tmp_bool_dir, *tmp_class_dir, *old_dentry;
 	unsigned int tmp_bool_num, old_bool_num;
 	char **tmp_bool_names, **old_bool_names;
-	unsigned int *tmp_bool_values, *old_bool_values;
+	int *tmp_bool_values, *old_bool_values;
 	unsigned long tmp_ino = fsi->last_ino; /* Don't increment last_ino in this function */
 
 	tmp_parent = sel_make_disconnected_dir(fsi->sb, &tmp_ino);
@@ -1423,7 +1423,7 @@ static void sel_remove_entries(struct dentry *de)
 
 static int sel_make_bools(struct selinux_policy *newpolicy, struct dentry *bool_dir,
 			  unsigned int *bool_num, char ***bool_pending_names,
-			  unsigned int **bool_pending_values)
+			  int **bool_pending_values)
 {
 	int ret;
 	ssize_t len;
@@ -1917,7 +1917,6 @@ static int sel_make_class_dir_entries(struct selinux_policy *newpolicy,
 	struct selinux_fs_info *fsi = sb->s_fs_info;
 	struct dentry *dentry = NULL;
 	struct inode *inode = NULL;
-	int rc;
 
 	dentry = d_alloc_name(dir, "index");
 	if (!dentry)
@@ -1937,9 +1936,7 @@ static int sel_make_class_dir_entries(struct selinux_policy *newpolicy,
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	rc = sel_make_perm_files(newpolicy, classname, index, dentry);
-
-	return rc;
+	return sel_make_perm_files(newpolicy, classname, index, dentry);
 }
 
 static int sel_make_classes(struct selinux_policy *newpolicy,
diff --git a/security/selinux/ss/context.h b/security/selinux/ss/context.h
index 62990aa1ec9e..eda32c3d4c0a 100644
--- a/security/selinux/ss/context.h
+++ b/security/selinux/ss/context.h
@@ -38,7 +38,7 @@ static inline void mls_context_init(struct context *c)
 	memset(&c->range, 0, sizeof(c->range));
 }
 
-static inline int mls_context_cpy(struct context *dst, struct context *src)
+static inline int mls_context_cpy(struct context *dst, const struct context *src)
 {
 	int rc;
 
@@ -58,7 +58,7 @@ out:
 /*
  * Sets both levels in the MLS range of 'dst' to the low level of 'src'.
  */
-static inline int mls_context_cpy_low(struct context *dst, struct context *src)
+static inline int mls_context_cpy_low(struct context *dst, const struct context *src)
 {
 	int rc;
 
@@ -78,7 +78,7 @@ out:
 /*
  * Sets both levels in the MLS range of 'dst' to the high level of 'src'.
  */
-static inline int mls_context_cpy_high(struct context *dst, struct context *src)
+static inline int mls_context_cpy_high(struct context *dst, const struct context *src)
 {
 	int rc;
 
@@ -97,9 +97,10 @@ out:
 
 
 static inline int mls_context_glblub(struct context *dst,
-				     struct context *c1, struct context *c2)
+				     const struct context *c1, const struct context *c2)
 {
-	struct mls_range *dr = &dst->range, *r1 = &c1->range, *r2 = &c2->range;
+	struct mls_range *dr = &dst->range;
+	const struct mls_range *r1 = &c1->range, *r2 = &c2->range;
 	int rc = 0;
 
 	if (r1->level[1].sens < r2->level[0].sens ||
@@ -127,7 +128,7 @@ out:
 	return rc;
 }
 
-static inline int mls_context_cmp(struct context *c1, struct context *c2)
+static inline int mls_context_cmp(const struct context *c1, const struct context *c2)
 {
 	return ((c1->range.level[0].sens == c2->range.level[0].sens) &&
 		ebitmap_cmp(&c1->range.level[0].cat, &c2->range.level[0].cat) &&
@@ -147,7 +148,7 @@ static inline void context_init(struct context *c)
 	memset(c, 0, sizeof(*c));
 }
 
-static inline int context_cpy(struct context *dst, struct context *src)
+static inline int context_cpy(struct context *dst, const struct context *src)
 {
 	int rc;
 
@@ -180,7 +181,7 @@ static inline void context_destroy(struct context *c)
 	mls_context_destroy(c);
 }
 
-static inline int context_cmp(struct context *c1, struct context *c2)
+static inline int context_cmp(const struct context *c1, const struct context *c2)
 {
 	if (c1->len && c2->len)
 		return (c1->len == c2->len && !strcmp(c1->str, c2->str));
diff --git a/security/selinux/ss/ebitmap.c b/security/selinux/ss/ebitmap.c
index abde349c8321..d31b87be9a1e 100644
--- a/security/selinux/ss/ebitmap.c
+++ b/security/selinux/ss/ebitmap.c
@@ -28,9 +28,9 @@
 
 static struct kmem_cache *ebitmap_node_cachep __ro_after_init;
 
-int ebitmap_cmp(struct ebitmap *e1, struct ebitmap *e2)
+int ebitmap_cmp(const struct ebitmap *e1, const struct ebitmap *e2)
 {
-	struct ebitmap_node *n1, *n2;
+	const struct ebitmap_node *n1, *n2;
 
 	if (e1->highbit != e2->highbit)
 		return 0;
@@ -50,9 +50,10 @@ int ebitmap_cmp(struct ebitmap *e1, struct ebitmap *e2)
 	return 1;
 }
 
-int ebitmap_cpy(struct ebitmap *dst, struct ebitmap *src)
+int ebitmap_cpy(struct ebitmap *dst, const struct ebitmap *src)
 {
-	struct ebitmap_node *n, *new, *prev;
+	struct ebitmap_node *new, *prev;
+	const struct ebitmap_node *n;
 
 	ebitmap_init(dst);
 	n = src->node;
@@ -78,7 +79,7 @@ int ebitmap_cpy(struct ebitmap *dst, struct ebitmap *src)
 	return 0;
 }
 
-int ebitmap_and(struct ebitmap *dst, struct ebitmap *e1, struct ebitmap *e2)
+int ebitmap_and(struct ebitmap *dst, const struct ebitmap *e1, const struct ebitmap *e2)
 {
 	struct ebitmap_node *n;
 	int bit, rc;
@@ -217,9 +218,9 @@ netlbl_import_failure:
  * if last_e2bit is non-zero, the highest set bit in e2 cannot exceed
  * last_e2bit.
  */
-int ebitmap_contains(struct ebitmap *e1, struct ebitmap *e2, u32 last_e2bit)
+int ebitmap_contains(const struct ebitmap *e1, const struct ebitmap *e2, u32 last_e2bit)
 {
-	struct ebitmap_node *n1, *n2;
+	const struct ebitmap_node *n1, *n2;
 	int i;
 
 	if (e1->highbit < e2->highbit)
@@ -258,9 +259,9 @@ int ebitmap_contains(struct ebitmap *e1, struct ebitmap *e2, u32 last_e2bit)
 	return 1;
 }
 
-int ebitmap_get_bit(struct ebitmap *e, unsigned long bit)
+int ebitmap_get_bit(const struct ebitmap *e, unsigned long bit)
 {
-	struct ebitmap_node *n;
+	const struct ebitmap_node *n;
 
 	if (e->highbit < bit)
 		return 0;
@@ -467,7 +468,7 @@ bad:
 	goto out;
 }
 
-int ebitmap_write(struct ebitmap *e, void *fp)
+int ebitmap_write(const struct ebitmap *e, void *fp)
 {
 	struct ebitmap_node *n;
 	u32 count;
diff --git a/security/selinux/ss/ebitmap.h b/security/selinux/ss/ebitmap.h
index 58eb822f11ee..e5b57dc3fc53 100644
--- a/security/selinux/ss/ebitmap.h
+++ b/security/selinux/ss/ebitmap.h
@@ -44,7 +44,7 @@ struct ebitmap {
 
 #define ebitmap_length(e) ((e)->highbit)
 
-static inline unsigned int ebitmap_start_positive(struct ebitmap *e,
+static inline unsigned int ebitmap_start_positive(const struct ebitmap *e,
 						  struct ebitmap_node **n)
 {
 	unsigned int ofs;
@@ -62,7 +62,7 @@ static inline void ebitmap_init(struct ebitmap *e)
 	memset(e, 0, sizeof(*e));
 }
 
-static inline unsigned int ebitmap_next_positive(struct ebitmap *e,
+static inline unsigned int ebitmap_next_positive(const struct ebitmap *e,
 						 struct ebitmap_node **n,
 						 unsigned int bit)
 {
@@ -85,7 +85,7 @@ static inline unsigned int ebitmap_next_positive(struct ebitmap *e,
 #define EBITMAP_NODE_OFFSET(node, bit)	\
 	(((bit) - (node)->startbit) % EBITMAP_UNIT_SIZE)
 
-static inline int ebitmap_node_get_bit(struct ebitmap_node *n,
+static inline int ebitmap_node_get_bit(const struct ebitmap_node *n,
 				       unsigned int bit)
 {
 	unsigned int index = EBITMAP_NODE_INDEX(n, bit);
@@ -122,15 +122,15 @@ static inline void ebitmap_node_clr_bit(struct ebitmap_node *n,
 	     (bit) < ebitmap_length(e);			\
 	     (bit) = ebitmap_next_positive(e, &(n), bit))	\
 
-int ebitmap_cmp(struct ebitmap *e1, struct ebitmap *e2);
-int ebitmap_cpy(struct ebitmap *dst, struct ebitmap *src);
-int ebitmap_and(struct ebitmap *dst, struct ebitmap *e1, struct ebitmap *e2);
-int ebitmap_contains(struct ebitmap *e1, struct ebitmap *e2, u32 last_e2bit);
-int ebitmap_get_bit(struct ebitmap *e, unsigned long bit);
+int ebitmap_cmp(const struct ebitmap *e1, const struct ebitmap *e2);
+int ebitmap_cpy(struct ebitmap *dst, const struct ebitmap *src);
+int ebitmap_and(struct ebitmap *dst, const struct ebitmap *e1, const struct ebitmap *e2);
+int ebitmap_contains(const struct ebitmap *e1, const struct ebitmap *e2, u32 last_e2bit);
+int ebitmap_get_bit(const struct ebitmap *e, unsigned long bit);
 int ebitmap_set_bit(struct ebitmap *e, unsigned long bit, int value);
 void ebitmap_destroy(struct ebitmap *e);
 int ebitmap_read(struct ebitmap *e, void *fp);
-int ebitmap_write(struct ebitmap *e, void *fp);
+int ebitmap_write(const struct ebitmap *e, void *fp);
 u32 ebitmap_hash(const struct ebitmap *e, u32 hash);
 
 #ifdef CONFIG_NETLABEL
diff --git a/security/selinux/ss/mls_types.h b/security/selinux/ss/mls_types.h
index 068e0d7809db..7d48d5e52233 100644
--- a/security/selinux/ss/mls_types.h
+++ b/security/selinux/ss/mls_types.h
@@ -27,13 +27,13 @@ struct mls_range {
 	struct mls_level level[2]; /* low == level[0], high == level[1] */
 };
 
-static inline int mls_level_eq(struct mls_level *l1, struct mls_level *l2)
+static inline int mls_level_eq(const struct mls_level *l1, const struct mls_level *l2)
 {
 	return ((l1->sens == l2->sens) &&
 		ebitmap_cmp(&l1->cat, &l2->cat));
 }
 
-static inline int mls_level_dom(struct mls_level *l1, struct mls_level *l2)
+static inline int mls_level_dom(const struct mls_level *l1, const struct mls_level *l2)
 {
 	return ((l1->sens >= l2->sens) &&
 		ebitmap_contains(&l1->cat, &l2->cat, 0));
diff --git a/security/smack/smack.h b/security/smack/smack.h
index fc837dcebf96..e2239be7bd60 100644
--- a/security/smack/smack.h
+++ b/security/smack/smack.h
@@ -180,15 +180,6 @@ struct smack_known_list_elem {
 	struct smack_known	*smk_label;
 };
 
-/* Super block security struct flags for mount options */
-#define FSDEFAULT_MNT	0x01
-#define FSFLOOR_MNT	0x02
-#define FSHAT_MNT	0x04
-#define FSROOT_MNT	0x08
-#define FSTRANS_MNT	0x10
-
-#define NUM_SMK_MNT_OPTS	5
-
 enum {
 	Opt_error = -1,
 	Opt_fsdefault = 0,
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 001831458fa2..dadcb9941da5 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -42,6 +42,7 @@
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
 #include <linux/watch_queue.h>
+#include <linux/io_uring.h>
 #include "smack.h"
 
 #define TRANS_TRUE	"TRUE"
@@ -496,13 +497,11 @@ static int smack_ptrace_access_check(struct task_struct *ctp, unsigned int mode)
  */
 static int smack_ptrace_traceme(struct task_struct *ptp)
 {
-	int rc;
 	struct smack_known *skp;
 
 	skp = smk_of_task(smack_cred(current_cred()));
 
-	rc = smk_ptrace_rule_check(ptp, skp, PTRACE_MODE_ATTACH, __func__);
-	return rc;
+	return smk_ptrace_rule_check(ptp, skp, PTRACE_MODE_ATTACH, __func__);
 }
 
 /**
@@ -2279,6 +2278,21 @@ static void smack_sk_free_security(struct sock *sk)
 }
 
 /**
+ * smack_sk_clone_security - Copy security context
+ * @sk: the old socket
+ * @newsk: the new socket
+ *
+ * Copy the security context of the old socket pointer to the cloned
+ */
+static void smack_sk_clone_security(const struct sock *sk, struct sock *newsk)
+{
+	struct socket_smack *ssp_old = sk->sk_security;
+	struct socket_smack *ssp_new = newsk->sk_security;
+
+	*ssp_new = *ssp_old;
+}
+
+/**
 * smack_ipv4host_label - check host based restrictions
 * @sip: the object end
 *
@@ -4732,6 +4746,36 @@ static int smack_uring_sqpoll(void)
 	return -EPERM;
 }
 
+/**
+ * smack_uring_cmd - check on file operations for io_uring
+ * @ioucmd: the command in question
+ *
+ * Make a best guess about whether a io_uring "command" should
+ * be allowed. Use the same logic used for determining if the
+ * file could be opened for read in the absence of better criteria.
+ */
+static int smack_uring_cmd(struct io_uring_cmd *ioucmd)
+{
+	struct file *file = ioucmd->file;
+	struct smk_audit_info ad;
+	struct task_smack *tsp;
+	struct inode *inode;
+	int rc;
+
+	if (!file)
+		return -EINVAL;
+
+	tsp = smack_cred(file->f_cred);
+	inode = file_inode(file);
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
+	smk_ad_setfield_u_fs_path(&ad, file->f_path);
+	rc = smk_tskacc(tsp, smk_of_inode(inode), MAY_READ, &ad);
+	rc = smk_bu_credfile(file->f_cred, file, MAY_READ, rc);
+
+	return rc;
+}
+
 #endif /* CONFIG_IO_URING */
 
 struct lsm_blob_sizes smack_blob_sizes __lsm_ro_after_init = {
@@ -4851,6 +4895,7 @@ static struct security_hook_list smack_hooks[] __lsm_ro_after_init = {
 	LSM_HOOK_INIT(socket_getpeersec_dgram, smack_socket_getpeersec_dgram),
 	LSM_HOOK_INIT(sk_alloc_security, smack_sk_alloc_security),
 	LSM_HOOK_INIT(sk_free_security, smack_sk_free_security),
+	LSM_HOOK_INIT(sk_clone_security, smack_sk_clone_security),
 	LSM_HOOK_INIT(sock_graft, smack_sock_graft),
 	LSM_HOOK_INIT(inet_conn_request, smack_inet_conn_request),
 	LSM_HOOK_INIT(inet_csk_clone, smack_inet_csk_clone),
@@ -4889,6 +4934,7 @@ static struct security_hook_list smack_hooks[] __lsm_ro_after_init = {
 #ifdef CONFIG_IO_URING
 	LSM_HOOK_INIT(uring_override_creds, smack_uring_override_creds),
 	LSM_HOOK_INIT(uring_sqpoll, smack_uring_sqpoll),
+	LSM_HOOK_INIT(uring_cmd, smack_uring_cmd),
 #endif
 };
 
diff --git a/sound/core/control.c b/sound/core/control.c
index f3e893715369..a7271927d875 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -385,14 +385,14 @@ static bool elem_id_matches(const struct snd_kcontrol *kctl,
 #define MULTIPLIER	37
 static unsigned long get_ctl_id_hash(const struct snd_ctl_elem_id *id)
 {
+	int i;
 	unsigned long h;
-	const unsigned char *p;
 
 	h = id->iface;
 	h = MULTIPLIER * h + id->device;
 	h = MULTIPLIER * h + id->subdevice;
-	for (p = id->name; *p; p++)
-		h = MULTIPLIER * h + *p;
+	for (i = 0; i < SNDRV_CTL_ELEM_ID_NAME_MAXLEN && id->name[i]; i++)
+		h = MULTIPLIER * h + id->name[i];
 	h = MULTIPLIER * h + id->index;
 	h &= LONG_MAX;
 	return h;
diff --git a/sound/core/info.c b/sound/core/info.c
index b8058b341178..0b2f04dcb589 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -111,9 +111,9 @@ static loff_t snd_info_entry_llseek(struct file *file, loff_t offset, int orig)
 	entry = data->entry;
 	mutex_lock(&entry->access);
 	if (entry->c.ops->llseek) {
-		offset = entry->c.ops->llseek(entry,
-					      data->file_private_data,
-					      file, offset, orig);
+		ret = entry->c.ops->llseek(entry,
+					   data->file_private_data,
+					   file, offset, orig);
 		goto out;
 	}
 
diff --git a/sound/core/init.c b/sound/core/init.c
index 193dae361fac..5377f94eb211 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -178,10 +178,8 @@ int snd_card_new(struct device *parent, int idx, const char *xid,
 		return -ENOMEM;
 
 	err = snd_card_init(card, parent, idx, xid, module, extra_size);
-	if (err < 0) {
-		kfree(card);
-		return err;
-	}
+	if (err < 0)
+		return err; /* card is freed by error handler */
 
 	*card_ret = card;
 	return 0;
@@ -233,7 +231,7 @@ int snd_devm_card_new(struct device *parent, int idx, const char *xid,
 	card->managed = true;
 	err = snd_card_init(card, parent, idx, xid, module, extra_size);
 	if (err < 0) {
-		devres_free(card);
+		devres_free(card); /* in managed mode, we need to free manually */
 		return err;
 	}
 
@@ -297,6 +295,8 @@ static int snd_card_init(struct snd_card *card, struct device *parent,
 		mutex_unlock(&snd_card_mutex);
 		dev_err(parent, "cannot find the slot for index %d (range 0-%i), error: %d\n",
 			 idx, snd_ecards_limit - 1, err);
+		if (!card->managed)
+			kfree(card); /* manually free here, as no destructor called */
 		return err;
 	}
 	set_bit(idx, snd_cards_lock);		/* lock it */
diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c
index d3885cb02270..cfcd8eff4139 100644
--- a/sound/core/memalloc.c
+++ b/sound/core/memalloc.c
@@ -20,6 +20,13 @@
 
 static const struct snd_malloc_ops *snd_dma_get_ops(struct snd_dma_buffer *dmab);
 
+#ifdef CONFIG_SND_DMA_SGBUF
+static void *do_alloc_fallback_pages(struct device *dev, size_t size,
+				     dma_addr_t *addr, bool wc);
+static void do_free_fallback_pages(void *p, size_t size, bool wc);
+static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size);
+#endif
+
 /* a cast to gfp flag from the dev pointer; for CONTINUOUS and VMALLOC types */
 static inline gfp_t snd_mem_get_gfp_flags(const struct snd_dma_buffer *dmab,
 					  gfp_t default_gfp)
@@ -277,16 +284,21 @@ EXPORT_SYMBOL(snd_sgbuf_get_chunk_size);
 /*
  * Continuous pages allocator
  */
-static void *snd_dma_continuous_alloc(struct snd_dma_buffer *dmab, size_t size)
+static void *do_alloc_pages(size_t size, dma_addr_t *addr, gfp_t gfp)
 {
-	gfp_t gfp = snd_mem_get_gfp_flags(dmab, GFP_KERNEL);
 	void *p = alloc_pages_exact(size, gfp);
 
 	if (p)
-		dmab->addr = page_to_phys(virt_to_page(p));
+		*addr = page_to_phys(virt_to_page(p));
 	return p;
 }
 
+static void *snd_dma_continuous_alloc(struct snd_dma_buffer *dmab, size_t size)
+{
+	return do_alloc_pages(size, &dmab->addr,
+			      snd_mem_get_gfp_flags(dmab, GFP_KERNEL));
+}
+
 static void snd_dma_continuous_free(struct snd_dma_buffer *dmab)
 {
 	free_pages_exact(dmab->area, dmab->bytes);
@@ -463,6 +475,25 @@ static const struct snd_malloc_ops snd_dma_dev_ops = {
 /*
  * Write-combined pages
  */
+/* x86-specific allocations */
+#ifdef CONFIG_SND_DMA_SGBUF
+static void *snd_dma_wc_alloc(struct snd_dma_buffer *dmab, size_t size)
+{
+	return do_alloc_fallback_pages(dmab->dev.dev, size, &dmab->addr, true);
+}
+
+static void snd_dma_wc_free(struct snd_dma_buffer *dmab)
+{
+	do_free_fallback_pages(dmab->area, dmab->bytes, true);
+}
+
+static int snd_dma_wc_mmap(struct snd_dma_buffer *dmab,
+			   struct vm_area_struct *area)
+{
+	area->vm_page_prot = pgprot_writecombine(area->vm_page_prot);
+	return snd_dma_continuous_mmap(dmab, area);
+}
+#else
 static void *snd_dma_wc_alloc(struct snd_dma_buffer *dmab, size_t size)
 {
 	return dma_alloc_wc(dmab->dev.dev, size, &dmab->addr, DEFAULT_GFP);
@@ -479,6 +510,7 @@ static int snd_dma_wc_mmap(struct snd_dma_buffer *dmab,
 	return dma_mmap_wc(dmab->dev.dev, area,
 			   dmab->area, dmab->addr, dmab->bytes);
 }
+#endif /* CONFIG_SND_DMA_SGBUF */
 
 static const struct snd_malloc_ops snd_dma_wc_ops = {
 	.alloc = snd_dma_wc_alloc,
@@ -486,10 +518,6 @@ static const struct snd_malloc_ops snd_dma_wc_ops = {
 	.mmap = snd_dma_wc_mmap,
 };
 
-#ifdef CONFIG_SND_DMA_SGBUF
-static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size);
-#endif
-
 /*
  * Non-contiguous pages allocator
  */
@@ -515,10 +543,13 @@ static void *snd_dma_noncontig_alloc(struct snd_dma_buffer *dmab, size_t size)
 	dmab->dev.need_sync = dma_need_sync(dmab->dev.dev,
 					    sg_dma_address(sgt->sgl));
 	p = dma_vmap_noncontiguous(dmab->dev.dev, size, sgt);
-	if (p)
+	if (p) {
 		dmab->private_data = sgt;
-	else
+		/* store the first page address for convenience */
+		dmab->addr = snd_sgbuf_get_addr(dmab, 0);
+	} else {
 		dma_free_noncontiguous(dmab->dev.dev, size, sgt, dmab->dev.dir);
+	}
 	return p;
 }
 
@@ -669,6 +700,37 @@ static const struct snd_malloc_ops snd_dma_sg_wc_ops = {
 	.get_chunk_size = snd_dma_noncontig_get_chunk_size,
 };
 
+/* manual page allocations with wc setup */
+static void *do_alloc_fallback_pages(struct device *dev, size_t size,
+				     dma_addr_t *addr, bool wc)
+{
+	gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
+	void *p;
+
+ again:
+	p = do_alloc_pages(size, addr, gfp);
+	if (!p || (*addr + size - 1) & ~dev->coherent_dma_mask) {
+		if (IS_ENABLED(CONFIG_ZONE_DMA32) && !(gfp & GFP_DMA32)) {
+			gfp |= GFP_DMA32;
+			goto again;
+		}
+		if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & GFP_DMA)) {
+			gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
+			goto again;
+		}
+	}
+	if (p && wc)
+		set_memory_wc((unsigned long)(p), size >> PAGE_SHIFT);
+	return p;
+}
+
+static void do_free_fallback_pages(void *p, size_t size, bool wc)
+{
+	if (wc)
+		set_memory_wb((unsigned long)(p), size >> PAGE_SHIFT);
+	free_pages_exact(p, size);
+}
+
 /* Fallback SG-buffer allocations for x86 */
 struct snd_dma_sg_fallback {
 	size_t count;
@@ -679,14 +741,11 @@ struct snd_dma_sg_fallback {
 static void __snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab,
 				       struct snd_dma_sg_fallback *sgbuf)
 {
+	bool wc = dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK;
 	size_t i;
 
-	if (sgbuf->count && dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK)
-		set_pages_array_wb(sgbuf->pages, sgbuf->count);
 	for (i = 0; i < sgbuf->count && sgbuf->pages[i]; i++)
-		dma_free_coherent(dmab->dev.dev, PAGE_SIZE,
-				  page_address(sgbuf->pages[i]),
-				  sgbuf->addrs[i]);
+		do_free_fallback_pages(page_address(sgbuf->pages[i]), PAGE_SIZE, wc);
 	kvfree(sgbuf->pages);
 	kvfree(sgbuf->addrs);
 	kfree(sgbuf);
@@ -698,6 +757,7 @@ static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size)
 	struct page **pages;
 	size_t i, count;
 	void *p;
+	bool wc = dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK;
 
 	sgbuf = kzalloc(sizeof(*sgbuf), GFP_KERNEL);
 	if (!sgbuf)
@@ -712,19 +772,19 @@ static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size)
 		goto error;
 
 	for (i = 0; i < count; sgbuf->count++, i++) {
-		p = dma_alloc_coherent(dmab->dev.dev, PAGE_SIZE,
-				       &sgbuf->addrs[i], DEFAULT_GFP);
+		p = do_alloc_fallback_pages(dmab->dev.dev, PAGE_SIZE,
+					    &sgbuf->addrs[i], wc);
 		if (!p)
 			goto error;
 		sgbuf->pages[i] = virt_to_page(p);
 	}
 
-	if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK)
-		set_pages_array_wc(pages, count);
 	p = vmap(pages, count, VM_MAP, PAGE_KERNEL);
 	if (!p)
 		goto error;
 	dmab->private_data = sgbuf;
+	/* store the first page address for convenience */
+	dmab->addr = snd_sgbuf_get_addr(dmab, 0);
 	return p;
 
  error:
diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c
index 90c3a367d7de..02df915eb3c6 100644
--- a/sound/core/oss/pcm_oss.c
+++ b/sound/core/oss/pcm_oss.c
@@ -1672,14 +1672,14 @@ static int snd_pcm_oss_sync(struct snd_pcm_oss_file *pcm_oss_file)
 		runtime = substream->runtime;
 		if (atomic_read(&substream->mmap_count))
 			goto __direct;
-		err = snd_pcm_oss_make_ready(substream);
-		if (err < 0)
-			return err;
 		atomic_inc(&runtime->oss.rw_ref);
 		if (mutex_lock_interruptible(&runtime->oss.params_lock)) {
 			atomic_dec(&runtime->oss.rw_ref);
 			return -ERESTARTSYS;
 		}
+		err = snd_pcm_oss_make_ready_locked(substream);
+		if (err < 0)
+			goto unlock;
 		format = snd_pcm_oss_format_from(runtime->oss.format);
 		width = snd_pcm_format_physical_width(format);
 		if (runtime->oss.buffer_used > 0) {
diff --git a/sound/core/seq/oss/seq_oss_midi.c b/sound/core/seq/oss/seq_oss_midi.c
index 1e3bf086f867..07efb38f58ac 100644
--- a/sound/core/seq/oss/seq_oss_midi.c
+++ b/sound/core/seq/oss/seq_oss_midi.c
@@ -270,7 +270,9 @@ snd_seq_oss_midi_clear_all(void)
 void
 snd_seq_oss_midi_setup(struct seq_oss_devinfo *dp)
 {
+	spin_lock_irq(&register_lock);
 	dp->max_mididev = max_midi_devs;
+	spin_unlock_irq(&register_lock);
 }
 
 /*
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 2e9d695d336c..2d707afa1ef1 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -121,13 +121,13 @@ struct snd_seq_client *snd_seq_client_use_ptr(int clientid)
 	spin_unlock_irqrestore(&clients_lock, flags);
 #ifdef CONFIG_MODULES
 	if (!in_interrupt()) {
-		static char client_requested[SNDRV_SEQ_GLOBAL_CLIENTS];
-		static char card_requested[SNDRV_CARDS];
+		static DECLARE_BITMAP(client_requested, SNDRV_SEQ_GLOBAL_CLIENTS);
+		static DECLARE_BITMAP(card_requested, SNDRV_CARDS);
+
 		if (clientid < SNDRV_SEQ_GLOBAL_CLIENTS) {
 			int idx;
 			
-			if (!client_requested[clientid]) {
-				client_requested[clientid] = 1;
+			if (!test_and_set_bit(clientid, client_requested)) {
 				for (idx = 0; idx < 15; idx++) {
 					if (seq_client_load[idx] < 0)
 						break;
@@ -142,10 +142,8 @@ struct snd_seq_client *snd_seq_client_use_ptr(int clientid)
 			int card = (clientid - SNDRV_SEQ_GLOBAL_CLIENTS) /
 				SNDRV_SEQ_CLIENTS_PER_CARD;
 			if (card < snd_ecards_limit) {
-				if (! card_requested[card]) {
-					card_requested[card] = 1;
+				if (!test_and_set_bit(card, card_requested))
 					snd_request_card(card);
-				}
 				snd_seq_device_load_drivers();
 			}
 		}
diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c
index 9b4a7cdb103a..12f12a294df5 100644
--- a/sound/drivers/aloop.c
+++ b/sound/drivers/aloop.c
@@ -605,17 +605,18 @@ static unsigned int loopback_jiffies_timer_pos_update
 			cable->streams[SNDRV_PCM_STREAM_PLAYBACK];
 	struct loopback_pcm *dpcm_capt =
 			cable->streams[SNDRV_PCM_STREAM_CAPTURE];
-	unsigned long delta_play = 0, delta_capt = 0;
+	unsigned long delta_play = 0, delta_capt = 0, cur_jiffies;
 	unsigned int running, count1, count2;
 
+	cur_jiffies = jiffies;
 	running = cable->running ^ cable->pause;
 	if (running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) {
-		delta_play = jiffies - dpcm_play->last_jiffies;
+		delta_play = cur_jiffies - dpcm_play->last_jiffies;
 		dpcm_play->last_jiffies += delta_play;
 	}
 
 	if (running & (1 << SNDRV_PCM_STREAM_CAPTURE)) {
-		delta_capt = jiffies - dpcm_capt->last_jiffies;
+		delta_capt = cur_jiffies - dpcm_capt->last_jiffies;
 		dpcm_capt->last_jiffies += delta_capt;
 	}
 
diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c
index d84ffdf47210..5a478649f338 100644
--- a/sound/hda/intel-dsp-config.c
+++ b/sound/hda/intel-dsp-config.c
@@ -450,6 +450,16 @@ static const struct config_entry config_table[] = {
 		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE,
 		.device = 0x51cb,
 	},
+	/* RaptorLake-M */
+	{
+		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE,
+		.device = 0x51ce,
+	},
+	/* RaptorLake-PX */
+	{
+		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE,
+		.device = 0x51cf,
+	},
 #endif
 
 };
diff --git a/sound/hda/intel-nhlt.c b/sound/hda/intel-nhlt.c
index 9db5ccd9aa2d..13bb0ccfb36c 100644
--- a/sound/hda/intel-nhlt.c
+++ b/sound/hda/intel-nhlt.c
@@ -55,16 +55,22 @@ int intel_nhlt_get_dmic_geo(struct device *dev, struct nhlt_acpi_table *nhlt)
 
 		/* find max number of channels based on format_configuration */
 		if (fmt_configs->fmt_count) {
+			struct nhlt_fmt_cfg *fmt_cfg = fmt_configs->fmt_config;
+
 			dev_dbg(dev, "found %d format definitions\n",
 				fmt_configs->fmt_count);
 
 			for (i = 0; i < fmt_configs->fmt_count; i++) {
 				struct wav_fmt_ext *fmt_ext;
 
-				fmt_ext = &fmt_configs->fmt_config[i].fmt_ext;
+				fmt_ext = &fmt_cfg->fmt_ext;
 
 				if (fmt_ext->fmt.channels > max_ch)
 					max_ch = fmt_ext->fmt.channels;
+
+				/* Move to the next nhlt_fmt_cfg */
+				fmt_cfg = (struct nhlt_fmt_cfg *)(fmt_cfg->config.caps +
+								  fmt_cfg->config.size);
 			}
 			dev_dbg(dev, "max channels found %d\n", max_ch);
 		} else {
diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c
index b2701a4452d8..48af77ae8020 100644
--- a/sound/pci/emu10k1/emupcm.c
+++ b/sound/pci/emu10k1/emupcm.c
@@ -124,7 +124,7 @@ static int snd_emu10k1_pcm_channel_alloc(struct snd_emu10k1_pcm * epcm, int voic
 	epcm->voices[0]->epcm = epcm;
 	if (voices > 1) {
 		for (i = 1; i < voices; i++) {
-			epcm->voices[i] = &epcm->emu->voices[epcm->voices[0]->number + i];
+			epcm->voices[i] = &epcm->emu->voices[(epcm->voices[0]->number + i) % NUM_G];
 			epcm->voices[i]->epcm = epcm;
 		}
 	}
diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c
index 129bffb431c2..15e2a0009080 100644
--- a/sound/pci/hda/cs35l41_hda.c
+++ b/sound/pci/hda/cs35l41_hda.c
@@ -1163,6 +1163,11 @@ static int cs35l41_no_acpi_dsd(struct cs35l41_hda *cs35l41, struct device *physd
 		hw_cfg->gpio1.func = CS35l41_VSPK_SWITCH;
 		hw_cfg->gpio1.valid = true;
 	} else {
+		/*
+		 * Note: CLSA010(0/1) are special cases which use a slightly different design.
+		 * All other HIDs e.g. CSC3551 require valid ACPI _DSD properties to be supported.
+		 */
+		dev_err(cs35l41->dev, "Error: ACPI _DSD Properties are missing for HID %s.\n", hid);
 		hw_cfg->valid = false;
 		hw_cfg->gpio1.valid = false;
 		hw_cfg->gpio2.valid = false;
diff --git a/sound/pci/hda/hda_bind.c b/sound/pci/hda/hda_bind.c
index cae9a975cbcc..1a868dd9dc4b 100644
--- a/sound/pci/hda/hda_bind.c
+++ b/sound/pci/hda/hda_bind.c
@@ -157,10 +157,10 @@ static int hda_codec_driver_remove(struct device *dev)
 		return codec->bus->core.ext_ops->hdev_detach(&codec->core);
 	}
 
-	refcount_dec(&codec->pcm_ref);
 	snd_hda_codec_disconnect_pcms(codec);
 	snd_hda_jack_tbl_disconnect(codec);
-	wait_event(codec->remove_sleep, !refcount_read(&codec->pcm_ref));
+	if (!refcount_dec_and_test(&codec->pcm_ref))
+		wait_event(codec->remove_sleep, !refcount_read(&codec->pcm_ref));
 	snd_power_sync_ref(codec->bus->card);
 
 	if (codec->patch_ops.free)
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index a77165bd92a9..6f30c374f896 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1817,7 +1817,7 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci,
 
 	/* use the non-cached pages in non-snoop mode */
 	if (!azx_snoop(chip))
-		azx_bus(chip)->dma_type = SNDRV_DMA_TYPE_DEV_WC;
+		azx_bus(chip)->dma_type = SNDRV_DMA_TYPE_DEV_WC_SG;
 
 	if (chip->driver_type == AZX_DRIVER_NVIDIA) {
 		dev_dbg(chip->card->dev, "Enable delay in RIRB handling\n");
@@ -2550,6 +2550,8 @@ static const struct pci_device_id azx_ids[] = {
 	/* 5 Series/3400 */
 	{ PCI_DEVICE(0x8086, 0x3b56),
 	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH_NOPM },
+	{ PCI_DEVICE(0x8086, 0x3b57),
+	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH_NOPM },
 	/* Poulsbo */
 	{ PCI_DEVICE(0x8086, 0x811b),
 	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH_BASE },
diff --git a/sound/pci/hda/hda_tegra.c b/sound/pci/hda/hda_tegra.c
index 7debb2c76aa6..976a112c7d00 100644
--- a/sound/pci/hda/hda_tegra.c
+++ b/sound/pci/hda/hda_tegra.c
@@ -474,7 +474,8 @@ MODULE_DEVICE_TABLE(of, hda_tegra_match);
 static int hda_tegra_probe(struct platform_device *pdev)
 {
 	const unsigned int driver_flags = AZX_DCAPS_CORBRP_SELF_CLEAR |
-					  AZX_DCAPS_PM_RUNTIME;
+					  AZX_DCAPS_PM_RUNTIME |
+					  AZX_DCAPS_4K_BDLE_BOUNDARY;
 	struct snd_card *card;
 	struct azx *chip;
 	struct hda_tegra *hda;
diff --git a/sound/pci/hda/patch_cs8409-tables.c b/sound/pci/hda/patch_cs8409-tables.c
index e0d3a8be2e38..b288874e401e 100644
--- a/sound/pci/hda/patch_cs8409-tables.c
+++ b/sound/pci/hda/patch_cs8409-tables.c
@@ -546,6 +546,10 @@ const struct snd_pci_quirk cs8409_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0BD6, "Dolphin", CS8409_DOLPHIN),
 	SND_PCI_QUIRK(0x1028, 0x0BD7, "Dolphin", CS8409_DOLPHIN),
 	SND_PCI_QUIRK(0x1028, 0x0BD8, "Dolphin", CS8409_DOLPHIN),
+	SND_PCI_QUIRK(0x1028, 0x0C43, "Dolphin", CS8409_DOLPHIN),
+	SND_PCI_QUIRK(0x1028, 0x0C50, "Dolphin", CS8409_DOLPHIN),
+	SND_PCI_QUIRK(0x1028, 0x0C51, "Dolphin", CS8409_DOLPHIN),
+	SND_PCI_QUIRK(0x1028, 0x0C52, "Dolphin", CS8409_DOLPHIN),
 	{} /* terminator */
 };
 
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 6c209cd26c0c..c239d9dbbaef 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -170,6 +170,8 @@ struct hdmi_spec {
 	bool dyn_pcm_no_legacy;
 	/* hdmi interrupt trigger control flag for Nvidia codec */
 	bool hdmi_intr_trig_ctrl;
+	bool nv_dp_workaround; /* workaround DP audio infoframe for Nvidia */
+
 	bool intel_hsw_fixup;	/* apply Intel platform-specific fixups */
 	/*
 	 * Non-generic VIA/NVIDIA specific
@@ -679,15 +681,24 @@ static void hdmi_pin_setup_infoframe(struct hda_codec *codec,
 				     int ca, int active_channels,
 				     int conn_type)
 {
+	struct hdmi_spec *spec = codec->spec;
 	union audio_infoframe ai;
 
 	memset(&ai, 0, sizeof(ai));
-	if (conn_type == 0) { /* HDMI */
+	if ((conn_type == 0) || /* HDMI */
+		/* Nvidia DisplayPort: Nvidia HW expects same layout as HDMI */
+		(conn_type == 1 && spec->nv_dp_workaround)) {
 		struct hdmi_audio_infoframe *hdmi_ai = &ai.hdmi;
 
-		hdmi_ai->type		= 0x84;
-		hdmi_ai->ver		= 0x01;
-		hdmi_ai->len		= 0x0a;
+		if (conn_type == 0) { /* HDMI */
+			hdmi_ai->type		= 0x84;
+			hdmi_ai->ver		= 0x01;
+			hdmi_ai->len		= 0x0a;
+		} else {/* Nvidia DP */
+			hdmi_ai->type		= 0x84;
+			hdmi_ai->ver		= 0x1b;
+			hdmi_ai->len		= 0x11 << 2;
+		}
 		hdmi_ai->CC02_CT47	= active_channels - 1;
 		hdmi_ai->CA		= ca;
 		hdmi_checksum_audio_infoframe(hdmi_ai);
@@ -1267,6 +1278,7 @@ static int hdmi_pcm_open(struct hda_pcm_stream *hinfo,
 	set_bit(pcm_idx, &spec->pcm_in_use);
 	per_pin = get_pin(spec, pin_idx);
 	per_pin->cvt_nid = per_cvt->cvt_nid;
+	per_pin->silent_stream = false;
 	hinfo->nid = per_cvt->cvt_nid;
 
 	/* flip stripe flag for the assigned stream if supported */
@@ -3617,6 +3629,7 @@ static int patch_nvhdmi_2ch(struct hda_codec *codec)
 	spec->pcm_playback.rates = SUPPORTED_RATES;
 	spec->pcm_playback.maxbps = SUPPORTED_MAXBPS;
 	spec->pcm_playback.formats = SUPPORTED_FORMATS;
+	spec->nv_dp_workaround = true;
 	return 0;
 }
 
@@ -3756,6 +3769,7 @@ static int patch_nvhdmi(struct hda_codec *codec)
 	spec->chmap.ops.chmap_cea_alloc_validate_get_type =
 		nvhdmi_chmap_cea_alloc_validate_get_type;
 	spec->chmap.ops.chmap_validate = nvhdmi_chmap_validate;
+	spec->nv_dp_workaround = true;
 
 	codec->link_down_at_suspend = 1;
 
@@ -3779,6 +3793,7 @@ static int patch_nvhdmi_legacy(struct hda_codec *codec)
 	spec->chmap.ops.chmap_cea_alloc_validate_get_type =
 		nvhdmi_chmap_cea_alloc_validate_get_type;
 	spec->chmap.ops.chmap_validate = nvhdmi_chmap_validate;
+	spec->nv_dp_workaround = true;
 
 	codec->link_down_at_suspend = 1;
 
@@ -3984,6 +3999,7 @@ static int tegra_hdmi_init(struct hda_codec *codec)
 
 	generic_hdmi_init_per_pins(codec);
 
+	codec->depop_delay = 10;
 	codec->patch_ops.build_pcms = tegra_hdmi_build_pcms;
 	spec->chmap.ops.chmap_cea_alloc_validate_get_type =
 		nvhdmi_chmap_cea_alloc_validate_get_type;
@@ -3992,6 +4008,7 @@ static int tegra_hdmi_init(struct hda_codec *codec)
 	spec->chmap.ops.chmap_cea_alloc_validate_get_type =
 		nvhdmi_chmap_cea_alloc_validate_get_type;
 	spec->chmap.ops.chmap_validate = nvhdmi_chmap_validate;
+	spec->nv_dp_workaround = true;
 
 	return 0;
 }
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index fd630d62b5a0..f9d46ae4c7b7 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4700,6 +4700,48 @@ static void alc236_fixup_hp_mute_led_micmute_vref(struct hda_codec *codec,
 	alc236_fixup_hp_micmute_led_vref(codec, fix, action);
 }
 
+static inline void alc298_samsung_write_coef_pack(struct hda_codec *codec,
+						  const unsigned short coefs[2])
+{
+	alc_write_coef_idx(codec, 0x23, coefs[0]);
+	alc_write_coef_idx(codec, 0x25, coefs[1]);
+	alc_write_coef_idx(codec, 0x26, 0xb011);
+}
+
+struct alc298_samsung_amp_desc {
+	unsigned char nid;
+	unsigned short init_seq[2][2];
+};
+
+static void alc298_fixup_samsung_amp(struct hda_codec *codec,
+				     const struct hda_fixup *fix, int action)
+{
+	int i, j;
+	static const unsigned short init_seq[][2] = {
+		{ 0x19, 0x00 }, { 0x20, 0xc0 }, { 0x22, 0x44 }, { 0x23, 0x08 },
+		{ 0x24, 0x85 }, { 0x25, 0x41 }, { 0x35, 0x40 }, { 0x36, 0x01 },
+		{ 0x38, 0x81 }, { 0x3a, 0x03 }, { 0x3b, 0x81 }, { 0x40, 0x3e },
+		{ 0x41, 0x07 }, { 0x400, 0x1 }
+	};
+	static const struct alc298_samsung_amp_desc amps[] = {
+		{ 0x3a, { { 0x18, 0x1 }, { 0x26, 0x0 } } },
+		{ 0x39, { { 0x18, 0x2 }, { 0x26, 0x1 } } }
+	};
+
+	if (action != HDA_FIXUP_ACT_INIT)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(amps); i++) {
+		alc_write_coef_idx(codec, 0x22, amps[i].nid);
+
+		for (j = 0; j < ARRAY_SIZE(amps[i].init_seq); j++)
+			alc298_samsung_write_coef_pack(codec, amps[i].init_seq[j]);
+
+		for (j = 0; j < ARRAY_SIZE(init_seq); j++)
+			alc298_samsung_write_coef_pack(codec, init_seq[j]);
+	}
+}
+
 #if IS_REACHABLE(CONFIG_INPUT)
 static void gpio2_mic_hotkey_event(struct hda_codec *codec,
 				   struct hda_jack_callback *event)
@@ -7025,11 +7067,14 @@ enum {
 	ALC294_FIXUP_ASUS_GU502_HP,
 	ALC294_FIXUP_ASUS_GU502_PINS,
 	ALC294_FIXUP_ASUS_GU502_VERBS,
+	ALC294_FIXUP_ASUS_G513_PINS,
+	ALC285_FIXUP_ASUS_G533Z_PINS,
 	ALC285_FIXUP_HP_GPIO_LED,
 	ALC285_FIXUP_HP_MUTE_LED,
 	ALC236_FIXUP_HP_GPIO_LED,
 	ALC236_FIXUP_HP_MUTE_LED,
 	ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF,
+	ALC298_FIXUP_SAMSUNG_AMP,
 	ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET,
 	ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET,
 	ALC295_FIXUP_ASUS_MIC_NO_PRESENCE,
@@ -8363,6 +8408,24 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc294_fixup_gu502_hp,
 	},
+	 [ALC294_FIXUP_ASUS_G513_PINS] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+				{ 0x19, 0x03a11050 }, /* front HP mic */
+				{ 0x1a, 0x03a11c30 }, /* rear external mic */
+				{ 0x21, 0x03211420 }, /* front HP out */
+				{ }
+		},
+	},
+	[ALC285_FIXUP_ASUS_G533Z_PINS] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x14, 0x90170120 },
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC294_FIXUP_ASUS_G513_PINS,
+	},
 	[ALC294_FIXUP_ASUS_COEF_1B] = {
 		.type = HDA_FIXUP_VERBS,
 		.v.verbs = (const struct hda_verb[]) {
@@ -8396,6 +8459,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc236_fixup_hp_mute_led_micmute_vref,
 	},
+	[ALC298_FIXUP_SAMSUNG_AMP] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc298_fixup_samsung_amp,
+		.chained = true,
+		.chain_id = ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET
+	},
 	[ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET] = {
 		.type = HDA_FIXUP_VERBS,
 		.v.verbs = (const struct hda_verb[]) {
@@ -9100,6 +9169,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0871, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1028, 0x0872, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1028, 0x0873, "Dell Precision 3930", ALC255_FIXUP_DUMMY_LINEOUT_VERB),
+	SND_PCI_QUIRK(0x1028, 0x087d, "Dell Precision 5530", ALC289_FIXUP_DUAL_SPK),
 	SND_PCI_QUIRK(0x1028, 0x08ad, "Dell WYSE AIO", ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x08ae, "Dell WYSE NB", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB),
@@ -9116,6 +9186,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0a9d, "Dell Latitude 5430", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0a9e, "Dell Latitude 5430", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0b19, "Dell XPS 15 9520", ALC289_FIXUP_DUAL_SPK),
+	SND_PCI_QUIRK(0x1028, 0x0b1a, "Dell Precision 5570", ALC289_FIXUP_DUAL_SPK),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
@@ -9243,6 +9314,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8896, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8902, "HP OMEN 16", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x896e, "HP EliteBook x360 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8971, "HP EliteBook 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8972, "HP EliteBook 840 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
@@ -9283,16 +9355,18 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1271, "ASUS X430UN", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1290, "ASUS X441SA", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x12a0, "ASUS X441UV", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1043, 0x12af, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
 	SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
+	SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK),
+	SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x1740, "ASUS UX430UA", ALC295_FIXUP_ASUS_DACS),
 	SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK),
-	SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK),
 	SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS),
 	SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC),
@@ -9303,18 +9377,21 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
 	SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1a8f, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B),
 	SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS),
 	SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE),
 	SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
 	SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS),
+	SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS),
 	SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401),
+	SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401),
-	SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401),
-	SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
 	SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC),
@@ -9340,13 +9417,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
 	SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE),
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
-	SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
-	SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
-	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Flex Book (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
-	SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
+	SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Flex Book (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8),
-	SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
-	SND_PCI_QUIRK(0x144d, 0xc830, "Samsung Galaxy Book Ion (NT950XCJ-X716A)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
+	SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc830, "Samsung Galaxy Book Ion (NT950XCJ-X716A)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc832, "Samsung Galaxy Book Flex Alpha (NP730QCJ)", ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
 	SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC),
@@ -9389,6 +9466,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1558, 0x70f4, "Clevo NH77EPY", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x70f6, "Clevo NH77DPQ-Y", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x7716, "Clevo NS50PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1558, 0x7717, "Clevo NS70PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x7718, "Clevo L140PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x8228, "Clevo NR40BU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x8520, "Clevo NH50D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
@@ -9490,6 +9568,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x3852, "Lenovo Yoga 7 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
 	SND_PCI_QUIRK(0x17aa, 0x3853, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
 	SND_PCI_QUIRK(0x17aa, 0x3855, "Legion 7 16ITHG6", ALC287_FIXUP_LEGION_16ITHG6),
+	SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
 	SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
@@ -9516,6 +9595,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD),
 	SND_PCI_QUIRK(0x1849, 0x1233, "ASRock NUC Box 1100", ALC233_FIXUP_NO_AUDIO_JACK),
 	SND_PCI_QUIRK(0x19e5, 0x3204, "Huawei MACH-WX9", ALC256_FIXUP_HUAWEI_MACH_WX9_PINS),
+	SND_PCI_QUIRK(0x19e5, 0x320f, "Huawei WRT-WX9 ", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1b35, 0x1235, "CZC B20", ALC269_FIXUP_CZC_B20),
 	SND_PCI_QUIRK(0x1b35, 0x1236, "CZC TMI", ALC269_FIXUP_CZC_TMI),
 	SND_PCI_QUIRK(0x1b35, 0x1237, "CZC L101", ALC269_FIXUP_CZC_L101),
@@ -9712,7 +9792,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC299_FIXUP_PREDATOR_SPK, .name = "predator-spk"},
 	{.id = ALC298_FIXUP_HUAWEI_MBX_STEREO, .name = "huawei-mbx-stereo"},
 	{.id = ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE, .name = "alc256-medion-headset"},
-	{.id = ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, .name = "alc298-samsung-headphone"},
+	{.id = ALC298_FIXUP_SAMSUNG_AMP, .name = "alc298-samsung-amp"},
 	{.id = ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, .name = "alc256-samsung-headphone"},
 	{.id = ALC255_FIXUP_XIAOMI_HEADSET_MIC, .name = "alc255-xiaomi-headset"},
 	{.id = ALC274_FIXUP_HP_MIC, .name = "alc274-hp-mic-detect"},
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 61df4d33c48f..7f340f18599c 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -209,6 +209,7 @@ struct sigmatel_spec {
 
 	/* beep widgets */
 	hda_nid_t anabeep_nid;
+	bool beep_power_on;
 
 	/* SPDIF-out mux */
 	const char * const *spdif_labels;
@@ -4443,6 +4444,28 @@ static int stac_suspend(struct hda_codec *codec)
 
 	return 0;
 }
+
+static int stac_check_power_status(struct hda_codec *codec, hda_nid_t nid)
+{
+#ifdef CONFIG_SND_HDA_INPUT_BEEP
+	struct sigmatel_spec *spec = codec->spec;
+#endif
+	int ret = snd_hda_gen_check_power_status(codec, nid);
+
+#ifdef CONFIG_SND_HDA_INPUT_BEEP
+	if (nid == spec->gen.beep_nid && codec->beep) {
+		if (codec->beep->enabled != spec->beep_power_on) {
+			spec->beep_power_on = codec->beep->enabled;
+			if (spec->beep_power_on)
+				snd_hda_power_up_pm(codec);
+			else
+				snd_hda_power_down_pm(codec);
+		}
+		ret |= spec->beep_power_on;
+	}
+#endif
+	return ret;
+}
 #else
 #define stac_suspend		NULL
 #endif /* CONFIG_PM */
@@ -4455,6 +4478,7 @@ static const struct hda_codec_ops stac_patch_ops = {
 	.unsol_event = snd_hda_jack_unsol_event,
 #ifdef CONFIG_PM
 	.suspend = stac_suspend,
+	.check_power_status = stac_check_power_status,
 #endif
 };
 
diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index ecfe7a790790..e0b24e1daef3 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -143,6 +143,34 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "21CL"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21EM"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21EN"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21J5"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21J6"),
+		}
+	},
 	{}
 };
 
diff --git a/sound/soc/atmel/mchp-spdiftx.c b/sound/soc/atmel/mchp-spdiftx.c
index 4850a177803d..ab2d7a791f39 100644
--- a/sound/soc/atmel/mchp-spdiftx.c
+++ b/sound/soc/atmel/mchp-spdiftx.c
@@ -196,7 +196,7 @@ struct mchp_spdiftx_dev {
 	struct clk				*pclk;
 	struct clk				*gclk;
 	unsigned int				fmt;
-	int					gclk_enabled:1;
+	unsigned int				gclk_enabled:1;
 };
 
 static inline int mchp_spdiftx_is_running(struct mchp_spdiftx_dev *dev)
diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c
index d545a593a251..daafd4251ce6 100644
--- a/sound/soc/codecs/cs42l42.c
+++ b/sound/soc/codecs/cs42l42.c
@@ -1617,7 +1617,6 @@ static irqreturn_t cs42l42_irq_thread(int irq, void *data)
 	unsigned int current_plug_status;
 	unsigned int current_button_status;
 	unsigned int i;
-	int report = 0;
 
 	mutex_lock(&cs42l42->irq_lock);
 	if (cs42l42->suspended) {
@@ -1711,13 +1710,15 @@ static irqreturn_t cs42l42_irq_thread(int irq, void *data)
 
 			if (current_button_status & CS42L42_M_DETECT_TF_MASK) {
 				dev_dbg(cs42l42->dev, "Button released\n");
-				report = 0;
+				snd_soc_jack_report(cs42l42->jack, 0,
+						    SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+						    SND_JACK_BTN_2 | SND_JACK_BTN_3);
 			} else if (current_button_status & CS42L42_M_DETECT_FT_MASK) {
-				report = cs42l42_handle_button_press(cs42l42);
-
+				snd_soc_jack_report(cs42l42->jack,
+						    cs42l42_handle_button_press(cs42l42),
+						    SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+						    SND_JACK_BTN_2 | SND_JACK_BTN_3);
 			}
-			snd_soc_jack_report(cs42l42->jack, report, SND_JACK_BTN_0 | SND_JACK_BTN_1 |
-								   SND_JACK_BTN_2 | SND_JACK_BTN_3);
 		}
 	}
 
diff --git a/sound/soc/codecs/nau8540.c b/sound/soc/codecs/nau8540.c
index 58f70a02f18a..0626d5694c22 100644
--- a/sound/soc/codecs/nau8540.c
+++ b/sound/soc/codecs/nau8540.c
@@ -357,17 +357,32 @@ static const struct snd_soc_dapm_route nau8540_dapm_routes[] = {
 	{"AIFTX", NULL, "Digital CH4 Mux"},
 };
 
-static int nau8540_clock_check(struct nau8540 *nau8540, int rate, int osr)
+static const struct nau8540_osr_attr *
+nau8540_get_osr(struct nau8540 *nau8540)
 {
+	unsigned int osr;
+
+	regmap_read(nau8540->regmap, NAU8540_REG_ADC_SAMPLE_RATE, &osr);
+	osr &= NAU8540_ADC_OSR_MASK;
 	if (osr >= ARRAY_SIZE(osr_adc_sel))
-		return -EINVAL;
+		return NULL;
+	return &osr_adc_sel[osr];
+}
+
+static int nau8540_dai_startup(struct snd_pcm_substream *substream,
+			       struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct nau8540 *nau8540 = snd_soc_component_get_drvdata(component);
+	const struct nau8540_osr_attr *osr;
 
-	if (rate * osr > CLK_ADC_MAX) {
-		dev_err(nau8540->dev, "exceed the maximum frequency of CLK_ADC\n");
+	osr = nau8540_get_osr(nau8540);
+	if (!osr || !osr->osr)
 		return -EINVAL;
-	}
 
-	return 0;
+	return snd_pcm_hw_constraint_minmax(substream->runtime,
+					    SNDRV_PCM_HW_PARAM_RATE,
+					    0, CLK_ADC_MAX / osr->osr);
 }
 
 static int nau8540_hw_params(struct snd_pcm_substream *substream,
@@ -375,7 +390,8 @@ static int nau8540_hw_params(struct snd_pcm_substream *substream,
 {
 	struct snd_soc_component *component = dai->component;
 	struct nau8540 *nau8540 = snd_soc_component_get_drvdata(component);
-	unsigned int val_len = 0, osr;
+	unsigned int val_len = 0;
+	const struct nau8540_osr_attr *osr;
 
 	/* CLK_ADC = OSR * FS
 	 * ADC clock frequency is defined as Over Sampling Rate (OSR)
@@ -383,13 +399,14 @@ static int nau8540_hw_params(struct snd_pcm_substream *substream,
 	 * values must be selected such that the maximum frequency is less
 	 * than 6.144 MHz.
 	 */
-	regmap_read(nau8540->regmap, NAU8540_REG_ADC_SAMPLE_RATE, &osr);
-	osr &= NAU8540_ADC_OSR_MASK;
-	if (nau8540_clock_check(nau8540, params_rate(params), osr))
+	osr = nau8540_get_osr(nau8540);
+	if (!osr || !osr->osr)
+		return -EINVAL;
+	if (params_rate(params) * osr->osr > CLK_ADC_MAX)
 		return -EINVAL;
 	regmap_update_bits(nau8540->regmap, NAU8540_REG_CLOCK_SRC,
 		NAU8540_CLK_ADC_SRC_MASK,
-		osr_adc_sel[osr].clk_src << NAU8540_CLK_ADC_SRC_SFT);
+		osr->clk_src << NAU8540_CLK_ADC_SRC_SFT);
 
 	switch (params_width(params)) {
 	case 16:
@@ -515,6 +532,7 @@ static int nau8540_set_tdm_slot(struct snd_soc_dai *dai,
 
 
 static const struct snd_soc_dai_ops nau8540_dai_ops = {
+	.startup = nau8540_dai_startup,
 	.hw_params = nau8540_hw_params,
 	.set_fmt = nau8540_set_fmt,
 	.set_tdm_slot = nau8540_set_tdm_slot,
diff --git a/sound/soc/codecs/nau8821.c b/sound/soc/codecs/nau8821.c
index 2d21339932e6..4a72b94e8410 100644
--- a/sound/soc/codecs/nau8821.c
+++ b/sound/soc/codecs/nau8821.c
@@ -670,28 +670,40 @@ static const struct snd_soc_dapm_route nau8821_dapm_routes[] = {
 	{"HPOR", NULL, "Class G"},
 };
 
-static int nau8821_clock_check(struct nau8821 *nau8821,
-	int stream, int rate, int osr)
+static const struct nau8821_osr_attr *
+nau8821_get_osr(struct nau8821 *nau8821, int stream)
 {
-	int osrate = 0;
+	unsigned int osr;
 
 	if (stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		regmap_read(nau8821->regmap, NAU8821_R2C_DAC_CTRL1, &osr);
+		osr &= NAU8821_DAC_OVERSAMPLE_MASK;
 		if (osr >= ARRAY_SIZE(osr_dac_sel))
-			return -EINVAL;
-		osrate = osr_dac_sel[osr].osr;
+			return NULL;
+		return &osr_dac_sel[osr];
 	} else {
+		regmap_read(nau8821->regmap, NAU8821_R2B_ADC_RATE, &osr);
+		osr &= NAU8821_ADC_SYNC_DOWN_MASK;
 		if (osr >= ARRAY_SIZE(osr_adc_sel))
-			return -EINVAL;
-		osrate = osr_adc_sel[osr].osr;
+			return NULL;
+		return &osr_adc_sel[osr];
 	}
+}
 
-	if (!osrate || rate * osrate > CLK_DA_AD_MAX) {
-		dev_err(nau8821->dev,
-			"exceed the maximum frequency of CLK_ADC or CLK_DAC");
+static int nau8821_dai_startup(struct snd_pcm_substream *substream,
+			       struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct nau8821 *nau8821 = snd_soc_component_get_drvdata(component);
+	const struct nau8821_osr_attr *osr;
+
+	osr = nau8821_get_osr(nau8821, substream->stream);
+	if (!osr || !osr->osr)
 		return -EINVAL;
-	}
 
-	return 0;
+	return snd_pcm_hw_constraint_minmax(substream->runtime,
+					    SNDRV_PCM_HW_PARAM_RATE,
+					    0, CLK_DA_AD_MAX / osr->osr);
 }
 
 static int nau8821_hw_params(struct snd_pcm_substream *substream,
@@ -699,7 +711,8 @@ static int nau8821_hw_params(struct snd_pcm_substream *substream,
 {
 	struct snd_soc_component *component = dai->component;
 	struct nau8821 *nau8821 = snd_soc_component_get_drvdata(component);
-	unsigned int val_len = 0, osr, ctrl_val, bclk_fs, clk_div;
+	unsigned int val_len = 0, ctrl_val, bclk_fs, clk_div;
+	const struct nau8821_osr_attr *osr;
 
 	nau8821->fs = params_rate(params);
 	/* CLK_DAC or CLK_ADC = OSR * FS
@@ -708,27 +721,19 @@ static int nau8821_hw_params(struct snd_pcm_substream *substream,
 	 * values must be selected such that the maximum frequency is less
 	 * than 6.144 MHz.
 	 */
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		regmap_read(nau8821->regmap, NAU8821_R2C_DAC_CTRL1, &osr);
-		osr &= NAU8821_DAC_OVERSAMPLE_MASK;
-		if (nau8821_clock_check(nau8821, substream->stream,
-			nau8821->fs, osr)) {
-			return -EINVAL;
-		}
+	osr = nau8821_get_osr(nau8821, substream->stream);
+	if (!osr || !osr->osr)
+		return -EINVAL;
+	if (nau8821->fs * osr->osr > CLK_DA_AD_MAX)
+		return -EINVAL;
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
 		regmap_update_bits(nau8821->regmap, NAU8821_R03_CLK_DIVIDER,
 			NAU8821_CLK_DAC_SRC_MASK,
-			osr_dac_sel[osr].clk_src << NAU8821_CLK_DAC_SRC_SFT);
-	} else {
-		regmap_read(nau8821->regmap, NAU8821_R2B_ADC_RATE, &osr);
-		osr &= NAU8821_ADC_SYNC_DOWN_MASK;
-		if (nau8821_clock_check(nau8821, substream->stream,
-			nau8821->fs, osr)) {
-			return -EINVAL;
-		}
+			osr->clk_src << NAU8821_CLK_DAC_SRC_SFT);
+	else
 		regmap_update_bits(nau8821->regmap, NAU8821_R03_CLK_DIVIDER,
 			NAU8821_CLK_ADC_SRC_MASK,
-			osr_adc_sel[osr].clk_src << NAU8821_CLK_ADC_SRC_SFT);
-	}
+			osr->clk_src << NAU8821_CLK_ADC_SRC_SFT);
 
 	/* make BCLK and LRC divde configuration if the codec as master. */
 	regmap_read(nau8821->regmap, NAU8821_R1D_I2S_PCM_CTRL2, &ctrl_val);
@@ -843,6 +848,7 @@ static int nau8821_digital_mute(struct snd_soc_dai *dai, int mute,
 }
 
 static const struct snd_soc_dai_ops nau8821_dai_ops = {
+	.startup = nau8821_dai_startup,
 	.hw_params = nau8821_hw_params,
 	.set_fmt = nau8821_set_dai_fmt,
 	.mute_stream = nau8821_digital_mute,
diff --git a/sound/soc/codecs/nau8824.c b/sound/soc/codecs/nau8824.c
index ad54d70f7d8e..4f19fd9b65d1 100644
--- a/sound/soc/codecs/nau8824.c
+++ b/sound/soc/codecs/nau8824.c
@@ -901,7 +901,10 @@ static void nau8824_jdet_work(struct work_struct *work)
 		NAU8824_IRQ_KEY_RELEASE_DIS |
 		NAU8824_IRQ_KEY_SHORT_PRESS_DIS, 0);
 
-	nau8824_sema_release(nau8824);
+	if (nau8824->resume_lock) {
+		nau8824_sema_release(nau8824);
+		nau8824->resume_lock = false;
+	}
 }
 
 static void nau8824_setup_auto_irq(struct nau8824 *nau8824)
@@ -966,7 +969,10 @@ static irqreturn_t nau8824_interrupt(int irq, void *data)
 		/* release semaphore held after resume,
 		 * and cancel jack detection
 		 */
-		nau8824_sema_release(nau8824);
+		if (nau8824->resume_lock) {
+			nau8824_sema_release(nau8824);
+			nau8824->resume_lock = false;
+		}
 		cancel_work_sync(&nau8824->jdet_work);
 	} else if (active_irq & NAU8824_KEY_SHORT_PRESS_IRQ) {
 		int key_status, button_pressed;
@@ -1014,27 +1020,42 @@ static irqreturn_t nau8824_interrupt(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int nau8824_clock_check(struct nau8824 *nau8824,
-	int stream, int rate, int osr)
+static const struct nau8824_osr_attr *
+nau8824_get_osr(struct nau8824 *nau8824, int stream)
 {
-	int osrate;
+	unsigned int osr;
 
 	if (stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		regmap_read(nau8824->regmap,
+			    NAU8824_REG_DAC_FILTER_CTRL_1, &osr);
+		osr &= NAU8824_DAC_OVERSAMPLE_MASK;
 		if (osr >= ARRAY_SIZE(osr_dac_sel))
-			return -EINVAL;
-		osrate = osr_dac_sel[osr].osr;
+			return NULL;
+		return &osr_dac_sel[osr];
 	} else {
+		regmap_read(nau8824->regmap,
+			    NAU8824_REG_ADC_FILTER_CTRL, &osr);
+		osr &= NAU8824_ADC_SYNC_DOWN_MASK;
 		if (osr >= ARRAY_SIZE(osr_adc_sel))
-			return -EINVAL;
-		osrate = osr_adc_sel[osr].osr;
+			return NULL;
+		return &osr_adc_sel[osr];
 	}
+}
+
+static int nau8824_dai_startup(struct snd_pcm_substream *substream,
+			       struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct nau8824 *nau8824 = snd_soc_component_get_drvdata(component);
+	const struct nau8824_osr_attr *osr;
 
-	if (!osrate || rate * osr > CLK_DA_AD_MAX) {
-		dev_err(nau8824->dev, "exceed the maximum frequency of CLK_ADC or CLK_DAC\n");
+	osr = nau8824_get_osr(nau8824, substream->stream);
+	if (!osr || !osr->osr)
 		return -EINVAL;
-	}
 
-	return 0;
+	return snd_pcm_hw_constraint_minmax(substream->runtime,
+					    SNDRV_PCM_HW_PARAM_RATE,
+					    0, CLK_DA_AD_MAX / osr->osr);
 }
 
 static int nau8824_hw_params(struct snd_pcm_substream *substream,
@@ -1042,7 +1063,9 @@ static int nau8824_hw_params(struct snd_pcm_substream *substream,
 {
 	struct snd_soc_component *component = dai->component;
 	struct nau8824 *nau8824 = snd_soc_component_get_drvdata(component);
-	unsigned int val_len = 0, osr, ctrl_val, bclk_fs, bclk_div;
+	unsigned int val_len = 0, ctrl_val, bclk_fs, bclk_div;
+	const struct nau8824_osr_attr *osr;
+	int err = -EINVAL;
 
 	nau8824_sema_acquire(nau8824, HZ);
 
@@ -1053,27 +1076,19 @@ static int nau8824_hw_params(struct snd_pcm_substream *substream,
 	 * than 6.144 MHz.
 	 */
 	nau8824->fs = params_rate(params);
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		regmap_read(nau8824->regmap,
-			NAU8824_REG_DAC_FILTER_CTRL_1, &osr);
-		osr &= NAU8824_DAC_OVERSAMPLE_MASK;
-		if (nau8824_clock_check(nau8824, substream->stream,
-			nau8824->fs, osr))
-			return -EINVAL;
+	osr = nau8824_get_osr(nau8824, substream->stream);
+	if (!osr || !osr->osr)
+		goto error;
+	if (nau8824->fs * osr->osr > CLK_DA_AD_MAX)
+		goto error;
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
 		regmap_update_bits(nau8824->regmap, NAU8824_REG_CLK_DIVIDER,
 			NAU8824_CLK_DAC_SRC_MASK,
-			osr_dac_sel[osr].clk_src << NAU8824_CLK_DAC_SRC_SFT);
-	} else {
-		regmap_read(nau8824->regmap,
-			NAU8824_REG_ADC_FILTER_CTRL, &osr);
-		osr &= NAU8824_ADC_SYNC_DOWN_MASK;
-		if (nau8824_clock_check(nau8824, substream->stream,
-			nau8824->fs, osr))
-			return -EINVAL;
+			osr->clk_src << NAU8824_CLK_DAC_SRC_SFT);
+	else
 		regmap_update_bits(nau8824->regmap, NAU8824_REG_CLK_DIVIDER,
 			NAU8824_CLK_ADC_SRC_MASK,
-			osr_adc_sel[osr].clk_src << NAU8824_CLK_ADC_SRC_SFT);
-	}
+			osr->clk_src << NAU8824_CLK_ADC_SRC_SFT);
 
 	/* make BCLK and LRC divde configuration if the codec as master. */
 	regmap_read(nau8824->regmap,
@@ -1090,7 +1105,7 @@ static int nau8824_hw_params(struct snd_pcm_substream *substream,
 		else if (bclk_fs <= 256)
 			bclk_div = 0;
 		else
-			return -EINVAL;
+			goto error;
 		regmap_update_bits(nau8824->regmap,
 			NAU8824_REG_PORT0_I2S_PCM_CTRL_2,
 			NAU8824_I2S_LRC_DIV_MASK | NAU8824_I2S_BLK_DIV_MASK,
@@ -1111,15 +1126,17 @@ static int nau8824_hw_params(struct snd_pcm_substream *substream,
 		val_len |= NAU8824_I2S_DL_32;
 		break;
 	default:
-		return -EINVAL;
+		goto error;
 	}
 
 	regmap_update_bits(nau8824->regmap, NAU8824_REG_PORT0_I2S_PCM_CTRL_1,
 		NAU8824_I2S_DL_MASK, val_len);
+	err = 0;
 
+ error:
 	nau8824_sema_release(nau8824);
 
-	return 0;
+	return err;
 }
 
 static int nau8824_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
@@ -1128,8 +1145,6 @@ static int nau8824_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	struct nau8824 *nau8824 = snd_soc_component_get_drvdata(component);
 	unsigned int ctrl1_val = 0, ctrl2_val = 0;
 
-	nau8824_sema_acquire(nau8824, HZ);
-
 	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
 	case SND_SOC_DAIFMT_CBM_CFM:
 		ctrl2_val |= NAU8824_I2S_MS_MASTER;
@@ -1171,6 +1186,8 @@ static int nau8824_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 		return -EINVAL;
 	}
 
+	nau8824_sema_acquire(nau8824, HZ);
+
 	regmap_update_bits(nau8824->regmap, NAU8824_REG_PORT0_I2S_PCM_CTRL_1,
 		NAU8824_I2S_DF_MASK | NAU8824_I2S_BP_MASK |
 		NAU8824_I2S_PCMB_EN, ctrl1_val);
@@ -1513,6 +1530,7 @@ static int __maybe_unused nau8824_suspend(struct snd_soc_component *component)
 static int __maybe_unused nau8824_resume(struct snd_soc_component *component)
 {
 	struct nau8824 *nau8824 = snd_soc_component_get_drvdata(component);
+	int ret;
 
 	regcache_cache_only(nau8824->regmap, false);
 	regcache_sync(nau8824->regmap);
@@ -1520,7 +1538,10 @@ static int __maybe_unused nau8824_resume(struct snd_soc_component *component)
 		/* Hold semaphore to postpone playback happening
 		 * until jack detection done.
 		 */
-		nau8824_sema_acquire(nau8824, 0);
+		nau8824->resume_lock = true;
+		ret = nau8824_sema_acquire(nau8824, 0);
+		if (ret)
+			nau8824->resume_lock = false;
 		enable_irq(nau8824->irq);
 	}
 
@@ -1547,6 +1568,7 @@ static const struct snd_soc_component_driver nau8824_component_driver = {
 };
 
 static const struct snd_soc_dai_ops nau8824_dai_ops = {
+	.startup = nau8824_dai_startup,
 	.hw_params = nau8824_hw_params,
 	.set_fmt = nau8824_set_fmt,
 	.set_tdm_slot = nau8824_set_tdm_slot,
@@ -1928,6 +1950,7 @@ static int nau8824_i2c_probe(struct i2c_client *i2c)
 	nau8824->regmap = devm_regmap_init_i2c(i2c, &nau8824_regmap_config);
 	if (IS_ERR(nau8824->regmap))
 		return PTR_ERR(nau8824->regmap);
+	nau8824->resume_lock = false;
 	nau8824->dev = dev;
 	nau8824->irq = i2c->irq;
 	sema_init(&nau8824->jd_sem, 1);
diff --git a/sound/soc/codecs/nau8824.h b/sound/soc/codecs/nau8824.h
index de4bae8281d0..5fcfc43dfc85 100644
--- a/sound/soc/codecs/nau8824.h
+++ b/sound/soc/codecs/nau8824.h
@@ -436,6 +436,7 @@ struct nau8824 {
 	struct semaphore jd_sem;
 	int fs;
 	int irq;
+	int resume_lock;
 	int micbias_voltage;
 	int vref_impedance;
 	int jkdet_polarity;
diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c
index 54ef7b0fa878..8213273f501e 100644
--- a/sound/soc/codecs/nau8825.c
+++ b/sound/soc/codecs/nau8825.c
@@ -1247,27 +1247,42 @@ static const struct snd_soc_dapm_route nau8825_dapm_routes[] = {
 	{"HPOR", NULL, "Class G"},
 };
 
-static int nau8825_clock_check(struct nau8825 *nau8825,
-	int stream, int rate, int osr)
+static const struct nau8825_osr_attr *
+nau8825_get_osr(struct nau8825 *nau8825, int stream)
 {
-	int osrate;
+	unsigned int osr;
 
 	if (stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		regmap_read(nau8825->regmap,
+			    NAU8825_REG_DAC_CTRL1, &osr);
+		osr &= NAU8825_DAC_OVERSAMPLE_MASK;
 		if (osr >= ARRAY_SIZE(osr_dac_sel))
-			return -EINVAL;
-		osrate = osr_dac_sel[osr].osr;
+			return NULL;
+		return &osr_dac_sel[osr];
 	} else {
+		regmap_read(nau8825->regmap,
+			    NAU8825_REG_ADC_RATE, &osr);
+		osr &= NAU8825_ADC_SYNC_DOWN_MASK;
 		if (osr >= ARRAY_SIZE(osr_adc_sel))
-			return -EINVAL;
-		osrate = osr_adc_sel[osr].osr;
+			return NULL;
+		return &osr_adc_sel[osr];
 	}
+}
 
-	if (!osrate || rate * osr > CLK_DA_AD_MAX) {
-		dev_err(nau8825->dev, "exceed the maximum frequency of CLK_ADC or CLK_DAC\n");
+static int nau8825_dai_startup(struct snd_pcm_substream *substream,
+			       struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct nau8825 *nau8825 = snd_soc_component_get_drvdata(component);
+	const struct nau8825_osr_attr *osr;
+
+	osr = nau8825_get_osr(nau8825, substream->stream);
+	if (!osr || !osr->osr)
 		return -EINVAL;
-	}
 
-	return 0;
+	return snd_pcm_hw_constraint_minmax(substream->runtime,
+					    SNDRV_PCM_HW_PARAM_RATE,
+					    0, CLK_DA_AD_MAX / osr->osr);
 }
 
 static int nau8825_hw_params(struct snd_pcm_substream *substream,
@@ -1276,7 +1291,9 @@ static int nau8825_hw_params(struct snd_pcm_substream *substream,
 {
 	struct snd_soc_component *component = dai->component;
 	struct nau8825 *nau8825 = snd_soc_component_get_drvdata(component);
-	unsigned int val_len = 0, osr, ctrl_val, bclk_fs, bclk_div;
+	unsigned int val_len = 0, ctrl_val, bclk_fs, bclk_div;
+	const struct nau8825_osr_attr *osr;
+	int err = -EINVAL;
 
 	nau8825_sema_acquire(nau8825, 3 * HZ);
 
@@ -1286,29 +1303,19 @@ static int nau8825_hw_params(struct snd_pcm_substream *substream,
 	 * values must be selected such that the maximum frequency is less
 	 * than 6.144 MHz.
 	 */
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		regmap_read(nau8825->regmap, NAU8825_REG_DAC_CTRL1, &osr);
-		osr &= NAU8825_DAC_OVERSAMPLE_MASK;
-		if (nau8825_clock_check(nau8825, substream->stream,
-			params_rate(params), osr)) {
-			nau8825_sema_release(nau8825);
-			return -EINVAL;
-		}
+	osr = nau8825_get_osr(nau8825, substream->stream);
+	if (!osr || !osr->osr)
+		goto error;
+	if (params_rate(params) * osr->osr > CLK_DA_AD_MAX)
+		goto error;
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
 		regmap_update_bits(nau8825->regmap, NAU8825_REG_CLK_DIVIDER,
 			NAU8825_CLK_DAC_SRC_MASK,
-			osr_dac_sel[osr].clk_src << NAU8825_CLK_DAC_SRC_SFT);
-	} else {
-		regmap_read(nau8825->regmap, NAU8825_REG_ADC_RATE, &osr);
-		osr &= NAU8825_ADC_SYNC_DOWN_MASK;
-		if (nau8825_clock_check(nau8825, substream->stream,
-			params_rate(params), osr)) {
-			nau8825_sema_release(nau8825);
-			return -EINVAL;
-		}
+			osr->clk_src << NAU8825_CLK_DAC_SRC_SFT);
+	else
 		regmap_update_bits(nau8825->regmap, NAU8825_REG_CLK_DIVIDER,
 			NAU8825_CLK_ADC_SRC_MASK,
-			osr_adc_sel[osr].clk_src << NAU8825_CLK_ADC_SRC_SFT);
-	}
+			osr->clk_src << NAU8825_CLK_ADC_SRC_SFT);
 
 	/* make BCLK and LRC divde configuration if the codec as master. */
 	regmap_read(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL2, &ctrl_val);
@@ -1321,10 +1328,8 @@ static int nau8825_hw_params(struct snd_pcm_substream *substream,
 			bclk_div = 1;
 		else if (bclk_fs <= 128)
 			bclk_div = 0;
-		else {
-			nau8825_sema_release(nau8825);
-			return -EINVAL;
-		}
+		else
+			goto error;
 		regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL2,
 			NAU8825_I2S_LRC_DIV_MASK | NAU8825_I2S_BLK_DIV_MASK,
 			((bclk_div + 1) << NAU8825_I2S_LRC_DIV_SFT) | bclk_div);
@@ -1344,17 +1349,18 @@ static int nau8825_hw_params(struct snd_pcm_substream *substream,
 		val_len |= NAU8825_I2S_DL_32;
 		break;
 	default:
-		nau8825_sema_release(nau8825);
-		return -EINVAL;
+		goto error;
 	}
 
 	regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL1,
 		NAU8825_I2S_DL_MASK, val_len);
+	err = 0;
 
+ error:
 	/* Release the semaphore. */
 	nau8825_sema_release(nau8825);
 
-	return 0;
+	return err;
 }
 
 static int nau8825_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
@@ -1420,6 +1426,7 @@ static int nau8825_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
 }
 
 static const struct snd_soc_dai_ops nau8825_dai_ops = {
+	.startup	= nau8825_dai_startup,
 	.hw_params	= nau8825_hw_params,
 	.set_fmt	= nau8825_set_dai_fmt,
 };
diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c
index 38ab8d4291c2..0f8e6dd214b0 100644
--- a/sound/soc/codecs/rt5640.c
+++ b/sound/soc/codecs/rt5640.c
@@ -1986,7 +1986,7 @@ static int rt5640_set_bias_level(struct snd_soc_component *component,
 		snd_soc_component_write(component, RT5640_PWR_MIXER, 0x0000);
 		if (rt5640->jd_src == RT5640_JD_SRC_HDA_HEADER)
 			snd_soc_component_write(component, RT5640_PWR_ANLG1,
-				0x0018);
+				0x2818);
 		else
 			snd_soc_component_write(component, RT5640_PWR_ANLG1,
 				0x0000);
@@ -2494,7 +2494,7 @@ static void rt5640_enable_jack_detect(struct snd_soc_component *component,
 
 	/* Select JD-source */
 	snd_soc_component_update_bits(component, RT5640_JD_CTRL,
-		RT5640_JD_MASK, rt5640->jd_src);
+		RT5640_JD_MASK, rt5640->jd_src << RT5640_JD_SFT);
 
 	/* Selecting GPIO01 as an interrupt */
 	snd_soc_component_update_bits(component, RT5640_GPIO_CTRL1,
@@ -2504,12 +2504,8 @@ static void rt5640_enable_jack_detect(struct snd_soc_component *component,
 	snd_soc_component_update_bits(component, RT5640_GPIO_CTRL3,
 		RT5640_GP1_PF_MASK, RT5640_GP1_PF_OUT);
 
-	/* Enabling jd2 in general control 1 */
 	snd_soc_component_write(component, RT5640_DUMMY1, 0x3f41);
 
-	/* Enabling jd2 in general control 2 */
-	snd_soc_component_write(component, RT5640_DUMMY2, 0x4001);
-
 	rt5640_set_ovcd_params(component);
 
 	/*
@@ -2518,12 +2514,25 @@ static void rt5640_enable_jack_detect(struct snd_soc_component *component,
 	 * pin 0/1 instead of it being stuck to 1. So we invert the JD polarity
 	 * on systems where the hardware does not already do this.
 	 */
-	if (rt5640->jd_inverted)
-		snd_soc_component_write(component, RT5640_IRQ_CTRL1,
-					RT5640_IRQ_JD_NOR);
-	else
-		snd_soc_component_write(component, RT5640_IRQ_CTRL1,
-					RT5640_IRQ_JD_NOR | RT5640_JD_P_INV);
+	if (rt5640->jd_inverted) {
+		if (rt5640->jd_src == RT5640_JD_SRC_JD1_IN4P)
+			snd_soc_component_write(component, RT5640_IRQ_CTRL1,
+				RT5640_IRQ_JD_NOR);
+		else if (rt5640->jd_src == RT5640_JD_SRC_JD2_IN4N)
+			snd_soc_component_update_bits(component, RT5640_DUMMY2,
+				RT5640_IRQ_JD2_MASK | RT5640_JD2_MASK,
+				RT5640_IRQ_JD2_NOR | RT5640_JD2_EN);
+	} else {
+		if (rt5640->jd_src == RT5640_JD_SRC_JD1_IN4P)
+			snd_soc_component_write(component, RT5640_IRQ_CTRL1,
+				RT5640_IRQ_JD_NOR | RT5640_JD_P_INV);
+		else if (rt5640->jd_src == RT5640_JD_SRC_JD2_IN4N)
+			snd_soc_component_update_bits(component, RT5640_DUMMY2,
+				RT5640_IRQ_JD2_MASK | RT5640_JD2_P_MASK |
+				RT5640_JD2_MASK,
+				RT5640_IRQ_JD2_NOR | RT5640_JD2_P_INV |
+				RT5640_JD2_EN);
+	}
 
 	rt5640->jack = jack;
 	if (rt5640->jack->status & SND_JACK_MICROPHONE) {
@@ -2600,7 +2609,8 @@ static void rt5640_enable_hda_jack_detect(
 	snd_soc_component_update_bits(component, RT5640_DUMMY1, 0x400, 0x0);
 
 	snd_soc_component_update_bits(component, RT5640_PWR_ANLG1,
-		RT5640_PWR_VREF2, RT5640_PWR_VREF2);
+		RT5640_PWR_VREF2 | RT5640_PWR_MB | RT5640_PWR_BG,
+		RT5640_PWR_VREF2 | RT5640_PWR_MB | RT5640_PWR_BG);
 	usleep_range(10000, 15000);
 	snd_soc_component_update_bits(component, RT5640_PWR_ANLG1,
 		RT5640_PWR_FV2, RT5640_PWR_FV2);
@@ -2724,10 +2734,8 @@ static int rt5640_probe(struct snd_soc_component *component)
 
 	if (device_property_read_u32(component->dev,
 				     "realtek,jack-detect-source", &val) == 0) {
-		if (val <= RT5640_JD_SRC_GPIO4)
-			rt5640->jd_src = val << RT5640_JD_SFT;
-		else if (val == RT5640_JD_SRC_HDA_HEADER)
-			rt5640->jd_src = RT5640_JD_SRC_HDA_HEADER;
+		if (val <= RT5640_JD_SRC_HDA_HEADER)
+			rt5640->jd_src = val;
 		else
 			dev_warn(component->dev, "Warning: Invalid jack-detect-source value: %d, leaving jack-detect disabled\n",
 				 val);
@@ -2808,12 +2816,31 @@ static int rt5640_resume(struct snd_soc_component *component)
 	regcache_sync(rt5640->regmap);
 
 	if (rt5640->jack) {
-		if (rt5640->jd_src == RT5640_JD_SRC_HDA_HEADER)
+		if (rt5640->jd_src == RT5640_JD_SRC_HDA_HEADER) {
 			snd_soc_component_update_bits(component,
 				RT5640_DUMMY2, 0x1100, 0x1100);
-		else
-			snd_soc_component_write(component, RT5640_DUMMY2,
-				0x4001);
+		} else {
+			if (rt5640->jd_inverted) {
+				if (rt5640->jd_src == RT5640_JD_SRC_JD2_IN4N)
+					snd_soc_component_update_bits(
+						component, RT5640_DUMMY2,
+						RT5640_IRQ_JD2_MASK |
+						RT5640_JD2_MASK,
+						RT5640_IRQ_JD2_NOR |
+						RT5640_JD2_EN);
+
+			} else {
+				if (rt5640->jd_src == RT5640_JD_SRC_JD2_IN4N)
+					snd_soc_component_update_bits(
+						component, RT5640_DUMMY2,
+						RT5640_IRQ_JD2_MASK |
+						RT5640_JD2_P_MASK |
+						RT5640_JD2_MASK,
+						RT5640_IRQ_JD2_NOR |
+						RT5640_JD2_P_INV |
+						RT5640_JD2_EN);
+			}
+		}
 
 		queue_delayed_work(system_long_wq, &rt5640->jack_work, 0);
 	}
diff --git a/sound/soc/codecs/rt5640.h b/sound/soc/codecs/rt5640.h
index 505c93514051..f58b88e3325b 100644
--- a/sound/soc/codecs/rt5640.h
+++ b/sound/soc/codecs/rt5640.h
@@ -1984,6 +1984,20 @@
 #define RT5640_M_MONO_ADC_R_SFT			12
 #define RT5640_MCLK_DET				(0x1 << 11)
 
+/* General Control 1 (0xfb) */
+#define RT5640_IRQ_JD2_MASK			(0x1 << 12)
+#define RT5640_IRQ_JD2_SFT			12
+#define RT5640_IRQ_JD2_BP			(0x0 << 12)
+#define RT5640_IRQ_JD2_NOR			(0x1 << 12)
+#define RT5640_JD2_P_MASK			(0x1 << 10)
+#define RT5640_JD2_P_SFT			10
+#define RT5640_JD2_P_NOR			(0x0 << 10)
+#define RT5640_JD2_P_INV			(0x1 << 10)
+#define RT5640_JD2_MASK				(0x1 << 8)
+#define RT5640_JD2_SFT				8
+#define RT5640_JD2_DIS				(0x0 << 8)
+#define RT5640_JD2_EN				(0x1 << 8)
+
 /* Codec Private Register definition */
 
 /* MIC Over current threshold scale factor (0x15) */
diff --git a/sound/soc/codecs/tas2770.c b/sound/soc/codecs/tas2770.c
index 3cb634c28261..b6765235a4b3 100644
--- a/sound/soc/codecs/tas2770.c
+++ b/sound/soc/codecs/tas2770.c
@@ -46,34 +46,22 @@ static void tas2770_reset(struct tas2770_priv *tas2770)
 	usleep_range(1000, 2000);
 }
 
-static int tas2770_set_bias_level(struct snd_soc_component *component,
-				 enum snd_soc_bias_level level)
+static int tas2770_update_pwr_ctrl(struct tas2770_priv *tas2770)
 {
-	struct tas2770_priv *tas2770 =
-			snd_soc_component_get_drvdata(component);
+	struct snd_soc_component *component = tas2770->component;
+	unsigned int val;
+	int ret;
 
-	switch (level) {
-	case SND_SOC_BIAS_ON:
-		snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-					      TAS2770_PWR_CTRL_MASK,
-					      TAS2770_PWR_CTRL_ACTIVE);
-		break;
-	case SND_SOC_BIAS_STANDBY:
-	case SND_SOC_BIAS_PREPARE:
-		snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-					      TAS2770_PWR_CTRL_MASK,
-					      TAS2770_PWR_CTRL_MUTE);
-		break;
-	case SND_SOC_BIAS_OFF:
-		snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-					      TAS2770_PWR_CTRL_MASK,
-					      TAS2770_PWR_CTRL_SHUTDOWN);
-		break;
+	if (tas2770->dac_powered)
+		val = tas2770->unmuted ?
+			TAS2770_PWR_CTRL_ACTIVE : TAS2770_PWR_CTRL_MUTE;
+	else
+		val = TAS2770_PWR_CTRL_SHUTDOWN;
 
-	default:
-		dev_err(tas2770->dev, "wrong power level setting %d\n", level);
-		return -EINVAL;
-	}
+	ret = snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
+					    TAS2770_PWR_CTRL_MASK, val);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
@@ -114,9 +102,7 @@ static int tas2770_codec_resume(struct snd_soc_component *component)
 		gpiod_set_value_cansleep(tas2770->sdz_gpio, 1);
 		usleep_range(1000, 2000);
 	} else {
-		ret = snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-						    TAS2770_PWR_CTRL_MASK,
-						    TAS2770_PWR_CTRL_ACTIVE);
+		ret = tas2770_update_pwr_ctrl(tas2770);
 		if (ret < 0)
 			return ret;
 	}
@@ -152,24 +138,19 @@ static int tas2770_dac_event(struct snd_soc_dapm_widget *w,
 
 	switch (event) {
 	case SND_SOC_DAPM_POST_PMU:
-		ret = snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-						    TAS2770_PWR_CTRL_MASK,
-						    TAS2770_PWR_CTRL_MUTE);
+		tas2770->dac_powered = 1;
+		ret = tas2770_update_pwr_ctrl(tas2770);
 		break;
 	case SND_SOC_DAPM_PRE_PMD:
-		ret = snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-						    TAS2770_PWR_CTRL_MASK,
-						    TAS2770_PWR_CTRL_SHUTDOWN);
+		tas2770->dac_powered = 0;
+		ret = tas2770_update_pwr_ctrl(tas2770);
 		break;
 	default:
 		dev_err(tas2770->dev, "Not supported evevt\n");
 		return -EINVAL;
 	}
 
-	if (ret < 0)
-		return ret;
-
-	return 0;
+	return ret;
 }
 
 static const struct snd_kcontrol_new isense_switch =
@@ -203,21 +184,11 @@ static const struct snd_soc_dapm_route tas2770_audio_map[] = {
 static int tas2770_mute(struct snd_soc_dai *dai, int mute, int direction)
 {
 	struct snd_soc_component *component = dai->component;
-	int ret;
-
-	if (mute)
-		ret = snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-						    TAS2770_PWR_CTRL_MASK,
-						    TAS2770_PWR_CTRL_MUTE);
-	else
-		ret = snd_soc_component_update_bits(component, TAS2770_PWR_CTRL,
-						    TAS2770_PWR_CTRL_MASK,
-						    TAS2770_PWR_CTRL_ACTIVE);
-
-	if (ret < 0)
-		return ret;
+	struct tas2770_priv *tas2770 =
+			snd_soc_component_get_drvdata(component);
 
-	return 0;
+	tas2770->unmuted = !mute;
+	return tas2770_update_pwr_ctrl(tas2770);
 }
 
 static int tas2770_set_bitwidth(struct tas2770_priv *tas2770, int bitwidth)
@@ -337,7 +308,7 @@ static int tas2770_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	struct snd_soc_component *component = dai->component;
 	struct tas2770_priv *tas2770 =
 			snd_soc_component_get_drvdata(component);
-	u8 tdm_rx_start_slot = 0, asi_cfg_1 = 0;
+	u8 tdm_rx_start_slot = 0, invert_fpol = 0, fpol_preinv = 0, asi_cfg_1 = 0;
 	int ret;
 
 	switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
@@ -349,9 +320,15 @@ static int tas2770_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	}
 
 	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_IF:
+		invert_fpol = 1;
+		fallthrough;
 	case SND_SOC_DAIFMT_NB_NF:
 		asi_cfg_1 |= TAS2770_TDM_CFG_REG1_RX_RSING;
 		break;
+	case SND_SOC_DAIFMT_IB_IF:
+		invert_fpol = 1;
+		fallthrough;
 	case SND_SOC_DAIFMT_IB_NF:
 		asi_cfg_1 |= TAS2770_TDM_CFG_REG1_RX_FALING;
 		break;
@@ -369,15 +346,19 @@ static int tas2770_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_I2S:
 		tdm_rx_start_slot = 1;
+		fpol_preinv = 0;
 		break;
 	case SND_SOC_DAIFMT_DSP_A:
 		tdm_rx_start_slot = 0;
+		fpol_preinv = 1;
 		break;
 	case SND_SOC_DAIFMT_DSP_B:
 		tdm_rx_start_slot = 1;
+		fpol_preinv = 1;
 		break;
 	case SND_SOC_DAIFMT_LEFT_J:
 		tdm_rx_start_slot = 0;
+		fpol_preinv = 1;
 		break;
 	default:
 		dev_err(tas2770->dev,
@@ -391,6 +372,14 @@ static int tas2770_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	if (ret < 0)
 		return ret;
 
+	ret = snd_soc_component_update_bits(component, TAS2770_TDM_CFG_REG0,
+					    TAS2770_TDM_CFG_REG0_FPOL_MASK,
+					    (fpol_preinv ^ invert_fpol)
+					     ? TAS2770_TDM_CFG_REG0_FPOL_RSING
+					     : TAS2770_TDM_CFG_REG0_FPOL_FALING);
+	if (ret < 0)
+		return ret;
+
 	return 0;
 }
 
@@ -489,7 +478,7 @@ static struct snd_soc_dai_driver tas2770_dai_driver[] = {
 		.id = 0,
 		.playback = {
 			.stream_name    = "ASI1 Playback",
-			.channels_min   = 2,
+			.channels_min   = 1,
 			.channels_max   = 2,
 			.rates      = TAS2770_RATES,
 			.formats    = TAS2770_FORMATS,
@@ -506,6 +495,8 @@ static struct snd_soc_dai_driver tas2770_dai_driver[] = {
 	},
 };
 
+static const struct regmap_config tas2770_i2c_regmap;
+
 static int tas2770_codec_probe(struct snd_soc_component *component)
 {
 	struct tas2770_priv *tas2770 =
@@ -519,6 +510,7 @@ static int tas2770_codec_probe(struct snd_soc_component *component)
 	}
 
 	tas2770_reset(tas2770);
+	regmap_reinit_cache(tas2770->regmap, &tas2770_i2c_regmap);
 
 	return 0;
 }
@@ -537,7 +529,6 @@ static const struct snd_soc_component_driver soc_component_driver_tas2770 = {
 	.probe			= tas2770_codec_probe,
 	.suspend		= tas2770_codec_suspend,
 	.resume			= tas2770_codec_resume,
-	.set_bias_level = tas2770_set_bias_level,
 	.controls		= tas2770_snd_controls,
 	.num_controls		= ARRAY_SIZE(tas2770_snd_controls),
 	.dapm_widgets		= tas2770_dapm_widgets,
diff --git a/sound/soc/codecs/tas2770.h b/sound/soc/codecs/tas2770.h
index d156666bcc55..f75f40781ab1 100644
--- a/sound/soc/codecs/tas2770.h
+++ b/sound/soc/codecs/tas2770.h
@@ -41,6 +41,9 @@
 #define TAS2770_TDM_CFG_REG0_31_44_1_48KHZ  0x6
 #define TAS2770_TDM_CFG_REG0_31_88_2_96KHZ  0x8
 #define TAS2770_TDM_CFG_REG0_31_176_4_192KHZ  0xa
+#define TAS2770_TDM_CFG_REG0_FPOL_MASK  BIT(0)
+#define TAS2770_TDM_CFG_REG0_FPOL_RSING  0
+#define TAS2770_TDM_CFG_REG0_FPOL_FALING  1
     /* TDM Configuration Reg1 */
 #define TAS2770_TDM_CFG_REG1  TAS2770_REG(0X0, 0x0B)
 #define TAS2770_TDM_CFG_REG1_MASK	GENMASK(5, 1)
@@ -135,6 +138,8 @@ struct tas2770_priv {
 	struct device *dev;
 	int v_sense_slot;
 	int i_sense_slot;
+	bool dac_powered;
+	bool unmuted;
 };
 
 #endif /* __TAS2770__ */
diff --git a/sound/soc/codecs/tlv320aic32x4.c b/sound/soc/codecs/tlv320aic32x4.c
index 4b74805cdd2e..ffe1828a4b7e 100644
--- a/sound/soc/codecs/tlv320aic32x4.c
+++ b/sound/soc/codecs/tlv320aic32x4.c
@@ -49,6 +49,8 @@ struct aic32x4_priv {
 	struct aic32x4_setup_data *setup;
 	struct device *dev;
 	enum aic32x4_type type;
+
+	unsigned int fmt;
 };
 
 static int aic32x4_reset_adc(struct snd_soc_dapm_widget *w,
@@ -611,6 +613,7 @@ static int aic32x4_set_dai_sysclk(struct snd_soc_dai *codec_dai,
 static int aic32x4_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
 {
 	struct snd_soc_component *component = codec_dai->component;
+	struct aic32x4_priv *aic32x4 = snd_soc_component_get_drvdata(component);
 	u8 iface_reg_1 = 0;
 	u8 iface_reg_2 = 0;
 	u8 iface_reg_3 = 0;
@@ -653,6 +656,8 @@ static int aic32x4_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
 		return -EINVAL;
 	}
 
+	aic32x4->fmt = fmt;
+
 	snd_soc_component_update_bits(component, AIC32X4_IFACE1,
 				AIC32X4_IFACE1_DATATYPE_MASK |
 				AIC32X4_IFACE1_MASTER_MASK, iface_reg_1);
@@ -757,6 +762,10 @@ static int aic32x4_setup_clocks(struct snd_soc_component *component,
 		return -EINVAL;
 	}
 
+	/* PCM over I2S is always 2-channel */
+	if ((aic32x4->fmt & SND_SOC_DAIFMT_FORMAT_MASK) == SND_SOC_DAIFMT_I2S)
+		channels = 2;
+
 	madc = DIV_ROUND_UP((32 * adc_resource_class), aosr);
 	max_dosr = (AIC32X4_MAX_DOSR_FREQ / sample_rate / dosr_increment) *
 			dosr_increment;
diff --git a/sound/soc/fsl/fsl_aud2htx.c b/sound/soc/fsl/fsl_aud2htx.c
index 873295f59ad7..1e421d9a03fb 100644
--- a/sound/soc/fsl/fsl_aud2htx.c
+++ b/sound/soc/fsl/fsl_aud2htx.c
@@ -234,18 +234,26 @@ static int fsl_aud2htx_probe(struct platform_device *pdev)
 
 	regcache_cache_only(aud2htx->regmap, true);
 
+	/*
+	 * Register platform component before registering cpu dai for there
+	 * is not defer probe for platform component in snd_soc_add_pcm_runtime().
+	 */
+	ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to pcm register\n");
+		pm_runtime_disable(&pdev->dev);
+		return ret;
+	}
+
 	ret = devm_snd_soc_register_component(&pdev->dev,
 					      &fsl_aud2htx_component,
 					      &fsl_aud2htx_dai, 1);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register ASoC DAI\n");
+		pm_runtime_disable(&pdev->dev);
 		return ret;
 	}
 
-	ret = imx_pcm_dma_init(pdev);
-	if (ret)
-		dev_err(&pdev->dev, "failed to init imx pcm dma: %d\n", ret);
-
 	return ret;
 }
 
diff --git a/sound/soc/fsl/fsl_mqs.c b/sound/soc/fsl/fsl_mqs.c
index c1e2f671191b..4922e6795b73 100644
--- a/sound/soc/fsl/fsl_mqs.c
+++ b/sound/soc/fsl/fsl_mqs.c
@@ -122,7 +122,7 @@ static int fsl_mqs_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	}
 
 	switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
-	case SND_SOC_DAIFMT_BP_FP:
+	case SND_SOC_DAIFMT_CBC_CFC:
 		break;
 	default:
 		return -EINVAL;
diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index 7523bb944b21..d430eece1d6b 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -1306,7 +1306,7 @@ static int fsl_sai_probe(struct platform_device *pdev)
 		sai->mclk_clk[i] = devm_clk_get(dev, tmp);
 		if (IS_ERR(sai->mclk_clk[i])) {
 			dev_err(dev, "failed to get mclk%d clock: %ld\n",
-					i + 1, PTR_ERR(sai->mclk_clk[i]));
+					i, PTR_ERR(sai->mclk_clk[i]));
 			sai->mclk_clk[i] = NULL;
 		}
 	}
diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c
index 14be29530fb5..3f128ced4180 100644
--- a/sound/soc/fsl/imx-card.c
+++ b/sound/soc/fsl/imx-card.c
@@ -698,6 +698,10 @@ static int imx_card_parse_of(struct imx_card_data *data)
 		of_node_put(cpu);
 		of_node_put(codec);
 		of_node_put(platform);
+
+		cpu = NULL;
+		codec = NULL;
+		platform = NULL;
 	}
 
 	return 0;
diff --git a/sound/soc/intel/avs/pcm.c b/sound/soc/intel/avs/pcm.c
index f21b0cdd3206..8fe5917b1e26 100644
--- a/sound/soc/intel/avs/pcm.c
+++ b/sound/soc/intel/avs/pcm.c
@@ -636,8 +636,8 @@ static ssize_t topology_name_read(struct file *file, char __user *user_buf, size
 	char buf[64];
 	size_t len;
 
-	len = snprintf(buf, sizeof(buf), "%s/%s\n", component->driver->topology_name_prefix,
-		       mach->tplg_filename);
+	len = scnprintf(buf, sizeof(buf), "%s/%s\n", component->driver->topology_name_prefix,
+			mach->tplg_filename);
 
 	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
 }
diff --git a/sound/soc/intel/boards/sof_es8336.c b/sound/soc/intel/boards/sof_es8336.c
index c7f33c89588e..606cc3242a60 100644
--- a/sound/soc/intel/boards/sof_es8336.c
+++ b/sound/soc/intel/boards/sof_es8336.c
@@ -760,6 +760,9 @@ static int sof_es8336_remove(struct platform_device *pdev)
 
 static const struct platform_device_id board_ids[] = {
 	{
+		.name = "sof-essx8336", /* default quirk == 0 */
+	},
+	{
 		.name = "adl_es83x6_c1_h02",
 		.driver_data = (kernel_ulong_t)(SOF_ES8336_SSP_CODEC(1) |
 					SOF_NO_OF_HDMI_CAPTURE_SSP(2) |
@@ -786,5 +789,4 @@ module_platform_driver(sof_es8336_driver);
 
 MODULE_DESCRIPTION("ASoC Intel(R) SOF + ES8336 Machine driver");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:sof-essx8336");
 MODULE_IMPORT_NS(SND_SOC_INTEL_HDA_DSP_COMMON);
diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index a49bfaab6b21..2ff30b40a1e4 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -270,6 +270,16 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = {
 		.callback = sof_sdw_quirk_cb,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0AFF")
+		},
+		.driver_data = (void *)(SOF_SDW_TGL_HDMI |
+					RT711_JD2 |
+					SOF_SDW_FOUR_SPK),
+	},
+	{
+		.callback = sof_sdw_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"),
 			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0B00")
 		},
 		.driver_data = (void *)(SOF_SDW_TGL_HDMI |
diff --git a/sound/soc/mediatek/mt8186/mt8186-dai-adda.c b/sound/soc/mediatek/mt8186/mt8186-dai-adda.c
index 266704556f37..094402470dc2 100644
--- a/sound/soc/mediatek/mt8186/mt8186-dai-adda.c
+++ b/sound/soc/mediatek/mt8186/mt8186-dai-adda.c
@@ -271,9 +271,6 @@ static int mtk_adda_ul_event(struct snd_soc_dapm_widget *w,
 		/* should delayed 1/fs(smallest is 8k) = 125us before afe off */
 		usleep_range(125, 135);
 		mt8186_afe_gpio_request(afe->dev, false, MT8186_DAI_ADDA, 1);
-
-		/* reset dmic */
-		afe_priv->mtkaif_dmic = 0;
 		break;
 	default:
 		break;
diff --git a/sound/soc/qcom/sm8250.c b/sound/soc/qcom/sm8250.c
index ce4a5713386a..98a2fde9e004 100644
--- a/sound/soc/qcom/sm8250.c
+++ b/sound/soc/qcom/sm8250.c
@@ -270,6 +270,7 @@ static int sm8250_platform_probe(struct platform_device *pdev)
 	if (!card)
 		return -ENOMEM;
 
+	card->owner = THIS_MODULE;
 	/* Allocate the private data */
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
diff --git a/sound/soc/sh/rz-ssi.c b/sound/soc/sh/rz-ssi.c
index 0d0594a0e4f6..7ace0c0db5b1 100644
--- a/sound/soc/sh/rz-ssi.c
+++ b/sound/soc/sh/rz-ssi.c
@@ -1017,32 +1017,36 @@ static int rz_ssi_probe(struct platform_device *pdev)
 
 	ssi->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL);
 	if (IS_ERR(ssi->rstc)) {
-		rz_ssi_release_dma_channels(ssi);
-		return PTR_ERR(ssi->rstc);
+		ret = PTR_ERR(ssi->rstc);
+		goto err_reset;
 	}
 
 	reset_control_deassert(ssi->rstc);
 	pm_runtime_enable(&pdev->dev);
 	ret = pm_runtime_resume_and_get(&pdev->dev);
 	if (ret < 0) {
-		rz_ssi_release_dma_channels(ssi);
-		pm_runtime_disable(ssi->dev);
-		reset_control_assert(ssi->rstc);
-		return dev_err_probe(ssi->dev, ret, "pm_runtime_resume_and_get failed\n");
+		dev_err(&pdev->dev, "pm_runtime_resume_and_get failed\n");
+		goto err_pm;
 	}
 
 	ret = devm_snd_soc_register_component(&pdev->dev, &rz_ssi_soc_component,
 					      rz_ssi_soc_dai,
 					      ARRAY_SIZE(rz_ssi_soc_dai));
 	if (ret < 0) {
-		rz_ssi_release_dma_channels(ssi);
-
-		pm_runtime_put(ssi->dev);
-		pm_runtime_disable(ssi->dev);
-		reset_control_assert(ssi->rstc);
 		dev_err(&pdev->dev, "failed to register snd component\n");
+		goto err_snd_soc;
 	}
 
+	return 0;
+
+err_snd_soc:
+	pm_runtime_put(ssi->dev);
+err_pm:
+	pm_runtime_disable(ssi->dev);
+	reset_control_assert(ssi->rstc);
+err_reset:
+	rz_ssi_release_dma_channels(ssi);
+
 	return ret;
 }
 
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 5b99bf2dbd08..4f60c0a83311 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1317,6 +1317,9 @@ static struct snd_soc_pcm_runtime *dpcm_get_be(struct snd_soc_card *card,
 		if (!be->dai_link->no_pcm)
 			continue;
 
+		if (!snd_soc_dpcm_get_substream(be, stream))
+			continue;
+
 		for_each_rtd_dais(be, i, dai) {
 			w = snd_soc_dai_get_widget(dai, stream);
 
diff --git a/sound/soc/sof/Kconfig b/sound/soc/sof/Kconfig
index e90f173d067c..37f7df5fde17 100644
--- a/sound/soc/sof/Kconfig
+++ b/sound/soc/sof/Kconfig
@@ -196,6 +196,7 @@ config SND_SOC_SOF_DEBUG_ENABLE_FIRMWARE_TRACE
 
 config SND_SOC_SOF_DEBUG_IPC_FLOOD_TEST
 	tristate "SOF enable IPC flood test"
+	depends on SND_SOC_SOF
 	select SND_SOC_SOF_CLIENT
 	help
 	  This option enables a separate client device for IPC flood test
@@ -214,6 +215,7 @@ config SND_SOC_SOF_DEBUG_IPC_FLOOD_TEST_NUM
 
 config SND_SOC_SOF_DEBUG_IPC_MSG_INJECTOR
 	tristate "SOF enable IPC message injector"
+	depends on SND_SOC_SOF
 	select SND_SOC_SOF_CLIENT
 	help
 	  This option enables the IPC message injector which can be used to send
diff --git a/sound/soc/sof/debug.c b/sound/soc/sof/debug.c
index c5d797e97c02..d9a3ce7b69e1 100644
--- a/sound/soc/sof/debug.c
+++ b/sound/soc/sof/debug.c
@@ -252,9 +252,9 @@ static int memory_info_update(struct snd_sof_dev *sdev, char *buf, size_t buff_s
 	}
 
 	for (i = 0, len = 0; i < reply->num_elems; i++) {
-		ret = snprintf(buf + len, buff_size - len, "zone %d.%d used %#8x free %#8x\n",
-			       reply->elems[i].zone, reply->elems[i].id,
-			       reply->elems[i].used, reply->elems[i].free);
+		ret = scnprintf(buf + len, buff_size - len, "zone %d.%d used %#8x free %#8x\n",
+				reply->elems[i].zone, reply->elems[i].id,
+				reply->elems[i].used, reply->elems[i].free);
 		if (ret < 0)
 			goto error;
 		len += ret;
diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index 8639ea63a10d..6d4ecbe14adf 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -574,7 +574,7 @@ static void hda_dsp_dump_ext_rom_status(struct snd_sof_dev *sdev, const char *le
 	chip = get_chip_info(sdev->pdata);
 	for (i = 0; i < HDA_EXT_ROM_STATUS_SIZE; i++) {
 		value = snd_sof_dsp_read(sdev, HDA_DSP_BAR, chip->rom_status_reg + i * 0x4);
-		len += snprintf(msg + len, sizeof(msg) - len, " 0x%x", value);
+		len += scnprintf(msg + len, sizeof(msg) - len, " 0x%x", value);
 	}
 
 	dev_printk(level, sdev->dev, "extended rom status: %s", msg);
diff --git a/sound/soc/sof/ipc3-topology.c b/sound/soc/sof/ipc3-topology.c
index b2cc046b9f60..65923e7a5976 100644
--- a/sound/soc/sof/ipc3-topology.c
+++ b/sound/soc/sof/ipc3-topology.c
@@ -2338,7 +2338,7 @@ static int sof_ipc3_parse_manifest(struct snd_soc_component *scomp, int index,
 	}
 
 	dev_info(scomp->dev,
-		 "Topology: ABI %d:%d:%d Kernel ABI %hhu:%hhu:%hhu\n",
+		 "Topology: ABI %d:%d:%d Kernel ABI %d:%d:%d\n",
 		 man->priv.data[0], man->priv.data[1], man->priv.data[2],
 		 SOF_ABI_MAJOR, SOF_ABI_MINOR, SOF_ABI_PATCH);
 
diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
index af072b484a60..64929dc9af39 100644
--- a/sound/soc/sof/ipc4-topology.c
+++ b/sound/soc/sof/ipc4-topology.c
@@ -771,7 +771,7 @@ static int sof_ipc4_widget_setup_comp_src(struct snd_sof_widget *swidget)
 		goto err;
 
 	ret = sof_update_ipc_object(scomp, src, SOF_SRC_TOKENS, swidget->tuples,
-				    swidget->num_tuples, sizeof(src), 1);
+				    swidget->num_tuples, sizeof(*src), 1);
 	if (ret) {
 		dev_err(scomp->dev, "Parsing SRC tokens failed\n");
 		goto err;
@@ -1251,7 +1251,7 @@ sof_ipc4_prepare_copier_module(struct snd_sof_widget *swidget,
 			if (blob->alh_cfg.count > 1) {
 				int group_id;
 
-				group_id = ida_alloc_max(&alh_group_ida, ALH_MULTI_GTW_COUNT,
+				group_id = ida_alloc_max(&alh_group_ida, ALH_MULTI_GTW_COUNT - 1,
 							 GFP_KERNEL);
 
 				if (group_id < 0)
diff --git a/sound/usb/card.c b/sound/usb/card.c
index d356743de2ff..706d249a9ad6 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -699,7 +699,7 @@ static bool check_delayed_register_option(struct snd_usb_audio *chip, int iface)
 		if (delayed_register[i] &&
 		    sscanf(delayed_register[i], "%x:%x", &id, &inum) == 2 &&
 		    id == chip->usb_id)
-			return inum != iface;
+			return iface < inum;
 	}
 
 	return false;
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index 0d7b73bf7945..eb71df9da831 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -924,6 +924,8 @@ void snd_usb_endpoint_close(struct snd_usb_audio *chip,
 		endpoint_set_interface(chip, ep, false);
 
 	if (!--ep->opened) {
+		if (ep->clock_ref && !atomic_read(&ep->clock_ref->locked))
+			ep->clock_ref->rate = 0;
 		ep->iface = 0;
 		ep->altsetting = 0;
 		ep->cur_audiofmt = NULL;
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 168fd802d70b..5b4d8f5eade2 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1764,7 +1764,7 @@ bool snd_usb_registration_quirk(struct snd_usb_audio *chip, int iface)
 
 	for (q = registration_quirks; q->usb_id; q++)
 		if (chip->usb_id == q->usb_id)
-			return iface != q->interface;
+			return iface < q->interface;
 
 	/* Register as normal */
 	return false;
@@ -1903,6 +1903,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x21b4, 0x0081, /* AudioQuest DragonFly */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x2522, 0x0007, /* LH Labs Geek Out HD Audio 1V5 */
+		   QUIRK_FLAG_SET_IFACE_FIRST),
 	DEVICE_FLG(0x2708, 0x0002, /* Audient iD14 */
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x2912, 0x30c8, /* Audioengine D1 */
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index ceb93d798182..f10f4e6d3fb8 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -495,6 +495,10 @@ static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip,
 			return 0;
 		}
 	}
+
+	if (chip->card->registered)
+		chip->need_delayed_register = true;
+
 	/* look for an empty stream */
 	list_for_each_entry(as, &chip->pcm_list, list) {
 		if (as->fmt_type != fp->fmt_type)
@@ -502,9 +506,6 @@ static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip,
 		subs = &as->substream[stream];
 		if (subs->ep_num)
 			continue;
-		if (snd_device_get_state(chip->card, as->pcm) !=
-		    SNDRV_DEV_BUILD)
-			chip->need_delayed_register = true;
 		err = snd_pcm_new_stream(as->pcm, stream, 1);
 		if (err < 0)
 			return err;
@@ -1105,7 +1106,7 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip,
 	 * Dallas DS4201 workaround: It presents 5 altsettings, but the last
 	 * one misses syncpipe, and does not produce any sound.
 	 */
-	if (chip->usb_id == USB_ID(0x04fa, 0x4201))
+	if (chip->usb_id == USB_ID(0x04fa, 0x4201) && num >= 4)
 		num = 4;
 
 	for (i = 0; i < num; i++) {
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 3bb134355874..316917b98707 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -75,9 +75,11 @@ struct kvm_regs {
 
 /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
 #define KVM_ARM_DEVICE_TYPE_SHIFT	0
-#define KVM_ARM_DEVICE_TYPE_MASK	(0xffff << KVM_ARM_DEVICE_TYPE_SHIFT)
+#define KVM_ARM_DEVICE_TYPE_MASK	GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \
+						KVM_ARM_DEVICE_TYPE_SHIFT)
 #define KVM_ARM_DEVICE_ID_SHIFT		16
-#define KVM_ARM_DEVICE_ID_MASK		(0xffff << KVM_ARM_DEVICE_ID_SHIFT)
+#define KVM_ARM_DEVICE_ID_MASK		GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \
+						KVM_ARM_DEVICE_ID_SHIFT)
 
 /* Supported device IDs */
 #define KVM_ARM_DEVICE_VGIC_V2		0
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 7a6b14874d65..a73cf01a1606 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -74,6 +74,7 @@ struct kvm_s390_io_adapter_req {
 #define KVM_S390_VM_CRYPTO		2
 #define KVM_S390_VM_CPU_MODEL		3
 #define KVM_S390_VM_MIGRATION		4
+#define KVM_S390_VM_CPU_TOPOLOGY	5
 
 /* kvm attributes for mem_ctrl */
 #define KVM_S390_VM_MEM_ENABLE_CMMA	0
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 8323ac5b7eee..ef4775c6db01 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -219,7 +219,7 @@
 #define X86_FEATURE_IBRS		( 7*32+25) /* Indirect Branch Restricted Speculation */
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 or above (Zen) */
+#define X86_FEATURE_ZEN			(7*32+28) /* "" CPU based on Zen microarchitecture */
 #define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 #define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
 #define X86_FEATURE_MSR_IA32_FEAT_CTL	( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
@@ -303,7 +303,7 @@
 #define X86_FEATURE_RETHUNK		(11*32+14) /* "" Use REturn THUNK */
 #define X86_FEATURE_UNRET		(11*32+15) /* "" AMD BTB untrain return */
 #define X86_FEATURE_USE_IBPB_FW		(11*32+16) /* "" Use IBPB during runtime firmware calls */
-#define X86_FEATURE_RSB_VMEXIT_LITE	(11*32+17) /* "" Fill RSB on VM-Exit when EIBRS is enabled */
+#define X86_FEATURE_RSB_VMEXIT_LITE	(11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
@@ -354,6 +354,7 @@
 #define X86_FEATURE_AVIC		(15*32+13) /* Virtual Interrupt Controller */
 #define X86_FEATURE_V_VMSAVE_VMLOAD	(15*32+15) /* Virtual VMSAVE VMLOAD */
 #define X86_FEATURE_VGIF		(15*32+16) /* Virtual GIF */
+#define X86_FEATURE_X2AVIC		(15*32+18) /* Virtual x2apic */
 #define X86_FEATURE_V_SPEC_CTRL		(15*32+20) /* Virtual SPEC_CTRL */
 #define X86_FEATURE_SVME_ADDR_CHK	(15*32+28) /* "" SVME addr check */
 
@@ -456,6 +457,8 @@
 #define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
 #define X86_BUG_SRBDS			X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
 #define X86_BUG_MMIO_STALE_DATA		X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */
-#define X86_BUG_RETBLEED		X86_BUG(26) /* CPU is affected by RETBleed */
+#define X86_BUG_MMIO_UNKNOWN		X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */
+#define X86_BUG_RETBLEED		X86_BUG(27) /* CPU is affected by RETBleed */
+#define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index e057e039173c..6674bdb096f3 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -235,6 +235,12 @@
 #define PERF_CAP_PT_IDX			16
 
 #define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
+#define PERF_CAP_PEBS_TRAP             BIT_ULL(6)
+#define PERF_CAP_ARCH_REG              BIT_ULL(7)
+#define PERF_CAP_PEBS_FORMAT           0xf00
+#define PERF_CAP_PEBS_BASELINE         BIT_ULL(14)
+#define PERF_CAP_PEBS_MASK	(PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \
+				 PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE)
 
 #define MSR_IA32_RTIT_CTL		0x00000570
 #define RTIT_CTL_TRACEEN		BIT(0)
@@ -392,6 +398,7 @@
 #define MSR_TURBO_ACTIVATION_RATIO	0x0000064C
 
 #define MSR_PLATFORM_ENERGY_STATUS	0x0000064D
+#define MSR_SECONDARY_TURBO_RATIO_LIMIT	0x00000650
 
 #define MSR_PKG_WEIGHTED_CORE_C0_RES	0x00000658
 #define MSR_PKG_ANY_CORE_C0_RES		0x00000659
@@ -1022,6 +1029,7 @@
 #define MSR_IA32_VMX_TRUE_EXIT_CTLS      0x0000048f
 #define MSR_IA32_VMX_TRUE_ENTRY_CTLS     0x00000490
 #define MSR_IA32_VMX_VMFUNC             0x00000491
+#define MSR_IA32_VMX_PROCBASED_CTLS3	0x00000492
 
 /* VMX_BASIC bits and bitmasks */
 #define VMX_BASIC_VMCS_SIZE_SHIFT	32
diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h
index fee7983a90b4..11ff975242ca 100644
--- a/tools/arch/x86/include/asm/rmwcc.h
+++ b/tools/arch/x86/include/asm/rmwcc.h
@@ -2,8 +2,6 @@
 #ifndef _TOOLS_LINUX_ASM_X86_RMWcc
 #define _TOOLS_LINUX_ASM_X86_RMWcc
 
-#ifdef CONFIG_CC_HAS_ASM_GOTO
-
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
 	asm_volatile_goto (fullop "; j" cc " %l[cc_label]"		\
@@ -20,23 +18,4 @@ cc_label:								\
 #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
 	__GEN_RMWcc(op " %1, " arg0, var, cc, vcon (val))
 
-#else /* !CONFIG_CC_HAS_ASM_GOTO */
-
-#define __GEN_RMWcc(fullop, var, cc, ...)				\
-do {									\
-	char c;								\
-	asm volatile (fullop "; set" cc " %1"				\
-			: "+m" (var), "=qm" (c)				\
-			: __VA_ARGS__ : "memory");			\
-	return c != 0;							\
-} while (0)
-
-#define GEN_UNARY_RMWcc(op, var, arg0, cc)				\
-	__GEN_RMWcc(op " " arg0, var, cc)
-
-#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
-	__GEN_RMWcc(op " %2, " arg0, var, cc, vcon (val))
-
-#endif /* CONFIG_CC_HAS_ASM_GOTO */
-
 #endif /* _TOOLS_LINUX_ASM_X86_RMWcc */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index ec53c9fa1da9..46de10a809ec 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -306,7 +306,8 @@ struct kvm_pit_state {
 	struct kvm_pit_channel_state channels[3];
 };
 
-#define KVM_PIT_FLAGS_HPET_LEGACY  0x00000001
+#define KVM_PIT_FLAGS_HPET_LEGACY     0x00000001
+#define KVM_PIT_FLAGS_SPEAKER_DATA_ON 0x00000002
 
 struct kvm_pit_state2 {
 	struct kvm_pit_channel_state channels[3];
@@ -325,6 +326,7 @@ struct kvm_reinject_control {
 #define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
 #define KVM_VCPUEVENT_VALID_SMM		0x00000008
 #define KVM_VCPUEVENT_VALID_PAYLOAD	0x00000010
+#define KVM_VCPUEVENT_VALID_TRIPLE_FAULT	0x00000020
 
 /* Interrupt shadow states */
 #define KVM_X86_SHADOW_INT_MOV_SS	0x01
@@ -359,7 +361,10 @@ struct kvm_vcpu_events {
 		__u8 smm_inside_nmi;
 		__u8 latched_init;
 	} smi;
-	__u8 reserved[27];
+	struct {
+		__u8 pending;
+	} triple_fault;
+	__u8 reserved[26];
 	__u8 exception_has_payload;
 	__u64 exception_payload;
 };
@@ -434,6 +439,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_OUT_7E_INC_RIP		(1 << 3)
 #define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT	(1 << 4)
 #define KVM_X86_QUIRK_FIX_HYPERCALL_INSN	(1 << 5)
+#define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS	(1 << 6)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index 946d761adbd3..a5faf6d88f1b 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -91,6 +91,7 @@
 #define EXIT_REASON_UMWAIT              67
 #define EXIT_REASON_TPAUSE              68
 #define EXIT_REASON_BUS_LOCK            74
+#define EXIT_REASON_NOTIFY              75
 
 #define VMX_EXIT_REASONS \
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -153,7 +154,8 @@
 	{ EXIT_REASON_XRSTORS,               "XRSTORS" }, \
 	{ EXIT_REASON_UMWAIT,                "UMWAIT" }, \
 	{ EXIT_REASON_TPAUSE,                "TPAUSE" }, \
-	{ EXIT_REASON_BUS_LOCK,              "BUS_LOCK" }
+	{ EXIT_REASON_BUS_LOCK,              "BUS_LOCK" }, \
+	{ EXIT_REASON_NOTIFY,                "NOTIFY" }
 
 #define VMX_EXIT_REASON_FLAGS \
 	{ VMX_EXIT_REASONS_FAILED_VMENTRY,	"FAILED_VMENTRY" }
diff --git a/tools/debugging/kernel-chktaint b/tools/debugging/kernel-chktaint
index f1af27ce9f20..279be06332be 100755
--- a/tools/debugging/kernel-chktaint
+++ b/tools/debugging/kernel-chktaint
@@ -187,6 +187,7 @@ else
 	echo " * auxiliary taint, defined for and used by distros (#16)"
 
 fi
+
 T=`expr $T / 2`
 if [ `expr $T % 2` -eq 0 ]; then
 	addout " "
@@ -195,6 +196,14 @@ else
 	echo " * kernel was built with the struct randomization plugin (#17)"
 fi
 
+T=`expr $T / 2`
+if [ `expr $T % 2` -eq 0 ]; then
+	addout " "
+else
+	addout "N"
+	echo " * an in-kernel test (such as a KUnit test) has been run (#18)"
+fi
+
 echo "For a more detailed explanation of the various taint flags see"
 echo " Documentation/admin-guide/tainted-kernels.rst in the Linux kernel sources"
 echo " or https://kernel.org/doc/html/latest/admin-guide/tainted-kernels.html"
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 1e6fd6ca513b..27f5e7dfc2f7 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -44,7 +44,7 @@
 
 /*
  * KVP protocol: The user mode component first registers with the
- * the kernel component. Subsequently, the kernel component requests, data
+ * kernel component. Subsequently, the kernel component requests, data
  * for the specified keys. In response to this message the user mode component
  * fills in the value corresponding to the specified key. We overload the
  * sequence field in the cn_msg header to define our KVP message types.
@@ -772,11 +772,11 @@ static int kvp_process_ip_address(void *addrp,
 	const char *str;
 
 	if (family == AF_INET) {
-		addr = (struct sockaddr_in *)addrp;
+		addr = addrp;
 		str = inet_ntop(family, &addr->sin_addr, tmp, 50);
 		addr_length = INET_ADDRSTRLEN;
 	} else {
-		addr6 = (struct sockaddr_in6 *)addrp;
+		addr6 = addrp;
 		str = inet_ntop(family, &addr6->sin6_addr.s6_addr, tmp, 50);
 		addr_length = INET6_ADDRSTRLEN;
 	}
diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h
index 24ae3054f304..1bdd834bdd57 100644
--- a/tools/include/linux/compiler_types.h
+++ b/tools/include/linux/compiler_types.h
@@ -36,4 +36,8 @@
 #include <linux/compiler-gcc.h>
 #endif
 
+#ifndef asm_volatile_goto
+#define asm_volatile_goto(x...) asm goto(x)
+#endif
+
 #endif /* __LINUX_COMPILER_TYPES_H */
diff --git a/tools/include/linux/gfp.h b/tools/include/linux/gfp.h
index b238dbc9eb85..6a10ff5f5be9 100644
--- a/tools/include/linux/gfp.h
+++ b/tools/include/linux/gfp.h
@@ -3,26 +3,7 @@
 #define _TOOLS_INCLUDE_LINUX_GFP_H
 
 #include <linux/types.h>
-
-#define __GFP_BITS_SHIFT 26
-#define __GFP_BITS_MASK ((gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
-
-#define __GFP_HIGH		0x20u
-#define __GFP_IO		0x40u
-#define __GFP_FS		0x80u
-#define __GFP_NOWARN		0x200u
-#define __GFP_ZERO		0x8000u
-#define __GFP_ATOMIC		0x80000u
-#define __GFP_ACCOUNT		0x100000u
-#define __GFP_DIRECT_RECLAIM	0x400000u
-#define __GFP_KSWAPD_RECLAIM	0x2000000u
-
-#define __GFP_RECLAIM	(__GFP_DIRECT_RECLAIM | __GFP_KSWAPD_RECLAIM)
-
-#define GFP_ZONEMASK	0x0fu
-#define GFP_ATOMIC	(__GFP_HIGH | __GFP_ATOMIC | __GFP_KSWAPD_RECLAIM)
-#define GFP_KERNEL	(__GFP_RECLAIM | __GFP_IO | __GFP_FS)
-#define GFP_NOWAIT	(__GFP_KSWAPD_RECLAIM)
+#include <linux/gfp_types.h>
 
 static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
 {
diff --git a/tools/include/linux/gfp_types.h b/tools/include/linux/gfp_types.h
new file mode 100644
index 000000000000..5f9f1ed190a0
--- /dev/null
+++ b/tools/include/linux/gfp_types.h
@@ -0,0 +1 @@
+#include "../../../include/linux/gfp_types.h"
diff --git a/tools/include/linux/kallsyms.h b/tools/include/linux/kallsyms.h
index efb6c3f5f2a9..5a37ccbec54f 100644
--- a/tools/include/linux/kallsyms.h
+++ b/tools/include/linux/kallsyms.h
@@ -6,7 +6,7 @@
 #include <stdio.h>
 #include <unistd.h>
 
-#define KSYM_NAME_LEN 128
+#define KSYM_NAME_LEN 512
 
 struct module;
 
diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h
index 95e2b7924925..ba04771cb3a3 100644
--- a/tools/include/nolibc/arch-riscv.h
+++ b/tools/include/nolibc/arch-riscv.h
@@ -190,7 +190,7 @@ __asm__ (".section .text\n"
     ".option norelax\n"
     "lla   gp, __global_pointer$\n"
     ".option pop\n"
-    "ld    a0, 0(sp)\n"          // argc (a0) was in the stack
+    "lw    a0, 0(sp)\n"          // argc (a0) was in the stack
     "add   a1, sp, "SZREG"\n"    // argv (a1) = sp
     "slli  a2, a0, "PTRLOG"\n"   // envp (a2) = SZREG*argc ...
     "add   a2, a2, "SZREG"\n"    //             + SZREG (skip null)
diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h
index 08491070387b..ce3ee03aa679 100644
--- a/tools/include/nolibc/sys.h
+++ b/tools/include/nolibc/sys.h
@@ -692,12 +692,12 @@ void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd,
 {
 #ifndef my_syscall6
 	/* Function not implemented. */
-	return -ENOSYS;
+	return (void *)-ENOSYS;
 #else
 
 	int n;
 
-#if defined(__i386__)
+#if defined(__NR_mmap2)
 	n = __NR_mmap2;
 	offset >>= 12;
 #else
diff --git a/tools/include/uapi/asm/errno.h b/tools/include/uapi/asm/errno.h
index d30439b4b8ab..869379f91fe4 100644
--- a/tools/include/uapi/asm/errno.h
+++ b/tools/include/uapi/asm/errno.h
@@ -9,8 +9,8 @@
 #include "../../../arch/alpha/include/uapi/asm/errno.h"
 #elif defined(__mips__)
 #include "../../../arch/mips/include/uapi/asm/errno.h"
-#elif defined(__xtensa__)
-#include "../../../arch/xtensa/include/uapi/asm/errno.h"
+#elif defined(__hppa__)
+#include "../../../arch/parisc/include/uapi/asm/errno.h"
 #else
 #include <asm-generic/errno.h>
 #endif
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index b28ff5d88145..520ad2691a99 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -751,14 +751,27 @@ typedef struct drm_i915_irq_wait {
 
 /* Must be kept compact -- no holes and well documented */
 
-typedef struct drm_i915_getparam {
+/**
+ * struct drm_i915_getparam - Driver parameter query structure.
+ */
+struct drm_i915_getparam {
+	/** @param: Driver parameter to query. */
 	__s32 param;
-	/*
+
+	/**
+	 * @value: Address of memory where queried value should be put.
+	 *
 	 * WARNING: Using pointers instead of fixed-size u64 means we need to write
 	 * compat32 code. Don't repeat this mistake.
 	 */
 	int __user *value;
-} drm_i915_getparam_t;
+};
+
+/**
+ * typedef drm_i915_getparam_t - Driver parameter query structure.
+ * See struct drm_i915_getparam.
+ */
+typedef struct drm_i915_getparam drm_i915_getparam_t;
 
 /* Ioctl to set kernel params:
  */
@@ -1239,76 +1252,119 @@ struct drm_i915_gem_exec_object2 {
 	__u64 rsvd2;
 };
 
+/**
+ * struct drm_i915_gem_exec_fence - An input or output fence for the execbuf
+ * ioctl.
+ *
+ * The request will wait for input fence to signal before submission.
+ *
+ * The returned output fence will be signaled after the completion of the
+ * request.
+ */
 struct drm_i915_gem_exec_fence {
-	/**
-	 * User's handle for a drm_syncobj to wait on or signal.
-	 */
+	/** @handle: User's handle for a drm_syncobj to wait on or signal. */
 	__u32 handle;
 
+	/**
+	 * @flags: Supported flags are:
+	 *
+	 * I915_EXEC_FENCE_WAIT:
+	 * Wait for the input fence before request submission.
+	 *
+	 * I915_EXEC_FENCE_SIGNAL:
+	 * Return request completion fence as output
+	 */
+	__u32 flags;
 #define I915_EXEC_FENCE_WAIT            (1<<0)
 #define I915_EXEC_FENCE_SIGNAL          (1<<1)
 #define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SIGNAL << 1))
-	__u32 flags;
 };
 
-/*
- * See drm_i915_gem_execbuffer_ext_timeline_fences.
- */
-#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
-
-/*
+/**
+ * struct drm_i915_gem_execbuffer_ext_timeline_fences - Timeline fences
+ * for execbuf ioctl.
+ *
  * This structure describes an array of drm_syncobj and associated points for
  * timeline variants of drm_syncobj. It is invalid to append this structure to
  * the execbuf if I915_EXEC_FENCE_ARRAY is set.
  */
 struct drm_i915_gem_execbuffer_ext_timeline_fences {
+#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
+	/** @base: Extension link. See struct i915_user_extension. */
 	struct i915_user_extension base;
 
 	/**
-	 * Number of element in the handles_ptr & value_ptr arrays.
+	 * @fence_count: Number of elements in the @handles_ptr & @value_ptr
+	 * arrays.
 	 */
 	__u64 fence_count;
 
 	/**
-	 * Pointer to an array of struct drm_i915_gem_exec_fence of length
-	 * fence_count.
+	 * @handles_ptr: Pointer to an array of struct drm_i915_gem_exec_fence
+	 * of length @fence_count.
 	 */
 	__u64 handles_ptr;
 
 	/**
-	 * Pointer to an array of u64 values of length fence_count. Values
-	 * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline
-	 * drm_syncobj is invalid as it turns a drm_syncobj into a binary one.
+	 * @values_ptr: Pointer to an array of u64 values of length
+	 * @fence_count.
+	 * Values must be 0 for a binary drm_syncobj. A Value of 0 for a
+	 * timeline drm_syncobj is invalid as it turns a drm_syncobj into a
+	 * binary one.
 	 */
 	__u64 values_ptr;
 };
 
+/**
+ * struct drm_i915_gem_execbuffer2 - Structure for DRM_I915_GEM_EXECBUFFER2
+ * ioctl.
+ */
 struct drm_i915_gem_execbuffer2 {
-	/**
-	 * List of gem_exec_object2 structs
-	 */
+	/** @buffers_ptr: Pointer to a list of gem_exec_object2 structs */
 	__u64 buffers_ptr;
+
+	/** @buffer_count: Number of elements in @buffers_ptr array */
 	__u32 buffer_count;
 
-	/** Offset in the batchbuffer to start execution from. */
+	/**
+	 * @batch_start_offset: Offset in the batchbuffer to start execution
+	 * from.
+	 */
 	__u32 batch_start_offset;
-	/** Bytes used in batchbuffer from batch_start_offset */
+
+	/**
+	 * @batch_len: Length in bytes of the batch buffer, starting from the
+	 * @batch_start_offset. If 0, length is assumed to be the batch buffer
+	 * object size.
+	 */
 	__u32 batch_len;
+
+	/** @DR1: deprecated */
 	__u32 DR1;
+
+	/** @DR4: deprecated */
 	__u32 DR4;
+
+	/** @num_cliprects: See @cliprects_ptr */
 	__u32 num_cliprects;
+
 	/**
-	 * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
-	 * & I915_EXEC_USE_EXTENSIONS are not set.
+	 * @cliprects_ptr: Kernel clipping was a DRI1 misfeature.
+	 *
+	 * It is invalid to use this field if I915_EXEC_FENCE_ARRAY or
+	 * I915_EXEC_USE_EXTENSIONS flags are not set.
 	 *
 	 * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array
-	 * of struct drm_i915_gem_exec_fence and num_cliprects is the length
-	 * of the array.
+	 * of &drm_i915_gem_exec_fence and @num_cliprects is the length of the
+	 * array.
 	 *
 	 * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a
-	 * single struct i915_user_extension and num_cliprects is 0.
+	 * single &i915_user_extension and num_cliprects is 0.
 	 */
 	__u64 cliprects_ptr;
+
+	/** @flags: Execbuf flags */
+	__u64 flags;
 #define I915_EXEC_RING_MASK              (0x3f)
 #define I915_EXEC_DEFAULT                (0<<0)
 #define I915_EXEC_RENDER                 (1<<0)
@@ -1326,10 +1382,6 @@ struct drm_i915_gem_execbuffer2 {
 #define I915_EXEC_CONSTANTS_REL_GENERAL (0<<6) /* default */
 #define I915_EXEC_CONSTANTS_ABSOLUTE 	(1<<6)
 #define I915_EXEC_CONSTANTS_REL_SURFACE (2<<6) /* gen4/5 only */
-	__u64 flags;
-	__u64 rsvd1; /* now used for context info */
-	__u64 rsvd2;
-};
 
 /** Resets the SO write offset registers for transform feedback on gen7. */
 #define I915_EXEC_GEN7_SOL_RESET	(1<<8)
@@ -1432,9 +1484,23 @@ struct drm_i915_gem_execbuffer2 {
  * drm_i915_gem_execbuffer_ext enum.
  */
 #define I915_EXEC_USE_EXTENSIONS	(1 << 21)
-
 #define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1))
 
+	/** @rsvd1: Context id */
+	__u64 rsvd1;
+
+	/**
+	 * @rsvd2: in and out sync_file file descriptors.
+	 *
+	 * When I915_EXEC_FENCE_IN or I915_EXEC_FENCE_SUBMIT flag is set, the
+	 * lower 32 bits of this field will have the in sync_file fd (input).
+	 *
+	 * When I915_EXEC_FENCE_OUT flag is set, the upper 32 bits of this
+	 * field will have the out sync_file fd (output).
+	 */
+	__u64 rsvd2;
+};
+
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
 	(eb2).rsvd1 = context & I915_EXEC_CONTEXT_ID_MASK
@@ -1814,19 +1880,58 @@ struct drm_i915_gem_context_create {
 	__u32 pad;
 };
 
+/**
+ * struct drm_i915_gem_context_create_ext - Structure for creating contexts.
+ */
 struct drm_i915_gem_context_create_ext {
-	__u32 ctx_id; /* output: id of new context*/
+	/** @ctx_id: Id of the created context (output) */
+	__u32 ctx_id;
+
+	/**
+	 * @flags: Supported flags are:
+	 *
+	 * I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS:
+	 *
+	 * Extensions may be appended to this structure and driver must check
+	 * for those. See @extensions.
+	 *
+	 * I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE
+	 *
+	 * Created context will have single timeline.
+	 */
 	__u32 flags;
 #define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS	(1u << 0)
 #define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE	(1u << 1)
 #define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \
 	(-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1))
+
+	/**
+	 * @extensions: Zero-terminated chain of extensions.
+	 *
+	 * I915_CONTEXT_CREATE_EXT_SETPARAM:
+	 * Context parameter to set or query during context creation.
+	 * See struct drm_i915_gem_context_create_ext_setparam.
+	 *
+	 * I915_CONTEXT_CREATE_EXT_CLONE:
+	 * This extension has been removed. On the off chance someone somewhere
+	 * has attempted to use it, never re-use this extension number.
+	 */
 	__u64 extensions;
+#define I915_CONTEXT_CREATE_EXT_SETPARAM 0
+#define I915_CONTEXT_CREATE_EXT_CLONE 1
 };
 
+/**
+ * struct drm_i915_gem_context_param - Context parameter to set or query.
+ */
 struct drm_i915_gem_context_param {
+	/** @ctx_id: Context id */
 	__u32 ctx_id;
+
+	/** @size: Size of the parameter @value */
 	__u32 size;
+
+	/** @param: Parameter to set or query */
 	__u64 param;
 #define I915_CONTEXT_PARAM_BAN_PERIOD	0x1
 /* I915_CONTEXT_PARAM_NO_ZEROMAP has been removed.  On the off chance
@@ -1973,6 +2078,7 @@ struct drm_i915_gem_context_param {
 #define I915_CONTEXT_PARAM_PROTECTED_CONTENT    0xd
 /* Must be kept compact -- no holes and well documented */
 
+	/** @value: Context parameter value to be set or queried */
 	__u64 value;
 };
 
@@ -2371,23 +2477,29 @@ struct i915_context_param_engines {
 	struct i915_engine_class_instance engines[N__]; \
 } __attribute__((packed)) name__
 
+/**
+ * struct drm_i915_gem_context_create_ext_setparam - Context parameter
+ * to set or query during context creation.
+ */
 struct drm_i915_gem_context_create_ext_setparam {
-#define I915_CONTEXT_CREATE_EXT_SETPARAM 0
+	/** @base: Extension link. See struct i915_user_extension. */
 	struct i915_user_extension base;
+
+	/**
+	 * @param: Context parameter to set or query.
+	 * See struct drm_i915_gem_context_param.
+	 */
 	struct drm_i915_gem_context_param param;
 };
 
-/* This API has been removed.  On the off chance someone somewhere has
- * attempted to use it, never re-use this extension number.
- */
-#define I915_CONTEXT_CREATE_EXT_CLONE 1
-
 struct drm_i915_gem_context_destroy {
 	__u32 ctx_id;
 	__u32 pad;
 };
 
-/*
+/**
+ * struct drm_i915_gem_vm_control - Structure to create or destroy VM.
+ *
  * DRM_I915_GEM_VM_CREATE -
  *
  * Create a new virtual memory address space (ppGTT) for use within a context
@@ -2397,20 +2509,23 @@ struct drm_i915_gem_context_destroy {
  * The id of new VM (bound to the fd) for use with I915_CONTEXT_PARAM_VM is
  * returned in the outparam @id.
  *
- * No flags are defined, with all bits reserved and must be zero.
- *
  * An extension chain maybe provided, starting with @extensions, and terminated
  * by the @next_extension being 0. Currently, no extensions are defined.
  *
  * DRM_I915_GEM_VM_DESTROY -
  *
- * Destroys a previously created VM id, specified in @id.
+ * Destroys a previously created VM id, specified in @vm_id.
  *
  * No extensions or flags are allowed currently, and so must be zero.
  */
 struct drm_i915_gem_vm_control {
+	/** @extensions: Zero-terminated chain of extensions. */
 	__u64 extensions;
+
+	/** @flags: reserved for future usage, currently MBZ */
 	__u32 flags;
+
+	/** @vm_id: Id of the VM created or to be destroyed */
 	__u32 vm_id;
 };
 
@@ -3207,36 +3322,6 @@ struct drm_i915_gem_memory_class_instance {
  * struct drm_i915_memory_region_info - Describes one region as known to the
  * driver.
  *
- * Note that we reserve some stuff here for potential future work. As an example
- * we might want expose the capabilities for a given region, which could include
- * things like if the region is CPU mappable/accessible, what are the supported
- * mapping types etc.
- *
- * Note that to extend struct drm_i915_memory_region_info and struct
- * drm_i915_query_memory_regions in the future the plan is to do the following:
- *
- * .. code-block:: C
- *
- *	struct drm_i915_memory_region_info {
- *		struct drm_i915_gem_memory_class_instance region;
- *		union {
- *			__u32 rsvd0;
- *			__u32 new_thing1;
- *		};
- *		...
- *		union {
- *			__u64 rsvd1[8];
- *			struct {
- *				__u64 new_thing2;
- *				__u64 new_thing3;
- *				...
- *			};
- *		};
- *	};
- *
- * With this things should remain source compatible between versions for
- * userspace, even as we add new fields.
- *
  * Note this is using both struct drm_i915_query_item and struct drm_i915_query.
  * For this new query we are adding the new query id DRM_I915_QUERY_MEMORY_REGIONS
  * at &drm_i915_query_item.query_id.
@@ -3248,14 +3333,81 @@ struct drm_i915_memory_region_info {
 	/** @rsvd0: MBZ */
 	__u32 rsvd0;
 
-	/** @probed_size: Memory probed by the driver (-1 = unknown) */
+	/**
+	 * @probed_size: Memory probed by the driver
+	 *
+	 * Note that it should not be possible to ever encounter a zero value
+	 * here, also note that no current region type will ever return -1 here.
+	 * Although for future region types, this might be a possibility. The
+	 * same applies to the other size fields.
+	 */
 	__u64 probed_size;
 
-	/** @unallocated_size: Estimate of memory remaining (-1 = unknown) */
+	/**
+	 * @unallocated_size: Estimate of memory remaining
+	 *
+	 * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable accounting.
+	 * Without this (or if this is an older kernel) the value here will
+	 * always equal the @probed_size. Note this is only currently tracked
+	 * for I915_MEMORY_CLASS_DEVICE regions (for other types the value here
+	 * will always equal the @probed_size).
+	 */
 	__u64 unallocated_size;
 
-	/** @rsvd1: MBZ */
-	__u64 rsvd1[8];
+	union {
+		/** @rsvd1: MBZ */
+		__u64 rsvd1[8];
+		struct {
+			/**
+			 * @probed_cpu_visible_size: Memory probed by the driver
+			 * that is CPU accessible.
+			 *
+			 * This will be always be <= @probed_size, and the
+			 * remainder (if there is any) will not be CPU
+			 * accessible.
+			 *
+			 * On systems without small BAR, the @probed_size will
+			 * always equal the @probed_cpu_visible_size, since all
+			 * of it will be CPU accessible.
+			 *
+			 * Note this is only tracked for
+			 * I915_MEMORY_CLASS_DEVICE regions (for other types the
+			 * value here will always equal the @probed_size).
+			 *
+			 * Note that if the value returned here is zero, then
+			 * this must be an old kernel which lacks the relevant
+			 * small-bar uAPI support (including
+			 * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS), but on
+			 * such systems we should never actually end up with a
+			 * small BAR configuration, assuming we are able to load
+			 * the kernel module. Hence it should be safe to treat
+			 * this the same as when @probed_cpu_visible_size ==
+			 * @probed_size.
+			 */
+			__u64 probed_cpu_visible_size;
+
+			/**
+			 * @unallocated_cpu_visible_size: Estimate of CPU
+			 * visible memory remaining.
+			 *
+			 * Note this is only tracked for
+			 * I915_MEMORY_CLASS_DEVICE regions (for other types the
+			 * value here will always equal the
+			 * @probed_cpu_visible_size).
+			 *
+			 * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable
+			 * accounting.  Without this the value here will always
+			 * equal the @probed_cpu_visible_size. Note this is only
+			 * currently tracked for I915_MEMORY_CLASS_DEVICE
+			 * regions (for other types the value here will also
+			 * always equal the @probed_cpu_visible_size).
+			 *
+			 * If this is an older kernel the value here will be
+			 * zero, see also @probed_cpu_visible_size.
+			 */
+			__u64 unallocated_cpu_visible_size;
+		};
+	};
 };
 
 /**
@@ -3329,11 +3481,11 @@ struct drm_i915_query_memory_regions {
  * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added
  * extension support using struct i915_user_extension.
  *
- * Note that in the future we want to have our buffer flags here, at least for
- * the stuff that is immutable. Previously we would have two ioctls, one to
- * create the object with gem_create, and another to apply various parameters,
- * however this creates some ambiguity for the params which are considered
- * immutable. Also in general we're phasing out the various SET/GET ioctls.
+ * Note that new buffer flags should be added here, at least for the stuff that
+ * is immutable. Previously we would have two ioctls, one to create the object
+ * with gem_create, and another to apply various parameters, however this
+ * creates some ambiguity for the params which are considered immutable. Also in
+ * general we're phasing out the various SET/GET ioctls.
  */
 struct drm_i915_gem_create_ext {
 	/**
@@ -3341,7 +3493,6 @@ struct drm_i915_gem_create_ext {
 	 *
 	 * The (page-aligned) allocated size for the object will be returned.
 	 *
-	 *
 	 * DG2 64K min page size implications:
 	 *
 	 * On discrete platforms, starting from DG2, we have to contend with GTT
@@ -3353,7 +3504,9 @@ struct drm_i915_gem_create_ext {
 	 *
 	 * Note that the returned size here will always reflect any required
 	 * rounding up done by the kernel, i.e 4K will now become 64K on devices
-	 * such as DG2.
+	 * such as DG2. The kernel will always select the largest minimum
+	 * page-size for the set of possible placements as the value to use when
+	 * rounding up the @size.
 	 *
 	 * Special DG2 GTT address alignment requirement:
 	 *
@@ -3377,14 +3530,58 @@ struct drm_i915_gem_create_ext {
 	 * is deemed to be a good compromise.
 	 */
 	__u64 size;
+
 	/**
 	 * @handle: Returned handle for the object.
 	 *
 	 * Object handles are nonzero.
 	 */
 	__u32 handle;
-	/** @flags: MBZ */
+
+	/**
+	 * @flags: Optional flags.
+	 *
+	 * Supported values:
+	 *
+	 * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS - Signal to the kernel that
+	 * the object will need to be accessed via the CPU.
+	 *
+	 * Only valid when placing objects in I915_MEMORY_CLASS_DEVICE, and only
+	 * strictly required on configurations where some subset of the device
+	 * memory is directly visible/mappable through the CPU (which we also
+	 * call small BAR), like on some DG2+ systems. Note that this is quite
+	 * undesirable, but due to various factors like the client CPU, BIOS etc
+	 * it's something we can expect to see in the wild. See
+	 * &drm_i915_memory_region_info.probed_cpu_visible_size for how to
+	 * determine if this system applies.
+	 *
+	 * Note that one of the placements MUST be I915_MEMORY_CLASS_SYSTEM, to
+	 * ensure the kernel can always spill the allocation to system memory,
+	 * if the object can't be allocated in the mappable part of
+	 * I915_MEMORY_CLASS_DEVICE.
+	 *
+	 * Also note that since the kernel only supports flat-CCS on objects
+	 * that can *only* be placed in I915_MEMORY_CLASS_DEVICE, we therefore
+	 * don't support I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS together with
+	 * flat-CCS.
+	 *
+	 * Without this hint, the kernel will assume that non-mappable
+	 * I915_MEMORY_CLASS_DEVICE is preferred for this object. Note that the
+	 * kernel can still migrate the object to the mappable part, as a last
+	 * resort, if userspace ever CPU faults this object, but this might be
+	 * expensive, and so ideally should be avoided.
+	 *
+	 * On older kernels which lack the relevant small-bar uAPI support (see
+	 * also &drm_i915_memory_region_info.probed_cpu_visible_size),
+	 * usage of the flag will result in an error, but it should NEVER be
+	 * possible to end up with a small BAR configuration, assuming we can
+	 * also successfully load the i915 kernel module. In such cases the
+	 * entire I915_MEMORY_CLASS_DEVICE region will be CPU accessible, and as
+	 * such there are zero restrictions on where the object can be placed.
+	 */
+#define I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS (1 << 0)
 	__u32 flags;
+
 	/**
 	 * @extensions: The chain of extensions to apply to this object.
 	 *
@@ -3443,6 +3640,22 @@ struct drm_i915_gem_create_ext {
  * At which point we get the object handle in &drm_i915_gem_create_ext.handle,
  * along with the final object size in &drm_i915_gem_create_ext.size, which
  * should account for any rounding up, if required.
+ *
+ * Note that userspace has no means of knowing the current backing region
+ * for objects where @num_regions is larger than one. The kernel will only
+ * ensure that the priority order of the @regions array is honoured, either
+ * when initially placing the object, or when moving memory around due to
+ * memory pressure
+ *
+ * On Flat-CCS capable HW, compression is supported for the objects residing
+ * in I915_MEMORY_CLASS_DEVICE. When such objects (compressed) have other
+ * memory class in @regions and migrated (by i915, due to memory
+ * constraints) to the non I915_MEMORY_CLASS_DEVICE region, then i915 needs to
+ * decompress the content. But i915 doesn't have the required information to
+ * decompress the userspace compressed objects.
+ *
+ * So i915 supports Flat-CCS, on the objects which can reside only on
+ * I915_MEMORY_CLASS_DEVICE regions.
  */
 struct drm_i915_gem_create_ext_memory_regions {
 	/** @base: Extension link. See struct i915_user_extension. */
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 9f4428be3e36..a756b29afcc2 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -27,7 +27,8 @@
 #define FSCRYPT_MODE_AES_128_CBC		5
 #define FSCRYPT_MODE_AES_128_CTS		6
 #define FSCRYPT_MODE_ADIANTUM			9
-/* If adding a mode number > 9, update FSCRYPT_MODE_MAX in fscrypt_private.h */
+#define FSCRYPT_MODE_AES_256_HCTR2		10
+/* If adding a mode number > 10, update FSCRYPT_MODE_MAX in fscrypt_private.h */
 
 /*
  * Legacy policy version; ad-hoc KDF and no key verification.
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index cb6e3846d27b..eed0315a77a6 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -270,6 +270,8 @@ struct kvm_xen_exit {
 #define KVM_EXIT_X86_BUS_LOCK     33
 #define KVM_EXIT_XEN              34
 #define KVM_EXIT_RISCV_SBI        35
+#define KVM_EXIT_RISCV_CSR        36
+#define KVM_EXIT_NOTIFY           37
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -496,6 +498,18 @@ struct kvm_run {
 			unsigned long args[6];
 			unsigned long ret[2];
 		} riscv_sbi;
+		/* KVM_EXIT_RISCV_CSR */
+		struct {
+			unsigned long csr_num;
+			unsigned long new_value;
+			unsigned long write_mask;
+			unsigned long ret_value;
+		} riscv_csr;
+		/* KVM_EXIT_NOTIFY */
+		struct {
+#define KVM_NOTIFY_CONTEXT_INVALID	(1 << 0)
+			__u32 flags;
+		} notify;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1157,6 +1171,12 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_VM_TSC_CONTROL 214
 #define KVM_CAP_SYSTEM_EVENT_DATA 215
 #define KVM_CAP_ARM_SYSTEM_SUSPEND 216
+#define KVM_CAP_S390_PROTECTED_DUMP 217
+#define KVM_CAP_X86_TRIPLE_FAULT_EVENT 218
+#define KVM_CAP_X86_NOTIFY_VMEXIT 219
+#define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220
+#define KVM_CAP_S390_ZPCI_OP 221
+#define KVM_CAP_S390_CPU_TOPOLOGY 222
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1660,6 +1680,55 @@ struct kvm_s390_pv_unp {
 	__u64 tweak;
 };
 
+enum pv_cmd_dmp_id {
+	KVM_PV_DUMP_INIT,
+	KVM_PV_DUMP_CONFIG_STOR_STATE,
+	KVM_PV_DUMP_COMPLETE,
+	KVM_PV_DUMP_CPU,
+};
+
+struct kvm_s390_pv_dmp {
+	__u64 subcmd;
+	__u64 buff_addr;
+	__u64 buff_len;
+	__u64 gaddr;		/* For dump storage state */
+	__u64 reserved[4];
+};
+
+enum pv_cmd_info_id {
+	KVM_PV_INFO_VM,
+	KVM_PV_INFO_DUMP,
+};
+
+struct kvm_s390_pv_info_dump {
+	__u64 dump_cpu_buffer_len;
+	__u64 dump_config_mem_buffer_per_1m;
+	__u64 dump_config_finalize_len;
+};
+
+struct kvm_s390_pv_info_vm {
+	__u64 inst_calls_list[4];
+	__u64 max_cpus;
+	__u64 max_guests;
+	__u64 max_guest_addr;
+	__u64 feature_indication;
+};
+
+struct kvm_s390_pv_info_header {
+	__u32 id;
+	__u32 len_max;
+	__u32 len_written;
+	__u32 reserved;
+};
+
+struct kvm_s390_pv_info {
+	struct kvm_s390_pv_info_header header;
+	union {
+		struct kvm_s390_pv_info_dump dump;
+		struct kvm_s390_pv_info_vm vm;
+	};
+};
+
 enum pv_cmd_id {
 	KVM_PV_ENABLE,
 	KVM_PV_DISABLE,
@@ -1668,6 +1737,8 @@ enum pv_cmd_id {
 	KVM_PV_VERIFY,
 	KVM_PV_PREP_RESET,
 	KVM_PV_UNSHARE_ALL,
+	KVM_PV_INFO,
+	KVM_PV_DUMP,
 };
 
 struct kvm_pv_cmd {
@@ -2119,4 +2190,41 @@ struct kvm_stats_desc {
 /* Available with KVM_CAP_XSAVE2 */
 #define KVM_GET_XSAVE2		  _IOR(KVMIO,  0xcf, struct kvm_xsave)
 
+/* Available with KVM_CAP_S390_PROTECTED_DUMP */
+#define KVM_S390_PV_CPU_COMMAND	_IOWR(KVMIO, 0xd0, struct kvm_pv_cmd)
+
+/* Available with KVM_CAP_X86_NOTIFY_VMEXIT */
+#define KVM_X86_NOTIFY_VMEXIT_ENABLED		(1ULL << 0)
+#define KVM_X86_NOTIFY_VMEXIT_USER		(1ULL << 1)
+
+/* Available with KVM_CAP_S390_ZPCI_OP */
+#define KVM_S390_ZPCI_OP         _IOW(KVMIO,  0xd1, struct kvm_s390_zpci_op)
+
+struct kvm_s390_zpci_op {
+	/* in */
+	__u32 fh;               /* target device */
+	__u8  op;               /* operation to perform */
+	__u8  pad[3];
+	union {
+		/* for KVM_S390_ZPCIOP_REG_AEN */
+		struct {
+			__u64 ibv;      /* Guest addr of interrupt bit vector */
+			__u64 sb;       /* Guest addr of summary bit */
+			__u32 flags;
+			__u32 noi;      /* Number of interrupts */
+			__u8 isc;       /* Guest interrupt subclass */
+			__u8 sbo;       /* Offset of guest summary bit vector */
+			__u16 pad;
+		} reg_aen;
+		__u64 reserved[8];
+	} u;
+};
+
+/* types for kvm_s390_zpci_op->op */
+#define KVM_S390_ZPCIOP_REG_AEN                0
+#define KVM_S390_ZPCIOP_DEREG_AEN      1
+
+/* flags for kvm_s390_zpci_op->u.reg_aen.flags */
+#define KVM_S390_ZPCIOP_REGAEN_HOST    (1 << 0)
+
 #endif /* __LINUX_KVM_H */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index e2b77fbca91e..581ed4bdc062 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -301,6 +301,7 @@ enum {
  *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
  *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		id;           } && PERF_FORMAT_ID
+ *	  { u64		lost;         } && PERF_FORMAT_LOST
  *	} && !PERF_FORMAT_GROUP
  *
  *	{ u64		nr;
@@ -308,6 +309,7 @@ enum {
  *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		value;
  *	    { u64	id;           } && PERF_FORMAT_ID
+ *	    { u64	lost;         } && PERF_FORMAT_LOST
  *	  }		cntr[nr];
  *	} && PERF_FORMAT_GROUP
  * };
@@ -317,8 +319,9 @@ enum perf_event_read_format {
 	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
 	PERF_FORMAT_ID				= 1U << 2,
 	PERF_FORMAT_GROUP			= 1U << 3,
+	PERF_FORMAT_LOST			= 1U << 4,
 
-	PERF_FORMAT_MAX = 1U << 4,		/* non-ABI */
+	PERF_FORMAT_MAX = 1U << 5,		/* non-ABI */
 };
 
 #define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index cab645d4a645..f9f115a7c75b 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -171,4 +171,13 @@
 #define VHOST_VDPA_SET_GROUP_ASID	_IOW(VHOST_VIRTIO, 0x7C, \
 					     struct vhost_vring_state)
 
+/* Suspend a device so it does not process virtqueue requests anymore
+ *
+ * After the return of ioctl the device must preserve all the necessary state
+ * (the virtqueue vring base plus the possible device specific states) that is
+ * required for restoring in the future. The device must not change its
+ * configuration after that point.
+ */
+#define VHOST_VDPA_SUSPEND		_IO(VHOST_VIRTIO, 0x7D)
+
 #endif
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index 384d5e076ee4..6cd0be7c1bb4 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -309,7 +309,7 @@ bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
 	return perf_cpu_map__idx(cpus, cpu) != -1;
 }
 
-struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map)
+struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map)
 {
 	struct perf_cpu result = {
 		.cpu = -1
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index e6c98a6e3908..8ec5b9f344e0 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -441,6 +441,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 
 	perf_evlist__for_each_entry(evlist, evsel) {
 		bool overwrite = evsel->attr.write_backward;
+		enum fdarray_flags flgs;
 		struct perf_mmap *map;
 		int *output, fd, cpu;
 
@@ -486,6 +487,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 			if (ops->idx)
 				ops->idx(evlist, evsel, mp, idx);
 
+			pr_debug("idx %d: mmapping fd %d\n", idx, *output);
 			if (ops->mmap(map, mp, *output, evlist_cpu) < 0)
 				return -1;
 
@@ -494,6 +496,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 			if (!idx)
 				perf_evlist__set_mmap_first(evlist, map, overwrite);
 		} else {
+			pr_debug("idx %d: set output fd %d -> %d\n", idx, fd, *output);
 			if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
 				return -1;
 
@@ -502,8 +505,8 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 
 		revent = !overwrite ? POLLIN : 0;
 
-		if (!evsel->system_wide &&
-		    perf_evlist__add_pollfd(evlist, fd, map, revent, fdarray_flag__default) < 0) {
+		flgs = evsel->system_wide ? fdarray_flag__nonfilterable : fdarray_flag__default;
+		if (perf_evlist__add_pollfd(evlist, fd, map, revent, flgs) < 0) {
 			perf_mmap__put(map);
 			return -1;
 		}
@@ -520,6 +523,48 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 }
 
 static int
+mmap_per_thread(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
+		struct perf_mmap_param *mp)
+{
+	int nr_threads = perf_thread_map__nr(evlist->threads);
+	int nr_cpus    = perf_cpu_map__nr(evlist->all_cpus);
+	int cpu, thread, idx = 0;
+	int nr_mmaps = 0;
+
+	pr_debug("%s: nr cpu values (may include -1) %d nr threads %d\n",
+		 __func__, nr_cpus, nr_threads);
+
+	/* per-thread mmaps */
+	for (thread = 0; thread < nr_threads; thread++, idx++) {
+		int output = -1;
+		int output_overwrite = -1;
+
+		if (mmap_per_evsel(evlist, ops, idx, mp, 0, thread, &output,
+				   &output_overwrite, &nr_mmaps))
+			goto out_unmap;
+	}
+
+	/* system-wide mmaps i.e. per-cpu */
+	for (cpu = 1; cpu < nr_cpus; cpu++, idx++) {
+		int output = -1;
+		int output_overwrite = -1;
+
+		if (mmap_per_evsel(evlist, ops, idx, mp, cpu, 0, &output,
+				   &output_overwrite, &nr_mmaps))
+			goto out_unmap;
+	}
+
+	if (nr_mmaps != evlist->nr_mmaps)
+		pr_err("Miscounted nr_mmaps %d vs %d\n", nr_mmaps, evlist->nr_mmaps);
+
+	return 0;
+
+out_unmap:
+	perf_evlist__munmap(evlist);
+	return -1;
+}
+
+static int
 mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 	     struct perf_mmap_param *mp)
 {
@@ -528,6 +573,8 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 	int nr_mmaps = 0;
 	int cpu, thread;
 
+	pr_debug("%s: nr cpu values %d nr threads %d\n", __func__, nr_cpus, nr_threads);
+
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		int output = -1;
 		int output_overwrite = -1;
@@ -569,6 +616,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 			  struct perf_evlist_mmap_ops *ops,
 			  struct perf_mmap_param *mp)
 {
+	const struct perf_cpu_map *cpus = evlist->all_cpus;
 	struct perf_evsel *evsel;
 
 	if (!ops || !ops->get || !ops->mmap)
@@ -588,6 +636,9 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 	if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
 		return -ENOMEM;
 
+	if (perf_cpu_map__empty(cpus))
+		return mmap_per_thread(evlist, ops, mp);
+
 	return mmap_per_cpu(evlist, ops, mp);
 }
 
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index 952f3520d5c2..8ce5bbd09666 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -305,6 +305,9 @@ int perf_evsel__read_size(struct perf_evsel *evsel)
 	if (read_format & PERF_FORMAT_ID)
 		entry += sizeof(u64);
 
+	if (read_format & PERF_FORMAT_LOST)
+		entry += sizeof(u64);
+
 	if (read_format & PERF_FORMAT_GROUP) {
 		nr = evsel->nr_members;
 		size += sizeof(u64);
@@ -314,24 +317,98 @@ int perf_evsel__read_size(struct perf_evsel *evsel)
 	return size;
 }
 
+/* This only reads values for the leader */
+static int perf_evsel__read_group(struct perf_evsel *evsel, int cpu_map_idx,
+				  int thread, struct perf_counts_values *count)
+{
+	size_t size = perf_evsel__read_size(evsel);
+	int *fd = FD(evsel, cpu_map_idx, thread);
+	u64 read_format = evsel->attr.read_format;
+	u64 *data;
+	int idx = 1;
+
+	if (fd == NULL || *fd < 0)
+		return -EINVAL;
+
+	data = calloc(1, size);
+	if (data == NULL)
+		return -ENOMEM;
+
+	if (readn(*fd, data, size) <= 0) {
+		free(data);
+		return -errno;
+	}
+
+	/*
+	 * This reads only the leader event intentionally since we don't have
+	 * perf counts values for sibling events.
+	 */
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		count->ena = data[idx++];
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		count->run = data[idx++];
+
+	/* value is always available */
+	count->val = data[idx++];
+	if (read_format & PERF_FORMAT_ID)
+		count->id = data[idx++];
+	if (read_format & PERF_FORMAT_LOST)
+		count->lost = data[idx++];
+
+	free(data);
+	return 0;
+}
+
+/*
+ * The perf read format is very flexible.  It needs to set the proper
+ * values according to the read format.
+ */
+static void perf_evsel__adjust_values(struct perf_evsel *evsel, u64 *buf,
+				      struct perf_counts_values *count)
+{
+	u64 read_format = evsel->attr.read_format;
+	int n = 0;
+
+	count->val = buf[n++];
+
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		count->ena = buf[n++];
+
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		count->run = buf[n++];
+
+	if (read_format & PERF_FORMAT_ID)
+		count->id = buf[n++];
+
+	if (read_format & PERF_FORMAT_LOST)
+		count->lost = buf[n++];
+}
+
 int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
 		     struct perf_counts_values *count)
 {
 	size_t size = perf_evsel__read_size(evsel);
 	int *fd = FD(evsel, cpu_map_idx, thread);
+	u64 read_format = evsel->attr.read_format;
+	struct perf_counts_values buf;
 
 	memset(count, 0, sizeof(*count));
 
 	if (fd == NULL || *fd < 0)
 		return -EINVAL;
 
+	if (read_format & PERF_FORMAT_GROUP)
+		return perf_evsel__read_group(evsel, cpu_map_idx, thread, count);
+
 	if (MMAP(evsel, cpu_map_idx, thread) &&
+	    !(read_format & (PERF_FORMAT_ID | PERF_FORMAT_LOST)) &&
 	    !perf_mmap__read_self(MMAP(evsel, cpu_map_idx, thread), count))
 		return 0;
 
-	if (readn(*fd, count->values, size) <= 0)
+	if (readn(*fd, buf.values, size) <= 0)
 		return -errno;
 
+	perf_evsel__adjust_values(evsel, buf.values, count);
 	return 0;
 }
 
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 24de795b09bb..03aceb72a783 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -23,7 +23,7 @@ LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
 LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
 LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
-LIBPERF_API struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map);
+LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map);
 LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
 
 #define perf_cpu_map__for_each_cpu(cpu, idx, cpus)		\
diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
index 556bb06798f2..d8ae4e944467 100644
--- a/tools/lib/perf/include/perf/event.h
+++ b/tools/lib/perf/include/perf/event.h
@@ -6,6 +6,7 @@
 #include <linux/types.h>
 #include <linux/limits.h>
 #include <linux/bpf.h>
+#include <linux/compiler.h>
 #include <sys/types.h> /* pid_t */
 
 #define event_contains(obj, mem) ((obj).header.size > offsetof(typeof(obj), mem))
@@ -76,7 +77,7 @@ struct perf_record_lost_samples {
 };
 
 /*
- * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID
+ * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID | PERF_FORMAT_LOST
  */
 struct perf_record_read {
 	struct perf_event_header header;
@@ -85,6 +86,7 @@ struct perf_record_read {
 	__u64			 time_enabled;
 	__u64			 time_running;
 	__u64			 id;
+	__u64			 lost;
 };
 
 struct perf_record_throttle {
@@ -95,7 +97,7 @@ struct perf_record_throttle {
 };
 
 #ifndef KSYM_NAME_LEN
-#define KSYM_NAME_LEN 256
+#define KSYM_NAME_LEN 512
 #endif
 
 struct perf_record_ksymbol {
@@ -153,22 +155,60 @@ enum {
 	PERF_CPU_MAP__MASK = 1,
 };
 
+/*
+ * Array encoding of a perf_cpu_map where nr is the number of entries in cpu[]
+ * and each entry is a value for a CPU in the map.
+ */
 struct cpu_map_entries {
 	__u16			 nr;
 	__u16			 cpu[];
 };
 
-struct perf_record_record_cpu_map {
+/* Bitmap encoding of a perf_cpu_map where bitmap entries are 32-bit. */
+struct perf_record_mask_cpu_map32 {
+	/* Number of mask values. */
+	__u16			 nr;
+	/* Constant 4. */
+	__u16			 long_size;
+	/* Bitmap data. */
+	__u32			 mask[];
+};
+
+/* Bitmap encoding of a perf_cpu_map where bitmap entries are 64-bit. */
+struct perf_record_mask_cpu_map64 {
+	/* Number of mask values. */
 	__u16			 nr;
+	/* Constant 8. */
 	__u16			 long_size;
-	unsigned long		 mask[];
+	/* Legacy padding. */
+	char                     __pad[4];
+	/* Bitmap data. */
+	__u64			 mask[];
 };
 
-struct perf_record_cpu_map_data {
+/*
+ * 'struct perf_record_cpu_map_data' is packed as unfortunately an earlier
+ * version had unaligned data and we wish to retain file format compatibility.
+ * -irogers
+ */
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wpacked"
+#pragma GCC diagnostic ignored "-Wattributes"
+
+struct __packed perf_record_cpu_map_data {
 	__u16			 type;
-	char			 data[];
+	union {
+		/* Used when type == PERF_CPU_MAP__CPUS. */
+		struct cpu_map_entries cpus_data;
+		/* Used when type == PERF_CPU_MAP__MASK and long_size == 4. */
+		struct perf_record_mask_cpu_map32 mask32_data;
+		/* Used when type == PERF_CPU_MAP__MASK and long_size == 8. */
+		struct perf_record_mask_cpu_map64 mask64_data;
+	};
 };
 
+#pragma GCC diagnostic pop
+
 struct perf_record_cpu_map {
 	struct perf_event_header	 header;
 	struct perf_record_cpu_map_data	 data;
diff --git a/tools/lib/perf/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h
index 699c0ed97d34..6f92204075c2 100644
--- a/tools/lib/perf/include/perf/evsel.h
+++ b/tools/lib/perf/include/perf/evsel.h
@@ -18,8 +18,10 @@ struct perf_counts_values {
 			uint64_t val;
 			uint64_t ena;
 			uint64_t run;
+			uint64_t id;
+			uint64_t lost;
 		};
-		uint64_t values[3];
+		uint64_t values[5];
 	};
 };
 
diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c
index 89be89afb24d..a11fc51bfb68 100644
--- a/tools/lib/perf/tests/test-evsel.c
+++ b/tools/lib/perf/tests/test-evsel.c
@@ -1,10 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdarg.h>
 #include <stdio.h>
+#include <string.h>
 #include <linux/perf_event.h>
+#include <linux/kernel.h>
 #include <perf/cpumap.h>
 #include <perf/threadmap.h>
 #include <perf/evsel.h>
+#include <internal/evsel.h>
 #include <internal/tests.h>
 #include "tests.h"
 
@@ -189,6 +192,163 @@ static int test_stat_user_read(int event)
 	return 0;
 }
 
+static int test_stat_read_format_single(struct perf_event_attr *attr, struct perf_thread_map *threads)
+{
+	struct perf_evsel *evsel;
+	struct perf_counts_values counts;
+	volatile int count = 0x100000;
+	int err;
+
+	evsel = perf_evsel__new(attr);
+	__T("failed to create evsel", evsel);
+
+	/* skip old kernels that don't support the format */
+	err = perf_evsel__open(evsel, NULL, threads);
+	if (err < 0)
+		return 0;
+
+	while (count--) ;
+
+	memset(&counts, -1, sizeof(counts));
+	perf_evsel__read(evsel, 0, 0, &counts);
+
+	__T("failed to read value", counts.val);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		__T("failed to read TOTAL_TIME_ENABLED", counts.ena);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		__T("failed to read TOTAL_TIME_RUNNING", counts.run);
+	if (attr->read_format & PERF_FORMAT_ID)
+		__T("failed to read ID", counts.id);
+	if (attr->read_format & PERF_FORMAT_LOST)
+		__T("failed to read LOST", counts.lost == 0);
+
+	perf_evsel__close(evsel);
+	perf_evsel__delete(evsel);
+	return 0;
+}
+
+static int test_stat_read_format_group(struct perf_event_attr *attr, struct perf_thread_map *threads)
+{
+	struct perf_evsel *leader, *member;
+	struct perf_counts_values counts;
+	volatile int count = 0x100000;
+	int err;
+
+	attr->read_format |= PERF_FORMAT_GROUP;
+	leader = perf_evsel__new(attr);
+	__T("failed to create leader", leader);
+
+	attr->read_format &= ~PERF_FORMAT_GROUP;
+	member = perf_evsel__new(attr);
+	__T("failed to create member", member);
+
+	member->leader = leader;
+	leader->nr_members = 2;
+
+	/* skip old kernels that don't support the format */
+	err = perf_evsel__open(leader, NULL, threads);
+	if (err < 0)
+		return 0;
+	err = perf_evsel__open(member, NULL, threads);
+	if (err < 0)
+		return 0;
+
+	while (count--) ;
+
+	memset(&counts, -1, sizeof(counts));
+	perf_evsel__read(leader, 0, 0, &counts);
+
+	__T("failed to read leader value", counts.val);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		__T("failed to read leader TOTAL_TIME_ENABLED", counts.ena);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		__T("failed to read leader TOTAL_TIME_RUNNING", counts.run);
+	if (attr->read_format & PERF_FORMAT_ID)
+		__T("failed to read leader ID", counts.id);
+	if (attr->read_format & PERF_FORMAT_LOST)
+		__T("failed to read leader LOST", counts.lost == 0);
+
+	memset(&counts, -1, sizeof(counts));
+	perf_evsel__read(member, 0, 0, &counts);
+
+	__T("failed to read member value", counts.val);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		__T("failed to read member TOTAL_TIME_ENABLED", counts.ena);
+	if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		__T("failed to read member TOTAL_TIME_RUNNING", counts.run);
+	if (attr->read_format & PERF_FORMAT_ID)
+		__T("failed to read member ID", counts.id);
+	if (attr->read_format & PERF_FORMAT_LOST)
+		__T("failed to read member LOST", counts.lost == 0);
+
+	perf_evsel__close(member);
+	perf_evsel__close(leader);
+	perf_evsel__delete(member);
+	perf_evsel__delete(leader);
+	return 0;
+}
+
+static int test_stat_read_format(void)
+{
+	struct perf_thread_map *threads;
+	struct perf_event_attr attr = {
+		.type	= PERF_TYPE_SOFTWARE,
+		.config	= PERF_COUNT_SW_TASK_CLOCK,
+	};
+	int err, i;
+
+#define FMT(_fmt)  PERF_FORMAT_ ## _fmt
+#define FMT_TIME  (FMT(TOTAL_TIME_ENABLED) | FMT(TOTAL_TIME_RUNNING))
+
+	uint64_t test_formats [] = {
+		0,
+		FMT_TIME,
+		FMT(ID),
+		FMT(LOST),
+		FMT_TIME | FMT(ID),
+		FMT_TIME | FMT(LOST),
+		FMT_TIME | FMT(ID) | FMT(LOST),
+		FMT(ID) | FMT(LOST),
+	};
+
+#undef FMT
+#undef FMT_TIME
+
+	threads = perf_thread_map__new_dummy();
+	__T("failed to create threads", threads);
+
+	perf_thread_map__set_pid(threads, 0, 0);
+
+	for (i = 0; i < (int)ARRAY_SIZE(test_formats); i++) {
+		attr.read_format = test_formats[i];
+		__T_VERBOSE("testing single read with read_format: %lx\n",
+			    (unsigned long)test_formats[i]);
+
+		err = test_stat_read_format_single(&attr, threads);
+		__T("failed to read single format", err == 0);
+	}
+
+	perf_thread_map__put(threads);
+
+	threads = perf_thread_map__new_array(2, NULL);
+	__T("failed to create threads", threads);
+
+	perf_thread_map__set_pid(threads, 0, 0);
+	perf_thread_map__set_pid(threads, 1, 0);
+
+	for (i = 0; i < (int)ARRAY_SIZE(test_formats); i++) {
+		attr.read_format = test_formats[i];
+		__T_VERBOSE("testing group read with read_format: %lx\n",
+			    (unsigned long)test_formats[i]);
+
+		err = test_stat_read_format_group(&attr, threads);
+		__T("failed to read group format", err == 0);
+	}
+
+	perf_thread_map__put(threads);
+	return 0;
+}
+
 int test_evsel(int argc, char **argv)
 {
 	__T_START;
@@ -200,6 +360,7 @@ int test_evsel(int argc, char **argv)
 	test_stat_thread_enable();
 	test_stat_user_read(PERF_COUNT_HW_INSTRUCTIONS);
 	test_stat_user_read(PERF_COUNT_HW_CPU_CYCLES);
+	test_stat_read_format();
 
 	__T_END;
 	return tests_failed == 0 ? 0 : -1;
diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h
index 72ab9870454b..542f9b059c3b 100644
--- a/tools/lib/symbol/kallsyms.h
+++ b/tools/lib/symbol/kallsyms.h
@@ -7,7 +7,7 @@
 #include <linux/types.h>
 
 #ifndef KSYM_NAME_LEN
-#define KSYM_NAME_LEN 256
+#define KSYM_NAME_LEN 512
 #endif
 
 static inline u8 kallsyms2elf_binding(char type)
diff --git a/tools/memory-model/Documentation/litmus-tests.txt b/tools/memory-model/Documentation/litmus-tests.txt
index 8a9d5d2787f9..26554b1c5575 100644
--- a/tools/memory-model/Documentation/litmus-tests.txt
+++ b/tools/memory-model/Documentation/litmus-tests.txt
@@ -946,22 +946,39 @@ Limitations of the Linux-kernel memory model (LKMM) include:
 	carrying a dependency, then the compiler can break that dependency
 	by substituting a constant of that value.
 
-	Conversely, LKMM sometimes doesn't recognize that a particular
-	optimization is not allowed, and as a result, thinks that a
-	dependency is not present (because the optimization would break it).
-	The memory model misses some pretty obvious control dependencies
-	because of this limitation.  A simple example is:
+	Conversely, LKMM will sometimes overestimate the amount of
+	reordering compilers and CPUs can carry out, leading it to miss
+	some pretty obvious cases of ordering.  A simple example is:
 
 		r1 = READ_ONCE(x);
 		if (r1 == 0)
 			smp_mb();
 		WRITE_ONCE(y, 1);
 
-	There is a control dependency from the READ_ONCE to the WRITE_ONCE,
-	even when r1 is nonzero, but LKMM doesn't realize this and thinks
-	that the write may execute before the read if r1 != 0.  (Yes, that
-	doesn't make sense if you think about it, but the memory model's
-	intelligence is limited.)
+	The WRITE_ONCE() does not depend on the READ_ONCE(), and as a
+	result, LKMM does not claim ordering.  However, even though no
+	dependency is present, the WRITE_ONCE() will not be executed before
+	the READ_ONCE().  There are two reasons for this:
+
+                The presence of the smp_mb() in one of the branches
+                prevents the compiler from moving the WRITE_ONCE()
+                up before the "if" statement, since the compiler has
+                to assume that r1 will sometimes be 0 (but see the
+                comment below);
+
+                CPUs do not execute stores before po-earlier conditional
+                branches, even in cases where the store occurs after the
+                two arms of the branch have recombined.
+
+	It is clear that it is not dangerous in the slightest for LKMM to
+	make weaker guarantees than architectures.  In fact, it is
+	desirable, as it gives compilers room for making optimizations.
+	For instance, suppose that a 0 value in r1 would trigger undefined
+	behavior elsewhere.  Then a clever compiler might deduce that r1
+	can never be 0 in the if condition.  As a result, said clever
+	compiler might deem it safe to optimize away the smp_mb(),
+	eliminating the branch and any ordering an architecture would
+	guarantee otherwise.
 
 2.	Multiple access sizes for a single variable are not supported,
 	and neither are misaligned or partially overlapping accesses.
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 0cec74da7ffe..4a9ba6ab80d5 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -162,32 +162,34 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
 
 	/*
 	 * Unfortunately these have to be hard coded because the noreturn
-	 * attribute isn't provided in ELF data.
+	 * attribute isn't provided in ELF data. Keep 'em sorted.
 	 */
 	static const char * const global_noreturns[] = {
+		"__invalid_creds",
+		"__module_put_and_kthread_exit",
+		"__reiserfs_panic",
 		"__stack_chk_fail",
-		"panic",
+		"__ubsan_handle_builtin_unreachable",
+		"cpu_bringup_and_idle",
+		"cpu_startup_entry",
 		"do_exit",
+		"do_group_exit",
 		"do_task_dead",
-		"kthread_exit",
-		"make_task_dead",
-		"__module_put_and_kthread_exit",
+		"ex_handler_msr_mce",
+		"fortify_panic",
 		"kthread_complete_and_exit",
-		"__reiserfs_panic",
+		"kthread_exit",
+		"kunit_try_catch_throw",
 		"lbug_with_loc",
-		"fortify_panic",
-		"usercopy_abort",
 		"machine_real_restart",
+		"make_task_dead",
+		"panic",
 		"rewind_stack_and_make_dead",
-		"kunit_try_catch_throw",
-		"xen_start_kernel",
-		"cpu_bringup_and_idle",
-		"do_group_exit",
+		"sev_es_terminate",
+		"snp_abort",
 		"stop_this_cpu",
-		"__invalid_creds",
-		"cpu_startup_entry",
-		"__ubsan_handle_builtin_unreachable",
-		"ex_handler_msr_mce",
+		"usercopy_abort",
+		"xen_start_kernel",
 	};
 
 	if (!func)
@@ -1071,6 +1073,9 @@ static const char *uaccess_safe_builtin[] = {
 	"copy_mc_fragile_handle_tail",
 	"copy_mc_enhanced_fast_string",
 	"ftrace_likely_update", /* CONFIG_TRACE_BRANCH_PROFILING */
+	"clear_user_erms",
+	"clear_user_rep_good",
+	"clear_user_original",
 	NULL
 };
 
@@ -3314,6 +3319,10 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 		next_insn = next_insn_to_validate(file, insn);
 
 		if (func && insn->func && func != insn->func->pfunc) {
+			/* Ignore KCFI type preambles, which always fall through */
+			if (!strncmp(func->name, "__cfi_", 6))
+				return 0;
+
 			WARN("%s() falls through to next function %s()",
 			     func->name, insn->func->name);
 			return 1;
@@ -4096,7 +4105,8 @@ static int validate_ibt(struct objtool_file *file)
 		 * These sections can reference text addresses, but not with
 		 * the intent to indirect branch to them.
 		 */
-		if (!strncmp(sec->name, ".discard", 8)			||
+		if ((!strncmp(sec->name, ".discard", 8) &&
+		     strcmp(sec->name, ".discard.ibt_endbr_noseal"))	||
 		    !strncmp(sec->name, ".debug", 6)			||
 		    !strcmp(sec->name, ".altinstructions")		||
 		    !strcmp(sec->name, ".ibt_endbr_seal")		||
@@ -4110,7 +4120,8 @@ static int validate_ibt(struct objtool_file *file)
 		    !strcmp(sec->name, "__bug_table")			||
 		    !strcmp(sec->name, "__ex_table")			||
 		    !strcmp(sec->name, "__jump_table")			||
-		    !strcmp(sec->name, "__mcount_loc"))
+		    !strcmp(sec->name, "__mcount_loc")			||
+		    !strcmp(sec->name, ".kcfi_traps"))
 			continue;
 
 		list_for_each_entry(reloc, &sec->reloc->reloc_list, list)
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index c25e957c1e52..7e24b09b1163 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -619,6 +619,11 @@ static int elf_update_symbol(struct elf *elf, struct section *symtab,
 	Elf64_Xword entsize = symtab->sh.sh_entsize;
 	int max_idx, idx = sym->idx;
 	Elf_Scn *s, *t = NULL;
+	bool is_special_shndx = sym->sym.st_shndx >= SHN_LORESERVE &&
+				sym->sym.st_shndx != SHN_XINDEX;
+
+	if (is_special_shndx)
+		shndx = sym->sym.st_shndx;
 
 	s = elf_getscn(elf->elf, symtab->idx);
 	if (!s) {
@@ -704,7 +709,7 @@ static int elf_update_symbol(struct elf *elf, struct section *symtab,
 	}
 
 	/* setup extended section index magic and write the symbol */
-	if (shndx >= SHN_UNDEF && shndx < SHN_LORESERVE) {
+	if ((shndx >= SHN_UNDEF && shndx < SHN_LORESERVE) || is_special_shndx) {
 		sym->sym.st_shndx = shndx;
 		if (!shndx_data)
 			shndx = 0;
diff --git a/tools/perf/Documentation/intel-hybrid.txt b/tools/perf/Documentation/intel-hybrid.txt
index c9302096dc46..e7a776ad25d7 100644
--- a/tools/perf/Documentation/intel-hybrid.txt
+++ b/tools/perf/Documentation/intel-hybrid.txt
@@ -21,11 +21,6 @@ cat /sys/devices/cpu_atom/cpus
 
 It indicates cpu0-cpu15 are core cpus and cpu16-cpu23 are atom cpus.
 
-Quickstart
-
-List hybrid event
------------------
-
 As before, use perf-list to list the symbolic event.
 
 perf list
@@ -40,7 +35,6 @@ the event is belong to. Same event name but with different pmu can
 be supported.
 
 Enable hybrid event with a specific pmu
----------------------------------------
 
 To enable a core only event or atom only event, following syntax is supported:
 
@@ -53,7 +47,6 @@ For example, count the 'cycles' event on core cpus.
 	perf stat -e cpu_core/cycles/
 
 Create two events for one hardware event automatically
-------------------------------------------------------
 
 When creating one event and the event is available on both atom and core,
 two events are created automatically. One is for atom, the other is for
@@ -132,7 +125,6 @@ For perf-stat result, it displays two events:
 The first 'cycles' is core event, the second 'cycles' is atom event.
 
 Thread mode example:
---------------------
 
 perf-stat reports the scaled counts for hybrid event and with a percentage
 displayed. The percentage is the event's running time/enabling time.
@@ -176,14 +168,12 @@ perf_event_attr:
        604,097,080      cpu_atom/cycles/                                              (99.57%)
 
 perf-record:
-------------
 
 If there is no '-e' specified in perf record, on hybrid platform,
 it creates two default 'cycles' and adds them to event list. One
 is for core, the other is for atom.
 
 perf-stat:
-----------
 
 If there is no '-e' specified in perf stat, on hybrid platform,
 besides of software events, following events are created and
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 099817ef5150..0228efc96686 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -397,6 +397,9 @@ following filters are defined:
 	- abort_tx: only when the target is a hardware transaction abort
 	- cond: conditional branches
 	- save_type: save branch type during sampling in case binary is not available later
+		     For the platforms with Intel Arch LBR support (12th-Gen+ client or
+		     4th-Gen Xeon+ server), the save branch type is unconditionally enabled
+		     when the taken branch stack sampling is enabled.
 
 +
 The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.
@@ -757,8 +760,6 @@ events in data directory files. Option specified with no or empty value
 defaults to CPU layout. Masks defined or provided by the option value are
 filtered through the mask provided by -C option.
 
-include::intel-hybrid.txt[]
-
 --debuginfod[=URLs]::
 	Specify debuginfod URL to be used when cacheing perf.data binaries,
 	it follows the same syntax as the DEBUGINFOD_URLS variable, like:
@@ -778,6 +779,8 @@ include::intel-hybrid.txt[]
 	only, as of now.  So the applications built without the frame
 	pointer might see bogus addresses.
 
+include::intel-hybrid.txt[]
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 0661a1cf9855..2171f02daf59 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -265,7 +265,7 @@ endif
 # defined. get-executable-or-default fails with an error if the first argument is supplied but
 # doesn't exist.
 override PYTHON_CONFIG := $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON_AUTO))
-override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_AUTO)))
+override PYTHON := $(call get-executable-or-default,PYTHON,$(subst -config,,$(PYTHON_CONFIG)))
 
 grep-libs  = $(filter -l%,$(1))
 strip-libs  = $(filter-out -l%,$(1))
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index e5921b347153..bd947885a639 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -954,11 +954,11 @@ ifndef NO_LIBBPF
 	$(call QUIET_INSTALL, bpf-headers) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'; \
-		$(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
-		$(INSTALL) include/bpf/linux/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'
+		$(INSTALL) include/bpf/*.h -m 644 -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
+		$(INSTALL) include/bpf/linux/*.h -m 644 -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'
 	$(call QUIET_INSTALL, bpf-examples) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \
-		$(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
+		$(INSTALL) examples/bpf/*.c -m 644 -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
 endif
 	$(call QUIET_INSTALL, perf-archive) \
 		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
@@ -967,13 +967,13 @@ endif
 ifndef NO_LIBAUDIT
 	$(call QUIET_INSTALL, strace/groups) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(STRACE_GROUPS_INSTDIR_SQ)'; \
-		$(INSTALL) trace/strace/groups/* -t '$(DESTDIR_SQ)$(STRACE_GROUPS_INSTDIR_SQ)'
+		$(INSTALL) trace/strace/groups/* -m 644 -t '$(DESTDIR_SQ)$(STRACE_GROUPS_INSTDIR_SQ)'
 endif
 ifndef NO_LIBPERL
 	$(call QUIET_INSTALL, perl-scripts) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
-		$(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
-		$(INSTALL) scripts/perl/*.pl -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'; \
+		$(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
+		$(INSTALL) scripts/perl/*.pl -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'; \
 		$(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
 endif
@@ -990,23 +990,23 @@ endif
 		$(INSTALL) $(DLFILTERS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/dlfilters';
 	$(call QUIET_INSTALL, perf_completion-script) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
-		$(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
+		$(INSTALL) perf-completion.sh -m 644 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
 	$(call QUIET_INSTALL, perf-tip) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(tip_instdir_SQ)'; \
-		$(INSTALL) Documentation/tips.txt -t '$(DESTDIR_SQ)$(tip_instdir_SQ)'
+		$(INSTALL) Documentation/tips.txt -m 644 -t '$(DESTDIR_SQ)$(tip_instdir_SQ)'
 
 install-tests: all install-gtk
 	$(call QUIET_INSTALL, tests) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
-		$(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
+		$(INSTALL) tests/attr.py -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
 		$(INSTALL) tests/pe-file.exe* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
-		$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
+		$(INSTALL) tests/attr/* -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \
 		$(INSTALL) tests/shell/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \
-		$(INSTALL) tests/shell/lib/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \
-		$(INSTALL) tests/shell/lib/*.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'
+		$(INSTALL) tests/shell/lib/*.sh -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \
+		$(INSTALL) tests/shell/lib/*.py -m 644 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'
 
 install-bin: install-tools install-tests install-traceevent-plugins
 
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 653e13b5037e..438fc222e213 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -146,15 +146,15 @@ static void *c2c_he_zalloc(size_t size)
 
 	c2c_he->cpuset = bitmap_zalloc(c2c.cpus_cnt);
 	if (!c2c_he->cpuset)
-		return NULL;
+		goto out_free;
 
 	c2c_he->nodeset = bitmap_zalloc(c2c.nodes_cnt);
 	if (!c2c_he->nodeset)
-		return NULL;
+		goto out_free;
 
 	c2c_he->node_stats = zalloc(c2c.nodes_cnt * sizeof(*c2c_he->node_stats));
 	if (!c2c_he->node_stats)
-		return NULL;
+		goto out_free;
 
 	init_stats(&c2c_he->cstats.lcl_hitm);
 	init_stats(&c2c_he->cstats.rmt_hitm);
@@ -163,6 +163,12 @@ static void *c2c_he_zalloc(size_t size)
 	init_stats(&c2c_he->cstats.load);
 
 	return &c2c_he->he;
+
+out_free:
+	free(c2c_he->nodeset);
+	free(c2c_he->cpuset);
+	free(c2c_he);
+	return NULL;
 }
 
 static void c2c_he_free(void *he)
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index dd11d3471baf..ea40ae52cd2c 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -1874,8 +1874,7 @@ int cmd_lock(int argc, const char **argv)
 		NULL
 	};
 	const char *const lock_subcommands[] = { "record", "report", "script",
-						 "info", "contention",
-						 "contention", NULL };
+						 "info", "contention", NULL };
 	const char *lock_usage[] = {
 		NULL,
 		NULL
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4713f0f3a6cf..0f711f88894c 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1906,14 +1906,18 @@ static int record__synthesize(struct record *rec, bool tail)
 
 	err = perf_event__synthesize_bpf_events(session, process_synthesized_event,
 						machine, opts);
-	if (err < 0)
+	if (err < 0) {
 		pr_warning("Couldn't synthesize bpf events.\n");
+		err = 0;
+	}
 
 	if (rec->opts.synth & PERF_SYNTH_CGROUP) {
 		err = perf_event__synthesize_cgroups(tool, process_synthesized_event,
 						     machine);
-		if (err < 0)
+		if (err < 0) {
 			pr_warning("Couldn't synthesize cgroup events.\n");
+			err = 0;
+		}
 	}
 
 	if (rec->opts.nr_threads_synthesize > 1) {
@@ -3358,16 +3362,24 @@ static struct option __record_options[] = {
 
 struct option *record_options = __record_options;
 
-static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cpu_map *cpus)
+static int record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cpu_map *cpus)
 {
 	struct perf_cpu cpu;
 	int idx;
 
 	if (cpu_map__is_dummy(cpus))
-		return;
+		return 0;
 
-	perf_cpu_map__for_each_cpu(cpu, idx, cpus)
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+		if (cpu.cpu == -1)
+			continue;
+		/* Return ENODEV is input cpu is greater than max cpu */
+		if ((unsigned long)cpu.cpu > mask->nbits)
+			return -ENODEV;
 		set_bit(cpu.cpu, mask->bits);
+	}
+
+	return 0;
 }
 
 static int record__mmap_cpu_mask_init_spec(struct mmap_cpu_mask *mask, const char *mask_spec)
@@ -3379,7 +3391,9 @@ static int record__mmap_cpu_mask_init_spec(struct mmap_cpu_mask *mask, const cha
 		return -ENOMEM;
 
 	bitmap_zero(mask->bits, mask->nbits);
-	record__mmap_cpu_mask_init(mask, cpus);
+	if (record__mmap_cpu_mask_init(mask, cpus))
+		return -ENODEV;
+
 	perf_cpu_map__put(cpus);
 
 	return 0;
@@ -3461,7 +3475,12 @@ static int record__init_thread_masks_spec(struct record *rec, struct perf_cpu_ma
 		pr_err("Failed to allocate CPUs mask\n");
 		return ret;
 	}
-	record__mmap_cpu_mask_init(&cpus_mask, cpus);
+
+	ret = record__mmap_cpu_mask_init(&cpus_mask, cpus);
+	if (ret) {
+		pr_err("Failed to init cpu mask\n");
+		goto out_free_cpu_mask;
+	}
 
 	ret = record__thread_mask_alloc(&full_mask, cpu__max_cpu().cpu);
 	if (ret) {
@@ -3702,7 +3721,8 @@ static int record__init_thread_default_masks(struct record *rec, struct perf_cpu
 	if (ret)
 		return ret;
 
-	record__mmap_cpu_mask_init(&rec->thread_masks->maps, cpus);
+	if (record__mmap_cpu_mask_init(&rec->thread_masks->maps, cpus))
+		return -ENODEV;
 
 	rec->nr_threads = 1;
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 2f6cd1b8b662..a5cf243c337f 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -3355,7 +3355,8 @@ static bool schedstat_events_exposed(void)
 static int __cmd_record(int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
-	const char **rec_argv;
+	char **rec_argv;
+	const char **rec_argv_copy;
 	const char * const record_args[] = {
 		"record",
 		"-a",
@@ -3384,6 +3385,7 @@ static int __cmd_record(int argc, const char **argv)
 		ARRAY_SIZE(schedstat_args) : 0;
 
 	struct tep_event *waking_event;
+	int ret;
 
 	/*
 	 * +2 for either "-e", "sched:sched_wakeup" or
@@ -3391,14 +3393,18 @@ static int __cmd_record(int argc, const char **argv)
 	 */
 	rec_argc = ARRAY_SIZE(record_args) + 2 + schedstat_argc + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
-
 	if (rec_argv == NULL)
 		return -ENOMEM;
+	rec_argv_copy = calloc(rec_argc + 1, sizeof(char *));
+	if (rec_argv_copy == NULL) {
+		free(rec_argv);
+		return -ENOMEM;
+	}
 
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = strdup(record_args[i]);
 
-	rec_argv[i++] = "-e";
+	rec_argv[i++] = strdup("-e");
 	waking_event = trace_event__tp_format("sched", "sched_waking");
 	if (!IS_ERR(waking_event))
 		rec_argv[i++] = strdup("sched:sched_waking");
@@ -3409,11 +3415,19 @@ static int __cmd_record(int argc, const char **argv)
 		rec_argv[i++] = strdup(schedstat_args[j]);
 
 	for (j = 1; j < (unsigned int)argc; j++, i++)
-		rec_argv[i] = argv[j];
+		rec_argv[i] = strdup(argv[j]);
 
 	BUG_ON(i != rec_argc);
 
-	return cmd_record(i, rec_argv);
+	memcpy(rec_argv_copy, rec_argv, sizeof(char *) * rec_argc);
+	ret = cmd_record(rec_argc, rec_argv_copy);
+
+	for (i = 0; i < rec_argc; i++)
+		free(rec_argv[i]);
+	free(rec_argv);
+	free(rec_argv_copy);
+
+	return ret;
 }
 
 int cmd_sched(int argc, const char **argv)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 13580a9c50b8..029b4330e59b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -445,6 +445,9 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
 	struct perf_event_attr *attr = &evsel->core.attr;
 	bool allow_user_set;
 
+	if (evsel__is_dummy_event(evsel))
+		return 0;
+
 	if (perf_header__has_feat(&session->header, HEADER_STAT))
 		return 0;
 
@@ -566,6 +569,8 @@ static struct evsel *find_first_output_type(struct evlist *evlist,
 	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
+		if (evsel__is_dummy_event(evsel))
+			continue;
 		if (output_type(evsel->core.attr.type) == (int)type)
 			return evsel;
 	}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7fb81a44672d..0b4a62e4ff67 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -826,6 +826,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	}
 
 	evlist__for_each_entry(evsel_list, counter) {
+		counter->reset_group = false;
 		if (bpf_counter__load(counter, &target))
 			return -1;
 		if (!evsel__is_bpf(counter))
@@ -1931,6 +1932,9 @@ setup_metrics:
 		free(str);
 	}
 
+	if (!stat_config.topdown_level)
+		stat_config.topdown_level = TOPDOWN_MAX_LEVEL;
+
 	if (!evsel_list->core.nr_entries) {
 		if (target__has_cpu(&target))
 			default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK;
@@ -1947,8 +1951,6 @@ setup_metrics:
 		}
 		if (evlist__add_default_attrs(evsel_list, default_attrs1) < 0)
 			return -1;
-
-		stat_config.topdown_level = TOPDOWN_MAX_LEVEL;
 		/* Platform specific attrs */
 		if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0)
 			return -1;
diff --git a/tools/perf/dlfilters/dlfilter-show-cycles.c b/tools/perf/dlfilters/dlfilter-show-cycles.c
index 9eccc97bff82..6d47298ebe9f 100644
--- a/tools/perf/dlfilters/dlfilter-show-cycles.c
+++ b/tools/perf/dlfilters/dlfilter-show-cycles.c
@@ -98,9 +98,9 @@ int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, vo
 static void print_vals(__u64 cycles, __u64 delta)
 {
 	if (delta)
-		printf("%10llu %10llu ", cycles, delta);
+		printf("%10llu %10llu ", (unsigned long long)cycles, (unsigned long long)delta);
 	else
-		printf("%10llu %10s ", cycles, "");
+		printf("%10llu %10s ", (unsigned long long)cycles, "");
 }
 
 int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx)
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index f94929ebb54b..7ea150cdc137 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -17,21 +17,23 @@ static int process_event_mask(struct perf_tool *tool __maybe_unused,
 			 struct machine *machine __maybe_unused)
 {
 	struct perf_record_cpu_map *map_event = &event->cpu_map;
-	struct perf_record_record_cpu_map *mask;
 	struct perf_record_cpu_map_data *data;
 	struct perf_cpu_map *map;
 	int i;
+	unsigned int long_size;
 
 	data = &map_event->data;
 
 	TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__MASK);
 
-	mask = (struct perf_record_record_cpu_map *)data->data;
+	long_size = data->mask32_data.long_size;
 
-	TEST_ASSERT_VAL("wrong nr",   mask->nr == 1);
+	TEST_ASSERT_VAL("wrong long_size", long_size == 4 || long_size == 8);
+
+	TEST_ASSERT_VAL("wrong nr",   data->mask32_data.nr == 1);
 
 	for (i = 0; i < 20; i++) {
-		TEST_ASSERT_VAL("wrong cpu", test_bit(i, mask->mask));
+		TEST_ASSERT_VAL("wrong cpu", perf_record_cpu_map_data__test_bit(i, data));
 	}
 
 	map = cpu_map__new_data(data);
@@ -51,7 +53,6 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 			 struct machine *machine __maybe_unused)
 {
 	struct perf_record_cpu_map *map_event = &event->cpu_map;
-	struct cpu_map_entries *cpus;
 	struct perf_record_cpu_map_data *data;
 	struct perf_cpu_map *map;
 
@@ -59,11 +60,9 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 
 	TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__CPUS);
 
-	cpus = (struct cpu_map_entries *)data->data;
-
-	TEST_ASSERT_VAL("wrong nr",   cpus->nr == 2);
-	TEST_ASSERT_VAL("wrong cpu",  cpus->cpu[0] == 1);
-	TEST_ASSERT_VAL("wrong cpu",  cpus->cpu[1] == 256);
+	TEST_ASSERT_VAL("wrong nr",   data->cpus_data.nr == 2);
+	TEST_ASSERT_VAL("wrong cpu",  data->cpus_data.cpu[0] == 1);
+	TEST_ASSERT_VAL("wrong cpu",  data->cpus_data.cpu[1] == 256);
 
 	map = cpu_map__new_data(data);
 	TEST_ASSERT_VAL("wrong nr",  perf_cpu_map__nr(map) == 2);
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index dfb6173b2a82..9e9a2b67de19 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -114,8 +114,7 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
 
 	for (i = 0; i < nsyscalls; ++i)
 		for (j = 0; j < expected_nr_events[i]; ++j) {
-			int foo = syscalls[i]();
-			++foo;
+			syscalls[i]();
 		}
 
 	md = &evlist->mmap[0];
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 6a001fcfed68..4952abe716f3 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -332,7 +332,7 @@ out_delete_evlist:
 out:
 	if (err == -EACCES)
 		return TEST_SKIP;
-	if (err < 0)
+	if (err < 0 || errs != 0)
 		return TEST_FAIL;
 	return TEST_OK;
 }
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 07f2411b0ad4..20930dd48ee0 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -86,10 +86,15 @@ static bool samples_same(const struct perf_sample *s1,
 			COMP(read.time_running);
 		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
 		if (read_format & PERF_FORMAT_GROUP) {
-			for (i = 0; i < s1->read.group.nr; i++)
-				MCOMP(read.group.values[i]);
+			for (i = 0; i < s1->read.group.nr; i++) {
+				/* FIXME: check values without LOST */
+				if (read_format & PERF_FORMAT_LOST)
+					MCOMP(read.group.values[i]);
+			}
 		} else {
 			COMP(read.one.id);
+			if (read_format & PERF_FORMAT_LOST)
+				COMP(read.one.lost);
 		}
 	}
 
@@ -263,7 +268,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 			.data	= (void *)aux_data,
 		},
 	};
-	struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
+	struct sample_read_value values[] = {{1, 5, 0}, {9, 3, 0}, {2, 7, 0}, {6, 4, 1},};
 	struct perf_sample sample_out, sample_out_endian;
 	size_t i, sz, bufsz;
 	int err, ret = -1;
@@ -286,6 +291,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 	} else {
 		sample.read.one.value = 0x08789faeb786aa87ULL;
 		sample.read.one.id    = 99;
+		sample.read.one.lost  = 1;
 	}
 
 	sz = perf_event__sample_event_size(&sample, sample_type, read_format);
@@ -370,7 +376,7 @@ out_free:
  */
 static int test__sample_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
-	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
+	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15, 20, 21, 22, 28, 29, 30, 31};
 	u64 sample_type;
 	u64 sample_regs;
 	size_t i;
diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index 00c7285ce1ac..301f95427159 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -61,7 +61,7 @@ test_register_capture() {
     echo "Register capture test [Skipped missing registers]"
     return
   fi
-  if ! perf record -o - --intr-regs=di,r8,dx,cx -e cpu/br_inst_retired.near_call/p \
+  if ! perf record -o - --intr-regs=di,r8,dx,cx -e br_inst_retired.near_call:p \
     -c 1000 --per-thread true 2> /dev/null \
     | perf script -F ip,sym,iregs -i - 2> /dev/null \
     | egrep -q "DI:"
diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh
index 9313ef2739e0..26a51b48aee4 100755
--- a/tools/perf/tests/shell/stat.sh
+++ b/tools/perf/tests/shell/stat.sh
@@ -28,6 +28,24 @@ test_stat_record_report() {
   echo "stat record and report test [Success]"
 }
 
+test_stat_repeat_weak_groups() {
+  echo "stat repeat weak groups test"
+  if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \
+     true 2>&1 | grep -q 'seconds time elapsed'
+  then
+    echo "stat repeat weak groups test [Skipped event parsing failed]"
+    return
+  fi
+  if ! perf stat -r2 -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}:W' \
+    true > /dev/null 2>&1
+  then
+    echo "stat repeat weak groups test [Failed]"
+    err=1
+    return
+  fi
+  echo "stat repeat weak groups test [Success]"
+}
+
 test_topdown_groups() {
   # Topdown events must be grouped with the slots event first. Test that
   # parse-events reorders this.
@@ -75,6 +93,7 @@ test_topdown_weak_groups() {
 
 test_default_stat
 test_stat_record_report
+test_stat_repeat_weak_groups
 test_topdown_groups
 test_topdown_weak_groups
 exit $err
diff --git a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
new file mode 100755
index 000000000000..d724855d097c
--- /dev/null
+++ b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
@@ -0,0 +1,83 @@
+#!/bin/sh
+# perf stat --bpf-counters --for-each-cgroup test
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+test_cgroups=
+if [ "$1" = "-v" ]; then
+	verbose="1"
+fi
+
+# skip if --bpf-counters --for-each-cgroup is not supported
+check_bpf_counter()
+{
+	if ! perf stat -a --bpf-counters --for-each-cgroup / true > /dev/null 2>&1; then
+		if [ "${verbose}" = "1" ]; then
+			echo "Skipping: --bpf-counters --for-each-cgroup not supported"
+			perf --no-pager stat -a --bpf-counters --for-each-cgroup / true || true
+		fi
+		exit 2
+	fi
+}
+
+# find two cgroups to measure
+find_cgroups()
+{
+	# try usual systemd slices first
+	if [ -d /sys/fs/cgroup/system.slice -a -d /sys/fs/cgroup/user.slice ]; then
+		test_cgroups="system.slice,user.slice"
+		return
+	fi
+
+	# try root and self cgroups
+	local self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3)
+	if [ -z ${self_cgrp} ]; then
+		# cgroup v2 doesn't specify perf_event
+		self_cgrp=$(grep ^0: /proc/self/cgroup | cut -d: -f3)
+	fi
+
+	if [ -z ${self_cgrp} ]; then
+		test_cgroups="/"
+	else
+		test_cgroups="/,${self_cgrp}"
+	fi
+}
+
+# As cgroup events are cpu-wide, we cannot simply compare the result.
+# Just check if it runs without failure and has non-zero results.
+check_system_wide_counted()
+{
+	local output
+
+	output=$(perf stat -a --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, sleep 1  2>&1)
+	if echo ${output} | grep -q -F "<not "; then
+		echo "Some system-wide events are not counted"
+		if [ "${verbose}" = "1" ]; then
+			echo ${output}
+		fi
+		exit 1
+	fi
+}
+
+check_cpu_list_counted()
+{
+	local output
+
+	output=$(perf stat -C 1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1  2>&1)
+	if echo ${output} | grep -q -F "<not "; then
+		echo "Some CPU events are not counted"
+		if [ "${verbose}" = "1" ]; then
+			echo ${output}
+		fi
+		exit 1
+	fi
+}
+
+check_bpf_counter
+find_cgroups
+
+check_system_wide_counted
+check_cpu_list_counted
+
+exit 0
diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh
index c644f94a6500..ec801cffae6b 100755
--- a/tools/perf/tests/shell/test_brstack.sh
+++ b/tools/perf/tests/shell/test_brstack.sh
@@ -12,7 +12,8 @@ if ! [ -x "$(command -v cc)" ]; then
 fi
 
 # skip the test if the hardware doesn't support branch stack sampling
-perf record -b -o- -B true > /dev/null 2>&1 || exit 2
+# and if the architecture doesn't support filter types: any,save_type,u
+perf record -b -o- -B --branch-filter any,save_type,u true > /dev/null 2>&1 || exit 2
 
 TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX)
 
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 4fd8d703ff19..8ab035b55875 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -43,10 +43,11 @@ static bool is_ignored_symbol(const char *name, char type)
 	/* Symbol names that begin with the following are ignored.*/
 	static const char * const ignored_prefixes[] = {
 		"$",			/* local symbols for ARM, MIPS, etc. */
-		".LASANPC",		/* s390 kasan local symbols */
+		".L",			/* local labels, .LBB,.Ltmpxxx,.L__unnamed_xx,.LASANPC, etc. */
 		"__crc_",		/* modversions */
 		"__efistub_",		/* arm64 EFI stub namespace */
-		"__kvm_nvhe_",		/* arm64 non-VHE KVM namespace */
+		"__kvm_nvhe_$",		/* arm64 local symbols in non-VHE KVM namespace */
+		"__kvm_nvhe_.L",	/* arm64 local symbols in non-VHE KVM namespace */
 		"__AArch64ADRPThunk_",	/* arm64 lld */
 		"__ARMV5PILongThunk_",	/* arm lld */
 		"__ARMV7PILongThunk_",
diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c
index 9d4c45184e71..56455da30341 100644
--- a/tools/perf/tests/wp.c
+++ b/tools/perf/tests/wp.c
@@ -2,7 +2,9 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <errno.h>
 #include <sys/ioctl.h>
+#include <linux/compiler.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/kernel.h>
 #include "tests.h"
@@ -137,8 +139,7 @@ static int test__wp_rw(struct test_suite *test __maybe_unused,
 #endif
 }
 
-static int test__wp_modify(struct test_suite *test __maybe_unused,
-			   int subtest __maybe_unused)
+static int test__wp_modify(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 #if defined(__s390x__)
 	return TEST_SKIP;
@@ -160,6 +161,11 @@ static int test__wp_modify(struct test_suite *test __maybe_unused,
 	new_attr.disabled = 1;
 	ret = ioctl(fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &new_attr);
 	if (ret < 0) {
+		if (errno == ENOTTY) {
+			test->test_cases[subtest].skip_reason = "missing kernel support";
+			ret = TEST_SKIP;
+		}
+
 		pr_debug("ioctl(PERF_EVENT_IOC_MODIFY_ATTRIBUTES) failed\n");
 		close(fd);
 		return ret;
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index 17311ad9f9af..de3701a2a212 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -14,6 +14,8 @@ struct file;
 struct pid;
 struct cred;
 struct socket;
+struct sock;
+struct sk_buff;
 
 #define __sockaddr_check_size(size)	\
 	BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage)))
@@ -69,6 +71,9 @@ struct msghdr {
 	unsigned int	msg_flags;	/* flags on received message */
 	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
 	struct kiocb	*msg_iocb;	/* ptr to iocb for async requests */
+	struct ubuf_info *msg_ubuf;
+	int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb,
+			    struct iov_iter *from, size_t length);
 };
 
 struct user_msghdr {
@@ -416,10 +421,9 @@ extern int recvmsg_copy_msghdr(struct msghdr *msg,
 			       struct user_msghdr __user *umsg, unsigned flags,
 			       struct sockaddr __user **uaddr,
 			       struct iovec **iov);
-extern int __copy_msghdr_from_user(struct msghdr *kmsg,
-				   struct user_msghdr __user *umsg,
-				   struct sockaddr __user **save_addr,
-				   struct iovec __user **uiov, size_t *nsegs);
+extern int __copy_msghdr(struct msghdr *kmsg,
+			 struct user_msghdr *umsg,
+			 struct sockaddr __user **save_addr);
 
 /* helpers which do the actual work for syscalls */
 extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
@@ -428,10 +432,6 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
 extern int __sys_sendto(int fd, void __user *buff, size_t len,
 			unsigned int flags, struct sockaddr __user *addr,
 			int addr_len);
-extern int __sys_accept4_file(struct file *file, unsigned file_flags,
-			struct sockaddr __user *upeer_sockaddr,
-			 int __user *upeer_addrlen, int flags,
-			 unsigned long nofile);
 extern struct file *do_accept(struct file *file, unsigned file_flags,
 			      struct sockaddr __user *upeer_sockaddr,
 			      int __user *upeer_addrlen, int flags);
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 9dfae1bda9cc..485e1a343165 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -269,7 +269,7 @@ CFLAGS_expr-flex.o          += $(flex_flags)
 bison_flags := -DYYENABLE_NLS=0
 BISON_GE_35 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 35)
 ifeq ($(BISON_GE_35),1)
-  bison_flags += -Wno-unused-parameter -Wno-nested-externs -Wno-implicit-function-declaration -Wno-switch-enum
+  bison_flags += -Wno-unused-parameter -Wno-nested-externs -Wno-implicit-function-declaration -Wno-switch-enum -Wno-unused-but-set-variable -Wno-unknown-warning-option
 else
   bison_flags += -w
 endif
diff --git a/tools/perf/util/affinity.c b/tools/perf/util/affinity.c
index 4d216c0dc425..4ee96b3c755b 100644
--- a/tools/perf/util/affinity.c
+++ b/tools/perf/util/affinity.c
@@ -49,8 +49,14 @@ void affinity__set(struct affinity *a, int cpu)
 {
 	int cpu_set_size = get_cpu_set_size();
 
-	if (cpu == -1)
+	/*
+	 * Return:
+	 * - if cpu is -1
+	 * - restrict out of bound access to sched_cpus
+	 */
+	if (cpu == -1 || ((cpu >= (cpu_set_size * 8))))
 		return;
+
 	a->changed = true;
 	set_bit(cpu, a->sched_cpus);
 	/*
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 22dcfe07e886..906476a839e1 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -498,7 +498,7 @@ static void arm_spe__synth_data_source_generic(const struct arm_spe_record *reco
 static u64 arm_spe__synth_data_source(const struct arm_spe_record *record, u64 midr)
 {
 	union perf_mem_data_src	data_src = { 0 };
-	bool is_neoverse = is_midr_in_range(midr, neoverse_spe);
+	bool is_neoverse = is_midr_in_range_list(midr, neoverse_spe);
 
 	if (record->op == ARM_SPE_LD)
 		data_src.mem_op = PERF_MEM_OP_LOAD;
diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c
index 63b9db657442..3c2df7522f6f 100644
--- a/tools/perf/util/bpf_counter_cgroup.c
+++ b/tools/perf/util/bpf_counter_cgroup.c
@@ -95,7 +95,7 @@ static int bperf_load_program(struct evlist *evlist)
 
 	perf_cpu_map__for_each_cpu(cpu, i, evlist->core.all_cpus) {
 		link = bpf_program__attach_perf_event(skel->progs.on_cgrp_switch,
-						      FD(cgrp_switch, cpu.cpu));
+						      FD(cgrp_switch, i));
 		if (IS_ERR(link)) {
 			pr_err("Failed to attach cgroup program\n");
 			err = PTR_ERR(link);
@@ -115,15 +115,15 @@ static int bperf_load_program(struct evlist *evlist)
 			evsel->cgrp = NULL;
 
 			/* open single copy of the events w/o cgroup */
-			err = evsel__open_per_cpu(evsel, evlist->core.all_cpus, -1);
+			err = evsel__open_per_cpu(evsel, evsel->core.cpus, -1);
 			if (err) {
 				pr_err("Failed to open first cgroup events\n");
 				goto out;
 			}
 
 			map_fd = bpf_map__fd(skel->maps.events);
-			perf_cpu_map__for_each_cpu(cpu, j, evlist->core.all_cpus) {
-				int fd = FD(evsel, cpu.cpu);
+			perf_cpu_map__for_each_cpu(cpu, j, evsel->core.cpus) {
+				int fd = FD(evsel, j);
 				__u32 idx = evsel->core.idx * total_cpus + cpu.cpu;
 
 				err = bpf_map_update_elem(map_fd, &idx, &fd,
@@ -269,7 +269,7 @@ static int bperf_cgrp__read(struct evsel *evsel)
 			goto out;
 		}
 
-		perf_cpu_map__for_each_cpu(cpu, i, evlist->core.all_cpus) {
+		perf_cpu_map__for_each_cpu(cpu, i, evsel->core.cpus) {
 			counts = perf_counts(evsel->counts, i, 0);
 			counts->val = values[cpu.cpu].counter;
 			counts->ena = values[cpu.cpu].enabled;
diff --git a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c
index 292c430768b5..9aa8cdd93de4 100644
--- a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c
+++ b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c
@@ -48,6 +48,7 @@ const volatile __u32 num_cpus = 1;
 
 int enabled = 0;
 int use_cgroup_v2 = 0;
+int perf_subsys_id = -1;
 
 static inline int get_cgroup_v1_idx(__u32 *cgrps, int size)
 {
@@ -58,7 +59,15 @@ static inline int get_cgroup_v1_idx(__u32 *cgrps, int size)
 	int level;
 	int cnt;
 
-	cgrp = BPF_CORE_READ(p, cgroups, subsys[perf_event_cgrp_id], cgroup);
+	if (perf_subsys_id == -1) {
+#if __has_builtin(__builtin_preserve_enum_value)
+		perf_subsys_id = bpf_core_enum_value(enum cgroup_subsys_id,
+						     perf_event_cgrp_id);
+#else
+		perf_subsys_id = perf_event_cgrp_id;
+#endif
+	}
+	cgrp = BPF_CORE_READ(p, cgroups, subsys[perf_subsys_id], cgroup);
 	level = BPF_CORE_READ(cgrp, level);
 
 	for (cnt = 0; i < MAX_LEVELS; i++) {
@@ -176,7 +185,7 @@ static int bperf_cgroup_count(void)
 }
 
 // This will be attached to cgroup-switches event for each cpu
-SEC("perf_events")
+SEC("perf_event")
 int BPF_PROG(on_cgrp_switch)
 {
 	return bperf_cgroup_count();
diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
index c4ba2bcf179f..38e3b287dbb2 100644
--- a/tools/perf/util/bpf_skel/off_cpu.bpf.c
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -94,6 +94,8 @@ const volatile bool has_prev_state = false;
 const volatile bool needs_cgroup = false;
 const volatile bool uses_cgroup_v1 = false;
 
+int perf_subsys_id = -1;
+
 /*
  * Old kernel used to call it task_struct->state and now it's '__state'.
  * Use BPF CO-RE "ignored suffix rule" to deal with it like below:
@@ -119,11 +121,19 @@ static inline __u64 get_cgroup_id(struct task_struct *t)
 {
 	struct cgroup *cgrp;
 
-	if (uses_cgroup_v1)
-		cgrp = BPF_CORE_READ(t, cgroups, subsys[perf_event_cgrp_id], cgroup);
-	else
-		cgrp = BPF_CORE_READ(t, cgroups, dfl_cgrp);
+	if (!uses_cgroup_v1)
+		return BPF_CORE_READ(t, cgroups, dfl_cgrp, kn, id);
+
+	if (perf_subsys_id == -1) {
+#if __has_builtin(__builtin_preserve_enum_value)
+		perf_subsys_id = bpf_core_enum_value(enum cgroup_subsys_id,
+						     perf_event_cgrp_id);
+#else
+		perf_subsys_id = perf_event_cgrp_id;
+#endif
+	}
 
+	cgrp = BPF_CORE_READ(t, cgroups, subsys[perf_subsys_id], cgroup);
 	return BPF_CORE_READ(cgrp, kn, id);
 }
 
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 12b2243222b0..ae43fb88f444 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -22,54 +22,102 @@ static int max_node_num;
  */
 static int *cpunode_map;
 
-static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
+bool perf_record_cpu_map_data__test_bit(int i,
+					const struct perf_record_cpu_map_data *data)
+{
+	int bit_word32 = i / 32;
+	__u32 bit_mask32 = 1U << (i & 31);
+	int bit_word64 = i / 64;
+	__u64 bit_mask64 = ((__u64)1) << (i & 63);
+
+	return (data->mask32_data.long_size == 4)
+		? (bit_word32 < data->mask32_data.nr) &&
+		(data->mask32_data.mask[bit_word32] & bit_mask32) != 0
+		: (bit_word64 < data->mask64_data.nr) &&
+		(data->mask64_data.mask[bit_word64] & bit_mask64) != 0;
+}
+
+/* Read ith mask value from data into the given 64-bit sized bitmap */
+static void perf_record_cpu_map_data__read_one_mask(const struct perf_record_cpu_map_data *data,
+						    int i, unsigned long *bitmap)
+{
+#if __SIZEOF_LONG__ == 8
+	if (data->mask32_data.long_size == 4)
+		bitmap[0] = data->mask32_data.mask[i];
+	else
+		bitmap[0] = data->mask64_data.mask[i];
+#else
+	if (data->mask32_data.long_size == 4) {
+		bitmap[0] = data->mask32_data.mask[i];
+		bitmap[1] = 0;
+	} else {
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+		bitmap[0] = (unsigned long)(data->mask64_data.mask[i] >> 32);
+		bitmap[1] = (unsigned long)data->mask64_data.mask[i];
+#else
+		bitmap[0] = (unsigned long)data->mask64_data.mask[i];
+		bitmap[1] = (unsigned long)(data->mask64_data.mask[i] >> 32);
+#endif
+	}
+#endif
+}
+static struct perf_cpu_map *cpu_map__from_entries(const struct perf_record_cpu_map_data *data)
 {
 	struct perf_cpu_map *map;
 
-	map = perf_cpu_map__empty_new(cpus->nr);
+	map = perf_cpu_map__empty_new(data->cpus_data.nr);
 	if (map) {
 		unsigned i;
 
-		for (i = 0; i < cpus->nr; i++) {
+		for (i = 0; i < data->cpus_data.nr; i++) {
 			/*
 			 * Special treatment for -1, which is not real cpu number,
 			 * and we need to use (int) -1 to initialize map[i],
 			 * otherwise it would become 65535.
 			 */
-			if (cpus->cpu[i] == (u16) -1)
+			if (data->cpus_data.cpu[i] == (u16) -1)
 				map->map[i].cpu = -1;
 			else
-				map->map[i].cpu = (int) cpus->cpu[i];
+				map->map[i].cpu = (int) data->cpus_data.cpu[i];
 		}
 	}
 
 	return map;
 }
 
-static struct perf_cpu_map *cpu_map__from_mask(struct perf_record_record_cpu_map *mask)
+static struct perf_cpu_map *cpu_map__from_mask(const struct perf_record_cpu_map_data *data)
 {
+	DECLARE_BITMAP(local_copy, 64);
+	int weight = 0, mask_nr = data->mask32_data.nr;
 	struct perf_cpu_map *map;
-	int nr, nbits = mask->nr * mask->long_size * BITS_PER_BYTE;
 
-	nr = bitmap_weight(mask->mask, nbits);
+	for (int i = 0; i < mask_nr; i++) {
+		perf_record_cpu_map_data__read_one_mask(data, i, local_copy);
+		weight += bitmap_weight(local_copy, 64);
+	}
+
+	map = perf_cpu_map__empty_new(weight);
+	if (!map)
+		return NULL;
 
-	map = perf_cpu_map__empty_new(nr);
-	if (map) {
-		int cpu, i = 0;
+	for (int i = 0, j = 0; i < mask_nr; i++) {
+		int cpus_per_i = (i * data->mask32_data.long_size  * BITS_PER_BYTE);
+		int cpu;
 
-		for_each_set_bit(cpu, mask->mask, nbits)
-			map->map[i++].cpu = cpu;
+		perf_record_cpu_map_data__read_one_mask(data, i, local_copy);
+		for_each_set_bit(cpu, local_copy, 64)
+			map->map[j++].cpu = cpu + cpus_per_i;
 	}
 	return map;
 
 }
 
-struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data)
+struct perf_cpu_map *cpu_map__new_data(const struct perf_record_cpu_map_data *data)
 {
 	if (data->type == PERF_CPU_MAP__CPUS)
-		return cpu_map__from_entries((struct cpu_map_entries *)data->data);
+		return cpu_map__from_entries(data);
 	else
-		return cpu_map__from_mask((struct perf_record_record_cpu_map *)data->data);
+		return cpu_map__from_mask(data);
 }
 
 size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp)
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 703ae6d3386e..fa8a5acdcae1 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -37,9 +37,11 @@ struct cpu_aggr_map {
 
 struct perf_record_cpu_map_data;
 
+bool perf_record_cpu_map_data__test_bit(int i, const struct perf_record_cpu_map_data *data);
+
 struct perf_cpu_map *perf_cpu_map__empty_new(int nr);
 
-struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data);
+struct perf_cpu_map *cpu_map__new_data(const struct perf_record_cpu_map_data *data);
 size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size);
 size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size);
 size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index a7b0931d5137..12eae6917022 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -65,7 +65,8 @@ struct stack_dump {
 
 struct sample_read_value {
 	u64 value;
-	u64 id;
+	u64 id;   /* only if PERF_FORMAT_ID */
+	u64 lost; /* only if PERF_FORMAT_LOST */
 };
 
 struct sample_read {
@@ -80,6 +81,24 @@ struct sample_read {
 	};
 };
 
+static inline size_t sample_read_value_size(u64 read_format)
+{
+	/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+	if (read_format & PERF_FORMAT_LOST)
+		return sizeof(struct sample_read_value);
+	else
+		return offsetof(struct sample_read_value, lost);
+}
+
+static inline struct sample_read_value *
+next_sample_read_value(struct sample_read_value *v, u64 read_format)
+{
+	return (void *)v + sample_read_value_size(read_format);
+}
+
+#define sample_read_group__for_each(v, nr, rf)		\
+	for (int __i = 0; __i < (int)nr; v = next_sample_read_value(v, rf), __i++)
+
 struct ip_callchain {
 	u64 nr;
 	u64 ips[];
@@ -463,10 +482,6 @@ size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FIL
 int kallsyms__get_function_start(const char *kallsyms_filename,
 				 const char *symbol_name, u64 *addr);
 
-void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max);
-void  cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map,
-			       u16 type, int max);
-
 void event_attr_init(struct perf_event_attr *attr);
 
 int perf_event_paranoid(void);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 4852089e1d79..18c3eb864d55 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1541,7 +1541,7 @@ static int evsel__read_one(struct evsel *evsel, int cpu_map_idx, int thread)
 }
 
 static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread,
-			     u64 val, u64 ena, u64 run)
+			     u64 val, u64 ena, u64 run, u64 lost)
 {
 	struct perf_counts_values *count;
 
@@ -1550,6 +1550,7 @@ static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread,
 	count->val    = val;
 	count->ena    = ena;
 	count->run    = run;
+	count->lost   = lost;
 
 	perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true);
 }
@@ -1558,7 +1559,7 @@ static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int
 {
 	u64 read_format = leader->core.attr.read_format;
 	struct sample_read_value *v;
-	u64 nr, ena = 0, run = 0, i;
+	u64 nr, ena = 0, run = 0, lost = 0;
 
 	nr = *data++;
 
@@ -1571,18 +1572,18 @@ static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int
 	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
 		run = *data++;
 
-	v = (struct sample_read_value *) data;
-
-	evsel__set_count(leader, cpu_map_idx, thread, v[0].value, ena, run);
-
-	for (i = 1; i < nr; i++) {
+	v = (void *)data;
+	sample_read_group__for_each(v, nr, read_format) {
 		struct evsel *counter;
 
-		counter = evlist__id2evsel(leader->evlist, v[i].id);
+		counter = evlist__id2evsel(leader->evlist, v->id);
 		if (!counter)
 			return -EINVAL;
 
-		evsel__set_count(counter, cpu_map_idx, thread, v[i].value, ena, run);
+		if (read_format & PERF_FORMAT_LOST)
+			lost = v->lost;
+
+		evsel__set_count(counter, cpu_map_idx, thread, v->value, ena, run, lost);
 	}
 
 	return 0;
@@ -2475,8 +2476,8 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 
 			if (data->read.group.nr > max_group_nr)
 				return -EFAULT;
-			sz = data->read.group.nr *
-			     sizeof(struct sample_read_value);
+
+			sz = data->read.group.nr * sample_read_value_size(read_format);
 			OVERFLOW_CHECK(array, sz, max_size);
 			data->read.group.values =
 					(struct sample_read_value *)array;
@@ -2485,6 +2486,12 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 			OVERFLOW_CHECK_u64(array);
 			data->read.one.id = *array;
 			array++;
+
+			if (read_format & PERF_FORMAT_LOST) {
+				OVERFLOW_CHECK_u64(array);
+				data->read.one.lost = *array;
+				array++;
+			}
 		}
 	}
 
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index 953338b9e887..d81b54563e96 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -30,10 +30,6 @@
 
 #define BUILD_ID_URANDOM /* different uuid for each run */
 
-// FIXME, remove this and fix the deprecation warnings before its removed and
-// We'll break for good here...
-#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
-
 #ifdef HAVE_LIBCRYPTO_SUPPORT
 
 #define BUILD_ID_MD5
@@ -45,6 +41,7 @@
 #endif
 
 #ifdef BUILD_ID_MD5
+#include <openssl/evp.h>
 #include <openssl/md5.h>
 #endif
 #endif
@@ -142,15 +139,20 @@ gen_build_id(struct buildid_note *note,
 static void
 gen_build_id(struct buildid_note *note, unsigned long load_addr, const void *code, size_t csize)
 {
-	MD5_CTX context;
+	EVP_MD_CTX *mdctx;
 
 	if (sizeof(note->build_id) < 16)
 		errx(1, "build_id too small for MD5");
 
-	MD5_Init(&context);
-	MD5_Update(&context, &load_addr, sizeof(load_addr));
-	MD5_Update(&context, code, csize);
-	MD5_Final((unsigned char *)note->build_id, &context);
+	mdctx = EVP_MD_CTX_new();
+	if (!mdctx)
+		errx(2, "failed to create EVP_MD_CTX");
+
+	EVP_DigestInit_ex(mdctx, EVP_md5(), NULL);
+	EVP_DigestUpdate(mdctx, &load_addr, sizeof(load_addr));
+	EVP_DigestUpdate(mdctx, code, csize);
+	EVP_DigestFinal_ex(mdctx, (unsigned char *)note->build_id, NULL);
+	EVP_MD_CTX_free(mdctx);
 }
 #endif
 
@@ -251,6 +253,7 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym,
 	Elf_Data *d;
 	Elf_Scn *scn;
 	Elf_Ehdr *ehdr;
+	Elf_Phdr *phdr;
 	Elf_Shdr *shdr;
 	uint64_t eh_frame_base_offset;
 	char *strsym = NULL;
@@ -286,6 +289,19 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym,
 	ehdr->e_shstrndx= unwinding ? 4 : 2; /* shdr index for section name */
 
 	/*
+	 * setup program header
+	 */
+	phdr = elf_newphdr(e, 1);
+	phdr[0].p_type = PT_LOAD;
+	phdr[0].p_offset = 0;
+	phdr[0].p_vaddr = 0;
+	phdr[0].p_paddr = 0;
+	phdr[0].p_filesz = csize;
+	phdr[0].p_memsz = csize;
+	phdr[0].p_flags = PF_X | PF_R;
+	phdr[0].p_align = 8;
+
+	/*
 	 * setup text section
 	 */
 	scn = elf_newscn(e);
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index ae138afe6c56..b5c909546e3f 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -53,8 +53,10 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
 
 #if GEN_ELF_CLASS == ELFCLASS64
 #define elf_newehdr	elf64_newehdr
+#define elf_newphdr	elf64_newphdr
 #define elf_getshdr	elf64_getshdr
 #define Elf_Ehdr	Elf64_Ehdr
+#define Elf_Phdr	Elf64_Phdr
 #define Elf_Shdr	Elf64_Shdr
 #define Elf_Sym		Elf64_Sym
 #define ELF_ST_TYPE(a)	ELF64_ST_TYPE(a)
@@ -62,8 +64,10 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
 #define ELF_ST_VIS(a)	ELF64_ST_VISIBILITY(a)
 #else
 #define elf_newehdr	elf32_newehdr
+#define elf_newphdr	elf32_newphdr
 #define elf_getshdr	elf32_getshdr
 #define Elf_Ehdr	Elf32_Ehdr
+#define Elf_Phdr	Elf32_Phdr
 #define Elf_Shdr	Elf32_Shdr
 #define Elf_Sym		Elf32_Sym
 #define ELF_ST_TYPE(a)	ELF32_ST_TYPE(a)
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 464475fd6b9a..c93bcaf6d55d 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -1655,6 +1655,9 @@ int metricgroup__parse_groups(const struct option *opt,
 	struct evlist *perf_evlist = *(struct evlist **)opt->value;
 	const struct pmu_events_table *table = pmu_events_table__find();
 
+	if (!table)
+		return -EINVAL;
+
 	return parse_groups(perf_evlist, str, metric_no_group,
 			    metric_no_merge, NULL, metric_events, table);
 }
diff --git a/tools/perf/util/parse-events-hybrid.c b/tools/perf/util/parse-events-hybrid.c
index 284f8eabd3b9..7c9f9150bad5 100644
--- a/tools/perf/util/parse-events-hybrid.c
+++ b/tools/perf/util/parse-events-hybrid.c
@@ -33,7 +33,8 @@ static void config_hybrid_attr(struct perf_event_attr *attr,
 	 * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied.
 	 */
 	attr->type = type;
-	attr->config = attr->config | ((__u64)pmu_type << PERF_PMU_TYPE_SHIFT);
+	attr->config = (attr->config & PERF_HW_EVENT_MASK) |
+			((__u64)pmu_type << PERF_PMU_TYPE_SHIFT);
 }
 
 static int create_event_hybrid(__u32 config_type, int *idx,
@@ -48,13 +49,25 @@ static int create_event_hybrid(__u32 config_type, int *idx,
 	__u64 config = attr->config;
 
 	config_hybrid_attr(attr, config_type, pmu->type);
+
+	/*
+	 * Some hybrid hardware cache events are only available on one CPU
+	 * PMU. For example, the 'L1-dcache-load-misses' is only available
+	 * on cpu_core, while the 'L1-icache-loads' is only available on
+	 * cpu_atom. We need to remove "not supported" hybrid cache events.
+	 */
+	if (attr->type == PERF_TYPE_HW_CACHE
+	    && !is_event_supported(attr->type, attr->config))
+		return 0;
+
 	evsel = parse_events__add_event_hybrid(list, idx, attr, name, metric_id,
 					       pmu, config_terms);
-	if (evsel)
+	if (evsel) {
 		evsel->pmu_name = strdup(pmu->name);
-	else
+		if (!evsel->pmu_name)
+			return -ENOMEM;
+	} else
 		return -ENOMEM;
-
 	attr->type = type;
 	attr->config = config;
 	return 0;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f05e15acd33f..f3b2c2a87456 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -28,6 +28,7 @@
 #include "util/parse-events-hybrid.h"
 #include "util/pmu-hybrid.h"
 #include "tracepoint.h"
+#include "thread_map.h"
 
 #define MAX_NAME_LEN 100
 
@@ -157,6 +158,44 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 #define PERF_EVENT_TYPE(config)		__PERF_EVENT_FIELD(config, TYPE)
 #define PERF_EVENT_ID(config)		__PERF_EVENT_FIELD(config, EVENT)
 
+bool is_event_supported(u8 type, u64 config)
+{
+	bool ret = true;
+	int open_return;
+	struct evsel *evsel;
+	struct perf_event_attr attr = {
+		.type = type,
+		.config = config,
+		.disabled = 1,
+	};
+	struct perf_thread_map *tmap = thread_map__new_by_tid(0);
+
+	if (tmap == NULL)
+		return false;
+
+	evsel = evsel__new(&attr);
+	if (evsel) {
+		open_return = evsel__open(evsel, NULL, tmap);
+		ret = open_return >= 0;
+
+		if (open_return == -EACCES) {
+			/*
+			 * This happens if the paranoid value
+			 * /proc/sys/kernel/perf_event_paranoid is set to 2
+			 * Re-run with exclude_kernel set; we don't do that
+			 * by default as some ARM machines do not support it.
+			 *
+			 */
+			evsel->core.attr.exclude_kernel = 1;
+			ret = evsel__open(evsel, NULL, tmap) >= 0;
+		}
+		evsel__delete(evsel);
+	}
+
+	perf_thread_map__put(tmap);
+	return ret;
+}
+
 const char *event_type(int type)
 {
 	switch (type) {
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 7e6a601d9cd0..07df7bb7b042 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -19,6 +19,7 @@ struct option;
 struct perf_pmu;
 
 bool have_tracepoints(struct list_head *evlist);
+bool is_event_supported(u8 type, u64 config);
 
 const char *event_type(int type);
 
diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index ba1ab5134685..c4d5d87fae2f 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -22,7 +22,6 @@
 #include "probe-file.h"
 #include "string2.h"
 #include "strlist.h"
-#include "thread_map.h"
 #include "tracepoint.h"
 #include "pfm.h"
 #include "pmu-hybrid.h"
@@ -239,44 +238,6 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob,
 	strlist__delete(sdtlist);
 }
 
-static bool is_event_supported(u8 type, unsigned int config)
-{
-	bool ret = true;
-	int open_return;
-	struct evsel *evsel;
-	struct perf_event_attr attr = {
-		.type = type,
-		.config = config,
-		.disabled = 1,
-	};
-	struct perf_thread_map *tmap = thread_map__new_by_tid(0);
-
-	if (tmap == NULL)
-		return false;
-
-	evsel = evsel__new(&attr);
-	if (evsel) {
-		open_return = evsel__open(evsel, NULL, tmap);
-		ret = open_return >= 0;
-
-		if (open_return == -EACCES) {
-			/*
-			 * This happens if the paranoid value
-			 * /proc/sys/kernel/perf_event_paranoid is set to 2
-			 * Re-run with exclude_kernel set; we don't do that
-			 * by default as some ARM machines do not support it.
-			 *
-			 */
-			evsel->core.attr.exclude_kernel = 1;
-			ret = evsel__open(evsel, NULL, tmap) >= 0;
-		}
-		evsel__delete(evsel);
-	}
-
-	perf_thread_map__put(tmap);
-	return ret;
-}
-
 int print_hwcache_events(const char *event_glob, bool name_only)
 {
 	unsigned int type, op, i, evt_i = 0, evt_num = 0, npmus = 0;
diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build
index c92326c2233a..0f5ba28339cf 100644
--- a/tools/perf/util/scripting-engines/Build
+++ b/tools/perf/util/scripting-engines/Build
@@ -3,4 +3,4 @@ perf-$(CONFIG_LIBPYTHON) += trace-event-python.o
 
 CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default -Wno-bad-function-cast -Wno-declaration-after-statement -Wno-switch-enum
 
-CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-error=deprecated-declarations
+CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-deprecated-declarations
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 9ef2406e0ede..1f2040f36d4e 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -642,15 +642,19 @@ exit:
 	return pylist;
 }
 
-static PyObject *get_sample_value_as_tuple(struct sample_read_value *value)
+static PyObject *get_sample_value_as_tuple(struct sample_read_value *value,
+					   u64 read_format)
 {
 	PyObject *t;
 
-	t = PyTuple_New(2);
+	t = PyTuple_New(3);
 	if (!t)
 		Py_FatalError("couldn't create Python tuple");
 	PyTuple_SetItem(t, 0, PyLong_FromUnsignedLongLong(value->id));
 	PyTuple_SetItem(t, 1, PyLong_FromUnsignedLongLong(value->value));
+	if (read_format & PERF_FORMAT_LOST)
+		PyTuple_SetItem(t, 2, PyLong_FromUnsignedLongLong(value->lost));
+
 	return t;
 }
 
@@ -681,12 +685,17 @@ static void set_sample_read_in_dict(PyObject *dict_sample,
 		Py_FatalError("couldn't create Python list");
 
 	if (read_format & PERF_FORMAT_GROUP) {
-		for (i = 0; i < sample->read.group.nr; i++) {
-			PyObject *t = get_sample_value_as_tuple(&sample->read.group.values[i]);
+		struct sample_read_value *v = sample->read.group.values;
+
+		i = 0;
+		sample_read_group__for_each(v, sample->read.group.nr, read_format) {
+			PyObject *t = get_sample_value_as_tuple(v, read_format);
 			PyList_SET_ITEM(values, i, t);
+			i++;
 		}
 	} else {
-		PyObject *t = get_sample_value_as_tuple(&sample->read.one);
+		PyObject *t = get_sample_value_as_tuple(&sample->read.one,
+							read_format);
 		PyList_SET_ITEM(values, 0, t);
 	}
 	pydict_set_item_string_decref(dict_sample, "values", values);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 98e16659a149..192c9274f7ad 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -916,30 +916,30 @@ static void perf_event__cpu_map_swap(union perf_event *event,
 				     bool sample_id_all __maybe_unused)
 {
 	struct perf_record_cpu_map_data *data = &event->cpu_map.data;
-	struct cpu_map_entries *cpus;
-	struct perf_record_record_cpu_map *mask;
-	unsigned i;
 
 	data->type = bswap_16(data->type);
 
 	switch (data->type) {
 	case PERF_CPU_MAP__CPUS:
-		cpus = (struct cpu_map_entries *)data->data;
-
-		cpus->nr = bswap_16(cpus->nr);
+		data->cpus_data.nr = bswap_16(data->cpus_data.nr);
 
-		for (i = 0; i < cpus->nr; i++)
-			cpus->cpu[i] = bswap_16(cpus->cpu[i]);
+		for (unsigned i = 0; i < data->cpus_data.nr; i++)
+			data->cpus_data.cpu[i] = bswap_16(data->cpus_data.cpu[i]);
 		break;
 	case PERF_CPU_MAP__MASK:
-		mask = (struct perf_record_record_cpu_map *)data->data;
-
-		mask->nr = bswap_16(mask->nr);
-		mask->long_size = bswap_16(mask->long_size);
+		data->mask32_data.long_size = bswap_16(data->mask32_data.long_size);
 
-		switch (mask->long_size) {
-		case 4: mem_bswap_32(&mask->mask, mask->nr); break;
-		case 8: mem_bswap_64(&mask->mask, mask->nr); break;
+		switch (data->mask32_data.long_size) {
+		case 4:
+			data->mask32_data.nr = bswap_16(data->mask32_data.nr);
+			for (unsigned i = 0; i < data->mask32_data.nr; i++)
+				data->mask32_data.mask[i] = bswap_32(data->mask32_data.mask[i]);
+			break;
+		case 8:
+			data->mask64_data.nr = bswap_16(data->mask64_data.nr);
+			for (unsigned i = 0; i < data->mask64_data.nr; i++)
+				data->mask64_data.mask[i] = bswap_64(data->mask64_data.mask[i]);
+			break;
 		default:
 			pr_err("cpu_map swap: unsupported long size\n");
 		}
@@ -1283,21 +1283,25 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format)
 		       sample->read.time_running);
 
 	if (read_format & PERF_FORMAT_GROUP) {
-		u64 i;
+		struct sample_read_value *value = sample->read.group.values;
 
 		printf(".... group nr %" PRIu64 "\n", sample->read.group.nr);
 
-		for (i = 0; i < sample->read.group.nr; i++) {
-			struct sample_read_value *value;
-
-			value = &sample->read.group.values[i];
+		sample_read_group__for_each(value, sample->read.group.nr, read_format) {
 			printf("..... id %016" PRIx64
-			       ", value %016" PRIx64 "\n",
+			       ", value %016" PRIx64,
 			       value->id, value->value);
+			if (read_format & PERF_FORMAT_LOST)
+				printf(", lost %" PRIu64, value->lost);
+			printf("\n");
 		}
-	} else
-		printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n",
+	} else {
+		printf("..... id %016" PRIx64 ", value %016" PRIx64,
 			sample->read.one.id, sample->read.one.value);
+		if (read_format & PERF_FORMAT_LOST)
+			printf(", lost %" PRIu64, sample->read.one.lost);
+		printf("\n");
+	}
 }
 
 static void dump_event(struct evlist *evlist, union perf_event *event,
@@ -1411,6 +1415,9 @@ static void dump_read(struct evsel *evsel, union perf_event *event)
 
 	if (read_format & PERF_FORMAT_ID)
 		printf("... id           : %" PRI_lu64 "\n", read_event->id);
+
+	if (read_format & PERF_FORMAT_LOST)
+		printf("... lost         : %" PRI_lu64 "\n", read_event->lost);
 }
 
 static struct machine *machines__find_for_cpumode(struct machines *machines,
@@ -1479,14 +1486,14 @@ static int deliver_sample_group(struct evlist *evlist,
 				struct perf_tool *tool,
 				union  perf_event *event,
 				struct perf_sample *sample,
-				struct machine *machine)
+				struct machine *machine,
+				u64 read_format)
 {
 	int ret = -EINVAL;
-	u64 i;
+	struct sample_read_value *v = sample->read.group.values;
 
-	for (i = 0; i < sample->read.group.nr; i++) {
-		ret = deliver_sample_value(evlist, tool, event, sample,
-					   &sample->read.group.values[i],
+	sample_read_group__for_each(v, sample->read.group.nr, read_format) {
+		ret = deliver_sample_value(evlist, tool, event, sample, v,
 					   machine);
 		if (ret)
 			break;
@@ -1510,7 +1517,7 @@ static int evlist__deliver_sample(struct evlist *evlist, struct perf_tool *tool,
 	/* For PERF_SAMPLE_READ we have either single or group mode. */
 	if (read_format & PERF_FORMAT_GROUP)
 		return deliver_sample_group(evlist, tool, event, sample,
-					    machine);
+					    machine, read_format);
 	else
 		return deliver_sample_value(evlist, tool, event, sample,
 					    &sample->read.one, machine);
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 979c8cb918f7..788ce5e46470 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -1193,7 +1193,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 						  &rsd);
 		if (retiring > 0.7)
 			color = PERF_COLOR_GREEN;
-		print_metric(config, ctxp, color, "%8.1f%%", "retiring",
+		print_metric(config, ctxp, color, "%8.1f%%", "Retiring",
 				retiring * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
 		   full_td(cpu_map_idx, st, &rsd)) {
@@ -1202,7 +1202,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 						  &rsd);
 		if (fe_bound > 0.2)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "Frontend Bound",
 				fe_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
 		   full_td(cpu_map_idx, st, &rsd)) {
@@ -1211,7 +1211,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 						  &rsd);
 		if (be_bound > 0.2)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "backend bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "Backend Bound",
 				be_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
 		   full_td(cpu_map_idx, st, &rsd)) {
@@ -1220,7 +1220,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 						  &rsd);
 		if (bad_spec > 0.1)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
+		print_metric(config, ctxp, color, "%8.1f%%", "Bad Speculation",
 				bad_spec * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_HEAVY_OPS) &&
 			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1234,13 +1234,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 		if (retiring > 0.7 && heavy_ops > 0.1)
 			color = PERF_COLOR_GREEN;
-		print_metric(config, ctxp, color, "%8.1f%%", "heavy operations",
+		print_metric(config, ctxp, color, "%8.1f%%", "Heavy Operations",
 				heavy_ops * 100.);
 		if (retiring > 0.7 && light_ops > 0.6)
 			color = PERF_COLOR_GREEN;
 		else
 			color = NULL;
-		print_metric(config, ctxp, color, "%8.1f%%", "light operations",
+		print_metric(config, ctxp, color, "%8.1f%%", "Light Operations",
 				light_ops * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BR_MISPREDICT) &&
 			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1254,13 +1254,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 		if (bad_spec > 0.1 && br_mis > 0.05)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "branch mispredict",
+		print_metric(config, ctxp, color, "%8.1f%%", "Branch Mispredict",
 				br_mis * 100.);
 		if (bad_spec > 0.1 && m_clears > 0.05)
 			color = PERF_COLOR_RED;
 		else
 			color = NULL;
-		print_metric(config, ctxp, color, "%8.1f%%", "machine clears",
+		print_metric(config, ctxp, color, "%8.1f%%", "Machine Clears",
 				m_clears * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_LAT) &&
 			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1274,13 +1274,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 		if (fe_bound > 0.2 && fetch_lat > 0.15)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "fetch latency",
+		print_metric(config, ctxp, color, "%8.1f%%", "Fetch Latency",
 				fetch_lat * 100.);
 		if (fe_bound > 0.2 && fetch_bw > 0.1)
 			color = PERF_COLOR_RED;
 		else
 			color = NULL;
-		print_metric(config, ctxp, color, "%8.1f%%", "fetch bandwidth",
+		print_metric(config, ctxp, color, "%8.1f%%", "Fetch Bandwidth",
 				fetch_bw * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_MEM_BOUND) &&
 			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
@@ -1294,13 +1294,13 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 		if (be_bound > 0.2 && mem_bound > 0.2)
 			color = PERF_COLOR_RED;
-		print_metric(config, ctxp, color, "%8.1f%%", "memory bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "Memory Bound",
 				mem_bound * 100.);
 		if (be_bound > 0.2 && core_bound > 0.1)
 			color = PERF_COLOR_RED;
 		else
 			color = NULL;
-		print_metric(config, ctxp, color, "%8.1f%%", "Core bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "Core Bound",
 				core_bound * 100.);
 	} else if (evsel->metric_expr) {
 		generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL,
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 75bec32d4f57..647b7dff8ef3 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -2102,8 +2102,8 @@ static int kcore_copy__compare_file(const char *from_dir, const char *to_dir,
  * unusual.  One significant peculiarity is that the mapping (start -> pgoff)
  * is not the same for the kernel map and the modules map.  That happens because
  * the data is copied adjacently whereas the original kcore has gaps.  Finally,
- * kallsyms and modules files are compared with their copies to check that
- * modules have not been loaded or unloaded while the copies were taking place.
+ * kallsyms file is compared with its copy to check that modules have not been
+ * loaded or unloaded while the copies were taking place.
  *
  * Return: %0 on success, %-1 on failure.
  */
@@ -2166,9 +2166,6 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 			goto out_extract_close;
 	}
 
-	if (kcore_copy__compare_file(from_dir, to_dir, "modules"))
-		goto out_extract_close;
-
 	if (kcore_copy__compare_file(from_dir, to_dir, "kallsyms"))
 		goto out_extract_close;
 
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 2ae59c03ae77..538790758e24 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -367,13 +367,24 @@ static void perf_record_mmap2__read_build_id(struct perf_record_mmap2 *event,
 					     bool is_kernel)
 {
 	struct build_id bid;
+	struct nsinfo *nsi;
+	struct nscookie nc;
 	int rc;
 
-	if (is_kernel)
+	if (is_kernel) {
 		rc = sysfs__read_build_id("/sys/kernel/notes", &bid);
-	else
-		rc = filename__read_build_id(event->filename, &bid) > 0 ? 0 : -1;
+		goto out;
+	}
+
+	nsi = nsinfo__new(event->pid);
+	nsinfo__mountns_enter(nsi, &nc);
 
+	rc = filename__read_build_id(event->filename, &bid) > 0 ? 0 : -1;
+
+	nsinfo__mountns_exit(&nc);
+	nsinfo__put(nsi);
+
+out:
 	if (rc == 0) {
 		memcpy(event->build_id, bid.data, sizeof(bid.data));
 		event->build_id_size = (u8) bid.size;
@@ -1184,52 +1195,48 @@ int perf_event__synthesize_thread_map2(struct perf_tool *tool,
 	return err;
 }
 
-static void synthesize_cpus(struct cpu_map_entries *cpus,
-			    struct perf_cpu_map *map)
+static void synthesize_cpus(struct perf_record_cpu_map_data *data,
+			    const struct perf_cpu_map *map)
 {
 	int i, map_nr = perf_cpu_map__nr(map);
 
-	cpus->nr = map_nr;
+	data->cpus_data.nr = map_nr;
 
 	for (i = 0; i < map_nr; i++)
-		cpus->cpu[i] = perf_cpu_map__cpu(map, i).cpu;
+		data->cpus_data.cpu[i] = perf_cpu_map__cpu(map, i).cpu;
 }
 
-static void synthesize_mask(struct perf_record_record_cpu_map *mask,
-			    struct perf_cpu_map *map, int max)
+static void synthesize_mask(struct perf_record_cpu_map_data *data,
+			    const struct perf_cpu_map *map, int max)
 {
-	int i;
+	int idx;
+	struct perf_cpu cpu;
+
+	/* Due to padding, the 4bytes per entry mask variant is always smaller. */
+	data->mask32_data.nr = BITS_TO_U32(max);
+	data->mask32_data.long_size = 4;
 
-	mask->nr = BITS_TO_LONGS(max);
-	mask->long_size = sizeof(long);
+	perf_cpu_map__for_each_cpu(cpu, idx, map) {
+		int bit_word = cpu.cpu / 32;
+		__u32 bit_mask = 1U << (cpu.cpu & 31);
 
-	for (i = 0; i < perf_cpu_map__nr(map); i++)
-		set_bit(perf_cpu_map__cpu(map, i).cpu, mask->mask);
+		data->mask32_data.mask[bit_word] |= bit_mask;
+	}
 }
 
-static size_t cpus_size(struct perf_cpu_map *map)
+static size_t cpus_size(const struct perf_cpu_map *map)
 {
 	return sizeof(struct cpu_map_entries) + perf_cpu_map__nr(map) * sizeof(u16);
 }
 
-static size_t mask_size(struct perf_cpu_map *map, int *max)
+static size_t mask_size(const struct perf_cpu_map *map, int *max)
 {
-	int i;
-
-	*max = 0;
-
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		/* bit position of the cpu is + 1 */
-		int bit = perf_cpu_map__cpu(map, i).cpu + 1;
-
-		if (bit > *max)
-			*max = bit;
-	}
-
-	return sizeof(struct perf_record_record_cpu_map) + BITS_TO_LONGS(*max) * sizeof(long);
+	*max = perf_cpu_map__max(map).cpu;
+	return sizeof(struct perf_record_mask_cpu_map32) + BITS_TO_U32(*max) * sizeof(__u32);
 }
 
-void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max)
+static void *cpu_map_data__alloc(const struct perf_cpu_map *map, size_t *size,
+				 u16 *type, int *max)
 {
 	size_t size_cpus, size_mask;
 	bool is_dummy = perf_cpu_map__empty(map);
@@ -1258,30 +1265,31 @@ void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int
 		*type  = PERF_CPU_MAP__MASK;
 	}
 
-	*size += sizeof(struct perf_record_cpu_map_data);
+	*size += sizeof(__u16); /* For perf_record_cpu_map_data.type. */
 	*size = PERF_ALIGN(*size, sizeof(u64));
 	return zalloc(*size);
 }
 
-void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map,
-			      u16 type, int max)
+static void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data,
+				     const struct perf_cpu_map *map,
+				     u16 type, int max)
 {
 	data->type = type;
 
 	switch (type) {
 	case PERF_CPU_MAP__CPUS:
-		synthesize_cpus((struct cpu_map_entries *) data->data, map);
+		synthesize_cpus(data, map);
 		break;
 	case PERF_CPU_MAP__MASK:
-		synthesize_mask((struct perf_record_record_cpu_map *)data->data, map, max);
+		synthesize_mask(data, map, max);
 	default:
 		break;
 	}
 }
 
-static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map)
+static struct perf_record_cpu_map *cpu_map_event__new(const struct perf_cpu_map *map)
 {
-	size_t size = sizeof(struct perf_record_cpu_map);
+	size_t size = sizeof(struct perf_event_header);
 	struct perf_record_cpu_map *event;
 	int max;
 	u16 type;
@@ -1299,7 +1307,7 @@ static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map)
 }
 
 int perf_event__synthesize_cpu_map(struct perf_tool *tool,
-				   struct perf_cpu_map *map,
+				   const struct perf_cpu_map *map,
 				   perf_event__handler_t process,
 				   struct machine *machine)
 {
@@ -1432,11 +1440,12 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 			result += sizeof(u64);
 		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
 		if (read_format & PERF_FORMAT_GROUP) {
-			sz = sample->read.group.nr *
-			     sizeof(struct sample_read_value);
-			result += sz;
+			sz = sample_read_value_size(read_format);
+			result += sz * sample->read.group.nr;
 		} else {
 			result += sizeof(u64);
+			if (read_format & PERF_FORMAT_LOST)
+				result += sizeof(u64);
 		}
 	}
 
@@ -1521,6 +1530,20 @@ void __weak arch_perf_synthesize_sample_weight(const struct perf_sample *data,
 	*array = data->weight;
 }
 
+static __u64 *copy_read_group_values(__u64 *array, __u64 read_format,
+				     const struct perf_sample *sample)
+{
+	size_t sz = sample_read_value_size(read_format);
+	struct sample_read_value *v = sample->read.group.values;
+
+	sample_read_group__for_each(v, sample->read.group.nr, read_format) {
+		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+		memcpy(array, v, sz);
+		array = (void *)array + sz;
+	}
+	return array;
+}
+
 int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format,
 				  const struct perf_sample *sample)
 {
@@ -1602,13 +1625,16 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
 
 		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
 		if (read_format & PERF_FORMAT_GROUP) {
-			sz = sample->read.group.nr *
-			     sizeof(struct sample_read_value);
-			memcpy(array, sample->read.group.values, sz);
-			array = (void *)array + sz;
+			array = copy_read_group_values(array, read_format,
+						       sample);
 		} else {
 			*array = sample->read.one.id;
 			array++;
+
+			if (read_format & PERF_FORMAT_LOST) {
+				*array = sample->read.one.lost;
+				array++;
+			}
 		}
 	}
 
diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h
index 81cb3d6af0b9..53737d1619a4 100644
--- a/tools/perf/util/synthetic-events.h
+++ b/tools/perf/util/synthetic-events.h
@@ -46,7 +46,7 @@ typedef int (*perf_event__handler_t)(struct perf_tool *tool, union perf_event *e
 int perf_event__synthesize_attrs(struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process);
 int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process);
 int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16 misc, perf_event__handler_t process, struct machine *machine);
-int perf_event__synthesize_cpu_map(struct perf_tool *tool, struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_cpu_map(struct perf_tool *tool, const struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
 int perf_event__synthesize_event_update_name(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
 int perf_event__synthesize_event_update_scale(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
diff --git a/tools/power/acpi/tools/pfrut/pfrut.c b/tools/power/acpi/tools/pfrut/pfrut.c
index d79c335594b2..52aa0351533c 100644
--- a/tools/power/acpi/tools/pfrut/pfrut.c
+++ b/tools/power/acpi/tools/pfrut/pfrut.c
@@ -190,7 +190,7 @@ int main(int argc, char *argv[])
 	void *addr_map_capsule;
 	struct stat st;
 	char *log_buf;
-	int ret = 0;
+	int ret;
 
 	if (getuid() != 0) {
 		printf("Please run the tool as root - Exiting.\n");
diff --git a/tools/testing/nvdimm/test/ndtest.c b/tools/testing/nvdimm/test/ndtest.c
index 4d1a947367f9..01ceb98c15a0 100644
--- a/tools/testing/nvdimm/test/ndtest.c
+++ b/tools/testing/nvdimm/test/ndtest.c
@@ -134,39 +134,6 @@ static struct ndtest_mapping region1_mapping[] = {
 	},
 };
 
-static struct ndtest_mapping region2_mapping[] = {
-	{
-		.dimm = 0,
-		.position = 0,
-		.start = 0,
-		.size = DIMM_SIZE,
-	},
-};
-
-static struct ndtest_mapping region3_mapping[] = {
-	{
-		.dimm = 1,
-		.start = 0,
-		.size = DIMM_SIZE,
-	}
-};
-
-static struct ndtest_mapping region4_mapping[] = {
-	{
-		.dimm = 2,
-		.start = 0,
-		.size = DIMM_SIZE,
-	}
-};
-
-static struct ndtest_mapping region5_mapping[] = {
-	{
-		.dimm = 3,
-		.start = 0,
-		.size = DIMM_SIZE,
-	}
-};
-
 static struct ndtest_region bus0_regions[] = {
 	{
 		.type = ND_DEVICE_NAMESPACE_PMEM,
@@ -182,34 +149,6 @@ static struct ndtest_region bus0_regions[] = {
 		.size = DIMM_SIZE * 2,
 		.range_index = 2,
 	},
-	{
-		.type = ND_DEVICE_NAMESPACE_BLK,
-		.num_mappings = ARRAY_SIZE(region2_mapping),
-		.mapping = region2_mapping,
-		.size = DIMM_SIZE,
-		.range_index = 3,
-	},
-	{
-		.type = ND_DEVICE_NAMESPACE_BLK,
-		.num_mappings = ARRAY_SIZE(region3_mapping),
-		.mapping = region3_mapping,
-		.size = DIMM_SIZE,
-		.range_index = 4,
-	},
-	{
-		.type = ND_DEVICE_NAMESPACE_BLK,
-		.num_mappings = ARRAY_SIZE(region4_mapping),
-		.mapping = region4_mapping,
-		.size = DIMM_SIZE,
-		.range_index = 5,
-	},
-	{
-		.type = ND_DEVICE_NAMESPACE_BLK,
-		.num_mappings = ARRAY_SIZE(region5_mapping),
-		.mapping = region5_mapping,
-		.size = DIMM_SIZE,
-		.range_index = 6,
-	},
 };
 
 static struct ndtest_mapping region6_mapping[] = {
@@ -501,21 +440,6 @@ static int ndtest_create_region(struct ndtest_priv *p,
 	nd_set->altcookie = nd_set->cookie1;
 	ndr_desc->nd_set = nd_set;
 
-	if (region->type == ND_DEVICE_NAMESPACE_BLK) {
-		mappings[0].start = 0;
-		mappings[0].size = DIMM_SIZE;
-		mappings[0].nvdimm = p->config->dimms[ndimm].nvdimm;
-
-		ndr_desc->mapping = &mappings[0];
-		ndr_desc->num_mappings = 1;
-		ndr_desc->num_lanes = 1;
-		ndbr_desc.enable = ndtest_blk_region_enable;
-		ndbr_desc.do_io = ndtest_blk_do_io;
-		region->region = nvdimm_blk_region_create(p->bus, ndr_desc);
-
-		goto done;
-	}
-
 	for (i = 0; i < region->num_mappings; i++) {
 		ndimm = region->mapping[i].dimm;
 		mappings[i].start = region->mapping[i].start;
@@ -527,7 +451,6 @@ static int ndtest_create_region(struct ndtest_priv *p,
 	ndr_desc->num_mappings = region->num_mappings;
 	region->region = nvdimm_pmem_region_create(p->bus, ndr_desc);
 
-done:
 	if (!region->region) {
 		dev_err(&p->pdev.dev, "Error registering region %pR\n",
 			ndr_desc->res);
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 10b34bb03bc1..1fc89b8ef433 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -12,6 +12,8 @@ TARGETS += cpu-hotplug
 TARGETS += damon
 TARGETS += drivers/dma-buf
 TARGETS += drivers/s390x/uvdevice
+TARGETS += drivers/net/bonding
+TARGETS += drivers/net/team
 TARGETS += efivarfs
 TARGETS += exec
 TARGETS += filesystems
diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x
index e33cab34d22f..db9810611788 100644
--- a/tools/testing/selftests/bpf/DENYLIST.s390x
+++ b/tools/testing/selftests/bpf/DENYLIST.s390x
@@ -65,3 +65,4 @@ send_signal                              # intermittently fails to receive signa
 select_reuseport                         # intermittently fails on new s390x setup
 xdp_synproxy                             # JIT does not support calling kernel function                                (kfunc)
 unpriv_bpf_disabled                      # fentry
+lru_bug                                  # prog 'printk': failed to auto-attach: -524
diff --git a/tools/testing/selftests/bpf/prog_tests/deny_namespace.c b/tools/testing/selftests/bpf/prog_tests/deny_namespace.c
new file mode 100644
index 000000000000..1bc6241b755b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/deny_namespace.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <test_progs.h>
+#include "test_deny_namespace.skel.h"
+#include <sched.h>
+#include "cap_helpers.h"
+#include <stdio.h>
+
+static int wait_for_pid(pid_t pid)
+{
+	int status, ret;
+
+again:
+	ret = waitpid(pid, &status, 0);
+	if (ret == -1) {
+		if (errno == EINTR)
+			goto again;
+
+		return -1;
+	}
+
+	if (!WIFEXITED(status))
+		return -1;
+
+	return WEXITSTATUS(status);
+}
+
+/* negative return value -> some internal error
+ * positive return value -> userns creation failed
+ * 0                     -> userns creation succeeded
+ */
+static int create_user_ns(void)
+{
+	pid_t pid;
+
+	pid = fork();
+	if (pid < 0)
+		return -1;
+
+	if (pid == 0) {
+		if (unshare(CLONE_NEWUSER))
+			_exit(EXIT_FAILURE);
+		_exit(EXIT_SUCCESS);
+	}
+
+	return wait_for_pid(pid);
+}
+
+static void test_userns_create_bpf(void)
+{
+	__u32 cap_mask = 1ULL << CAP_SYS_ADMIN;
+	__u64 old_caps = 0;
+
+	cap_enable_effective(cap_mask, &old_caps);
+
+	ASSERT_OK(create_user_ns(), "priv new user ns");
+
+	cap_disable_effective(cap_mask, &old_caps);
+
+	ASSERT_EQ(create_user_ns(), EPERM, "unpriv new user ns");
+
+	if (cap_mask & old_caps)
+		cap_enable_effective(cap_mask, NULL);
+}
+
+static void test_unpriv_userns_create_no_bpf(void)
+{
+	__u32 cap_mask = 1ULL << CAP_SYS_ADMIN;
+	__u64 old_caps = 0;
+
+	cap_disable_effective(cap_mask, &old_caps);
+
+	ASSERT_OK(create_user_ns(), "no-bpf unpriv new user ns");
+
+	if (cap_mask & old_caps)
+		cap_enable_effective(cap_mask, NULL);
+}
+
+void test_deny_namespace(void)
+{
+	struct test_deny_namespace *skel = NULL;
+	int err;
+
+	if (test__start_subtest("unpriv_userns_create_no_bpf"))
+		test_unpriv_userns_create_no_bpf();
+
+	skel = test_deny_namespace__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel load"))
+		goto close_prog;
+
+	err = test_deny_namespace__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto close_prog;
+
+	if (test__start_subtest("userns_create_bpf"))
+		test_userns_create_bpf();
+
+	test_deny_namespace__detach(skel);
+
+close_prog:
+	test_deny_namespace__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_deny_namespace.c b/tools/testing/selftests/bpf/progs/test_deny_namespace.c
new file mode 100644
index 000000000000..09ad5a4ebd1f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_deny_namespace.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <errno.h>
+#include <linux/capability.h>
+
+struct kernel_cap_struct {
+	__u32 cap[_LINUX_CAPABILITY_U32S_3];
+} __attribute__((preserve_access_index));
+
+struct cred {
+	struct kernel_cap_struct cap_effective;
+} __attribute__((preserve_access_index));
+
+char _license[] SEC("license") = "GPL";
+
+SEC("lsm.s/userns_create")
+int BPF_PROG(test_userns_create, const struct cred *cred, int ret)
+{
+	struct kernel_cap_struct caps = cred->cap_effective;
+	int cap_index = CAP_TO_INDEX(CAP_SYS_ADMIN);
+	__u32 cap_mask = CAP_TO_MASK(CAP_SYS_ADMIN);
+
+	if (ret)
+		return 0;
+
+	ret = -EPERM;
+	if (caps.cap[cap_index] & cap_mask)
+		return 0;
+
+	return -EPERM;
+}
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 9e754423fa8b..6c03a7d805f9 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -192,3 +192,28 @@
 	.result = VERBOSE_ACCEPT,
 	.retval = -1,
 },
+{
+	"precise: mark_chain_precision for ARG_CONST_ALLOC_SIZE_OR_ZERO",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, offsetof(struct xdp_md, ingress_ifindex)),
+	BPF_LD_MAP_FD(BPF_REG_6, 0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_MOV64_IMM(BPF_REG_2, 1),
+	BPF_MOV64_IMM(BPF_REG_3, 0),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 0, 1),
+	BPF_MOV64_IMM(BPF_REG_2, 0x1000),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 42),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_ringbuf = { 1 },
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = BPF_F_TEST_STATE_FREQ,
+	.errstr = "invalid access to memory, mem_size=1 off=42 size=8",
+	.result = REJECT,
+},
diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile
new file mode 100644
index 000000000000..1d866658e541
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for net selftests
+
+TEST_PROGS := bond-break-lacpdu-tx.sh \
+	      dev_addr_lists.sh \
+	      bond-arp-interval-causes-panic.sh
+
+TEST_FILES := lag_lib.sh
+
+include ../../../lib.mk
diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh
new file mode 100755
index 000000000000..71c00bfafbc9
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh
@@ -0,0 +1,49 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# cause kernel oops in bond_rr_gen_slave_id
+DEBUG=${DEBUG:-0}
+
+set -e
+test ${DEBUG} -ne 0 && set -x
+
+finish()
+{
+	ip netns delete server || true
+	ip netns delete client || true
+	ip link del link1_1 || true
+}
+
+trap finish EXIT
+
+client_ip4=192.168.1.198
+server_ip4=192.168.1.254
+
+# setup kernel so it reboots after causing the panic
+echo 180 >/proc/sys/kernel/panic
+
+# build namespaces
+ip link add dev link1_1 type veth peer name link1_2
+
+ip netns add "server"
+ip link set dev link1_2 netns server up name eth0
+ip netns exec server ip addr add ${server_ip4}/24 dev eth0
+
+ip netns add "client"
+ip link set dev link1_1 netns client down name eth0
+ip netns exec client ip link add dev bond0 down type bond mode 1 \
+	miimon 100 all_slaves_active 1
+ip netns exec client ip link set dev eth0 down master bond0
+ip netns exec client ip link set dev bond0 up
+ip netns exec client ip addr add ${client_ip4}/24 dev bond0
+ip netns exec client ping -c 5 $server_ip4 >/dev/null
+
+ip netns exec client ip link set dev eth0 down nomaster
+ip netns exec client ip link set dev bond0 down
+ip netns exec client ip link set dev bond0 type bond mode 0 \
+	arp_interval 1000 arp_ip_target "+${server_ip4}"
+ip netns exec client ip link set dev eth0 down master bond0
+ip netns exec client ip link set dev bond0 up
+ip netns exec client ping -c 5 $server_ip4 >/dev/null
+
+exit 0
diff --git a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh
new file mode 100755
index 000000000000..47ab90596acb
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh
@@ -0,0 +1,81 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+# Regression Test:
+#   Verify LACPDUs get transmitted after setting the MAC address of
+#   the bond.
+#
+# https://bugzilla.redhat.com/show_bug.cgi?id=2020773
+#
+#       +---------+
+#       | fab-br0 |
+#       +---------+
+#            |
+#       +---------+
+#       |  fbond  |
+#       +---------+
+#        |       |
+#    +------+ +------+
+#    |veth1 | |veth2 |
+#    +------+ +------+
+#
+# We use veths instead of physical interfaces
+
+set -e
+tmp=$(mktemp -q dump.XXXXXX)
+cleanup() {
+	ip link del fab-br0 >/dev/null 2>&1 || :
+	ip link del fbond  >/dev/null 2>&1 || :
+	ip link del veth1-bond  >/dev/null 2>&1 || :
+	ip link del veth2-bond  >/dev/null 2>&1 || :
+	modprobe -r bonding  >/dev/null 2>&1 || :
+	rm -f -- ${tmp}
+}
+
+trap cleanup 0 1 2
+cleanup
+sleep 1
+
+# create the bridge
+ip link add fab-br0 address 52:54:00:3B:7C:A6 mtu 1500 type bridge \
+	forward_delay 15
+
+# create the bond
+ip link add fbond type bond mode 4 miimon 200 xmit_hash_policy 1 \
+	ad_actor_sys_prio 65535 lacp_rate fast
+
+# set bond address
+ip link set fbond address 52:54:00:3B:7C:A6
+ip link set fbond up
+
+# set again bond sysfs parameters
+ip link set fbond type bond ad_actor_sys_prio 65535
+
+# create veths
+ip link add name veth1-bond type veth peer name veth1-end
+ip link add name veth2-bond type veth peer name veth2-end
+
+# add ports
+ip link set fbond master fab-br0
+ip link set veth1-bond down master fbond
+ip link set veth2-bond down master fbond
+
+# bring up
+ip link set veth1-end up
+ip link set veth2-end up
+ip link set fab-br0 up
+ip link set fbond up
+ip addr add dev fab-br0 10.0.0.3
+
+tcpdump -n -i veth1-end -e ether proto 0x8809 >${tmp} 2>&1 &
+sleep 15
+pkill tcpdump >/dev/null 2>&1
+rc=0
+num=$(grep "packets captured" ${tmp} | awk '{print $1}')
+if test "$num" -gt 0; then
+	echo "PASS, captured ${num}"
+else
+	echo "FAIL"
+	rc=1
+fi
+exit $rc
diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config
new file mode 100644
index 000000000000..70638fa50b2c
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/config
@@ -0,0 +1,2 @@
+CONFIG_BONDING=y
+CONFIG_MACVLAN=y
diff --git a/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh b/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh
new file mode 100755
index 000000000000..e6fa24eded5b
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh
@@ -0,0 +1,109 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test bond device handling of addr lists (dev->uc, mc)
+#
+
+ALL_TESTS="
+	bond_cleanup_mode1
+	bond_cleanup_mode4
+	bond_listen_lacpdu_multicast_case_down
+	bond_listen_lacpdu_multicast_case_up
+"
+
+REQUIRE_MZ=no
+NUM_NETIFS=0
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+
+source "$lib_dir"/lag_lib.sh
+
+
+destroy()
+{
+	local ifnames=(dummy1 dummy2 bond1 mv0)
+	local ifname
+
+	for ifname in "${ifnames[@]}"; do
+		ip link del "$ifname" &>/dev/null
+	done
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	destroy
+}
+
+
+# bond driver control paths vary between modes that have a primary slave
+# (bond_uses_primary()) and others. Test both kinds of modes.
+
+bond_cleanup_mode1()
+{
+	RET=0
+
+	test_LAG_cleanup "bonding" "active-backup"
+}
+
+bond_cleanup_mode4() {
+	RET=0
+
+	test_LAG_cleanup "bonding" "802.3ad"
+}
+
+bond_listen_lacpdu_multicast()
+{
+	# Initial state of bond device, up | down
+	local init_state=$1
+	local lacpdu_mc="01:80:c2:00:00:02"
+
+	ip link add dummy1 type dummy
+	ip link add bond1 "$init_state" type bond mode 802.3ad
+	ip link set dev dummy1 master bond1
+	if [ "$init_state" = "down" ]; then
+		ip link set dev bond1 up
+	fi
+
+	grep_bridge_fdb "$lacpdu_mc" bridge fdb show brport dummy1 >/dev/null
+	check_err $? "LACPDU multicast address not present on slave (1)"
+
+	ip link set dev bond1 down
+
+	not grep_bridge_fdb "$lacpdu_mc" bridge fdb show brport dummy1 >/dev/null
+	check_err $? "LACPDU multicast address still present on slave"
+
+	ip link set dev bond1 up
+
+	grep_bridge_fdb "$lacpdu_mc" bridge fdb show brport dummy1 >/dev/null
+	check_err $? "LACPDU multicast address not present on slave (2)"
+
+	cleanup
+
+	log_test "bonding LACPDU multicast address to slave (from bond $init_state)"
+}
+
+# The LACPDU mc addr is added by different paths depending on the initial state
+# of the bond when enslaving a device. Test both cases.
+
+bond_listen_lacpdu_multicast_case_down()
+{
+	RET=0
+
+	bond_listen_lacpdu_multicast "down"
+}
+
+bond_listen_lacpdu_multicast_case_up()
+{
+	RET=0
+
+	bond_listen_lacpdu_multicast "up"
+}
+
+
+trap cleanup EXIT
+
+tests_run
+
+exit "$EXIT_STATUS"
diff --git a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
new file mode 100644
index 000000000000..16c7fb858ac1
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
@@ -0,0 +1,61 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test that a link aggregation device (bonding, team) removes the hardware
+# addresses that it adds on its underlying devices.
+test_LAG_cleanup()
+{
+	local driver=$1
+	local mode=$2
+	local ucaddr="02:00:00:12:34:56"
+	local addr6="fe80::78:9abc/64"
+	local mcaddr="33:33:ff:78:9a:bc"
+	local name
+
+	ip link add dummy1 type dummy
+	ip link add dummy2 type dummy
+	if [ "$driver" = "bonding" ]; then
+		name="bond1"
+		ip link add "$name" up type bond mode "$mode"
+		ip link set dev dummy1 master "$name"
+		ip link set dev dummy2 master "$name"
+	elif [ "$driver" = "team" ]; then
+		name="team0"
+		teamd -d -c '
+			{
+				"device": "'"$name"'",
+				"runner": {
+					"name": "'"$mode"'"
+				},
+				"ports": {
+					"dummy1":
+						{},
+					"dummy2":
+						{}
+				}
+			}
+		'
+		ip link set dev "$name" up
+	else
+		check_err 1
+		log_test test_LAG_cleanup ": unknown driver \"$driver\""
+		return
+	fi
+
+	# Used to test dev->uc handling
+	ip link add mv0 link "$name" up address "$ucaddr" type macvlan
+	# Used to test dev->mc handling
+	ip address add "$addr6" dev "$name"
+	ip link set dev "$name" down
+	ip link del "$name"
+
+	not grep_bridge_fdb "$ucaddr" bridge fdb show >/dev/null
+	check_err $? "macvlan unicast address still present on a slave"
+
+	not grep_bridge_fdb "$mcaddr" bridge fdb show >/dev/null
+	check_err $? "IPv6 solicited-node multicast mac address still present on a slave"
+
+	cleanup
+
+	log_test "$driver cleanup mode $mode"
+}
diff --git a/tools/testing/selftests/drivers/net/bonding/settings b/tools/testing/selftests/drivers/net/bonding/settings
new file mode 100644
index 000000000000..867e118223cd
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/settings
@@ -0,0 +1 @@
+timeout=60
diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile
new file mode 100644
index 000000000000..642d8df1c137
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/team/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for net selftests
+
+TEST_PROGS := dev_addr_lists.sh
+
+include ../../../lib.mk
diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config
new file mode 100644
index 000000000000..265b6882cc21
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/team/config
@@ -0,0 +1,3 @@
+CONFIG_NET_TEAM=y
+CONFIG_NET_TEAM_MODE_LOADBALANCE=y
+CONFIG_MACVLAN=y
diff --git a/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh b/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh
new file mode 100755
index 000000000000..debda7262956
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh
@@ -0,0 +1,51 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test team device handling of addr lists (dev->uc, mc)
+#
+
+ALL_TESTS="
+	team_cleanup
+"
+
+REQUIRE_MZ=no
+NUM_NETIFS=0
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+
+source "$lib_dir"/../bonding/lag_lib.sh
+
+
+destroy()
+{
+	local ifnames=(dummy0 dummy1 team0 mv0)
+	local ifname
+
+	for ifname in "${ifnames[@]}"; do
+		ip link del "$ifname" &>/dev/null
+	done
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	destroy
+}
+
+
+team_cleanup()
+{
+	RET=0
+
+	test_LAG_cleanup "team" "lacp"
+}
+
+
+require_command teamd
+
+trap cleanup EXIT
+
+tests_run
+
+exit "$EXIT_STATUS"
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 4c122f1b1737..6448cb9f710f 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -48,6 +48,8 @@ LIBKVM += lib/rbtree.c
 LIBKVM += lib/sparsebit.c
 LIBKVM += lib/test_util.c
 
+LIBKVM_STRING += lib/string_override.c
+
 LIBKVM_x86_64 += lib/x86_64/apic.c
 LIBKVM_x86_64 += lib/x86_64/handlers.S
 LIBKVM_x86_64 += lib/x86_64/perf_test_util.c
@@ -220,7 +222,8 @@ LIBKVM_C := $(filter %.c,$(LIBKVM))
 LIBKVM_S := $(filter %.S,$(LIBKVM))
 LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
 LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
-LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)
+LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING))
+LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ)
 
 EXTRA_CLEAN += $(LIBKVM_OBJS) cscope.*
 
@@ -231,6 +234,12 @@ $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
 $(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
+# Compile the string overrides as freestanding to prevent the compiler from
+# generating self-referential code, e.g. without "freestanding" the compiler may
+# "optimize" memcmp() by invoking memcmp(), thus causing infinite recursion.
+$(LIBKVM_STRING_OBJ): $(OUTPUT)/%.o: %.c
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c -ffreestanding $< -o $@
+
 x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
 $(TEST_GEN_PROGS): $(LIBKVM_OBJS)
 $(TEST_GEN_PROGS_EXTENDED): $(LIBKVM_OBJS)
diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index 1c2749b1481a..76c583a07ea2 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -31,8 +31,9 @@
  * These limitations are worked around in this test by using a large enough
  * region of memory for each vCPU such that the number of translations cached in
  * the TLB and the number of pages held in pagevecs are a small fraction of the
- * overall workload. And if either of those conditions are not true this test
- * will fail rather than silently passing.
+ * overall workload. And if either of those conditions are not true (for example
+ * in nesting, where TLB size is unlimited) this test will print a warning
+ * rather than silently passing.
  */
 #include <inttypes.h>
 #include <limits.h>
@@ -172,17 +173,23 @@ static void mark_vcpu_memory_idle(struct kvm_vm *vm,
 		    vcpu_idx, no_pfn, pages);
 
 	/*
-	 * Test that at least 90% of memory has been marked idle (the rest might
-	 * not be marked idle because the pages have not yet made it to an LRU
-	 * list or the translations are still cached in the TLB). 90% is
+	 * Check that at least 90% of memory has been marked idle (the rest
+	 * might not be marked idle because the pages have not yet made it to an
+	 * LRU list or the translations are still cached in the TLB). 90% is
 	 * arbitrary; high enough that we ensure most memory access went through
 	 * access tracking but low enough as to not make the test too brittle
 	 * over time and across architectures.
+	 *
+	 * Note that when run in nested virtualization, this check will trigger
+	 * much more frequently because TLB size is unlimited and since no flush
+	 * happens, much more pages are cached there and guest won't see the
+	 * "idle" bit cleared.
 	 */
-	TEST_ASSERT(still_idle < pages / 10,
-		    "vCPU%d: Too many pages still idle (%"PRIu64 " out of %"
-		    PRIu64 ").\n",
-		    vcpu_idx, still_idle, pages);
+	if (still_idle < pages / 10)
+		printf("WARNING: vCPU%d: Too many pages still idle (%" PRIu64
+		       "out of %" PRIu64 "), this will affect performance results"
+		       ".\n",
+		       vcpu_idx, still_idle, pages);
 
 	close(page_idle_fd);
 	close(pagemap_fd);
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 45edf45821d0..0cbc71b7af50 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -754,7 +754,7 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector,
 			void (*handler)(struct ex_regs *));
 
 /* If a toddler were to say "abracadabra". */
-#define KVM_EXCEPTION_MAGIC 0xabacadabaull
+#define KVM_EXCEPTION_MAGIC 0xabacadabaULL
 
 /*
  * KVM selftest exception fixup uses registers to coordinate with the exception
@@ -786,7 +786,7 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector,
 	"lea 1f(%%rip), %%r10\n\t"				\
 	"lea 2f(%%rip), %%r11\n\t"				\
 	"1: " insn "\n\t"					\
-	"mov $0, %[vector]\n\t"					\
+	"movb $0, %[vector]\n\t"				\
 	"jmp 3f\n\t"						\
 	"2:\n\t"						\
 	"mov  %%r9b, %[vector]\n\t"				\
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 99fa1410964c..790c6d1ecb34 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -617,6 +617,7 @@ void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
 			uint32_t memslot);
 void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm,
 			    uint64_t addr, uint64_t size);
+bool kvm_vm_has_ept(struct kvm_vm *vm);
 void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
 		  uint32_t eptp_memslot);
 void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm);
diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c
index 71ade6100fd3..2bd25b191d15 100644
--- a/tools/testing/selftests/kvm/lib/assert.c
+++ b/tools/testing/selftests/kvm/lib/assert.c
@@ -22,7 +22,7 @@ static void test_dump_stack(void)
 	 * Build and run this command:
 	 *
 	 *	addr2line -s -e /proc/$PPID/exe -fpai {backtrace addresses} | \
-	 *		grep -v test_dump_stack | cat -n 1>&2
+	 *		cat -n 1>&2
 	 *
 	 * Note that the spacing is different and there's no newline.
 	 */
@@ -36,18 +36,24 @@ static void test_dump_stack(void)
 		 n * (((sizeof(void *)) * 2) + 1) +
 		 /* Null terminator: */
 		 1];
-	char *c;
+	char *c = cmd;
 
 	n = backtrace(stack, n);
-	c = &cmd[0];
-	c += sprintf(c, "%s", addr2line);
 	/*
-	 * Skip the first 3 frames: backtrace, test_dump_stack, and
-	 * test_assert. We hope that backtrace isn't inlined and the other two
-	 * we've declared noinline.
+	 * Skip the first 2 frames, which should be test_dump_stack() and
+	 * test_assert(); both of which are declared noinline.  Bail if the
+	 * resulting stack trace would be empty. Otherwise, addr2line will block
+	 * waiting for addresses to be passed in via stdin.
 	 */
+	if (n <= 2) {
+		fputs("  (stack trace empty)\n", stderr);
+		return;
+	}
+
+	c += sprintf(c, "%s", addr2line);
 	for (i = 2; i < n; i++)
 		c += sprintf(c, " %lx", ((unsigned long) stack[i]) - 1);
+
 	c += sprintf(c, "%s", pipeline);
 #pragma GCC diagnostic push
 #pragma GCC diagnostic ignored "-Wunused-result"
diff --git a/tools/testing/selftests/kvm/lib/string_override.c b/tools/testing/selftests/kvm/lib/string_override.c
new file mode 100644
index 000000000000..632398adc229
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/string_override.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <stddef.h>
+
+/*
+ * Override the "basic" built-in string helpers so that they can be used in
+ * guest code.  KVM selftests don't support dynamic loading in guest code and
+ * will jump into the weeds if the compiler decides to insert an out-of-line
+ * call via the PLT.
+ */
+int memcmp(const void *cs, const void *ct, size_t count)
+{
+	const unsigned char *su1, *su2;
+	int res = 0;
+
+	for (su1 = cs, su2 = ct; 0 < count; ++su1, ++su2, count--) {
+		if ((res = *su1 - *su2) != 0)
+			break;
+	}
+	return res;
+}
+
+void *memcpy(void *dest, const void *src, size_t count)
+{
+	char *tmp = dest;
+	const char *s = src;
+
+	while (count--)
+		*tmp++ = *s++;
+	return dest;
+}
+
+void *memset(void *s, int c, size_t count)
+{
+	char *xs = s;
+
+	while (count--)
+		*xs++ = c;
+	return s;
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index 80a568c439b8..d21049c38fc5 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -5,6 +5,8 @@
  * Copyright (C) 2018, Google LLC.
  */
 
+#include <asm/msr-index.h>
+
 #include "test_util.h"
 #include "kvm_util.h"
 #include "processor.h"
@@ -542,9 +544,27 @@ void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm,
 	__nested_map(vmx, vm, addr, addr, size, PG_LEVEL_1G);
 }
 
+bool kvm_vm_has_ept(struct kvm_vm *vm)
+{
+	struct kvm_vcpu *vcpu;
+	uint64_t ctrl;
+
+	vcpu = list_first_entry(&vm->vcpus, struct kvm_vcpu, list);
+	TEST_ASSERT(vcpu, "Cannot determine EPT support without vCPUs.\n");
+
+	ctrl = vcpu_get_msr(vcpu, MSR_IA32_VMX_TRUE_PROCBASED_CTLS) >> 32;
+	if (!(ctrl & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
+		return false;
+
+	ctrl = vcpu_get_msr(vcpu, MSR_IA32_VMX_PROCBASED_CTLS2) >> 32;
+	return ctrl & SECONDARY_EXEC_ENABLE_EPT;
+}
+
 void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
 		  uint32_t eptp_memslot)
 {
+	TEST_REQUIRE(kvm_vm_has_ept(vm));
+
 	vmx->eptp = (void *)vm_vaddr_alloc_page(vm);
 	vmx->eptp_hva = addr_gva2hva(vm, (uintptr_t)vmx->eptp);
 	vmx->eptp_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->eptp);
diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c
index fac248a43666..6f88da7e60be 100644
--- a/tools/testing/selftests/kvm/rseq_test.c
+++ b/tools/testing/selftests/kvm/rseq_test.c
@@ -227,7 +227,7 @@ int main(int argc, char *argv[])
 	ucall_init(vm, NULL);
 
 	pthread_create(&migration_thread, NULL, migration_worker,
-		       (void *)(unsigned long)gettid());
+		       (void *)(unsigned long)syscall(SYS_gettid));
 
 	for (i = 0; !done; i++) {
 		vcpu_run(vcpu);
diff --git a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c
index b1905d280ef5..e0004bd26536 100644
--- a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c
+++ b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c
@@ -14,6 +14,9 @@
 #include "kvm_util.h"
 #include "processor.h"
 
+/* VMCALL and VMMCALL are both 3-byte opcodes. */
+#define HYPERCALL_INSN_SIZE	3
+
 static bool ud_expected;
 
 static void guest_ud_handler(struct ex_regs *regs)
@@ -22,7 +25,7 @@ static void guest_ud_handler(struct ex_regs *regs)
 	GUEST_DONE();
 }
 
-extern unsigned char svm_hypercall_insn;
+extern uint8_t svm_hypercall_insn[HYPERCALL_INSN_SIZE];
 static uint64_t svm_do_sched_yield(uint8_t apic_id)
 {
 	uint64_t ret;
@@ -39,7 +42,7 @@ static uint64_t svm_do_sched_yield(uint8_t apic_id)
 	return ret;
 }
 
-extern unsigned char vmx_hypercall_insn;
+extern uint8_t vmx_hypercall_insn[HYPERCALL_INSN_SIZE];
 static uint64_t vmx_do_sched_yield(uint8_t apic_id)
 {
 	uint64_t ret;
@@ -56,30 +59,20 @@ static uint64_t vmx_do_sched_yield(uint8_t apic_id)
 	return ret;
 }
 
-static void assert_hypercall_insn(unsigned char *exp_insn, unsigned char *obs_insn)
-{
-	uint32_t exp = 0, obs = 0;
-
-	memcpy(&exp, exp_insn, sizeof(exp));
-	memcpy(&obs, obs_insn, sizeof(obs));
-
-	GUEST_ASSERT_EQ(exp, obs);
-}
-
 static void guest_main(void)
 {
-	unsigned char *native_hypercall_insn, *hypercall_insn;
+	uint8_t *native_hypercall_insn, *hypercall_insn;
 	uint8_t apic_id;
 
 	apic_id = GET_APIC_ID_FIELD(xapic_read_reg(APIC_ID));
 
 	if (is_intel_cpu()) {
-		native_hypercall_insn = &vmx_hypercall_insn;
-		hypercall_insn = &svm_hypercall_insn;
+		native_hypercall_insn = vmx_hypercall_insn;
+		hypercall_insn = svm_hypercall_insn;
 		svm_do_sched_yield(apic_id);
 	} else if (is_amd_cpu()) {
-		native_hypercall_insn = &svm_hypercall_insn;
-		hypercall_insn = &vmx_hypercall_insn;
+		native_hypercall_insn = svm_hypercall_insn;
+		hypercall_insn = vmx_hypercall_insn;
 		vmx_do_sched_yield(apic_id);
 	} else {
 		GUEST_ASSERT(0);
@@ -87,8 +80,13 @@ static void guest_main(void)
 		return;
 	}
 
+	/*
+	 * The hypercall didn't #UD (guest_ud_handler() signals "done" if a #UD
+	 * occurs).  Verify that a #UD is NOT expected and that KVM patched in
+	 * the native hypercall.
+	 */
 	GUEST_ASSERT(!ud_expected);
-	assert_hypercall_insn(native_hypercall_insn, hypercall_insn);
+	GUEST_ASSERT(!memcmp(native_hypercall_insn, hypercall_insn, HYPERCALL_INSN_SIZE));
 	GUEST_DONE();
 }
 
diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile
index a6959df28eb0..6632bfff486b 100644
--- a/tools/testing/selftests/landlock/Makefile
+++ b/tools/testing/selftests/landlock/Makefile
@@ -1,6 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
+#
+# First run: make -C ../../../.. headers_install
 
 CFLAGS += -Wall -O2 $(KHDR_INCLUDES)
+LDLIBS += -lcap
+
+LOCAL_HDRS += common.h
 
 src_test := $(wildcard *_test.c)
 
@@ -8,11 +13,10 @@ TEST_GEN_PROGS := $(src_test:.c=)
 
 TEST_GEN_PROGS_EXTENDED := true
 
-OVERRIDE_TARGETS := 1
-include ../lib.mk
+# Static linking for short targets:
+$(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static
 
-$(OUTPUT)/true: true.c
-	$(LINK.c) $< $(LDLIBS) -o $@ -static
+include ../lib.mk
 
-$(OUTPUT)/%_test: %_test.c ../kselftest_harness.h common.h
-	$(LINK.c) $< $(LDLIBS) -o $@ -lcap
+# Static linking for targets with $(OUTPUT)/ prefix:
+$(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static
diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
index 21a2ce8fa739..45de42a027c5 100644
--- a/tools/testing/selftests/landlock/fs_test.c
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -4,7 +4,7 @@
  *
  * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
  * Copyright © 2020 ANSSI
- * Copyright © 2020-2021 Microsoft Corporation
+ * Copyright © 2020-2022 Microsoft Corporation
  */
 
 #define _GNU_SOURCE
@@ -371,6 +371,13 @@ TEST_F_FORK(layout1, inval)
 	ASSERT_EQ(EINVAL, errno);
 	path_beneath.allowed_access &= ~LANDLOCK_ACCESS_FS_EXECUTE;
 
+	/* Tests with denied-by-default access right. */
+	path_beneath.allowed_access |= LANDLOCK_ACCESS_FS_REFER;
+	ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+					&path_beneath, 0));
+	ASSERT_EQ(EINVAL, errno);
+	path_beneath.allowed_access &= ~LANDLOCK_ACCESS_FS_REFER;
+
 	/* Test with unknown (64-bits) value. */
 	path_beneath.allowed_access |= (1ULL << 60);
 	ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
@@ -1826,6 +1833,20 @@ TEST_F_FORK(layout1, link)
 	ASSERT_EQ(0, link(file1_s1d3, file2_s1d3));
 }
 
+static int test_rename(const char *const oldpath, const char *const newpath)
+{
+	if (rename(oldpath, newpath))
+		return errno;
+	return 0;
+}
+
+static int test_exchange(const char *const oldpath, const char *const newpath)
+{
+	if (renameat2(AT_FDCWD, oldpath, AT_FDCWD, newpath, RENAME_EXCHANGE))
+		return errno;
+	return 0;
+}
+
 TEST_F_FORK(layout1, rename_file)
 {
 	const struct rule rules[] = {
@@ -1867,10 +1888,10 @@ TEST_F_FORK(layout1, rename_file)
 	 * to a different directory (which allows file removal).
 	 */
 	ASSERT_EQ(-1, rename(file1_s2d1, file1_s1d3));
-	ASSERT_EQ(EXDEV, errno);
+	ASSERT_EQ(EACCES, errno);
 	ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d1, AT_FDCWD, file1_s1d3,
 				RENAME_EXCHANGE));
-	ASSERT_EQ(EXDEV, errno);
+	ASSERT_EQ(EACCES, errno);
 	ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s2d2, AT_FDCWD, file1_s1d3,
 				RENAME_EXCHANGE));
 	ASSERT_EQ(EXDEV, errno);
@@ -1894,7 +1915,7 @@ TEST_F_FORK(layout1, rename_file)
 	ASSERT_EQ(EXDEV, errno);
 	ASSERT_EQ(0, unlink(file1_s1d3));
 	ASSERT_EQ(-1, rename(file1_s2d1, file1_s1d3));
-	ASSERT_EQ(EXDEV, errno);
+	ASSERT_EQ(EACCES, errno);
 
 	/* Exchanges and renames files with same parent. */
 	ASSERT_EQ(0, renameat2(AT_FDCWD, file2_s2d3, AT_FDCWD, file1_s2d3,
@@ -2014,6 +2035,115 @@ TEST_F_FORK(layout1, reparent_refer)
 	ASSERT_EQ(0, rename(dir_s1d3, dir_s2d3));
 }
 
+/* Checks renames beneath dir_s1d1. */
+static void refer_denied_by_default(struct __test_metadata *const _metadata,
+				    const struct rule layer1[],
+				    const int layer1_err,
+				    const struct rule layer2[])
+{
+	int ruleset_fd;
+
+	ASSERT_EQ(0, unlink(file1_s1d2));
+
+	ruleset_fd = create_ruleset(_metadata, layer1[0].access, layer1);
+	ASSERT_LE(0, ruleset_fd);
+	enforce_ruleset(_metadata, ruleset_fd);
+	ASSERT_EQ(0, close(ruleset_fd));
+
+	/*
+	 * If the first layer handles LANDLOCK_ACCESS_FS_REFER (according to
+	 * layer1_err), then it allows some different-parent renames and links.
+	 */
+	ASSERT_EQ(layer1_err, test_rename(file1_s1d1, file1_s1d2));
+	if (layer1_err == 0)
+		ASSERT_EQ(layer1_err, test_rename(file1_s1d2, file1_s1d1));
+	ASSERT_EQ(layer1_err, test_exchange(file2_s1d1, file2_s1d2));
+	ASSERT_EQ(layer1_err, test_exchange(file2_s1d2, file2_s1d1));
+
+	ruleset_fd = create_ruleset(_metadata, layer2[0].access, layer2);
+	ASSERT_LE(0, ruleset_fd);
+	enforce_ruleset(_metadata, ruleset_fd);
+	ASSERT_EQ(0, close(ruleset_fd));
+
+	/*
+	 * Now, either the first or the second layer does not handle
+	 * LANDLOCK_ACCESS_FS_REFER, which means that any different-parent
+	 * renames and links are denied, thus making the layer handling
+	 * LANDLOCK_ACCESS_FS_REFER null and void.
+	 */
+	ASSERT_EQ(EXDEV, test_rename(file1_s1d1, file1_s1d2));
+	ASSERT_EQ(EXDEV, test_exchange(file2_s1d1, file2_s1d2));
+	ASSERT_EQ(EXDEV, test_exchange(file2_s1d2, file2_s1d1));
+}
+
+const struct rule layer_dir_s1d1_refer[] = {
+	{
+		.path = dir_s1d1,
+		.access = LANDLOCK_ACCESS_FS_REFER,
+	},
+	{},
+};
+
+const struct rule layer_dir_s1d1_execute[] = {
+	{
+		/* Matches a parent directory. */
+		.path = dir_s1d1,
+		.access = LANDLOCK_ACCESS_FS_EXECUTE,
+	},
+	{},
+};
+
+const struct rule layer_dir_s2d1_execute[] = {
+	{
+		/* Does not match a parent directory. */
+		.path = dir_s2d1,
+		.access = LANDLOCK_ACCESS_FS_EXECUTE,
+	},
+	{},
+};
+
+/*
+ * Tests precedence over renames: denied by default for different parent
+ * directories, *with* a rule matching a parent directory, but not directly
+ * denying access (with MAKE_REG nor REMOVE).
+ */
+TEST_F_FORK(layout1, refer_denied_by_default1)
+{
+	refer_denied_by_default(_metadata, layer_dir_s1d1_refer, 0,
+				layer_dir_s1d1_execute);
+}
+
+/*
+ * Same test but this time turning around the ABI version order: the first
+ * layer does not handle LANDLOCK_ACCESS_FS_REFER.
+ */
+TEST_F_FORK(layout1, refer_denied_by_default2)
+{
+	refer_denied_by_default(_metadata, layer_dir_s1d1_execute, EXDEV,
+				layer_dir_s1d1_refer);
+}
+
+/*
+ * Tests precedence over renames: denied by default for different parent
+ * directories, *without* a rule matching a parent directory, but not directly
+ * denying access (with MAKE_REG nor REMOVE).
+ */
+TEST_F_FORK(layout1, refer_denied_by_default3)
+{
+	refer_denied_by_default(_metadata, layer_dir_s1d1_refer, 0,
+				layer_dir_s2d1_execute);
+}
+
+/*
+ * Same test but this time turning around the ABI version order: the first
+ * layer does not handle LANDLOCK_ACCESS_FS_REFER.
+ */
+TEST_F_FORK(layout1, refer_denied_by_default4)
+{
+	refer_denied_by_default(_metadata, layer_dir_s2d1_execute, EXDEV,
+				layer_dir_s1d1_refer);
+}
+
 TEST_F_FORK(layout1, reparent_link)
 {
 	const struct rule layer1[] = {
@@ -2336,11 +2466,12 @@ TEST_F_FORK(layout1, reparent_exdev_layers_rename1)
 	ASSERT_EQ(EXDEV, errno);
 
 	/*
-	 * However, moving the file2_s1d3 file below dir_s2d3 is allowed
-	 * because it cannot inherit MAKE_REG nor MAKE_DIR rights (which are
-	 * dedicated to directories).
+	 * Moving the file2_s1d3 file below dir_s2d3 is denied because the
+	 * second layer does not handle REFER, which is always denied by
+	 * default.
 	 */
-	ASSERT_EQ(0, rename(file2_s1d3, file1_s2d3));
+	ASSERT_EQ(-1, rename(file2_s1d3, file1_s2d3));
+	ASSERT_EQ(EXDEV, errno);
 }
 
 TEST_F_FORK(layout1, reparent_exdev_layers_rename2)
@@ -2373,8 +2504,12 @@ TEST_F_FORK(layout1, reparent_exdev_layers_rename2)
 	ASSERT_EQ(EACCES, errno);
 	ASSERT_EQ(-1, rename(file1_s1d1, file1_s2d3));
 	ASSERT_EQ(EXDEV, errno);
-	/* Modify layout! */
-	ASSERT_EQ(0, rename(file2_s1d2, file1_s2d3));
+	/*
+	 * Modifying the layout is now denied because the second layer does not
+	 * handle REFER, which is always denied by default.
+	 */
+	ASSERT_EQ(-1, rename(file2_s1d2, file1_s2d3));
+	ASSERT_EQ(EXDEV, errno);
 
 	/* Without REFER source, EACCES wins over EXDEV. */
 	ASSERT_EQ(-1, rename(dir_s1d1, file1_s2d2));
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 947fc72413e9..9d4cb94cf437 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -40,6 +40,11 @@ ifeq (0,$(MAKELEVEL))
     endif
 endif
 selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST))))
+top_srcdir = $(selfdir)/../../..
+
+ifeq ($(KHDR_INCLUDES),)
+KHDR_INCLUDES := -isystem $(top_srcdir)/usr/include
+endif
 
 # The following are built by lib.mk common compile rules.
 # TEST_CUSTOM_PROGS should be used by tests that require
diff --git a/tools/testing/selftests/lkdtm/tests.txt b/tools/testing/selftests/lkdtm/tests.txt
index 65e53eb0840b..607b8d7e3ea3 100644
--- a/tools/testing/selftests/lkdtm/tests.txt
+++ b/tools/testing/selftests/lkdtm/tests.txt
@@ -75,7 +75,9 @@ USERCOPY_KERNEL
 STACKLEAK_ERASING OK: the rest of the thread stack is properly erased
 CFI_FORWARD_PROTO
 CFI_BACKWARD call trace:|ok: control flow unchanged
-FORTIFIED_STRSCPY
-FORTIFIED_OBJECT
-FORTIFIED_SUBOBJECT
+FORTIFY_STRSCPY detected buffer overflow
+FORTIFY_STR_OBJECT detected buffer overflow
+FORTIFY_STR_MEMBER detected buffer overflow
+FORTIFY_MEM_OBJECT detected buffer overflow
+FORTIFY_MEM_MEMBER detected field-spanning write
 PPC_SLB_MULTIHIT Recovered
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 0e5751af6247..de7d5cc15f85 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -1,42 +1,42 @@
 # SPDX-License-Identifier: GPL-2.0-only
+cmsg_sender
+fin_ack_lat
+gro
+hwtstamp_config
+ioam6_parser
+ip_defrag
 ipsec
+ipv6_flowlabel
+ipv6_flowlabel_mgr
 msg_zerocopy
-socket
+nettest
 psock_fanout
 psock_snd
 psock_tpacket
-stress_reuseport_listen
+reuseaddr_conflict
+reuseaddr_ports_exhausted
 reuseport_addr_any
 reuseport_bpf
 reuseport_bpf_cpu
 reuseport_bpf_numa
 reuseport_dualstack
-reuseaddr_conflict
-tcp_mmap
-udpgso
-udpgso_bench_rx
-udpgso_bench_tx
-tcp_inq
-tls
-txring_overwrite
-ip_defrag
-ipv6_flowlabel
-ipv6_flowlabel_mgr
-so_txtime
-tcp_fastopen_backup_key
-nettest
-fin_ack_lat
-reuseaddr_ports_exhausted
-hwtstamp_config
 rxtimestamp
-timestamping
-txtimestamp
+socket
 so_netns_cookie
+so_txtime
+stress_reuseport_listen
+tap
+tcp_fastopen_backup_key
+tcp_inq
+tcp_mmap
 test_unix_oob
-gro
-ioam6_parser
+timestamping
+tls
 toeplitz
 tun
-cmsg_sender
+txring_overwrite
+txtimestamp
+udpgso
+udpgso_bench_rx
+udpgso_bench_tx
 unix_connect
-tap
\ No newline at end of file
diff --git a/tools/testing/selftests/net/forwarding/router_multicast.sh b/tools/testing/selftests/net/forwarding/router_multicast.sh
index 57e90c873a2c..5a58b1ec8aef 100755
--- a/tools/testing/selftests/net/forwarding/router_multicast.sh
+++ b/tools/testing/selftests/net/forwarding/router_multicast.sh
@@ -28,7 +28,7 @@
 # +------------------+       +------------------+
 #
 
-ALL_TESTS="mcast_v4 mcast_v6 rpf_v4 rpf_v6"
+ALL_TESTS="mcast_v4 mcast_v6 rpf_v4 rpf_v6 unres_v4 unres_v6"
 NUM_NETIFS=6
 source lib.sh
 source tc_common.sh
@@ -406,6 +406,96 @@ rpf_v6()
 	log_test "RPF IPv6"
 }
 
+unres_v4()
+{
+	# Send a multicast packet not corresponding to an installed route,
+	# causing the kernel to queue the packet for resolution and emit an
+	# IGMPMSG_NOCACHE notification. smcrouted will react to this
+	# notification by consulting its (*, G) list and installing an (S, G)
+	# route, which will be used to forward the queued packet.
+
+	RET=0
+
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 1 flower \
+		dst_ip 225.1.2.3 ip_proto udp dst_port 12345 action drop
+	tc filter add dev $h3 ingress protocol ip pref 1 handle 1 flower \
+		dst_ip 225.1.2.3 ip_proto udp dst_port 12345 action drop
+
+	# Forwarding should fail before installing a matching (*, G).
+	$MZ $h1 -c 1 -p 128 -t udp "ttl=10,sp=54321,dp=12345" \
+		-a 00:11:22:33:44:55 -b 01:00:5e:01:02:03 \
+		-A 198.51.100.2 -B 225.1.2.3 -q
+
+	tc_check_packets "dev $h2 ingress" 1 0
+	check_err $? "Multicast received on first host when should not"
+	tc_check_packets "dev $h3 ingress" 1 0
+	check_err $? "Multicast received on second host when should not"
+
+	# Create (*, G). Will not be installed in the kernel.
+	create_mcast_sg $rp1 0.0.0.0 225.1.2.3 $rp2 $rp3
+
+	$MZ $h1 -c 1 -p 128 -t udp "ttl=10,sp=54321,dp=12345" \
+		-a 00:11:22:33:44:55 -b 01:00:5e:01:02:03 \
+		-A 198.51.100.2 -B 225.1.2.3 -q
+
+	tc_check_packets "dev $h2 ingress" 1 1
+	check_err $? "Multicast not received on first host"
+	tc_check_packets "dev $h3 ingress" 1 1
+	check_err $? "Multicast not received on second host"
+
+	delete_mcast_sg $rp1 0.0.0.0 225.1.2.3 $rp2 $rp3
+
+	tc filter del dev $h3 ingress protocol ip pref 1 handle 1 flower
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 1 flower
+
+	log_test "Unresolved queue IPv4"
+}
+
+unres_v6()
+{
+	# Send a multicast packet not corresponding to an installed route,
+	# causing the kernel to queue the packet for resolution and emit an
+	# MRT6MSG_NOCACHE notification. smcrouted will react to this
+	# notification by consulting its (*, G) list and installing an (S, G)
+	# route, which will be used to forward the queued packet.
+
+	RET=0
+
+	tc filter add dev $h2 ingress protocol ipv6 pref 1 handle 1 flower \
+		dst_ip ff0e::3 ip_proto udp dst_port 12345 action drop
+	tc filter add dev $h3 ingress protocol ipv6 pref 1 handle 1 flower \
+		dst_ip ff0e::3 ip_proto udp dst_port 12345 action drop
+
+	# Forwarding should fail before installing a matching (*, G).
+	$MZ $h1 -6 -c 1 -p 128 -t udp "ttl=10,sp=54321,dp=12345" \
+		-a 00:11:22:33:44:55 -b 33:33:00:00:00:03 \
+		-A 2001:db8:1::2 -B ff0e::3 -q
+
+	tc_check_packets "dev $h2 ingress" 1 0
+	check_err $? "Multicast received on first host when should not"
+	tc_check_packets "dev $h3 ingress" 1 0
+	check_err $? "Multicast received on second host when should not"
+
+	# Create (*, G). Will not be installed in the kernel.
+	create_mcast_sg $rp1 :: ff0e::3 $rp2 $rp3
+
+	$MZ $h1 -6 -c 1 -p 128 -t udp "ttl=10,sp=54321,dp=12345" \
+		-a 00:11:22:33:44:55 -b 33:33:00:00:00:03 \
+		-A 2001:db8:1::2 -B ff0e::3 -q
+
+	tc_check_packets "dev $h2 ingress" 1 1
+	check_err $? "Multicast not received on first host"
+	tc_check_packets "dev $h3 ingress" 1 1
+	check_err $? "Multicast not received on second host"
+
+	delete_mcast_sg $rp1 :: ff0e::3 $rp2 $rp3
+
+	tc filter del dev $h3 ingress protocol ipv6 pref 1 handle 1 flower
+	tc filter del dev $h2 ingress protocol ipv6 pref 1 handle 1 flower
+
+	log_test "Unresolved queue IPv6"
+}
+
 trap cleanup EXIT
 
 setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/sch_red.sh b/tools/testing/selftests/net/forwarding/sch_red.sh
index e714bae473fb..81f31179ac88 100755
--- a/tools/testing/selftests/net/forwarding/sch_red.sh
+++ b/tools/testing/selftests/net/forwarding/sch_red.sh
@@ -1,3 +1,4 @@
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 # This test sends one stream of traffic from H1 through a TBF shaper, to a RED
diff --git a/tools/testing/selftests/net/io_uring_zerocopy_tx.c b/tools/testing/selftests/net/io_uring_zerocopy_tx.c
index 9d64c560a2d6..8ce48aca8321 100644
--- a/tools/testing/selftests/net/io_uring_zerocopy_tx.c
+++ b/tools/testing/selftests/net/io_uring_zerocopy_tx.c
@@ -47,7 +47,6 @@ enum {
 	MODE_MIXED	= 3,
 };
 
-static bool cfg_flush		= false;
 static bool cfg_cork		= false;
 static int  cfg_mode		= MODE_ZC_FIXED;
 static int  cfg_nr_reqs		= 8;
@@ -166,21 +165,6 @@ static int io_uring_register_buffers(struct io_uring *ring,
 	return (ret < 0) ? -errno : ret;
 }
 
-static int io_uring_register_notifications(struct io_uring *ring,
-					   unsigned nr,
-					   struct io_uring_notification_slot *slots)
-{
-	int ret;
-	struct io_uring_notification_register r = {
-		.nr_slots = nr,
-		.data = (unsigned long)slots,
-	};
-
-	ret = syscall(__NR_io_uring_register, ring->ring_fd,
-		      IORING_REGISTER_NOTIFIERS, &r, sizeof(r));
-	return (ret < 0) ? -errno : ret;
-}
-
 static int io_uring_mmap(int fd, struct io_uring_params *p,
 			 struct io_uring_sq *sq, struct io_uring_cq *cq)
 {
@@ -297,11 +281,10 @@ static inline void io_uring_prep_send(struct io_uring_sqe *sqe, int sockfd,
 
 static inline void io_uring_prep_sendzc(struct io_uring_sqe *sqe, int sockfd,
 				        const void *buf, size_t len, int flags,
-				        unsigned slot_idx, unsigned zc_flags)
+				        unsigned zc_flags)
 {
 	io_uring_prep_send(sqe, sockfd, buf, len, flags);
-	sqe->opcode = (__u8) IORING_OP_SENDZC_NOTIF;
-	sqe->notification_idx = slot_idx;
+	sqe->opcode = (__u8) IORING_OP_SEND_ZC;
 	sqe->ioprio = zc_flags;
 }
 
@@ -374,7 +357,6 @@ static int do_setup_tx(int domain, int type, int protocol)
 
 static void do_tx(int domain, int type, int protocol)
 {
-	struct io_uring_notification_slot b[1] = {{.tag = NOTIF_TAG}};
 	struct io_uring_sqe *sqe;
 	struct io_uring_cqe *cqe;
 	unsigned long packets = 0, bytes = 0;
@@ -390,10 +372,6 @@ static void do_tx(int domain, int type, int protocol)
 	if (ret)
 		error(1, ret, "io_uring: queue init");
 
-	ret = io_uring_register_notifications(&ring, 1, b);
-	if (ret)
-		error(1, ret, "io_uring: tx ctx registration");
-
 	iov.iov_base = payload;
 	iov.iov_len = cfg_payload_len;
 
@@ -409,9 +387,8 @@ static void do_tx(int domain, int type, int protocol)
 		for (i = 0; i < cfg_nr_reqs; i++) {
 			unsigned zc_flags = 0;
 			unsigned buf_idx = 0;
-			unsigned slot_idx = 0;
 			unsigned mode = cfg_mode;
-			unsigned msg_flags = 0;
+			unsigned msg_flags = MSG_WAITALL;
 
 			if (cfg_mode == MODE_MIXED)
 				mode = rand() % 3;
@@ -423,13 +400,10 @@ static void do_tx(int domain, int type, int protocol)
 						   cfg_payload_len, msg_flags);
 				sqe->user_data = NONZC_TAG;
 			} else {
-				if (cfg_flush) {
-					zc_flags |= IORING_RECVSEND_NOTIF_FLUSH;
-					compl_cqes++;
-				}
+				compl_cqes++;
 				io_uring_prep_sendzc(sqe, fd, payload,
 						     cfg_payload_len,
-						     msg_flags, slot_idx, zc_flags);
+						     msg_flags, zc_flags);
 				if (mode == MODE_ZC_FIXED) {
 					sqe->ioprio |= IORING_RECVSEND_FIXED_BUF;
 					sqe->buf_index = buf_idx;
@@ -442,51 +416,57 @@ static void do_tx(int domain, int type, int protocol)
 		if (ret != cfg_nr_reqs)
 			error(1, ret, "submit");
 
+		if (cfg_cork)
+			do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 0);
 		for (i = 0; i < cfg_nr_reqs; i++) {
 			ret = io_uring_wait_cqe(&ring, &cqe);
 			if (ret)
 				error(1, ret, "wait cqe");
 
-			if (cqe->user_data == NOTIF_TAG) {
+			if (cqe->user_data != NONZC_TAG &&
+			    cqe->user_data != ZC_TAG)
+				error(1, -EINVAL, "invalid cqe->user_data");
+
+			if (cqe->flags & IORING_CQE_F_NOTIF) {
+				if (cqe->flags & IORING_CQE_F_MORE)
+					error(1, -EINVAL, "invalid notif flags");
 				compl_cqes--;
 				i--;
-			} else if (cqe->user_data != NONZC_TAG &&
-				   cqe->user_data != ZC_TAG) {
-				error(1, cqe->res, "invalid user_data");
-			} else if (cqe->res <= 0 && cqe->res != -EAGAIN) {
+			} else if (cqe->res <= 0) {
+				if (cqe->flags & IORING_CQE_F_MORE)
+					error(1, cqe->res, "more with a failed send");
 				error(1, cqe->res, "send failed");
 			} else {
-				if (cqe->res > 0) {
-					packets++;
-					bytes += cqe->res;
-				}
-				/* failed requests don't flush */
-				if (cfg_flush &&
-				    cqe->res <= 0 &&
-				    cqe->user_data == ZC_TAG)
-					compl_cqes--;
+				if (cqe->user_data == ZC_TAG &&
+				    !(cqe->flags & IORING_CQE_F_MORE))
+					error(1, cqe->res, "missing more flag");
+				packets++;
+				bytes += cqe->res;
 			}
 			io_uring_cqe_seen(&ring);
 		}
-		if (cfg_cork)
-			do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 0);
 	} while (gettimeofday_ms() < tstop);
 
-	if (close(fd))
-		error(1, errno, "close");
-
-	fprintf(stderr, "tx=%lu (MB=%lu), tx/s=%lu (MB/s=%lu)\n",
-			packets, bytes >> 20,
-			packets / (cfg_runtime_ms / 1000),
-			(bytes >> 20) / (cfg_runtime_ms / 1000));
-
 	while (compl_cqes) {
 		ret = io_uring_wait_cqe(&ring, &cqe);
 		if (ret)
 			error(1, ret, "wait cqe");
+		if (cqe->flags & IORING_CQE_F_MORE)
+			error(1, -EINVAL, "invalid notif flags");
+		if (!(cqe->flags & IORING_CQE_F_NOTIF))
+			error(1, -EINVAL, "missing notif flag");
+
 		io_uring_cqe_seen(&ring);
 		compl_cqes--;
 	}
+
+	fprintf(stderr, "tx=%lu (MB=%lu), tx/s=%lu (MB/s=%lu)\n",
+			packets, bytes >> 20,
+			packets / (cfg_runtime_ms / 1000),
+			(bytes >> 20) / (cfg_runtime_ms / 1000));
+
+	if (close(fd))
+		error(1, errno, "close");
 }
 
 static void do_test(int domain, int type, int protocol)
@@ -500,8 +480,8 @@ static void do_test(int domain, int type, int protocol)
 
 static void usage(const char *filepath)
 {
-	error(1, 0, "Usage: %s [-f] [-n<N>] [-z0] [-s<payload size>] "
-		    "(-4|-6) [-t<time s>] -D<dst_ip> udp", filepath);
+	error(1, 0, "Usage: %s (-4|-6) (udp|tcp) -D<dst_ip> [-s<payload size>] "
+		    "[-t<time s>] [-n<batch>] [-p<port>] [-m<mode>]", filepath);
 }
 
 static void parse_opts(int argc, char **argv)
@@ -519,7 +499,7 @@ static void parse_opts(int argc, char **argv)
 		usage(argv[0]);
 	cfg_payload_len = max_payload_len;
 
-	while ((c = getopt(argc, argv, "46D:p:s:t:n:fc:m:")) != -1) {
+	while ((c = getopt(argc, argv, "46D:p:s:t:n:c:m:")) != -1) {
 		switch (c) {
 		case '4':
 			if (cfg_family != PF_UNSPEC)
@@ -548,9 +528,6 @@ static void parse_opts(int argc, char **argv)
 		case 'n':
 			cfg_nr_reqs = strtoul(optarg, NULL, 0);
 			break;
-		case 'f':
-			cfg_flush = 1;
-			break;
 		case 'c':
 			cfg_cork = strtol(optarg, NULL, 0);
 			break;
@@ -583,8 +560,6 @@ static void parse_opts(int argc, char **argv)
 
 	if (cfg_payload_len > max_payload_len)
 		error(1, 0, "-s: payload exceeds max (%d)", max_payload_len);
-	if (cfg_mode == MODE_NONZC && cfg_flush)
-		error(1, 0, "-f: only zerocopy modes support notifications");
 	if (optind != argc - 1)
 		usage(argv[0]);
 }
diff --git a/tools/testing/selftests/net/io_uring_zerocopy_tx.sh b/tools/testing/selftests/net/io_uring_zerocopy_tx.sh
index 6a65e4437640..32aa6e9dacc2 100755
--- a/tools/testing/selftests/net/io_uring_zerocopy_tx.sh
+++ b/tools/testing/selftests/net/io_uring_zerocopy_tx.sh
@@ -25,15 +25,11 @@ readonly path_sysctl_mem="net.core.optmem_max"
 # No arguments: automated test
 if [[ "$#" -eq "0" ]]; then
 	IPs=( "4" "6" )
-	protocols=( "tcp" "udp" )
 
 	for IP in "${IPs[@]}"; do
-		for proto in "${protocols[@]}"; do
-			for mode in $(seq 1 3); do
-				$0 "$IP" "$proto" -m "$mode" -t 1 -n 32
-				$0 "$IP" "$proto" -m "$mode" -t 1 -n 32 -f
-				$0 "$IP" "$proto" -m "$mode" -t 1 -n 32 -c -f
-			done
+		for mode in $(seq 1 3); do
+			$0 "$IP" udp -m "$mode" -t 1 -n 32
+			$0 "$IP" tcp -m "$mode" -t 1 -n 32
 		done
 	done
 
diff --git a/tools/testing/selftests/net/reuseport_bpf.c b/tools/testing/selftests/net/reuseport_bpf.c
index 072d709c96b4..65aea27d761c 100644
--- a/tools/testing/selftests/net/reuseport_bpf.c
+++ b/tools/testing/selftests/net/reuseport_bpf.c
@@ -328,7 +328,7 @@ static void test_extra_filter(const struct test_params p)
 	if (bind(fd1, addr, sockaddr_size()))
 		error(1, errno, "failed to bind recv socket 1");
 
-	if (!bind(fd2, addr, sockaddr_size()) && errno != EADDRINUSE)
+	if (!bind(fd2, addr, sockaddr_size()) || errno != EADDRINUSE)
 		error(1, errno, "bind socket 2 should fail with EADDRINUSE");
 
 	free(addr);
diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh
index a6991877e50c..e908009576c7 100755
--- a/tools/testing/selftests/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/netfilter/nft_concat_range.sh
@@ -91,7 +91,7 @@ src
 start		1
 count		5
 src_delta	2000
-tools		sendip nc bash
+tools		sendip socat nc bash
 proto		udp
 
 race_repeat	3
@@ -116,7 +116,7 @@ src
 start		10
 count		5
 src_delta	2000
-tools		sendip nc bash
+tools		sendip socat nc bash
 proto		udp6
 
 race_repeat	3
@@ -141,7 +141,7 @@ src
 start		1
 count		5
 src_delta	2000
-tools		sendip nc bash
+tools		sendip socat nc bash
 proto		udp
 
 race_repeat	0
@@ -163,7 +163,7 @@ src		mac
 start		10
 count		5
 src_delta	2000
-tools		sendip nc bash
+tools		sendip socat nc bash
 proto		udp6
 
 race_repeat	0
@@ -185,7 +185,7 @@ src		mac proto
 start		10
 count		5
 src_delta	2000
-tools		sendip nc bash
+tools		sendip socat nc bash
 proto		udp6
 
 race_repeat	0
@@ -207,7 +207,7 @@ src		addr4
 start		1
 count		5
 src_delta	2000
-tools		sendip nc bash
+tools		sendip socat nc bash
 proto		udp
 
 race_repeat	3
@@ -227,7 +227,7 @@ src		addr6 port
 start		10
 count		5
 src_delta	2000
-tools		sendip nc
+tools		sendip socat nc
 proto		udp6
 
 race_repeat	3
@@ -247,7 +247,7 @@ src		mac proto addr4
 start		1
 count		5
 src_delta	2000
-tools		sendip nc bash
+tools		sendip socat nc bash
 proto		udp
 
 race_repeat	0
@@ -264,7 +264,7 @@ src		mac
 start		1
 count		5
 src_delta	2000
-tools		sendip nc bash
+tools		sendip socat nc bash
 proto		udp
 
 race_repeat	0
@@ -286,7 +286,7 @@ src		mac addr4
 start		1
 count		5
 src_delta	2000
-tools		sendip nc bash
+tools		sendip socat nc bash
 proto		udp
 
 race_repeat	0
@@ -337,7 +337,7 @@ src		addr4
 start		1
 count		5
 src_delta	2000
-tools		sendip nc
+tools		sendip socat nc
 proto		udp
 
 race_repeat	3
@@ -363,7 +363,7 @@ src		mac
 start		1
 count		1
 src_delta	2000
-tools		sendip nc bash
+tools		sendip socat nc bash
 proto		udp
 
 race_repeat	0
@@ -541,6 +541,24 @@ setup_send_udp() {
 			dst_port=
 			src_addr4=
 		}
+	elif command -v socat -v >/dev/null; then
+		send_udp() {
+			if [ -n "${src_addr4}" ]; then
+				B ip addr add "${src_addr4}" dev veth_b
+				__socatbind=",bind=${src_addr4}"
+				if [ -n "${src_port}" ];then
+					__socatbind="${__socatbind}:${src_port}"
+				fi
+			fi
+
+			ip addr add "${dst_addr4}" dev veth_a 2>/dev/null
+			[ -z "${dst_port}" ] && dst_port=12345
+
+			echo "test4" | B socat -t 0.01 STDIN UDP4-DATAGRAM:${dst_addr4}:${dst_port}"${__socatbind}"
+
+			src_addr4=
+			src_port=
+		}
 	elif command -v nc >/dev/null; then
 		if nc -u -w0 1.1.1.1 1 2>/dev/null; then
 			# OpenBSD netcat
@@ -606,6 +624,29 @@ setup_send_udp6() {
 			dst_port=
 			src_addr6=
 		}
+	elif command -v socat -v >/dev/null; then
+		send_udp6() {
+			ip -6 addr add "${dst_addr6}" dev veth_a nodad \
+				2>/dev/null
+
+			__socatbind6=
+
+			if [ -n "${src_addr6}" ]; then
+				if [ -n "${src_addr6} != "${src_addr6_added} ]; then
+					B ip addr add "${src_addr6}" dev veth_b nodad
+
+					src_addr6_added=${src_addr6}
+				fi
+
+				__socatbind6=",bind=[${src_addr6}]"
+
+				if [ -n "${src_port}" ] ;then
+					__socatbind6="${__socatbind6}:${src_port}"
+				fi
+			fi
+
+			echo "test6" | B socat -t 0.01 STDIN UDP6-DATAGRAM:[${dst_addr6}]:${dst_port}"${__socatbind6}"
+		}
 	elif command -v nc >/dev/null && nc -u -w0 1.1.1.1 1 2>/dev/null; then
 		# GNU netcat might not work with IPv6, try next tool
 		send_udp6() {
diff --git a/tools/testing/selftests/netfilter/nft_conntrack_helper.sh b/tools/testing/selftests/netfilter/nft_conntrack_helper.sh
index bf6b9626c7dd..faa7778d7bd1 100755
--- a/tools/testing/selftests/netfilter/nft_conntrack_helper.sh
+++ b/tools/testing/selftests/netfilter/nft_conntrack_helper.sh
@@ -102,26 +102,42 @@ check_for_helper()
 
 	ip netns exec ${netns} conntrack -L -f $family -p tcp --dport $port 2> /dev/null |grep -q 'helper=ftp'
 	if [ $? -ne 0 ] ; then
-		echo "FAIL: ${netns} did not show attached helper $message" 1>&2
-		ret=1
+		if [ $autoassign -eq 0 ] ;then
+			echo "FAIL: ${netns} did not show attached helper $message" 1>&2
+			ret=1
+		else
+			echo "PASS: ${netns} did not show attached helper $message" 1>&2
+		fi
+	else
+		if [ $autoassign -eq 0 ] ;then
+			echo "PASS: ${netns} connection on port $port has ftp helper attached" 1>&2
+		else
+			echo "FAIL: ${netns} connection on port $port has ftp helper attached" 1>&2
+			ret=1
+		fi
 	fi
 
-	echo "PASS: ${netns} connection on port $port has ftp helper attached" 1>&2
 	return 0
 }
 
 test_helper()
 {
 	local port=$1
-	local msg=$2
+	local autoassign=$2
+
+	if [ $autoassign -eq 0 ] ;then
+		msg="set via ruleset"
+	else
+		msg="auto-assign"
+	fi
 
 	sleep 3 | ip netns exec ${ns2} nc -w 2 -l -p $port > /dev/null &
 
 	sleep 1 | ip netns exec ${ns1} nc -w 2 10.0.1.2 $port > /dev/null &
 	sleep 1
 
-	check_for_helper "$ns1" "ip $msg" $port
-	check_for_helper "$ns2" "ip $msg" $port
+	check_for_helper "$ns1" "ip $msg" $port $autoassign
+	check_for_helper "$ns2" "ip $msg" $port $autoassign
 
 	wait
 
@@ -173,9 +189,9 @@ if [ $? -ne 0 ];then
 	fi
 fi
 
-test_helper 2121 "set via ruleset"
-ip netns exec ${ns1} sysctl -q 'net.netfilter.nf_conntrack_helper=1'
-ip netns exec ${ns2} sysctl -q 'net.netfilter.nf_conntrack_helper=1'
-test_helper 21 "auto-assign"
+test_helper 2121 0
+ip netns exec ${ns1} sysctl -qe 'net.netfilter.nf_conntrack_helper=1'
+ip netns exec ${ns2} sysctl -qe 'net.netfilter.nf_conntrack_helper=1'
+test_helper 21 1
 
 exit $ret
diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh
index d4ffebb989f8..7060bae04ec8 100755
--- a/tools/testing/selftests/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/netfilter/nft_flowtable.sh
@@ -14,13 +14,17 @@
 # nft_flowtable.sh -o8000 -l1500 -r2000
 #
 
+sfx=$(mktemp -u "XXXXXXXX")
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+nsr1="nsr1-$sfx"
+nsr2="nsr2-$sfx"
 
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 ret=0
 
-ns1in=""
-ns2in=""
+nsin=""
 ns1out=""
 ns2out=""
 
@@ -36,21 +40,19 @@ checktool (){
 checktool "nft --version" "run test without nft tool"
 checktool "ip -Version" "run test without ip tool"
 checktool "which nc" "run test without nc (netcat)"
-checktool "ip netns add nsr1" "create net namespace"
+checktool "ip netns add $nsr1" "create net namespace $nsr1"
 
-ip netns add ns1
-ip netns add ns2
-
-ip netns add nsr2
+ip netns add $ns1
+ip netns add $ns2
+ip netns add $nsr2
 
 cleanup() {
-	for i in 1 2; do
-		ip netns del ns$i
-		ip netns del nsr$i
-	done
+	ip netns del $ns1
+	ip netns del $ns2
+	ip netns del $nsr1
+	ip netns del $nsr2
 
-	rm -f "$ns1in" "$ns1out"
-	rm -f "$ns2in" "$ns2out"
+	rm -f "$nsin" "$ns1out" "$ns2out"
 
 	[ $log_netns -eq 0 ] && sysctl -q net.netfilter.nf_log_all_netns=$log_netns
 }
@@ -59,22 +61,21 @@ trap cleanup EXIT
 
 sysctl -q net.netfilter.nf_log_all_netns=1
 
-ip link add veth0 netns nsr1 type veth peer name eth0 netns ns1
-ip link add veth1 netns nsr1 type veth peer name veth0 netns nsr2
+ip link add veth0 netns $nsr1 type veth peer name eth0 netns $ns1
+ip link add veth1 netns $nsr1 type veth peer name veth0 netns $nsr2
 
-ip link add veth1 netns nsr2 type veth peer name eth0 netns ns2
+ip link add veth1 netns $nsr2 type veth peer name eth0 netns $ns2
 
 for dev in lo veth0 veth1; do
-  for i in 1 2; do
-    ip -net nsr$i link set $dev up
-  done
+    ip -net $nsr1 link set $dev up
+    ip -net $nsr2 link set $dev up
 done
 
-ip -net nsr1 addr add 10.0.1.1/24 dev veth0
-ip -net nsr1 addr add dead:1::1/64 dev veth0
+ip -net $nsr1 addr add 10.0.1.1/24 dev veth0
+ip -net $nsr1 addr add dead:1::1/64 dev veth0
 
-ip -net nsr2 addr add 10.0.2.1/24 dev veth1
-ip -net nsr2 addr add dead:2::1/64 dev veth1
+ip -net $nsr2 addr add 10.0.2.1/24 dev veth1
+ip -net $nsr2 addr add dead:2::1/64 dev veth1
 
 # set different MTUs so we need to push packets coming from ns1 (large MTU)
 # to ns2 (smaller MTU) to stack either to perform fragmentation (ip_no_pmtu_disc=1),
@@ -106,85 +107,76 @@ do
 	esac
 done
 
-if ! ip -net nsr1 link set veth0 mtu $omtu; then
+if ! ip -net $nsr1 link set veth0 mtu $omtu; then
 	exit 1
 fi
 
-ip -net ns1 link set eth0 mtu $omtu
+ip -net $ns1 link set eth0 mtu $omtu
 
-if ! ip -net nsr2 link set veth1 mtu $rmtu; then
+if ! ip -net $nsr2 link set veth1 mtu $rmtu; then
 	exit 1
 fi
 
-ip -net ns2 link set eth0 mtu $rmtu
+ip -net $ns2 link set eth0 mtu $rmtu
 
 # transfer-net between nsr1 and nsr2.
 # these addresses are not used for connections.
-ip -net nsr1 addr add 192.168.10.1/24 dev veth1
-ip -net nsr1 addr add fee1:2::1/64 dev veth1
-
-ip -net nsr2 addr add 192.168.10.2/24 dev veth0
-ip -net nsr2 addr add fee1:2::2/64 dev veth0
-
-for i in 1 2; do
-  ip netns exec nsr$i sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
-  ip netns exec nsr$i sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
-
-  ip -net ns$i link set lo up
-  ip -net ns$i link set eth0 up
-  ip -net ns$i addr add 10.0.$i.99/24 dev eth0
-  ip -net ns$i route add default via 10.0.$i.1
-  ip -net ns$i addr add dead:$i::99/64 dev eth0
-  ip -net ns$i route add default via dead:$i::1
-  if ! ip netns exec ns$i sysctl net.ipv4.tcp_no_metrics_save=1 > /dev/null; then
+ip -net $nsr1 addr add 192.168.10.1/24 dev veth1
+ip -net $nsr1 addr add fee1:2::1/64 dev veth1
+
+ip -net $nsr2 addr add 192.168.10.2/24 dev veth0
+ip -net $nsr2 addr add fee1:2::2/64 dev veth0
+
+for i in 0 1; do
+  ip netns exec $nsr1 sysctl net.ipv4.conf.veth$i.forwarding=1 > /dev/null
+  ip netns exec $nsr2 sysctl net.ipv4.conf.veth$i.forwarding=1 > /dev/null
+done
+
+for ns in $ns1 $ns2;do
+  ip -net $ns link set lo up
+  ip -net $ns link set eth0 up
+
+  if ! ip netns exec $ns sysctl net.ipv4.tcp_no_metrics_save=1 > /dev/null; then
 	echo "ERROR: Check Originator/Responder values (problem during address addition)"
 	exit 1
   fi
-
   # don't set ip DF bit for first two tests
-  ip netns exec ns$i sysctl net.ipv4.ip_no_pmtu_disc=1 > /dev/null
+  ip netns exec $ns sysctl net.ipv4.ip_no_pmtu_disc=1 > /dev/null
 done
 
-ip -net nsr1 route add default via 192.168.10.2
-ip -net nsr2 route add default via 192.168.10.1
+ip -net $ns1 addr add 10.0.1.99/24 dev eth0
+ip -net $ns2 addr add 10.0.2.99/24 dev eth0
+ip -net $ns1 route add default via 10.0.1.1
+ip -net $ns2 route add default via 10.0.2.1
+ip -net $ns1 addr add dead:1::99/64 dev eth0
+ip -net $ns2 addr add dead:2::99/64 dev eth0
+ip -net $ns1 route add default via dead:1::1
+ip -net $ns2 route add default via dead:2::1
+
+ip -net $nsr1 route add default via 192.168.10.2
+ip -net $nsr2 route add default via 192.168.10.1
 
-ip netns exec nsr1 nft -f - <<EOF
+ip netns exec $nsr1 nft -f - <<EOF
 table inet filter {
   flowtable f1 {
      hook ingress priority 0
      devices = { veth0, veth1 }
    }
 
+   counter routed_orig { }
+   counter routed_repl { }
+
    chain forward {
       type filter hook forward priority 0; policy drop;
 
       # flow offloaded? Tag ct with mark 1, so we can detect when it fails.
-      meta oif "veth1" tcp dport 12345 flow offload @f1 counter
-
-      # use packet size to trigger 'should be offloaded by now'.
-      # otherwise, if 'flow offload' expression never offloads, the
-      # test will pass.
-      tcp dport 12345 meta length gt 200 ct mark set 1 counter
+      meta oif "veth1" tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept
 
-      # this turns off flow offloading internally, so expect packets again
-      tcp flags fin,rst ct mark set 0 accept
-
-      # this allows large packets from responder, we need this as long
-      # as PMTUd is off.
-      # This rule is deleted for the last test, when we expect PMTUd
-      # to kick in and ensure all packets meet mtu requirements.
-      meta length gt $lmtu accept comment something-to-grep-for
-
-      # next line blocks connection w.o. working offload.
-      # we only do this for reverse dir, because we expect packets to
-      # enter slow path due to MTU mismatch of veth0 and veth1.
-      tcp sport 12345 ct mark 1 counter log prefix "mark failure " drop
+      # count packets supposedly offloaded as per direction.
+      ct mark 1 counter name ct direction map { original : routed_orig, reply : routed_repl } accept
 
       ct state established,related accept
 
-      # for packets that we can't offload yet, i.e. SYN (any ct that is not confirmed)
-      meta length lt 200 oif "veth1" tcp dport 12345 counter accept
-
       meta nfproto ipv4 meta l4proto icmp accept
       meta nfproto ipv6 meta l4proto icmpv6 accept
    }
@@ -197,30 +189,30 @@ if [ $? -ne 0 ]; then
 fi
 
 # test basic connectivity
-if ! ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then
-  echo "ERROR: ns1 cannot reach ns2" 1>&2
+if ! ip netns exec $ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then
+  echo "ERROR: $ns1 cannot reach ns2" 1>&2
   exit 1
 fi
 
-if ! ip netns exec ns2 ping -c 1 -q 10.0.1.99 > /dev/null; then
-  echo "ERROR: ns2 cannot reach ns1" 1>&2
+if ! ip netns exec $ns2 ping -c 1 -q 10.0.1.99 > /dev/null; then
+  echo "ERROR: $ns2 cannot reach $ns1" 1>&2
   exit 1
 fi
 
 if [ $ret -eq 0 ];then
-	echo "PASS: netns routing/connectivity: ns1 can reach ns2"
+	echo "PASS: netns routing/connectivity: $ns1 can reach $ns2"
 fi
 
-ns1in=$(mktemp)
+nsin=$(mktemp)
 ns1out=$(mktemp)
-ns2in=$(mktemp)
 ns2out=$(mktemp)
 
 make_file()
 {
 	name=$1
 
-	SIZE=$((RANDOM % (1024 * 8)))
+	SIZE=$((RANDOM % (1024 * 128)))
+	SIZE=$((SIZE + (1024 * 8)))
 	TSIZE=$((SIZE * 1024))
 
 	dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null
@@ -231,6 +223,38 @@ make_file()
 	dd if=/dev/urandom conf=notrunc of="$name" bs=1 count=$SIZE 2> /dev/null
 }
 
+check_counters()
+{
+	local what=$1
+	local ok=1
+
+	local orig=$(ip netns exec $nsr1 nft reset counter inet filter routed_orig | grep packets)
+	local repl=$(ip netns exec $nsr1 nft reset counter inet filter routed_repl | grep packets)
+
+	local orig_cnt=${orig#*bytes}
+	local repl_cnt=${repl#*bytes}
+
+	local fs=$(du -sb $nsin)
+	local max_orig=${fs%%/*}
+	local max_repl=$((max_orig/4))
+
+	if [ $orig_cnt -gt $max_orig ];then
+		echo "FAIL: $what: original counter $orig_cnt exceeds expected value $max_orig" 1>&2
+		ret=1
+		ok=0
+	fi
+
+	if [ $repl_cnt -gt $max_repl ];then
+		echo "FAIL: $what: reply counter $repl_cnt exceeds expected value $max_repl" 1>&2
+		ret=1
+		ok=0
+	fi
+
+	if [ $ok -eq 1 ]; then
+		echo "PASS: $what"
+	fi
+}
+
 check_transfer()
 {
 	in=$1
@@ -255,11 +279,11 @@ test_tcp_forwarding_ip()
 	local dstport=$4
 	local lret=0
 
-	ip netns exec $nsb nc -w 5 -l -p 12345 < "$ns2in" > "$ns2out" &
+	ip netns exec $nsb nc -w 5 -l -p 12345 < "$nsin" > "$ns2out" &
 	lpid=$!
 
 	sleep 1
-	ip netns exec $nsa nc -w 4 "$dstip" "$dstport" < "$ns1in" > "$ns1out" &
+	ip netns exec $nsa nc -w 4 "$dstip" "$dstport" < "$nsin" > "$ns1out" &
 	cpid=$!
 
 	sleep 3
@@ -274,11 +298,11 @@ test_tcp_forwarding_ip()
 
 	wait
 
-	if ! check_transfer "$ns1in" "$ns2out" "ns1 -> ns2"; then
+	if ! check_transfer "$nsin" "$ns2out" "ns1 -> ns2"; then
 		lret=1
 	fi
 
-	if ! check_transfer "$ns2in" "$ns1out" "ns1 <- ns2"; then
+	if ! check_transfer "$nsin" "$ns1out" "ns1 <- ns2"; then
 		lret=1
 	fi
 
@@ -295,41 +319,59 @@ test_tcp_forwarding()
 test_tcp_forwarding_nat()
 {
 	local lret
+	local pmtu
 
 	test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
 	lret=$?
 
+	pmtu=$3
+	what=$4
+
 	if [ $lret -eq 0 ] ; then
+		if [ $pmtu -eq 1 ] ;then
+			check_counters "flow offload for ns1/ns2 with masquerade and pmtu discovery $what"
+		else
+			echo "PASS: flow offload for ns1/ns2 with masquerade $what"
+		fi
+
 		test_tcp_forwarding_ip "$1" "$2" 10.6.6.6 1666
 		lret=$?
+		if [ $pmtu -eq 1 ] ;then
+			check_counters "flow offload for ns1/ns2 with dnat and pmtu discovery $what"
+		elif [ $lret -eq 0 ] ; then
+			echo "PASS: flow offload for ns1/ns2 with dnat $what"
+		fi
 	fi
 
 	return $lret
 }
 
-make_file "$ns1in"
-make_file "$ns2in"
+make_file "$nsin"
 
 # First test:
 # No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed.
-if test_tcp_forwarding ns1 ns2; then
+# Due to MTU mismatch in both directions, all packets (except small packets like pure
+# acks) have to be handled by normal forwarding path.  Therefore, packet counters
+# are not checked.
+if test_tcp_forwarding $ns1 $ns2; then
 	echo "PASS: flow offloaded for ns1/ns2"
 else
 	echo "FAIL: flow offload for ns1/ns2:" 1>&2
-	ip netns exec nsr1 nft list ruleset
+	ip netns exec $nsr1 nft list ruleset
 	ret=1
 fi
 
 # delete default route, i.e. ns2 won't be able to reach ns1 and
 # will depend on ns1 being masqueraded in nsr1.
 # expect ns1 has nsr1 address.
-ip -net ns2 route del default via 10.0.2.1
-ip -net ns2 route del default via dead:2::1
-ip -net ns2 route add 192.168.10.1 via 10.0.2.1
+ip -net $ns2 route del default via 10.0.2.1
+ip -net $ns2 route del default via dead:2::1
+ip -net $ns2 route add 192.168.10.1 via 10.0.2.1
 
 # Second test:
-# Same, but with NAT enabled.
-ip netns exec nsr1 nft -f - <<EOF
+# Same, but with NAT enabled.  Same as in first test: we expect normal forward path
+# to handle most packets.
+ip netns exec $nsr1 nft -f - <<EOF
 table ip nat {
    chain prerouting {
       type nat hook prerouting priority 0; policy accept;
@@ -343,47 +385,45 @@ table ip nat {
 }
 EOF
 
-if test_tcp_forwarding_nat ns1 ns2; then
-	echo "PASS: flow offloaded for ns1/ns2 with NAT"
-else
+if ! test_tcp_forwarding_nat $ns1 $ns2 0 ""; then
 	echo "FAIL: flow offload for ns1/ns2 with NAT" 1>&2
-	ip netns exec nsr1 nft list ruleset
+	ip netns exec $nsr1 nft list ruleset
 	ret=1
 fi
 
 # Third test:
-# Same as second test, but with PMTU discovery enabled.
-handle=$(ip netns exec nsr1 nft -a list table inet filter | grep something-to-grep-for | cut -d \# -f 2)
-
-if ! ip netns exec nsr1 nft delete rule inet filter forward $handle; then
-	echo "FAIL: Could not delete large-packet accept rule"
-	exit 1
-fi
-
-ip netns exec ns1 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
-ip netns exec ns2 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
-
-if test_tcp_forwarding_nat ns1 ns2; then
-	echo "PASS: flow offloaded for ns1/ns2 with NAT and pmtu discovery"
-else
+# Same as second test, but with PMTU discovery enabled. This
+# means that we expect the fastpath to handle packets as soon
+# as the endpoints adjust the packet size.
+ip netns exec $ns1 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
+ip netns exec $ns2 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
+
+# reset counters.
+# With pmtu in-place we'll also check that nft counters
+# are lower than file size and packets were forwarded via flowtable layer.
+# For earlier tests (large mtus), packets cannot be handled via flowtable
+# (except pure acks and other small packets).
+ip netns exec $nsr1 nft reset counters table inet filter >/dev/null
+
+if ! test_tcp_forwarding_nat $ns1 $ns2 1 ""; then
 	echo "FAIL: flow offload for ns1/ns2 with NAT and pmtu discovery" 1>&2
-	ip netns exec nsr1 nft list ruleset
+	ip netns exec $nsr1 nft list ruleset
 fi
 
 # Another test:
 # Add bridge interface br0 to Router1, with NAT enabled.
-ip -net nsr1 link add name br0 type bridge
-ip -net nsr1 addr flush dev veth0
-ip -net nsr1 link set up dev veth0
-ip -net nsr1 link set veth0 master br0
-ip -net nsr1 addr add 10.0.1.1/24 dev br0
-ip -net nsr1 addr add dead:1::1/64 dev br0
-ip -net nsr1 link set up dev br0
+ip -net $nsr1 link add name br0 type bridge
+ip -net $nsr1 addr flush dev veth0
+ip -net $nsr1 link set up dev veth0
+ip -net $nsr1 link set veth0 master br0
+ip -net $nsr1 addr add 10.0.1.1/24 dev br0
+ip -net $nsr1 addr add dead:1::1/64 dev br0
+ip -net $nsr1 link set up dev br0
 
-ip netns exec nsr1 sysctl net.ipv4.conf.br0.forwarding=1 > /dev/null
+ip netns exec $nsr1 sysctl net.ipv4.conf.br0.forwarding=1 > /dev/null
 
 # br0 with NAT enabled.
-ip netns exec nsr1 nft -f - <<EOF
+ip netns exec $nsr1 nft -f - <<EOF
 flush table ip nat
 table ip nat {
    chain prerouting {
@@ -398,59 +438,56 @@ table ip nat {
 }
 EOF
 
-if test_tcp_forwarding_nat ns1 ns2; then
-	echo "PASS: flow offloaded for ns1/ns2 with bridge NAT"
-else
+if ! test_tcp_forwarding_nat $ns1 $ns2 1 "on bridge"; then
 	echo "FAIL: flow offload for ns1/ns2 with bridge NAT" 1>&2
-	ip netns exec nsr1 nft list ruleset
+	ip netns exec $nsr1 nft list ruleset
 	ret=1
 fi
 
+
 # Another test:
 # Add bridge interface br0 to Router1, with NAT and VLAN.
-ip -net nsr1 link set veth0 nomaster
-ip -net nsr1 link set down dev veth0
-ip -net nsr1 link add link veth0 name veth0.10 type vlan id 10
-ip -net nsr1 link set up dev veth0
-ip -net nsr1 link set up dev veth0.10
-ip -net nsr1 link set veth0.10 master br0
-
-ip -net ns1 addr flush dev eth0
-ip -net ns1 link add link eth0 name eth0.10 type vlan id 10
-ip -net ns1 link set eth0 up
-ip -net ns1 link set eth0.10 up
-ip -net ns1 addr add 10.0.1.99/24 dev eth0.10
-ip -net ns1 route add default via 10.0.1.1
-ip -net ns1 addr add dead:1::99/64 dev eth0.10
-
-if test_tcp_forwarding_nat ns1 ns2; then
-	echo "PASS: flow offloaded for ns1/ns2 with bridge NAT and VLAN"
-else
+ip -net $nsr1 link set veth0 nomaster
+ip -net $nsr1 link set down dev veth0
+ip -net $nsr1 link add link veth0 name veth0.10 type vlan id 10
+ip -net $nsr1 link set up dev veth0
+ip -net $nsr1 link set up dev veth0.10
+ip -net $nsr1 link set veth0.10 master br0
+
+ip -net $ns1 addr flush dev eth0
+ip -net $ns1 link add link eth0 name eth0.10 type vlan id 10
+ip -net $ns1 link set eth0 up
+ip -net $ns1 link set eth0.10 up
+ip -net $ns1 addr add 10.0.1.99/24 dev eth0.10
+ip -net $ns1 route add default via 10.0.1.1
+ip -net $ns1 addr add dead:1::99/64 dev eth0.10
+
+if ! test_tcp_forwarding_nat $ns1 $ns2 1 "bridge and VLAN"; then
 	echo "FAIL: flow offload for ns1/ns2 with bridge NAT and VLAN" 1>&2
-	ip netns exec nsr1 nft list ruleset
+	ip netns exec $nsr1 nft list ruleset
 	ret=1
 fi
 
 # restore test topology (remove bridge and VLAN)
-ip -net nsr1 link set veth0 nomaster
-ip -net nsr1 link set veth0 down
-ip -net nsr1 link set veth0.10 down
-ip -net nsr1 link delete veth0.10 type vlan
-ip -net nsr1 link delete br0 type bridge
-ip -net ns1 addr flush dev eth0.10
-ip -net ns1 link set eth0.10 down
-ip -net ns1 link set eth0 down
-ip -net ns1 link delete eth0.10 type vlan
+ip -net $nsr1 link set veth0 nomaster
+ip -net $nsr1 link set veth0 down
+ip -net $nsr1 link set veth0.10 down
+ip -net $nsr1 link delete veth0.10 type vlan
+ip -net $nsr1 link delete br0 type bridge
+ip -net $ns1 addr flush dev eth0.10
+ip -net $ns1 link set eth0.10 down
+ip -net $ns1 link set eth0 down
+ip -net $ns1 link delete eth0.10 type vlan
 
 # restore address in ns1 and nsr1
-ip -net ns1 link set eth0 up
-ip -net ns1 addr add 10.0.1.99/24 dev eth0
-ip -net ns1 route add default via 10.0.1.1
-ip -net ns1 addr add dead:1::99/64 dev eth0
-ip -net ns1 route add default via dead:1::1
-ip -net nsr1 addr add 10.0.1.1/24 dev veth0
-ip -net nsr1 addr add dead:1::1/64 dev veth0
-ip -net nsr1 link set up dev veth0
+ip -net $ns1 link set eth0 up
+ip -net $ns1 addr add 10.0.1.99/24 dev eth0
+ip -net $ns1 route add default via 10.0.1.1
+ip -net $ns1 addr add dead:1::99/64 dev eth0
+ip -net $ns1 route add default via dead:1::1
+ip -net $nsr1 addr add 10.0.1.1/24 dev veth0
+ip -net $nsr1 addr add dead:1::1/64 dev veth0
+ip -net $nsr1 link set up dev veth0
 
 KEY_SHA="0x"$(ps -xaf | sha1sum | cut -d " " -f 1)
 KEY_AES="0x"$(ps -xaf | md5sum | cut -d " " -f 1)
@@ -480,23 +517,23 @@ do_esp() {
 
 }
 
-do_esp nsr1 192.168.10.1 192.168.10.2 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2
+do_esp $nsr1 192.168.10.1 192.168.10.2 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2
 
-do_esp nsr2 192.168.10.2 192.168.10.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1
+do_esp $nsr2 192.168.10.2 192.168.10.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1
 
-ip netns exec nsr1 nft delete table ip nat
+ip netns exec $nsr1 nft delete table ip nat
 
 # restore default routes
-ip -net ns2 route del 192.168.10.1 via 10.0.2.1
-ip -net ns2 route add default via 10.0.2.1
-ip -net ns2 route add default via dead:2::1
+ip -net $ns2 route del 192.168.10.1 via 10.0.2.1
+ip -net $ns2 route add default via 10.0.2.1
+ip -net $ns2 route add default via dead:2::1
 
-if test_tcp_forwarding ns1 ns2; then
-	echo "PASS: ipsec tunnel mode for ns1/ns2"
+if test_tcp_forwarding $ns1 $ns2; then
+	check_counters "ipsec tunnel mode for ns1/ns2"
 else
 	echo "FAIL: ipsec tunnel mode for ns1/ns2"
-	ip netns exec nsr1 nft list ruleset 1>&2
-	ip netns exec nsr1 cat /proc/net/xfrm_stat 1>&2
+	ip netns exec $nsr1 nft list ruleset 1>&2
+	ip netns exec $nsr1 cat /proc/net/xfrm_stat 1>&2
 fi
 
 exit $ret
diff --git a/tools/testing/selftests/nolibc/.gitignore b/tools/testing/selftests/nolibc/.gitignore
new file mode 100644
index 000000000000..4696df589d68
--- /dev/null
+++ b/tools/testing/selftests/nolibc/.gitignore
@@ -0,0 +1,4 @@
+/initramfs/
+/nolibc-test
+/run.out
+/sysroot/
diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile
new file mode 100644
index 000000000000..69ea659caca9
--- /dev/null
+++ b/tools/testing/selftests/nolibc/Makefile
@@ -0,0 +1,135 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for nolibc tests
+include ../../../scripts/Makefile.include
+
+# we're in ".../tools/testing/selftests/nolibc"
+ifeq ($(srctree),)
+srctree := $(patsubst %/tools/testing/selftests/,%,$(dir $(CURDIR)))
+endif
+
+ifeq ($(ARCH),)
+include $(srctree)/scripts/subarch.include
+ARCH = $(SUBARCH)
+endif
+
+# kernel image names by architecture
+IMAGE_i386    = arch/x86/boot/bzImage
+IMAGE_x86     = arch/x86/boot/bzImage
+IMAGE_arm64   = arch/arm64/boot/Image
+IMAGE_arm     = arch/arm/boot/zImage
+IMAGE_mips    = vmlinuz
+IMAGE_riscv   = arch/riscv/boot/Image
+IMAGE         = $(IMAGE_$(ARCH))
+IMAGE_NAME    = $(notdir $(IMAGE))
+
+# default kernel configurations that appear to be usable
+DEFCONFIG_i386    = defconfig
+DEFCONFIG_x86     = defconfig
+DEFCONFIG_arm64   = defconfig
+DEFCONFIG_arm     = multi_v7_defconfig
+DEFCONFIG_mips    = malta_defconfig
+DEFCONFIG_riscv   = defconfig
+DEFCONFIG         = $(DEFCONFIG_$(ARCH))
+
+# optional tests to run (default = all)
+TEST =
+
+# QEMU_ARCH: arch names used by qemu
+QEMU_ARCH_i386    = i386
+QEMU_ARCH_x86     = x86_64
+QEMU_ARCH_arm64   = aarch64
+QEMU_ARCH_arm     = arm
+QEMU_ARCH_mips    = mipsel  # works with malta_defconfig
+QEMU_ARCH_riscv   = riscv64
+QEMU_ARCH         = $(QEMU_ARCH_$(ARCH))
+
+# QEMU_ARGS : some arch-specific args to pass to qemu
+QEMU_ARGS_i386    = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)"
+QEMU_ARGS_x86     = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)"
+QEMU_ARGS_arm64   = -M virt -cpu cortex-a53 -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)"
+QEMU_ARGS_arm     = -M virt -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)"
+QEMU_ARGS_mips    = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)"
+QEMU_ARGS_riscv   = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
+QEMU_ARGS         = $(QEMU_ARGS_$(ARCH))
+
+# OUTPUT is only set when run from the main makefile, otherwise
+# it defaults to this nolibc directory.
+OUTPUT ?= $(CURDIR)/
+
+ifeq ($(V),1)
+Q=
+else
+Q=@
+endif
+
+CFLAGS  ?= -Os -fno-ident -fno-asynchronous-unwind-tables
+LDFLAGS := -s
+
+help:
+	@echo "Supported targets under selftests/nolibc:"
+	@echo "  all          call the \"run\" target below"
+	@echo "  help         this help"
+	@echo "  sysroot      create the nolibc sysroot here (uses \$$ARCH)"
+	@echo "  nolibc-test  build the executable (uses \$$CC and \$$CROSS_COMPILE)"
+	@echo "  initramfs    prepare the initramfs with nolibc-test"
+	@echo "  defconfig    create a fresh new default config (uses \$$ARCH)"
+	@echo "  kernel       (re)build the kernel with the initramfs (uses \$$ARCH)"
+	@echo "  run          runs the kernel in QEMU after building it (uses \$$ARCH, \$$TEST)"
+	@echo "  rerun        runs a previously prebuilt kernel in QEMU (uses \$$ARCH, \$$TEST)"
+	@echo "  clean        clean the sysroot, initramfs, build and output files"
+	@echo ""
+	@echo "The output file is \"run.out\". Test ranges may be passed using \$$TEST."
+	@echo ""
+	@echo "Currently using the following variables:"
+	@echo "  ARCH          = $(ARCH)"
+	@echo "  CROSS_COMPILE = $(CROSS_COMPILE)"
+	@echo "  CC            = $(CC)"
+	@echo "  OUTPUT        = $(OUTPUT)"
+	@echo "  TEST          = $(TEST)"
+	@echo "  QEMU_ARCH     = $(if $(QEMU_ARCH),$(QEMU_ARCH),UNKNOWN_ARCH) [determined from \$$ARCH]"
+	@echo "  IMAGE_NAME    = $(if $(IMAGE_NAME),$(IMAGE_NAME),UNKNOWN_ARCH) [determined from \$$ARCH]"
+	@echo ""
+
+all: run
+
+sysroot: sysroot/$(ARCH)/include
+
+sysroot/$(ARCH)/include:
+	$(QUIET_MKDIR)mkdir -p sysroot
+	$(Q)$(MAKE) -C ../../../include/nolibc ARCH=$(ARCH) OUTPUT=$(CURDIR)/sysroot/ headers_standalone
+	$(Q)mv sysroot/sysroot sysroot/$(ARCH)
+
+nolibc-test: nolibc-test.c sysroot/$(ARCH)/include
+	$(QUIET_CC)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ \
+	  -nostdlib -static -Isysroot/$(ARCH)/include $< -lgcc
+
+initramfs: nolibc-test
+	$(QUIET_MKDIR)mkdir -p initramfs
+	$(call QUIET_INSTALL, initramfs/init)
+	$(Q)cp nolibc-test initramfs/init
+
+defconfig:
+	$(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) mrproper $(DEFCONFIG) prepare
+
+kernel: initramfs
+	$(Q)$(MAKE) -C $(srctree) ARCH=$(ARCH) CC=$(CC) CROSS_COMPILE=$(CROSS_COMPILE) $(IMAGE_NAME) CONFIG_INITRAMFS_SOURCE=$(CURDIR)/initramfs
+
+# run the tests after building the kernel
+run: kernel
+	$(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(srctree)/$(IMAGE)" -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out"
+	$(Q)grep -w FAIL "$(CURDIR)/run.out" && echo "See all results in $(CURDIR)/run.out" || echo "$$(grep -c ^[0-9].*OK $(CURDIR)/run.out) test(s) passed."
+
+# re-run the tests from an existing kernel
+rerun:
+	$(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(srctree)/$(IMAGE)" -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out"
+	$(Q)grep -w FAIL "$(CURDIR)/run.out" && echo "See all results in $(CURDIR)/run.out" || echo "$$(grep -c ^[0-9].*OK $(CURDIR)/run.out) test(s) passed."
+
+clean:
+	$(call QUIET_CLEAN, sysroot)
+	$(Q)rm -rf sysroot
+	$(call QUIET_CLEAN, nolibc-test)
+	$(Q)rm -f nolibc-test
+	$(call QUIET_CLEAN, initramfs)
+	$(Q)rm -rf initramfs
+	$(call QUIET_CLEAN, run.out)
+	$(Q)rm -rf run.out
diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c
new file mode 100644
index 000000000000..78bced95ac63
--- /dev/null
+++ b/tools/testing/selftests/nolibc/nolibc-test.c
@@ -0,0 +1,757 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+/* platform-specific include files coming from the compiler */
+#include <limits.h>
+
+/* libc-specific include files
+ * The program may be built in 3 ways:
+ *   $(CC) -nostdlib -include /path/to/nolibc.h => NOLIBC already defined
+ *   $(CC) -nostdlib -I/path/to/nolibc/sysroot  => _NOLIBC_* guards are present
+ *   $(CC) with default libc                    => NOLIBC* never defined
+ */
+#ifndef NOLIBC
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#ifndef _NOLIBC_STDIO_H
+/* standard libcs need more includes */
+#include <linux/reboot.h>
+#include <sys/io.h>
+#include <sys/ioctl.h>
+#include <sys/mount.h>
+#include <sys/reboot.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/sysmacros.h>
+#include <sys/time.h>
+#include <sys/wait.h>
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdarg.h>
+#include <unistd.h>
+#endif
+#endif
+
+/* will be used by nolibc by getenv() */
+char **environ;
+
+/* definition of a series of tests */
+struct test {
+	const char *name;              // test name
+	int (*func)(int min, int max); // handler
+};
+
+#ifndef _NOLIBC_STDLIB_H
+char *itoa(int i)
+{
+	static char buf[12];
+	int ret;
+
+	ret = snprintf(buf, sizeof(buf), "%d", i);
+	return (ret >= 0 && ret < sizeof(buf)) ? buf : "#err";
+}
+#endif
+
+#define CASE_ERR(err) \
+	case err: return #err
+
+/* returns the error name (e.g. "ENOENT") for common errors, "SUCCESS" for 0,
+ * or the decimal value for less common ones.
+ */
+const char *errorname(int err)
+{
+	switch (err) {
+	case 0: return "SUCCESS";
+	CASE_ERR(EPERM);
+	CASE_ERR(ENOENT);
+	CASE_ERR(ESRCH);
+	CASE_ERR(EINTR);
+	CASE_ERR(EIO);
+	CASE_ERR(ENXIO);
+	CASE_ERR(E2BIG);
+	CASE_ERR(ENOEXEC);
+	CASE_ERR(EBADF);
+	CASE_ERR(ECHILD);
+	CASE_ERR(EAGAIN);
+	CASE_ERR(ENOMEM);
+	CASE_ERR(EACCES);
+	CASE_ERR(EFAULT);
+	CASE_ERR(ENOTBLK);
+	CASE_ERR(EBUSY);
+	CASE_ERR(EEXIST);
+	CASE_ERR(EXDEV);
+	CASE_ERR(ENODEV);
+	CASE_ERR(ENOTDIR);
+	CASE_ERR(EISDIR);
+	CASE_ERR(EINVAL);
+	CASE_ERR(ENFILE);
+	CASE_ERR(EMFILE);
+	CASE_ERR(ENOTTY);
+	CASE_ERR(ETXTBSY);
+	CASE_ERR(EFBIG);
+	CASE_ERR(ENOSPC);
+	CASE_ERR(ESPIPE);
+	CASE_ERR(EROFS);
+	CASE_ERR(EMLINK);
+	CASE_ERR(EPIPE);
+	CASE_ERR(EDOM);
+	CASE_ERR(ERANGE);
+	CASE_ERR(ENOSYS);
+	default:
+		return itoa(err);
+	}
+}
+
+static int pad_spc(int llen, int cnt, const char *fmt, ...)
+{
+	va_list args;
+	int len;
+	int ret;
+
+	for (len = 0; len < cnt - llen; len++)
+		putchar(' ');
+
+	va_start(args, fmt);
+	ret = vfprintf(stdout, fmt, args);
+	va_end(args);
+	return ret < 0 ? ret : ret + len;
+}
+
+/* The tests below are intended to be used by the macroes, which evaluate
+ * expression <expr>, print the status to stdout, and update the "ret"
+ * variable to count failures. The functions themselves return the number
+ * of failures, thus either 0 or 1.
+ */
+
+#define EXPECT_ZR(cond, expr)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_zr(expr, llen); } while (0)
+
+static int expect_zr(int expr, int llen)
+{
+	int ret = !(expr == 0);
+
+	llen += printf(" = %d ", expr);
+	pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n");
+	return ret;
+}
+
+
+#define EXPECT_NZ(cond, expr, val)			\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_nz(expr, llen; } while (0)
+
+static int expect_nz(int expr, int llen)
+{
+	int ret = !(expr != 0);
+
+	llen += printf(" = %d ", expr);
+	pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n");
+	return ret;
+}
+
+
+#define EXPECT_EQ(cond, expr, val)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_eq(expr, llen, val); } while (0)
+
+static int expect_eq(int expr, int llen, int val)
+{
+	int ret = !(expr == val);
+
+	llen += printf(" = %d ", expr);
+	pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n");
+	return ret;
+}
+
+
+#define EXPECT_NE(cond, expr, val)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_ne(expr, llen, val); } while (0)
+
+static int expect_ne(int expr, int llen, int val)
+{
+	int ret = !(expr != val);
+
+	llen += printf(" = %d ", expr);
+	pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n");
+	return ret;
+}
+
+
+#define EXPECT_GE(cond, expr, val)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_ge(expr, llen, val); } while (0)
+
+static int expect_ge(int expr, int llen, int val)
+{
+	int ret = !(expr >= val);
+
+	llen += printf(" = %d ", expr);
+	pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n");
+	return ret;
+}
+
+
+#define EXPECT_GT(cond, expr, val)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_gt(expr, llen, val); } while (0)
+
+static int expect_gt(int expr, int llen, int val)
+{
+	int ret = !(expr > val);
+
+	llen += printf(" = %d ", expr);
+	pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n");
+	return ret;
+}
+
+
+#define EXPECT_LE(cond, expr, val)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_le(expr, llen, val); } while (0)
+
+static int expect_le(int expr, int llen, int val)
+{
+	int ret = !(expr <= val);
+
+	llen += printf(" = %d ", expr);
+	pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n");
+	return ret;
+}
+
+
+#define EXPECT_LT(cond, expr, val)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_lt(expr, llen, val); } while (0)
+
+static int expect_lt(int expr, int llen, int val)
+{
+	int ret = !(expr < val);
+
+	llen += printf(" = %d ", expr);
+	pad_spc(llen, 40, ret ? "[FAIL]\n" : " [OK]\n");
+	return ret;
+}
+
+
+#define EXPECT_SYSZR(cond, expr)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_syszr(expr, llen); } while (0)
+
+static int expect_syszr(int expr, int llen)
+{
+	int ret = 0;
+
+	if (expr) {
+		ret = 1;
+		llen += printf(" = %d %s ", expr, errorname(errno));
+		llen += pad_spc(llen, 40, "[FAIL]\n");
+	} else {
+		llen += printf(" = %d ", expr);
+		llen += pad_spc(llen, 40, " [OK]\n");
+	}
+	return ret;
+}
+
+
+#define EXPECT_SYSEQ(cond, expr, val)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_syseq(expr, llen, val); } while (0)
+
+static int expect_syseq(int expr, int llen, int val)
+{
+	int ret = 0;
+
+	if (expr != val) {
+		ret = 1;
+		llen += printf(" = %d %s ", expr, errorname(errno));
+		llen += pad_spc(llen, 40, "[FAIL]\n");
+	} else {
+		llen += printf(" = %d ", expr);
+		llen += pad_spc(llen, 40, " [OK]\n");
+	}
+	return ret;
+}
+
+
+#define EXPECT_SYSNE(cond, expr, val)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_sysne(expr, llen, val); } while (0)
+
+static int expect_sysne(int expr, int llen, int val)
+{
+	int ret = 0;
+
+	if (expr == val) {
+		ret = 1;
+		llen += printf(" = %d %s ", expr, errorname(errno));
+		llen += pad_spc(llen, 40, "[FAIL]\n");
+	} else {
+		llen += printf(" = %d ", expr);
+		llen += pad_spc(llen, 40, " [OK]\n");
+	}
+	return ret;
+}
+
+
+#define EXPECT_SYSER(cond, expr, expret, experr)			\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_syserr(expr, expret, experr, llen); } while (0)
+
+static int expect_syserr(int expr, int expret, int experr, int llen)
+{
+	int ret = 0;
+	int _errno = errno;
+
+	llen += printf(" = %d %s ", expr, errorname(_errno));
+	if (expr != expret || _errno != experr) {
+		ret = 1;
+		llen += printf(" != (%d %s) ", expret, errorname(experr));
+		llen += pad_spc(llen, 40, "[FAIL]\n");
+	} else {
+		llen += pad_spc(llen, 40, " [OK]\n");
+	}
+	return ret;
+}
+
+
+#define EXPECT_PTRZR(cond, expr)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_ptrzr(expr, llen); } while (0)
+
+static int expect_ptrzr(const void *expr, int llen)
+{
+	int ret = 0;
+
+	llen += printf(" = <%p> ", expr);
+	if (expr) {
+		ret = 1;
+		llen += pad_spc(llen, 40, "[FAIL]\n");
+	} else {
+		llen += pad_spc(llen, 40, " [OK]\n");
+	}
+	return ret;
+}
+
+
+#define EXPECT_PTRNZ(cond, expr)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_ptrnz(expr, llen); } while (0)
+
+static int expect_ptrnz(const void *expr, int llen)
+{
+	int ret = 0;
+
+	llen += printf(" = <%p> ", expr);
+	if (!expr) {
+		ret = 1;
+		llen += pad_spc(llen, 40, "[FAIL]\n");
+	} else {
+		llen += pad_spc(llen, 40, " [OK]\n");
+	}
+	return ret;
+}
+
+
+#define EXPECT_STRZR(cond, expr)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_strzr(expr, llen); } while (0)
+
+static int expect_strzr(const char *expr, int llen)
+{
+	int ret = 0;
+
+	llen += printf(" = <%s> ", expr);
+	if (expr) {
+		ret = 1;
+		llen += pad_spc(llen, 40, "[FAIL]\n");
+	} else {
+		llen += pad_spc(llen, 40, " [OK]\n");
+	}
+	return ret;
+}
+
+
+#define EXPECT_STRNZ(cond, expr)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_strnz(expr, llen); } while (0)
+
+static int expect_strnz(const char *expr, int llen)
+{
+	int ret = 0;
+
+	llen += printf(" = <%s> ", expr);
+	if (!expr) {
+		ret = 1;
+		llen += pad_spc(llen, 40, "[FAIL]\n");
+	} else {
+		llen += pad_spc(llen, 40, " [OK]\n");
+	}
+	return ret;
+}
+
+
+#define EXPECT_STREQ(cond, expr, cmp)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_streq(expr, llen, cmp); } while (0)
+
+static int expect_streq(const char *expr, int llen, const char *cmp)
+{
+	int ret = 0;
+
+	llen += printf(" = <%s> ", expr);
+	if (strcmp(expr, cmp) != 0) {
+		ret = 1;
+		llen += pad_spc(llen, 40, "[FAIL]\n");
+	} else {
+		llen += pad_spc(llen, 40, " [OK]\n");
+	}
+	return ret;
+}
+
+
+#define EXPECT_STRNE(cond, expr, cmp)				\
+	do { if (!cond) pad_spc(llen, 40, "[SKIPPED]\n"); else ret += expect_strne(expr, llen, cmp); } while (0)
+
+static int expect_strne(const char *expr, int llen, const char *cmp)
+{
+	int ret = 0;
+
+	llen += printf(" = <%s> ", expr);
+	if (strcmp(expr, cmp) == 0) {
+		ret = 1;
+		llen += pad_spc(llen, 40, "[FAIL]\n");
+	} else {
+		llen += pad_spc(llen, 40, " [OK]\n");
+	}
+	return ret;
+}
+
+
+/* declare tests based on line numbers. There must be exactly one test per line. */
+#define CASE_TEST(name) \
+	case __LINE__: llen += printf("%d %s", test, #name);
+
+
+/* used by some syscall tests below */
+int test_getdents64(const char *dir)
+{
+	char buffer[4096];
+	int fd, ret;
+	int err;
+
+	ret = fd = open(dir, O_RDONLY | O_DIRECTORY, 0);
+	if (ret < 0)
+		return ret;
+
+	ret = getdents64(fd, (void *)buffer, sizeof(buffer));
+	err = errno;
+	close(fd);
+
+	errno = err;
+	return ret;
+}
+
+/* Run syscall tests between IDs <min> and <max>.
+ * Return 0 on success, non-zero on failure.
+ */
+int run_syscall(int min, int max)
+{
+	struct stat stat_buf;
+	int proc;
+	int test;
+	int tmp;
+	int ret = 0;
+	void *p1, *p2;
+
+	/* <proc> indicates whether or not /proc is mounted */
+	proc = stat("/proc", &stat_buf) == 0;
+
+	for (test = min; test >= 0 && test <= max; test++) {
+		int llen = 0; // line length
+
+		/* avoid leaving empty lines below, this will insert holes into
+		 * test numbers.
+		 */
+		switch (test + __LINE__ + 1) {
+		CASE_TEST(getpid);            EXPECT_SYSNE(1, getpid(), -1); break;
+		CASE_TEST(getppid);           EXPECT_SYSNE(1, getppid(), -1); break;
+#ifdef NOLIBC
+		CASE_TEST(gettid);            EXPECT_SYSNE(1, gettid(), -1); break;
+#endif
+		CASE_TEST(getpgid_self);      EXPECT_SYSNE(1, getpgid(0), -1); break;
+		CASE_TEST(getpgid_bad);       EXPECT_SYSER(1, getpgid(-1), -1, ESRCH); break;
+		CASE_TEST(kill_0);            EXPECT_SYSZR(1, kill(getpid(), 0)); break;
+		CASE_TEST(kill_CONT);         EXPECT_SYSZR(1, kill(getpid(), 0)); break;
+		CASE_TEST(kill_BADPID);       EXPECT_SYSER(1, kill(INT_MAX, 0), -1, ESRCH); break;
+		CASE_TEST(sbrk);              if ((p1 = p2 = sbrk(4096)) != (void *)-1) p2 = sbrk(-4096); EXPECT_SYSZR(1, (p2 == (void *)-1) || p2 == p1); break;
+		CASE_TEST(brk);               EXPECT_SYSZR(1, brk(sbrk(0))); break;
+		CASE_TEST(chdir_root);        EXPECT_SYSZR(1, chdir("/")); break;
+		CASE_TEST(chdir_dot);         EXPECT_SYSZR(1, chdir(".")); break;
+		CASE_TEST(chdir_blah);        EXPECT_SYSER(1, chdir("/blah"), -1, ENOENT); break;
+		CASE_TEST(chmod_net);         EXPECT_SYSZR(proc, chmod("/proc/self/net", 0555)); break;
+		CASE_TEST(chmod_self);        EXPECT_SYSER(proc, chmod("/proc/self", 0555), -1, EPERM); break;
+		CASE_TEST(chown_self);        EXPECT_SYSER(proc, chown("/proc/self", 0, 0), -1, EPERM); break;
+		CASE_TEST(chroot_root);       EXPECT_SYSZR(1, chroot("/")); break;
+		CASE_TEST(chroot_blah);       EXPECT_SYSER(1, chroot("/proc/self/blah"), -1, ENOENT); break;
+		CASE_TEST(chroot_exe);        EXPECT_SYSER(proc, chroot("/proc/self/exe"), -1, ENOTDIR); break;
+		CASE_TEST(close_m1);          EXPECT_SYSER(1, close(-1), -1, EBADF); break;
+		CASE_TEST(close_dup);         EXPECT_SYSZR(1, close(dup(0))); break;
+		CASE_TEST(dup_0);             tmp = dup(0);  EXPECT_SYSNE(1, tmp, -1); close(tmp); break;
+		CASE_TEST(dup_m1);            tmp = dup(-1); EXPECT_SYSER(1, tmp, -1, EBADF); if (tmp != -1) close(tmp); break;
+		CASE_TEST(dup2_0);            tmp = dup2(0, 100);  EXPECT_SYSNE(1, tmp, -1); close(tmp); break;
+		CASE_TEST(dup2_m1);           tmp = dup2(-1, 100); EXPECT_SYSER(1, tmp, -1, EBADF); if (tmp != -1) close(tmp); break;
+		CASE_TEST(dup3_0);            tmp = dup3(0, 100, 0);  EXPECT_SYSNE(1, tmp, -1); close(tmp); break;
+		CASE_TEST(dup3_m1);           tmp = dup3(-1, 100, 0); EXPECT_SYSER(1, tmp, -1, EBADF); if (tmp != -1) close(tmp); break;
+		CASE_TEST(execve_root);       EXPECT_SYSER(1, execve("/", (char*[]){ [0] = "/", [1] = NULL }, NULL), -1, EACCES); break;
+		CASE_TEST(getdents64_root);   EXPECT_SYSNE(1, test_getdents64("/"), -1); break;
+		CASE_TEST(getdents64_null);   EXPECT_SYSER(1, test_getdents64("/dev/null"), -1, ENOTDIR); break;
+		CASE_TEST(gettimeofday_null); EXPECT_SYSZR(1, gettimeofday(NULL, NULL)); break;
+#ifdef NOLIBC
+		CASE_TEST(gettimeofday_bad1); EXPECT_SYSER(1, gettimeofday((void *)1, NULL), -1, EFAULT); break;
+		CASE_TEST(gettimeofday_bad2); EXPECT_SYSER(1, gettimeofday(NULL, (void *)1), -1, EFAULT); break;
+		CASE_TEST(gettimeofday_bad2); EXPECT_SYSER(1, gettimeofday(NULL, (void *)1), -1, EFAULT); break;
+#endif
+		CASE_TEST(ioctl_tiocinq);     EXPECT_SYSZR(1, ioctl(0, TIOCINQ, &tmp)); break;
+		CASE_TEST(ioctl_tiocinq);     EXPECT_SYSZR(1, ioctl(0, TIOCINQ, &tmp)); break;
+		CASE_TEST(link_root1);        EXPECT_SYSER(1, link("/", "/"), -1, EEXIST); break;
+		CASE_TEST(link_blah);         EXPECT_SYSER(1, link("/proc/self/blah", "/blah"), -1, ENOENT); break;
+		CASE_TEST(link_dir);          EXPECT_SYSER(1, link("/", "/blah"), -1, EPERM); break;
+		CASE_TEST(link_cross);        EXPECT_SYSER(proc, link("/proc/self/net", "/blah"), -1, EXDEV); break;
+		CASE_TEST(lseek_m1);          EXPECT_SYSER(1, lseek(-1, 0, SEEK_SET), -1, EBADF); break;
+		CASE_TEST(lseek_0);           EXPECT_SYSER(1, lseek(0, 0, SEEK_SET), -1, ESPIPE); break;
+		CASE_TEST(mkdir_root);        EXPECT_SYSER(1, mkdir("/", 0755), -1, EEXIST); break;
+		CASE_TEST(open_tty);          EXPECT_SYSNE(1, tmp = open("/dev/null", 0), -1); if (tmp != -1) close(tmp); break;
+		CASE_TEST(open_blah);         EXPECT_SYSER(1, tmp = open("/proc/self/blah", 0), -1, ENOENT); if (tmp != -1) close(tmp); break;
+		CASE_TEST(poll_null);         EXPECT_SYSZR(1, poll(NULL, 0, 0)); break;
+		CASE_TEST(poll_stdout);       EXPECT_SYSNE(1, ({ struct pollfd fds = { 1, POLLOUT, 0}; poll(&fds, 1, 0); }), -1); break;
+		CASE_TEST(poll_fault);        EXPECT_SYSER(1, poll((void *)1, 1, 0), -1, EFAULT); break;
+		CASE_TEST(read_badf);         EXPECT_SYSER(1, read(-1, &tmp, 1), -1, EBADF); break;
+		CASE_TEST(sched_yield);       EXPECT_SYSZR(1, sched_yield()); break;
+		CASE_TEST(select_null);       EXPECT_SYSZR(1, ({ struct timeval tv = { 0 }; select(0, NULL, NULL, NULL, &tv); })); break;
+		CASE_TEST(select_stdout);     EXPECT_SYSNE(1, ({ fd_set fds; FD_ZERO(&fds); FD_SET(1, &fds); select(2, NULL, &fds, NULL, NULL); }), -1); break;
+		CASE_TEST(select_fault);      EXPECT_SYSER(1, select(1, (void *)1, NULL, NULL, 0), -1, EFAULT); break;
+		CASE_TEST(stat_blah);         EXPECT_SYSER(1, stat("/proc/self/blah", &stat_buf), -1, ENOENT); break;
+		CASE_TEST(stat_fault);        EXPECT_SYSER(1, stat(NULL, &stat_buf), -1, EFAULT); break;
+		CASE_TEST(symlink_root);      EXPECT_SYSER(1, symlink("/", "/"), -1, EEXIST); break;
+		CASE_TEST(unlink_root);       EXPECT_SYSER(1, unlink("/"), -1, EISDIR); break;
+		CASE_TEST(unlink_blah);       EXPECT_SYSER(1, unlink("/proc/self/blah"), -1, ENOENT); break;
+		CASE_TEST(wait_child);        EXPECT_SYSER(1, wait(&tmp), -1, ECHILD); break;
+		CASE_TEST(waitpid_min);       EXPECT_SYSER(1, waitpid(INT_MIN, &tmp, WNOHANG), -1, ESRCH); break;
+		CASE_TEST(waitpid_child);     EXPECT_SYSER(1, waitpid(getpid(), &tmp, WNOHANG), -1, ECHILD); break;
+		CASE_TEST(write_badf);        EXPECT_SYSER(1, write(-1, &tmp, 1), -1, EBADF); break;
+		CASE_TEST(write_zero);        EXPECT_SYSZR(1, write(1, &tmp, 0)); break;
+		case __LINE__:
+			return ret; /* must be last */
+		/* note: do not set any defaults so as to permit holes above */
+		}
+	}
+	return ret;
+}
+
+int run_stdlib(int min, int max)
+{
+	int test;
+	int tmp;
+	int ret = 0;
+	void *p1, *p2;
+
+	for (test = min; test >= 0 && test <= max; test++) {
+		int llen = 0; // line length
+
+		/* avoid leaving empty lines below, this will insert holes into
+		 * test numbers.
+		 */
+		switch (test + __LINE__ + 1) {
+		CASE_TEST(getenv_TERM);        EXPECT_STRNZ(1, getenv("TERM")); break;
+		CASE_TEST(getenv_blah);        EXPECT_STRZR(1, getenv("blah")); break;
+		CASE_TEST(setcmp_blah_blah);   EXPECT_EQ(1, strcmp("blah", "blah"), 0); break;
+		CASE_TEST(setcmp_blah_blah2);  EXPECT_NE(1, strcmp("blah", "blah2"), 0); break;
+		CASE_TEST(setncmp_blah_blah);  EXPECT_EQ(1, strncmp("blah", "blah", 10), 0); break;
+		CASE_TEST(setncmp_blah_blah4); EXPECT_EQ(1, strncmp("blah", "blah4", 4), 0); break;
+		CASE_TEST(setncmp_blah_blah5); EXPECT_NE(1, strncmp("blah", "blah5", 5), 0); break;
+		CASE_TEST(setncmp_blah_blah6); EXPECT_NE(1, strncmp("blah", "blah6", 6), 0); break;
+		CASE_TEST(strchr_foobar_o);    EXPECT_STREQ(1, strchr("foobar", 'o'), "oobar"); break;
+		CASE_TEST(strchr_foobar_z);    EXPECT_STRZR(1, strchr("foobar", 'z')); break;
+		CASE_TEST(strrchr_foobar_o);   EXPECT_STREQ(1, strrchr("foobar", 'o'), "obar"); break;
+		CASE_TEST(strrchr_foobar_z);   EXPECT_STRZR(1, strrchr("foobar", 'z')); break;
+		case __LINE__:
+			return ret; /* must be last */
+		/* note: do not set any defaults so as to permit holes above */
+		}
+	}
+	return ret;
+}
+
+/* prepare what needs to be prepared for pid 1 (stdio, /dev, /proc, etc) */
+int prepare(void)
+{
+	struct stat stat_buf;
+
+	/* It's possible that /dev doesn't even exist or was not mounted, so
+	 * we'll try to create it, mount it, or create minimal entries into it.
+	 * We want at least /dev/null and /dev/console.
+	 */
+	if (stat("/dev/.", &stat_buf) == 0 || mkdir("/dev", 0755) == 0) {
+		if (stat("/dev/console", &stat_buf) != 0 ||
+		    stat("/dev/null", &stat_buf) != 0) {
+			/* try devtmpfs first, otherwise fall back to manual creation */
+			if (mount("/dev", "/dev", "devtmpfs", 0, 0) != 0) {
+				mknod("/dev/console", 0600 | S_IFCHR, makedev(5, 1));
+				mknod("/dev/null",    0666 | S_IFCHR, makedev(1, 3));
+			}
+		}
+	}
+
+	/* If no /dev/console was found before calling init, stdio is closed so
+	 * we need to reopen it from /dev/console. If it failed above, it will
+	 * still fail here and we cannot emit a message anyway.
+	 */
+	if (close(dup(1)) == -1) {
+		int fd = open("/dev/console", O_RDWR);
+
+		if (fd >= 0) {
+			if (fd != 0)
+				dup2(fd, 0);
+			if (fd != 1)
+				dup2(fd, 1);
+			if (fd != 2)
+				dup2(fd, 2);
+			if (fd > 2)
+				close(fd);
+			puts("\nSuccessfully reopened /dev/console.");
+		}
+	}
+
+	/* try to mount /proc if not mounted. Silently fail otherwise */
+	if (stat("/proc/.", &stat_buf) == 0 || mkdir("/proc", 0755) == 0) {
+		if (stat("/proc/self", &stat_buf) != 0)
+			mount("/proc", "/proc", "proc", 0, 0);
+	}
+
+	return 0;
+}
+
+/* This is the definition of known test names, with their functions */
+static struct test test_names[] = {
+	/* add new tests here */
+	{ .name = "syscall",   .func = run_syscall  },
+	{ .name = "stdlib",    .func = run_stdlib   },
+	{ 0 }
+};
+
+int main(int argc, char **argv, char **envp)
+{
+	int min = 0;
+	int max = __INT_MAX__;
+	int ret = 0;
+	int err;
+	int idx;
+	char *test;
+
+	environ = envp;
+
+	/* when called as init, it's possible that no console was opened, for
+	 * example if no /dev file system was provided. We'll check that fd#1
+	 * was opened, and if not we'll attempt to create and open /dev/console
+	 * and /dev/null that we'll use for later tests.
+	 */
+	if (getpid() == 1)
+		prepare();
+
+	/* the definition of a series of tests comes from either argv[1] or the
+	 * "NOLIBC_TEST" environment variable. It's made of a comma-delimited
+	 * series of test names and optional ranges:
+	 *    syscall:5-15[:.*],stdlib:8-10
+	 */
+	test = argv[1];
+	if (!test)
+		test = getenv("NOLIBC_TEST");
+
+	if (test) {
+		char *comma, *colon, *dash, *value;
+
+		do {
+			comma = strchr(test, ',');
+			if (comma)
+				*(comma++) = '\0';
+
+			colon = strchr(test, ':');
+			if (colon)
+				*(colon++) = '\0';
+
+			for (idx = 0; test_names[idx].name; idx++) {
+				if (strcmp(test, test_names[idx].name) == 0)
+					break;
+			}
+
+			if (test_names[idx].name) {
+				/* The test was named, it will be called at least
+				 * once. We may have an optional range at <colon>
+				 * here, which defaults to the full range.
+				 */
+				do {
+					min = 0; max = __INT_MAX__;
+					value = colon;
+					if (value && *value) {
+						colon = strchr(value, ':');
+						if (colon)
+							*(colon++) = '\0';
+
+						dash = strchr(value, '-');
+						if (dash)
+							*(dash++) = '\0';
+
+						/* support :val: :min-max: :min-: :-max: */
+						if (*value)
+							min = atoi(value);
+						if (!dash)
+							max = min;
+						else if (*dash)
+							max = atoi(dash);
+
+						value = colon;
+					}
+
+					/* now's time to call the test */
+					printf("Running test '%s'\n", test_names[idx].name);
+					err = test_names[idx].func(min, max);
+					ret += err;
+					printf("Errors during this test: %d\n\n", err);
+				} while (colon && *colon);
+			} else
+				printf("Ignoring unknown test name '%s'\n", test);
+
+			test = comma;
+		} while (test && *test);
+	} else {
+		/* no test mentioned, run everything */
+		for (idx = 0; test_names[idx].name; idx++) {
+			printf("Running test '%s'\n", test_names[idx].name);
+			err = test_names[idx].func(min, max);
+			ret += err;
+			printf("Errors during this test: %d\n\n", err);
+		}
+	}
+
+	printf("Total number of errors: %d\n", ret);
+
+	if (getpid() == 1) {
+		/* we're running as init, there's no other process on the
+		 * system, thus likely started from a VM for a quick check.
+		 * Exiting will provoke a kernel panic that may be reported
+		 * as an error by Qemu or the hypervisor, while stopping
+		 * cleanly will often be reported as a success. This allows
+		 * to use the output of this program for bisecting kernels.
+		 */
+		printf("Leaving init with final status: %d\n", !!ret);
+		if (ret == 0)
+			reboot(LINUX_REBOOT_CMD_POWER_OFF);
+#if defined(__x86_64__)
+		/* QEMU started with "-device isa-debug-exit -no-reboot" will
+		 * exit with status code 2N+1 when N is written to 0x501. We
+		 * hard-code the syscall here as it's arch-dependent.
+		 */
+#if defined(_NOLIBC_SYS_H)
+		else if (my_syscall3(__NR_ioperm, 0x501, 1, 1) == 0)
+#else
+		else if (ioperm(0x501, 1, 1) == 0)
+#endif
+			asm volatile ("outb %%al, %%dx" :: "d"(0x501), "a"(0));
+		/* if it does nothing, fall back to the regular panic */
+#endif
+	}
+
+	printf("Exiting with status %d\n", !!ret);
+	return !!ret;
+}
diff --git a/tools/testing/selftests/powerpc/pmu/event_code_tests/.gitignore b/tools/testing/selftests/powerpc/pmu/event_code_tests/.gitignore
new file mode 100644
index 000000000000..5710683da525
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/event_code_tests/.gitignore
@@ -0,0 +1,20 @@
+blacklisted_events_test
+event_alternatives_tests_p10
+event_alternatives_tests_p9
+generic_events_valid_test
+group_constraint_cache_test
+group_constraint_l2l3_sel_test
+group_constraint_mmcra_sample_test
+group_constraint_pmc56_test
+group_constraint_pmc_count_test
+group_constraint_radix_scope_qual_test
+group_constraint_repeat_test
+group_constraint_thresh_cmp_test
+group_constraint_thresh_ctl_test
+group_constraint_thresh_sel_test
+group_constraint_unit_test
+group_pmc56_exclude_constraints_test
+hw_cache_event_type_test
+invalid_event_code_test
+reserved_bits_mmcra_sample_elig_mode_test
+reserved_bits_mmcra_thresh_ctl_test
diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/.gitignore b/tools/testing/selftests/powerpc/pmu/sampling_tests/.gitignore
index 0fce5a694684..f93b4c7c3a8a 100644
--- a/tools/testing/selftests/powerpc/pmu/sampling_tests/.gitignore
+++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/.gitignore
@@ -1,11 +1,21 @@
-mmcr0_exceptionbits_test
+bhrb_filter_map_test
+bhrb_no_crash_wo_pmu_test
+intr_regs_no_crash_wo_pmu_test
 mmcr0_cc56run_test
-mmcr0_pmccext_test
-mmcr0_pmcjce_test
+mmcr0_exceptionbits_test
 mmcr0_fc56_pmc1ce_test
 mmcr0_fc56_pmc56_test
+mmcr0_pmccext_test
+mmcr0_pmcjce_test
 mmcr1_comb_test
-mmcr2_l2l3_test
+mmcr1_sel_unit_cache_test
 mmcr2_fcs_fch_test
+mmcr2_l2l3_test
 mmcr3_src_test
+mmcra_bhrb_any_test
+mmcra_bhrb_cond_test
+mmcra_bhrb_disable_no_branch_test
+mmcra_bhrb_disable_test
+mmcra_bhrb_ind_call_test
+mmcra_thresh_cmp_test
 mmcra_thresh_marked_sample_test
diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c
index 50c5ab1aa6fa..a07896a46364 100644
--- a/tools/testing/selftests/sgx/sigstruct.c
+++ b/tools/testing/selftests/sgx/sigstruct.c
@@ -17,6 +17,12 @@
 #include "defines.h"
 #include "main.h"
 
+/*
+ * FIXME: OpenSSL 3.0 has deprecated some functions. For now just ignore
+ * the warnings.
+ */
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
+
 struct q1q2_ctx {
 	BN_CTX *bn_ctx;
 	BIGNUM *m;
diff --git a/tools/testing/selftests/timens/Makefile b/tools/testing/selftests/timens/Makefile
index f0d51d4d2c87..3a5936cc10ab 100644
--- a/tools/testing/selftests/timens/Makefile
+++ b/tools/testing/selftests/timens/Makefile
@@ -1,4 +1,4 @@
-TEST_GEN_PROGS := timens timerfd timer clock_nanosleep procfs exec futex vfork_exec
+TEST_GEN_PROGS := timens timerfd timer clock_nanosleep procfs exec futex
 TEST_GEN_PROGS_EXTENDED := gettime_perf
 
 CFLAGS := -Wall -Werror -pthread
diff --git a/tools/testing/selftests/timens/vfork_exec.c b/tools/testing/selftests/timens/vfork_exec.c
deleted file mode 100644
index e6ccd900f30a..000000000000
--- a/tools/testing/selftests/timens/vfork_exec.c
+++ /dev/null
@@ -1,90 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#define _GNU_SOURCE
-#include <errno.h>
-#include <fcntl.h>
-#include <sched.h>
-#include <stdio.h>
-#include <stdbool.h>
-#include <sys/stat.h>
-#include <sys/syscall.h>
-#include <sys/types.h>
-#include <sys/wait.h>
-#include <time.h>
-#include <unistd.h>
-#include <string.h>
-
-#include "log.h"
-#include "timens.h"
-
-#define OFFSET (36000)
-
-int main(int argc, char *argv[])
-{
-	struct timespec now, tst;
-	int status, i;
-	pid_t pid;
-
-	if (argc > 1) {
-		if (sscanf(argv[1], "%ld", &now.tv_sec) != 1)
-			return pr_perror("sscanf");
-
-		for (i = 0; i < 2; i++) {
-			_gettime(CLOCK_MONOTONIC, &tst, i);
-			if (abs(tst.tv_sec - now.tv_sec) > 5)
-				return pr_fail("%ld %ld\n", now.tv_sec, tst.tv_sec);
-		}
-		return 0;
-	}
-
-	nscheck();
-
-	ksft_set_plan(1);
-
-	clock_gettime(CLOCK_MONOTONIC, &now);
-
-	if (unshare_timens())
-		return 1;
-
-	if (_settime(CLOCK_MONOTONIC, OFFSET))
-		return 1;
-
-	for (i = 0; i < 2; i++) {
-		_gettime(CLOCK_MONOTONIC, &tst, i);
-		if (abs(tst.tv_sec - now.tv_sec) > 5)
-			return pr_fail("%ld %ld\n",
-					now.tv_sec, tst.tv_sec);
-	}
-
-	pid = vfork();
-	if (pid < 0)
-		return pr_perror("fork");
-
-	if (pid == 0) {
-		char now_str[64];
-		char *cargv[] = {"exec", now_str, NULL};
-		char *cenv[] = {NULL};
-
-		// Check that we are still in the source timens.
-		for (i = 0; i < 2; i++) {
-			_gettime(CLOCK_MONOTONIC, &tst, i);
-			if (abs(tst.tv_sec - now.tv_sec) > 5)
-				return pr_fail("%ld %ld\n",
-						now.tv_sec, tst.tv_sec);
-		}
-
-		/* Check for proper vvar offsets after execve. */
-		snprintf(now_str, sizeof(now_str), "%ld", now.tv_sec + OFFSET);
-		execve("/proc/self/exe", cargv, cenv);
-		return pr_perror("execve");
-	}
-
-	if (waitpid(pid, &status, 0) != pid)
-		return pr_perror("waitpid");
-
-	if (status)
-		ksft_exit_fail();
-
-	ksft_test_result_pass("exec\n");
-	ksft_exit_pass();
-	return 0;
-}
diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile
index fda76282d34b..e95bd56b332f 100644
--- a/tools/testing/selftests/wireguard/qemu/Makefile
+++ b/tools/testing/selftests/wireguard/qemu/Makefile
@@ -343,8 +343,10 @@ $(KERNEL_BZIMAGE): $(TOOLCHAIN_PATH)/.installed $(KERNEL_BUILD_PATH)/.config $(B
 .PHONY: $(KERNEL_BZIMAGE)
 
 $(TOOLCHAIN_PATH)/$(CHOST)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config $(TOOLCHAIN_PATH)/.installed
+ifneq ($(ARCH),um)
 	rm -rf $(TOOLCHAIN_PATH)/$(CHOST)/include/linux
 	$(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(TOOLCHAIN_PATH)/$(CHOST) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install
+endif
 	touch $@
 
 $(TOOLCHAIN_PATH)/.installed: $(TOOLCHAIN_TAR)
diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile
index 1bea2d16d4c1..22e28b76f800 100644
--- a/tools/tracing/rtla/Makefile
+++ b/tools/tracing/rtla/Makefile
@@ -30,8 +30,8 @@ WOPTS	:= 	-Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_A
 
 TRACEFS_HEADERS	:= $$($(PKG_CONFIG) --cflags libtracefs)
 
-CFLAGS	:=	-O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS)
-LDFLAGS	:=	-ggdb
+CFLAGS	:=	-O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS)
+LDFLAGS	:=	-ggdb $(EXTRA_LDFLAGS)
 LIBS	:=	$$($(PKG_CONFIG) --libs libtracefs)
 
 SRC	:=	$(wildcard src/*.c)
@@ -61,40 +61,50 @@ endif
 LIBTRACEEVENT_MIN_VERSION = 1.5
 LIBTRACEFS_MIN_VERSION = 1.3
 
+.PHONY:	all warnings show_warnings
+all:	warnings rtla
+
 TEST_LIBTRACEEVENT = $(shell sh -c "$(PKG_CONFIG) --atleast-version $(LIBTRACEEVENT_MIN_VERSION) libtraceevent > /dev/null 2>&1 || echo n")
 ifeq ("$(TEST_LIBTRACEEVENT)", "n")
-.PHONY: warning_traceevent
-warning_traceevent:
-	@echo "********************************************"
-	@echo "** NOTICE: libtraceevent version $(LIBTRACEEVENT_MIN_VERSION) or higher not found"
-	@echo "**"
-	@echo "** Consider installing the latest libtraceevent from your"
-	@echo "** distribution, e.g., 'dnf install libtraceevent' on Fedora,"
-	@echo "** or from source:"
-	@echo "**"
-	@echo "**  https://git.kernel.org/pub/scm/libs/libtrace/libtraceevent.git/ "
-	@echo "**"
-	@echo "********************************************"
+WARNINGS = show_warnings
+MISSING_LIBS += echo "**   libtraceevent version $(LIBTRACEEVENT_MIN_VERSION) or higher";
+MISSING_PACKAGES += "libtraceevent-devel"
+MISSING_SOURCE += echo "**  https://git.kernel.org/pub/scm/libs/libtrace/libtraceevent.git/ ";
 endif
 
 TEST_LIBTRACEFS = $(shell sh -c "$(PKG_CONFIG) --atleast-version $(LIBTRACEFS_MIN_VERSION) libtracefs > /dev/null 2>&1 || echo n")
 ifeq ("$(TEST_LIBTRACEFS)", "n")
-.PHONY: warning_tracefs
-warning_tracefs:
-	@echo "********************************************"
-	@echo "** NOTICE: libtracefs version $(LIBTRACEFS_MIN_VERSION) or higher not found"
-	@echo "**"
-	@echo "** Consider installing the latest libtracefs from your"
-	@echo "** distribution, e.g., 'dnf install libtracefs' on Fedora,"
-	@echo "** or from source:"
-	@echo "**"
-	@echo "**  https://git.kernel.org/pub/scm/libs/libtrace/libtracefs.git/ "
-	@echo "**"
-	@echo "********************************************"
+WARNINGS = show_warnings
+MISSING_LIBS += echo "**   libtracefs version $(LIBTRACEFS_MIN_VERSION) or higher";
+MISSING_PACKAGES += "libtracefs-devel"
+MISSING_SOURCE += echo "**  https://git.kernel.org/pub/scm/libs/libtrace/libtracefs.git/ ";
 endif
 
-.PHONY:	all
-all:	rtla
+define show_dependencies
+	@echo "********************************************";				\
+	echo "** NOTICE: Failed build dependencies";					\
+	echo "**";									\
+	echo "** Required Libraries:";							\
+	$(MISSING_LIBS)									\
+	echo "**";									\
+	echo "** Consider installing the latest libtracefs from your";			\
+	echo "** distribution, e.g., 'dnf install $(MISSING_PACKAGES)' on Fedora,";	\
+	echo "** or from source:";							\
+	echo "**";									\
+	$(MISSING_SOURCE)								\
+	echo "**";									\
+	echo "********************************************"
+endef
+
+show_warnings:
+	$(call show_dependencies);
+
+ifneq ("$(WARNINGS)", "")
+ERROR_OUT = $(error Please add the necessary dependencies)
+
+warnings: $(WARNINGS)
+	$(ERROR_OUT)
+endif
 
 rtla: $(OBJ)
 	$(CC) -o rtla $(LDFLAGS) $(OBJ) $(LIBS)
@@ -108,9 +118,9 @@ install: doc_install
 	$(INSTALL) rtla -m 755 $(DESTDIR)$(BINDIR)
 	$(STRIP) $(DESTDIR)$(BINDIR)/rtla
 	@test ! -f $(DESTDIR)$(BINDIR)/osnoise || rm $(DESTDIR)$(BINDIR)/osnoise
-	ln -s $(DESTDIR)$(BINDIR)/rtla $(DESTDIR)$(BINDIR)/osnoise
+	ln -s rtla $(DESTDIR)$(BINDIR)/osnoise
 	@test ! -f $(DESTDIR)$(BINDIR)/timerlat || rm $(DESTDIR)$(BINDIR)/timerlat
-	ln -s $(DESTDIR)$(BINDIR)/rtla $(DESTDIR)$(BINDIR)/timerlat
+	ln -s rtla $(DESTDIR)$(BINDIR)/timerlat
 
 .PHONY: clean tarball
 clean: doc_clean
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index f3ec628f5e51..4b48af8a8309 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -892,7 +892,7 @@ int timerlat_hist_main(int argc, char *argv[])
 	return_value = 0;
 
 	if (trace_is_off(&tool->trace, &record->trace)) {
-		printf("rtla timelat hit stop tracing\n");
+		printf("rtla timerlat hit stop tracing\n");
 		if (params->trace_output) {
 			printf("  Saving trace to %s\n", params->trace_output);
 			save_trace_to_file(record->trace.inst, params->trace_output);
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
index 35452a1d45e9..334271935222 100644
--- a/tools/tracing/rtla/src/timerlat_top.c
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -687,7 +687,7 @@ int timerlat_top_main(int argc, char *argv[])
 	return_value = 0;
 
 	if (trace_is_off(&top->trace, &record->trace)) {
-		printf("rtla timelat hit stop tracing\n");
+		printf("rtla timerlat hit stop tracing\n");
 		if (params->trace_output) {
 			printf("  Saving trace to %s\n", params->trace_output);
 			save_trace_to_file(record->trace.inst, params->trace_output);
diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h
index 363b98228301..5d3440f474dd 100644
--- a/tools/virtio/linux/virtio.h
+++ b/tools/virtio/linux/virtio.h
@@ -14,6 +14,7 @@ struct virtio_device {
 	u64 features;
 	struct list_head vqs;
 	spinlock_t vqs_list_lock;
+	const struct virtio_config_ops *config;
 };
 
 struct virtqueue {
@@ -23,7 +24,9 @@ struct virtqueue {
 	struct virtio_device *vdev;
         unsigned int index;
         unsigned int num_free;
+	unsigned int num_max;
 	void *priv;
+	bool reset;
 };
 
 /* Interfaces exported by virtio_ring. */
diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h
index f2640e505c4e..2a8a70e2a950 100644
--- a/tools/virtio/linux/virtio_config.h
+++ b/tools/virtio/linux/virtio_config.h
@@ -3,6 +3,11 @@
 #include <linux/virtio.h>
 #include <uapi/linux/virtio_config.h>
 
+struct virtio_config_ops {
+	int (*disable_vq_and_reset)(struct virtqueue *vq);
+	int (*enable_vq_after_reset)(struct virtqueue *vq);
+};
+
 /*
  * __virtio_test_bit - helper to test feature bits. For use by transports.
  *                     Devices should normally use virtio_has_feature,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 515dfe9d3bcf..584a5bab3af3 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -702,30 +702,31 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 
 	/*
 	 * .change_pte() must be surrounded by .invalidate_range_{start,end}().
-	 * If mmu_notifier_count is zero, then no in-progress invalidations,
-	 * including this one, found a relevant memslot at start(); rechecking
-	 * memslots here is unnecessary.  Note, a false positive (count elevated
-	 * by a different invalidation) is sub-optimal but functionally ok.
+	 * If mmu_invalidate_in_progress is zero, then no in-progress
+	 * invalidations, including this one, found a relevant memslot at
+	 * start(); rechecking memslots here is unnecessary.  Note, a false
+	 * positive (count elevated by a different invalidation) is sub-optimal
+	 * but functionally ok.
 	 */
 	WARN_ON_ONCE(!READ_ONCE(kvm->mn_active_invalidate_count));
-	if (!READ_ONCE(kvm->mmu_notifier_count))
+	if (!READ_ONCE(kvm->mmu_invalidate_in_progress))
 		return;
 
 	kvm_handle_hva_range(mn, address, address + 1, pte, kvm_set_spte_gfn);
 }
 
-void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
-				   unsigned long end)
+void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
+			      unsigned long end)
 {
 	/*
 	 * The count increase must become visible at unlock time as no
 	 * spte can be established without taking the mmu_lock and
 	 * count is also read inside the mmu_lock critical section.
 	 */
-	kvm->mmu_notifier_count++;
-	if (likely(kvm->mmu_notifier_count == 1)) {
-		kvm->mmu_notifier_range_start = start;
-		kvm->mmu_notifier_range_end = end;
+	kvm->mmu_invalidate_in_progress++;
+	if (likely(kvm->mmu_invalidate_in_progress == 1)) {
+		kvm->mmu_invalidate_range_start = start;
+		kvm->mmu_invalidate_range_end = end;
 	} else {
 		/*
 		 * Fully tracking multiple concurrent ranges has diminishing
@@ -736,10 +737,10 @@ void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
 		 * accumulate and persist until all outstanding invalidates
 		 * complete.
 		 */
-		kvm->mmu_notifier_range_start =
-			min(kvm->mmu_notifier_range_start, start);
-		kvm->mmu_notifier_range_end =
-			max(kvm->mmu_notifier_range_end, end);
+		kvm->mmu_invalidate_range_start =
+			min(kvm->mmu_invalidate_range_start, start);
+		kvm->mmu_invalidate_range_end =
+			max(kvm->mmu_invalidate_range_end, end);
 	}
 }
 
@@ -752,7 +753,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 		.end		= range->end,
 		.pte		= __pte(0),
 		.handler	= kvm_unmap_gfn_range,
-		.on_lock	= kvm_inc_notifier_count,
+		.on_lock	= kvm_mmu_invalidate_begin,
 		.on_unlock	= kvm_arch_guest_memory_reclaimed,
 		.flush_on_ret	= true,
 		.may_block	= mmu_notifier_range_blockable(range),
@@ -763,7 +764,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	/*
 	 * Prevent memslot modification between range_start() and range_end()
 	 * so that conditionally locking provides the same result in both
-	 * functions.  Without that guarantee, the mmu_notifier_count
+	 * functions.  Without that guarantee, the mmu_invalidate_in_progress
 	 * adjustments will be imbalanced.
 	 *
 	 * Pairs with the decrement in range_end().
@@ -779,7 +780,8 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	 * any given time, and the caches themselves can check for hva overlap,
 	 * i.e. don't need to rely on memslot overlap checks for performance.
 	 * Because this runs without holding mmu_lock, the pfn caches must use
-	 * mn_active_invalidate_count (see above) instead of mmu_notifier_count.
+	 * mn_active_invalidate_count (see above) instead of
+	 * mmu_invalidate_in_progress.
 	 */
 	gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
 					  hva_range.may_block);
@@ -789,22 +791,22 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	return 0;
 }
 
-void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start,
-				   unsigned long end)
+void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
+			    unsigned long end)
 {
 	/*
 	 * This sequence increase will notify the kvm page fault that
 	 * the page that is going to be mapped in the spte could have
 	 * been freed.
 	 */
-	kvm->mmu_notifier_seq++;
+	kvm->mmu_invalidate_seq++;
 	smp_wmb();
 	/*
 	 * The above sequence increase must be visible before the
 	 * below count decrease, which is ensured by the smp_wmb above
-	 * in conjunction with the smp_rmb in mmu_notifier_retry().
+	 * in conjunction with the smp_rmb in mmu_invalidate_retry().
 	 */
-	kvm->mmu_notifier_count--;
+	kvm->mmu_invalidate_in_progress--;
 }
 
 static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
@@ -816,7 +818,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 		.end		= range->end,
 		.pte		= __pte(0),
 		.handler	= (void *)kvm_null_fn,
-		.on_lock	= kvm_dec_notifier_count,
+		.on_lock	= kvm_mmu_invalidate_end,
 		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= mmu_notifier_range_blockable(range),
@@ -837,7 +839,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 	if (wake)
 		rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait);
 
-	BUG_ON(kvm->mmu_notifier_count < 0);
+	BUG_ON(kvm->mmu_invalidate_in_progress < 0);
 }
 
 static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
@@ -1134,6 +1136,9 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
 
+	/* KVM is pinned via open("/dev/kvm"), the fd passed to this ioctl(). */
+	__module_get(kvm_chardev_ops.owner);
+
 	KVM_MMU_LOCK_INIT(kvm);
 	mmgrab(current->mm);
 	kvm->mm = current->mm;
@@ -1211,9 +1216,17 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (r)
 		goto out_err_no_mmu_notifier;
 
+	r = kvm_coalesced_mmio_init(kvm);
+	if (r < 0)
+		goto out_no_coalesced_mmio;
+
+	r = kvm_create_vm_debugfs(kvm, fdname);
+	if (r)
+		goto out_err_no_debugfs;
+
 	r = kvm_arch_post_init_vm(kvm);
 	if (r)
-		goto out_err_mmu_notifier;
+		goto out_err;
 
 	mutex_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
@@ -1222,25 +1235,13 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	preempt_notifier_inc();
 	kvm_init_pm_notifier(kvm);
 
-	/*
-	 * When the fd passed to this ioctl() is opened it pins the module,
-	 * but try_module_get() also prevents getting a reference if the module
-	 * is in MODULE_STATE_GOING (e.g. if someone ran "rmmod --wait").
-	 */
-	if (!try_module_get(kvm_chardev_ops.owner)) {
-		r = -ENODEV;
-		goto out_err_mmu_notifier;
-	}
-
-	r = kvm_create_vm_debugfs(kvm, fdname);
-	if (r)
-		goto out_err;
-
 	return kvm;
 
 out_err:
-	module_put(kvm_chardev_ops.owner);
-out_err_mmu_notifier:
+	kvm_destroy_vm_debugfs(kvm);
+out_err_no_debugfs:
+	kvm_coalesced_mmio_free(kvm);
+out_no_coalesced_mmio:
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 	if (kvm->mmu_notifier.ops)
 		mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
@@ -1259,6 +1260,7 @@ out_err_no_irq_srcu:
 out_err_no_srcu:
 	kvm_arch_free_vm(kvm);
 	mmdrop(current->mm);
+	module_put(kvm_chardev_ops.owner);
 	return ERR_PTR(r);
 }
 
@@ -2516,7 +2518,7 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
 {
 	unsigned int flags = FOLL_HWPOISON;
 	struct page *page;
-	int npages = 0;
+	int npages;
 
 	might_sleep();
 
@@ -4378,7 +4380,7 @@ void kvm_unregister_device_ops(u32 type)
 static int kvm_ioctl_create_device(struct kvm *kvm,
 				   struct kvm_create_device *cd)
 {
-	const struct kvm_device_ops *ops = NULL;
+	const struct kvm_device_ops *ops;
 	struct kvm_device *dev;
 	bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
 	int type;
@@ -4913,11 +4915,6 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 		goto put_fd;
 	}
 
-#ifdef CONFIG_KVM_MMIO
-	r = kvm_coalesced_mmio_init(kvm);
-	if (r < 0)
-		goto put_kvm;
-#endif
 	file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
 	if (IS_ERR(file)) {
 		r = PTR_ERR(file);
diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c
index ab519f72f2cd..68ff41d39545 100644
--- a/virt/kvm/pfncache.c
+++ b/virt/kvm/pfncache.c
@@ -112,27 +112,28 @@ static inline bool mmu_notifier_retry_cache(struct kvm *kvm, unsigned long mmu_s
 {
 	/*
 	 * mn_active_invalidate_count acts for all intents and purposes
-	 * like mmu_notifier_count here; but the latter cannot be used
-	 * here because the invalidation of caches in the mmu_notifier
-	 * event occurs _before_ mmu_notifier_count is elevated.
+	 * like mmu_invalidate_in_progress here; but the latter cannot
+	 * be used here because the invalidation of caches in the
+	 * mmu_notifier event occurs _before_ mmu_invalidate_in_progress
+	 * is elevated.
 	 *
 	 * Note, it does not matter that mn_active_invalidate_count
 	 * is not protected by gpc->lock.  It is guaranteed to
 	 * be elevated before the mmu_notifier acquires gpc->lock, and
-	 * isn't dropped until after mmu_notifier_seq is updated.
+	 * isn't dropped until after mmu_invalidate_seq is updated.
 	 */
 	if (kvm->mn_active_invalidate_count)
 		return true;
 
 	/*
 	 * Ensure mn_active_invalidate_count is read before
-	 * mmu_notifier_seq.  This pairs with the smp_wmb() in
+	 * mmu_invalidate_seq.  This pairs with the smp_wmb() in
 	 * mmu_notifier_invalidate_range_end() to guarantee either the
 	 * old (non-zero) value of mn_active_invalidate_count or the
-	 * new (incremented) value of mmu_notifier_seq is observed.
+	 * new (incremented) value of mmu_invalidate_seq is observed.
 	 */
 	smp_rmb();
-	return kvm->mmu_notifier_seq != mmu_seq;
+	return kvm->mmu_invalidate_seq != mmu_seq;
 }
 
 static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
@@ -155,7 +156,7 @@ static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
 	gpc->valid = false;
 
 	do {
-		mmu_seq = kvm->mmu_notifier_seq;
+		mmu_seq = kvm->mmu_invalidate_seq;
 		smp_rmb();
 
 		write_unlock_irq(&gpc->lock);